Training in progress, step 513, checkpoint

checkpoint-513/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "jeiku/completion4B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128019,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-513/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "transformers_version": "4.46.0.dev0"
+}

checkpoint-513/global_step513/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f668361510aad9c977240a6e8476afdb31accc17674546b3e7acbb2c699c6af4
+size 13609807299

checkpoint-513/global_step513/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e8f5baf68b345192b3b35bb1b8d69ab1b1bbd3db28ffc26a593cd842c315d77
+size 13609807299

checkpoint-513/global_step513/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443c88a53c2709a9f6f7bb763dcbcaddffcc39fe92690c8a534889d0506b4f72
+size 152293

checkpoint-513/global_step513/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf15bbb02e65e749ae281386a19ce77c710383f417606b2bb215a7cf2e969172
+size 152293

checkpoint-513/latest

@@ -0,0 +1 @@
+global_step513

checkpoint-513/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f7672a1bee57b005fc5a134f74ddd04a504031c2338087926522e546db8a9da
+size 4978354640

checkpoint-513/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0034629051632e4e47c5b54e71cd38dd0087624b7936fe6339d6378376ffa78
+size 4047172128

checkpoint-513/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 9025492992
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-513/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dcb161b22b2558dbf7e3f8c871050cec383d11a40423fab11f18d5e630639bf
+size 14512

checkpoint-513/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d50af6aef769414a6f28fa1b1bc51ce707dc8ecd15474e03f99a2f10fde086be
+size 14512

checkpoint-513/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c3f9baae3360df0d3a60841cfbf602b7769e7c34f633b4e452ad187e836f59
+size 1064

checkpoint-513/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-513/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
+size 17209884

checkpoint-513/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-513/trainer_state.json

@@ -0,0 +1,3672 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.49768574908648,
+  "eval_steps": 86,
+  "global_step": 513,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0029254022428083864,
+      "grad_norm": 56.61502838582006,
+      "learning_rate": 1.4705882352941178e-07,
+      "loss": 1.336,
+      "step": 1
+    },
+    {
+      "epoch": 0.0029254022428083864,
+      "eval_loss": 1.7113733291625977,
+      "eval_runtime": 65.4428,
+      "eval_samples_per_second": 14.807,
+      "eval_steps_per_second": 2.475,
+      "step": 1
+    },
+    {
+      "epoch": 0.005850804485616773,
+      "grad_norm": 51.81724700444768,
+      "learning_rate": 2.9411764705882356e-07,
+      "loss": 1.3698,
+      "step": 2
+    },
+    {
+      "epoch": 0.008776206728425159,
+      "grad_norm": 47.60979608727599,
+      "learning_rate": 4.4117647058823536e-07,
+      "loss": 1.34,
+      "step": 3
+    },
+    {
+      "epoch": 0.011701608971233545,
+      "grad_norm": 48.80875038414928,
+      "learning_rate": 5.882352941176471e-07,
+      "loss": 1.3392,
+      "step": 4
+    },
+    {
+      "epoch": 0.01462701121404193,
+      "grad_norm": 53.27305939885202,
+      "learning_rate": 7.352941176470589e-07,
+      "loss": 1.3409,
+      "step": 5
+    },
+    {
+      "epoch": 0.017552413456850317,
+      "grad_norm": 47.925702270624,
+      "learning_rate": 8.823529411764707e-07,
+      "loss": 1.3373,
+      "step": 6
+    },
+    {
+      "epoch": 0.020477815699658702,
+      "grad_norm": 48.37389105675583,
+      "learning_rate": 1.0294117647058825e-06,
+      "loss": 1.3137,
+      "step": 7
+    },
+    {
+      "epoch": 0.02340321794246709,
+      "grad_norm": 39.37861206526259,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 1.3369,
+      "step": 8
+    },
+    {
+      "epoch": 0.026328620185275476,
+      "grad_norm": 25.61893601522815,
+      "learning_rate": 1.323529411764706e-06,
+      "loss": 1.3237,
+      "step": 9
+    },
+    {
+      "epoch": 0.02925402242808386,
+      "grad_norm": 24.674790384396417,
+      "learning_rate": 1.4705882352941177e-06,
+      "loss": 1.3056,
+      "step": 10
+    },
+    {
+      "epoch": 0.03217942467089225,
+      "grad_norm": 24.91679564935755,
+      "learning_rate": 1.6176470588235297e-06,
+      "loss": 1.3015,
+      "step": 11
+    },
+    {
+      "epoch": 0.035104826913700635,
+      "grad_norm": 16.05920632953936,
+      "learning_rate": 1.7647058823529414e-06,
+      "loss": 1.2387,
+      "step": 12
+    },
+    {
+      "epoch": 0.03803022915650902,
+      "grad_norm": 17.21678860344456,
+      "learning_rate": 1.9117647058823528e-06,
+      "loss": 1.2592,
+      "step": 13
+    },
+    {
+      "epoch": 0.040955631399317405,
+      "grad_norm": 9.449613433058063,
+      "learning_rate": 2.058823529411765e-06,
+      "loss": 1.2485,
+      "step": 14
+    },
+    {
+      "epoch": 0.04388103364212579,
+      "grad_norm": 6.021711489397231,
+      "learning_rate": 2.2058823529411767e-06,
+      "loss": 1.2225,
+      "step": 15
+    },
+    {
+      "epoch": 0.04680643588493418,
+      "grad_norm": 5.216307369247847,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 1.2108,
+      "step": 16
+    },
+    {
+      "epoch": 0.04973183812774257,
+      "grad_norm": 3.0940157822273058,
+      "learning_rate": 2.5e-06,
+      "loss": 1.1818,
+      "step": 17
+    },
+    {
+      "epoch": 0.05265724037055095,
+      "grad_norm": 2.91820920733528,
+      "learning_rate": 2.647058823529412e-06,
+      "loss": 1.1673,
+      "step": 18
+    },
+    {
+      "epoch": 0.05558264261335934,
+      "grad_norm": 1.8161119748737125,
+      "learning_rate": 2.7941176470588237e-06,
+      "loss": 1.1415,
+      "step": 19
+    },
+    {
+      "epoch": 0.05850804485616772,
+      "grad_norm": 1.7624989349292328,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 1.1534,
+      "step": 20
+    },
+    {
+      "epoch": 0.06143344709897611,
+      "grad_norm": 1.8082316113855639,
+      "learning_rate": 3.0882352941176476e-06,
+      "loss": 1.1441,
+      "step": 21
+    },
+    {
+      "epoch": 0.0643588493417845,
+      "grad_norm": 1.2223752752561972,
+      "learning_rate": 3.2352941176470594e-06,
+      "loss": 1.1258,
+      "step": 22
+    },
+    {
+      "epoch": 0.06728425158459288,
+      "grad_norm": 1.1968274873672384,
+      "learning_rate": 3.382352941176471e-06,
+      "loss": 1.1235,
+      "step": 23
+    },
+    {
+      "epoch": 0.07020965382740127,
+      "grad_norm": 1.6582129576098923,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 1.1197,
+      "step": 24
+    },
+    {
+      "epoch": 0.07313505607020965,
+      "grad_norm": 1.4716149175252013,
+      "learning_rate": 3.6764705882352946e-06,
+      "loss": 1.1242,
+      "step": 25
+    },
+    {
+      "epoch": 0.07606045831301804,
+      "grad_norm": 1.406278144326081,
+      "learning_rate": 3.8235294117647055e-06,
+      "loss": 1.1048,
+      "step": 26
+    },
+    {
+      "epoch": 0.07898586055582643,
+      "grad_norm": 1.2947816562679035,
+      "learning_rate": 3.970588235294118e-06,
+      "loss": 1.078,
+      "step": 27
+    },
+    {
+      "epoch": 0.08191126279863481,
+      "grad_norm": 1.3762114230758338,
+      "learning_rate": 4.11764705882353e-06,
+      "loss": 1.082,
+      "step": 28
+    },
+    {
+      "epoch": 0.0848366650414432,
+      "grad_norm": 0.924113394021786,
+      "learning_rate": 4.264705882352942e-06,
+      "loss": 1.0763,
+      "step": 29
+    },
+    {
+      "epoch": 0.08776206728425158,
+      "grad_norm": 1.2229665744650906,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 1.0967,
+      "step": 30
+    },
+    {
+      "epoch": 0.09068746952705997,
+      "grad_norm": 0.7673671598420616,
+      "learning_rate": 4.558823529411765e-06,
+      "loss": 1.092,
+      "step": 31
+    },
+    {
+      "epoch": 0.09361287176986836,
+      "grad_norm": 1.0178922272446433,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 1.0787,
+      "step": 32
+    },
+    {
+      "epoch": 0.09653827401267674,
+      "grad_norm": 0.9452497607845647,
+      "learning_rate": 4.852941176470589e-06,
+      "loss": 1.068,
+      "step": 33
+    },
+    {
+      "epoch": 0.09946367625548513,
+      "grad_norm": 0.8975537032410301,
+      "learning_rate": 5e-06,
+      "loss": 1.0575,
+      "step": 34
+    },
+    {
+      "epoch": 0.10238907849829351,
+      "grad_norm": 0.8883502117498131,
+      "learning_rate": 5.147058823529411e-06,
+      "loss": 1.0562,
+      "step": 35
+    },
+    {
+      "epoch": 0.1053144807411019,
+      "grad_norm": 0.7786108075639211,
+      "learning_rate": 5.294117647058824e-06,
+      "loss": 1.0628,
+      "step": 36
+    },
+    {
+      "epoch": 0.10823988298391028,
+      "grad_norm": 0.7164270179895762,
+      "learning_rate": 5.441176470588236e-06,
+      "loss": 1.0647,
+      "step": 37
+    },
+    {
+      "epoch": 0.11116528522671867,
+      "grad_norm": 0.6489067271106712,
+      "learning_rate": 5.588235294117647e-06,
+      "loss": 1.0377,
+      "step": 38
+    },
+    {
+      "epoch": 0.11409068746952707,
+      "grad_norm": 0.7092316432914678,
+      "learning_rate": 5.735294117647059e-06,
+      "loss": 1.0349,
+      "step": 39
+    },
+    {
+      "epoch": 0.11701608971233544,
+      "grad_norm": 0.8243939653767051,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 1.051,
+      "step": 40
+    },
+    {
+      "epoch": 0.11994149195514384,
+      "grad_norm": 0.6741750939661741,
+      "learning_rate": 6.029411764705883e-06,
+      "loss": 1.0402,
+      "step": 41
+    },
+    {
+      "epoch": 0.12286689419795221,
+      "grad_norm": 0.7267097354641292,
+      "learning_rate": 6.176470588235295e-06,
+      "loss": 1.0288,
+      "step": 42
+    },
+    {
+      "epoch": 0.1257922964407606,
+      "grad_norm": 0.8103776243322237,
+      "learning_rate": 6.323529411764706e-06,
+      "loss": 1.0408,
+      "step": 43
+    },
+    {
+      "epoch": 0.128717698683569,
+      "grad_norm": 0.7774449672806364,
+      "learning_rate": 6.470588235294119e-06,
+      "loss": 1.0151,
+      "step": 44
+    },
+    {
+      "epoch": 0.13164310092637738,
+      "grad_norm": 0.6835822537993219,
+      "learning_rate": 6.61764705882353e-06,
+      "loss": 1.0032,
+      "step": 45
+    },
+    {
+      "epoch": 0.13456850316918575,
+      "grad_norm": 0.7671516033152175,
+      "learning_rate": 6.764705882352942e-06,
+      "loss": 1.0031,
+      "step": 46
+    },
+    {
+      "epoch": 0.13749390541199416,
+      "grad_norm": 0.6872713961130001,
+      "learning_rate": 6.911764705882353e-06,
+      "loss": 1.0366,
+      "step": 47
+    },
+    {
+      "epoch": 0.14041930765480254,
+      "grad_norm": 0.6944081716419906,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 1.0206,
+      "step": 48
+    },
+    {
+      "epoch": 0.14334470989761092,
+      "grad_norm": 0.6724442918688381,
+      "learning_rate": 7.205882352941177e-06,
+      "loss": 1.0054,
+      "step": 49
+    },
+    {
+      "epoch": 0.1462701121404193,
+      "grad_norm": 0.70069910168755,
+      "learning_rate": 7.352941176470589e-06,
+      "loss": 0.984,
+      "step": 50
+    },
+    {
+      "epoch": 0.1491955143832277,
+      "grad_norm": 0.8321780541795489,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.0222,
+      "step": 51
+    },
+    {
+      "epoch": 0.15212091662603608,
+      "grad_norm": 0.7461017416034388,
+      "learning_rate": 7.647058823529411e-06,
+      "loss": 0.9958,
+      "step": 52
+    },
+    {
+      "epoch": 0.15504631886884446,
+      "grad_norm": 0.7638996030200154,
+      "learning_rate": 7.794117647058825e-06,
+      "loss": 1.0099,
+      "step": 53
+    },
+    {
+      "epoch": 0.15797172111165286,
+      "grad_norm": 0.8833995259882905,
+      "learning_rate": 7.941176470588236e-06,
+      "loss": 0.9979,
+      "step": 54
+    },
+    {
+      "epoch": 0.16089712335446124,
+      "grad_norm": 0.7840192819559926,
+      "learning_rate": 8.088235294117648e-06,
+      "loss": 0.9948,
+      "step": 55
+    },
+    {
+      "epoch": 0.16382252559726962,
+      "grad_norm": 0.7644797684213736,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 1.0009,
+      "step": 56
+    },
+    {
+      "epoch": 0.166747927840078,
+      "grad_norm": 0.688025084080775,
+      "learning_rate": 8.382352941176472e-06,
+      "loss": 1.0178,
+      "step": 57
+    },
+    {
+      "epoch": 0.1696733300828864,
+      "grad_norm": 0.7265519968150936,
+      "learning_rate": 8.529411764705883e-06,
+      "loss": 0.9973,
+      "step": 58
+    },
+    {
+      "epoch": 0.17259873232569478,
+      "grad_norm": 0.683233517732171,
+      "learning_rate": 8.676470588235295e-06,
+      "loss": 0.9954,
+      "step": 59
+    },
+    {
+      "epoch": 0.17552413456850316,
+      "grad_norm": 0.704502531642411,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.9876,
+      "step": 60
+    },
+    {
+      "epoch": 0.17844953681131157,
+      "grad_norm": 0.743891308875026,
+      "learning_rate": 8.970588235294119e-06,
+      "loss": 0.9763,
+      "step": 61
+    },
+    {
+      "epoch": 0.18137493905411994,
+      "grad_norm": 0.7598121118829709,
+      "learning_rate": 9.11764705882353e-06,
+      "loss": 0.9587,
+      "step": 62
+    },
+    {
+      "epoch": 0.18430034129692832,
+      "grad_norm": 0.8066231503341631,
+      "learning_rate": 9.264705882352942e-06,
+      "loss": 0.9989,
+      "step": 63
+    },
+    {
+      "epoch": 0.18722574353973673,
+      "grad_norm": 0.7979897760646133,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 1.0033,
+      "step": 64
+    },
+    {
+      "epoch": 0.1901511457825451,
+      "grad_norm": 0.7334146161657895,
+      "learning_rate": 9.558823529411766e-06,
+      "loss": 0.9882,
+      "step": 65
+    },
+    {
+      "epoch": 0.19307654802535348,
+      "grad_norm": 0.676521441443209,
+      "learning_rate": 9.705882352941177e-06,
+      "loss": 0.9789,
+      "step": 66
+    },
+    {
+      "epoch": 0.19600195026816186,
+      "grad_norm": 0.7552083619322828,
+      "learning_rate": 9.852941176470589e-06,
+      "loss": 0.9834,
+      "step": 67
+    },
+    {
+      "epoch": 0.19892735251097027,
+      "grad_norm": 0.7613688019506333,
+      "learning_rate": 1e-05,
+      "loss": 0.984,
+      "step": 68
+    },
+    {
+      "epoch": 0.20185275475377865,
+      "grad_norm": 0.740622944338628,
+      "learning_rate": 9.999934551143319e-06,
+      "loss": 0.9401,
+      "step": 69
+    },
+    {
+      "epoch": 0.20477815699658702,
+      "grad_norm": 0.7221110895270001,
+      "learning_rate": 9.9997382062867e-06,
+      "loss": 0.9822,
+      "step": 70
+    },
+    {
+      "epoch": 0.20770355923939543,
+      "grad_norm": 0.7826701133526415,
+      "learning_rate": 9.999410970570358e-06,
+      "loss": 0.9631,
+      "step": 71
+    },
+    {
+      "epoch": 0.2106289614822038,
+      "grad_norm": 0.8740335657819791,
+      "learning_rate": 9.998952852561176e-06,
+      "loss": 0.9726,
+      "step": 72
+    },
+    {
+      "epoch": 0.2135543637250122,
+      "grad_norm": 0.7252364315085953,
+      "learning_rate": 9.998363864252474e-06,
+      "loss": 0.9686,
+      "step": 73
+    },
+    {
+      "epoch": 0.21647976596782056,
+      "grad_norm": 0.6747540030851431,
+      "learning_rate": 9.997644021063698e-06,
+      "loss": 0.9739,
+      "step": 74
+    },
+    {
+      "epoch": 0.21940516821062897,
+      "grad_norm": 0.7824714311195131,
+      "learning_rate": 9.99679334184001e-06,
+      "loss": 0.9655,
+      "step": 75
+    },
+    {
+      "epoch": 0.22233057045343735,
+      "grad_norm": 0.7945498898412752,
+      "learning_rate": 9.995811848851807e-06,
+      "loss": 0.964,
+      "step": 76
+    },
+    {
+      "epoch": 0.22525597269624573,
+      "grad_norm": 0.6630711865020658,
+      "learning_rate": 9.994699567794123e-06,
+      "loss": 0.9911,
+      "step": 77
+    },
+    {
+      "epoch": 0.22818137493905413,
+      "grad_norm": 0.6575181705021402,
+      "learning_rate": 9.99345652778597e-06,
+      "loss": 0.9723,
+      "step": 78
+    },
+    {
+      "epoch": 0.2311067771818625,
+      "grad_norm": 0.8716226724365626,
+      "learning_rate": 9.992082761369567e-06,
+      "loss": 0.9545,
+      "step": 79
+    },
+    {
+      "epoch": 0.2340321794246709,
+      "grad_norm": 0.7058306465830354,
+      "learning_rate": 9.990578304509488e-06,
+      "loss": 0.9483,
+      "step": 80
+    },
+    {
+      "epoch": 0.23695758166747927,
+      "grad_norm": 0.7161030185458794,
+      "learning_rate": 9.988943196591727e-06,
+      "loss": 0.9826,
+      "step": 81
+    },
+    {
+      "epoch": 0.23988298391028767,
+      "grad_norm": 0.7246834402057637,
+      "learning_rate": 9.987177480422663e-06,
+      "loss": 0.9743,
+      "step": 82
+    },
+    {
+      "epoch": 0.24280838615309605,
+      "grad_norm": 0.7675354559101374,
+      "learning_rate": 9.985281202227936e-06,
+      "loss": 0.9611,
+      "step": 83
+    },
+    {
+      "epoch": 0.24573378839590443,
+      "grad_norm": 0.6584357041279372,
+      "learning_rate": 9.983254411651242e-06,
+      "loss": 0.9474,
+      "step": 84
+    },
+    {
+      "epoch": 0.24865919063871283,
+      "grad_norm": 0.7664607604465142,
+      "learning_rate": 9.981097161753032e-06,
+      "loss": 0.9618,
+      "step": 85
+    },
+    {
+      "epoch": 0.2515845928815212,
+      "grad_norm": 0.6944551302100264,
+      "learning_rate": 9.978809509009121e-06,
+      "loss": 0.9631,
+      "step": 86
+    },
+    {
+      "epoch": 0.2515845928815212,
+      "eval_loss": 1.4097907543182373,
+      "eval_runtime": 65.4251,
+      "eval_samples_per_second": 14.811,
+      "eval_steps_per_second": 2.476,
+      "step": 86
+    },
+    {
+      "epoch": 0.2545099951243296,
+      "grad_norm": 0.6240545271387105,
+      "learning_rate": 9.976391513309212e-06,
+      "loss": 0.9676,
+      "step": 87
+    },
+    {
+      "epoch": 0.257435397367138,
+      "grad_norm": 0.7423832349267365,
+      "learning_rate": 9.973843237955328e-06,
+      "loss": 0.979,
+      "step": 88
+    },
+    {
+      "epoch": 0.26036079960994635,
+      "grad_norm": 0.6689567084685912,
+      "learning_rate": 9.971164749660149e-06,
+      "loss": 0.9611,
+      "step": 89
+    },
+    {
+      "epoch": 0.26328620185275475,
+      "grad_norm": 0.6301374142385534,
+      "learning_rate": 9.968356118545277e-06,
+      "loss": 0.9702,
+      "step": 90
+    },
+    {
+      "epoch": 0.26621160409556316,
+      "grad_norm": 0.7418455357086029,
+      "learning_rate": 9.96541741813939e-06,
+      "loss": 0.9615,
+      "step": 91
+    },
+    {
+      "epoch": 0.2691370063383715,
+      "grad_norm": 0.6892741528738031,
+      "learning_rate": 9.962348725376318e-06,
+      "loss": 0.938,
+      "step": 92
+    },
+    {
+      "epoch": 0.2720624085811799,
+      "grad_norm": 0.6706415096539721,
+      "learning_rate": 9.959150120593035e-06,
+      "loss": 0.9629,
+      "step": 93
+    },
+    {
+      "epoch": 0.2749878108239883,
+      "grad_norm": 0.7046784189658271,
+      "learning_rate": 9.955821687527554e-06,
+      "loss": 0.9664,
+      "step": 94
+    },
+    {
+      "epoch": 0.27791321306679667,
+      "grad_norm": 0.7485580596660371,
+      "learning_rate": 9.952363513316727e-06,
+      "loss": 0.9482,
+      "step": 95
+    },
+    {
+      "epoch": 0.2808386153096051,
+      "grad_norm": 0.6878028657133218,
+      "learning_rate": 9.948775688493974e-06,
+      "loss": 0.9498,
+      "step": 96
+    },
+    {
+      "epoch": 0.2837640175524135,
+      "grad_norm": 0.6680669216250931,
+      "learning_rate": 9.945058306986911e-06,
+      "loss": 0.9435,
+      "step": 97
+    },
+    {
+      "epoch": 0.28668941979522183,
+      "grad_norm": 0.6898717996278425,
+      "learning_rate": 9.941211466114883e-06,
+      "loss": 0.9684,
+      "step": 98
+    },
+    {
+      "epoch": 0.28961482203803024,
+      "grad_norm": 0.6484486515830594,
+      "learning_rate": 9.937235266586425e-06,
+      "loss": 0.9434,
+      "step": 99
+    },
+    {
+      "epoch": 0.2925402242808386,
+      "grad_norm": 0.7331156843054286,
+      "learning_rate": 9.933129812496623e-06,
+      "loss": 0.9491,
+      "step": 100
+    },
+    {
+      "epoch": 0.295465626523647,
+      "grad_norm": 0.6159411880792645,
+      "learning_rate": 9.928895211324387e-06,
+      "loss": 0.9414,
+      "step": 101
+    },
+    {
+      "epoch": 0.2983910287664554,
+      "grad_norm": 0.6680220411471304,
+      "learning_rate": 9.924531573929641e-06,
+      "loss": 0.9293,
+      "step": 102
+    },
+    {
+      "epoch": 0.30131643100926375,
+      "grad_norm": 0.639276890448279,
+      "learning_rate": 9.920039014550413e-06,
+      "loss": 0.9545,
+      "step": 103
+    },
+    {
+      "epoch": 0.30424183325207216,
+      "grad_norm": 0.6428680336292386,
+      "learning_rate": 9.915417650799855e-06,
+      "loss": 0.9506,
+      "step": 104
+    },
+    {
+      "epoch": 0.30716723549488056,
+      "grad_norm": 0.6169710049517818,
+      "learning_rate": 9.910667603663156e-06,
+      "loss": 0.9786,
+      "step": 105
+    },
+    {
+      "epoch": 0.3100926377376889,
+      "grad_norm": 0.684509417371433,
+      "learning_rate": 9.905788997494377e-06,
+      "loss": 0.9525,
+      "step": 106
+    },
+    {
+      "epoch": 0.3130180399804973,
+      "grad_norm": 0.6503641190326895,
+      "learning_rate": 9.9007819600132e-06,
+      "loss": 0.9325,
+      "step": 107
+    },
+    {
+      "epoch": 0.3159434422233057,
+      "grad_norm": 0.6372262818423288,
+      "learning_rate": 9.89564662230157e-06,
+      "loss": 0.9469,
+      "step": 108
+    },
+    {
+      "epoch": 0.3188688444661141,
+      "grad_norm": 0.741895816894913,
+      "learning_rate": 9.890383118800287e-06,
+      "loss": 0.9433,
+      "step": 109
+    },
+    {
+      "epoch": 0.3217942467089225,
+      "grad_norm": 0.6678635900965723,
+      "learning_rate": 9.884991587305459e-06,
+      "loss": 0.9507,
+      "step": 110
+    },
+    {
+      "epoch": 0.3247196489517309,
+      "grad_norm": 0.6557776782736461,
+      "learning_rate": 9.87947216896492e-06,
+      "loss": 0.9489,
+      "step": 111
+    },
+    {
+      "epoch": 0.32764505119453924,
+      "grad_norm": 0.8386523679095728,
+      "learning_rate": 9.873825008274514e-06,
+      "loss": 0.9513,
+      "step": 112
+    },
+    {
+      "epoch": 0.33057045343734764,
+      "grad_norm": 0.6871663810393576,
+      "learning_rate": 9.868050253074328e-06,
+      "loss": 0.9461,
+      "step": 113
+    },
+    {
+      "epoch": 0.333495855680156,
+      "grad_norm": 0.668413921617873,
+      "learning_rate": 9.862148054544812e-06,
+      "loss": 0.9658,
+      "step": 114
+    },
+    {
+      "epoch": 0.3364212579229644,
+      "grad_norm": 0.7873362433736362,
+      "learning_rate": 9.85611856720282e-06,
+      "loss": 0.9397,
+      "step": 115
+    },
+    {
+      "epoch": 0.3393466601657728,
+      "grad_norm": 0.607062349214138,
+      "learning_rate": 9.849961948897582e-06,
+      "loss": 0.9241,
+      "step": 116
+    },
+    {
+      "epoch": 0.34227206240858116,
+      "grad_norm": 0.6608850440766699,
+      "learning_rate": 9.843678360806542e-06,
+      "loss": 0.9459,
+      "step": 117
+    },
+    {
+      "epoch": 0.34519746465138956,
+      "grad_norm": 0.648707994851676,
+      "learning_rate": 9.837267967431164e-06,
+      "loss": 0.9375,
+      "step": 118
+    },
+    {
+      "epoch": 0.34812286689419797,
+      "grad_norm": 0.7079372926717654,
+      "learning_rate": 9.830730936592615e-06,
+      "loss": 0.9182,
+      "step": 119
+    },
+    {
+      "epoch": 0.3510482691370063,
+      "grad_norm": 0.7662791064726716,
+      "learning_rate": 9.824067439427374e-06,
+      "loss": 0.9202,
+      "step": 120
+    },
+    {
+      "epoch": 0.3539736713798147,
+      "grad_norm": 0.6847400348854458,
+      "learning_rate": 9.81727765038275e-06,
+      "loss": 0.9554,
+      "step": 121
+    },
+    {
+      "epoch": 0.35689907362262313,
+      "grad_norm": 0.7143572416493496,
+      "learning_rate": 9.810361747212313e-06,
+      "loss": 0.9479,
+      "step": 122
+    },
+    {
+      "epoch": 0.3598244758654315,
+      "grad_norm": 0.796457278880475,
+      "learning_rate": 9.803319910971248e-06,
+      "loss": 0.9514,
+      "step": 123
+    },
+    {
+      "epoch": 0.3627498781082399,
+      "grad_norm": 0.7165439305935597,
+      "learning_rate": 9.796152326011604e-06,
+      "loss": 0.9301,
+      "step": 124
+    },
+    {
+      "epoch": 0.3656752803510483,
+      "grad_norm": 0.7105461017783379,
+      "learning_rate": 9.788859179977478e-06,
+      "loss": 0.9197,
+      "step": 125
+    },
+    {
+      "epoch": 0.36860068259385664,
+      "grad_norm": 0.6678675689530374,
+      "learning_rate": 9.781440663800099e-06,
+      "loss": 0.9327,
+      "step": 126
+    },
+    {
+      "epoch": 0.37152608483666505,
+      "grad_norm": 0.6998315944401519,
+      "learning_rate": 9.77389697169283e-06,
+      "loss": 0.9424,
+      "step": 127
+    },
+    {
+      "epoch": 0.37445148707947346,
+      "grad_norm": 0.7063153026165354,
+      "learning_rate": 9.766228301146074e-06,
+      "loss": 0.9117,
+      "step": 128
+    },
+    {
+      "epoch": 0.3773768893222818,
+      "grad_norm": 0.665683830431616,
+      "learning_rate": 9.758434852922124e-06,
+      "loss": 0.9338,
+      "step": 129
+    },
+    {
+      "epoch": 0.3803022915650902,
+      "grad_norm": 0.6511286552329526,
+      "learning_rate": 9.75051683104989e-06,
+      "loss": 0.9239,
+      "step": 130
+    },
+    {
+      "epoch": 0.38322769380789856,
+      "grad_norm": 0.7263937749419739,
+      "learning_rate": 9.742474442819561e-06,
+      "loss": 0.9469,
+      "step": 131
+    },
+    {
+      "epoch": 0.38615309605070697,
+      "grad_norm": 0.6877891571625458,
+      "learning_rate": 9.734307898777187e-06,
+      "loss": 0.9448,
+      "step": 132
+    },
+    {
+      "epoch": 0.3890784982935154,
+      "grad_norm": 0.652680067409742,
+      "learning_rate": 9.726017412719151e-06,
+      "loss": 0.9387,
+      "step": 133
+    },
+    {
+      "epoch": 0.3920039005363237,
+      "grad_norm": 0.7368224595734011,
+      "learning_rate": 9.71760320168659e-06,
+      "loss": 0.947,
+      "step": 134
+    },
+    {
+      "epoch": 0.39492930277913213,
+      "grad_norm": 0.5904957774047593,
+      "learning_rate": 9.7090654859597e-06,
+      "loss": 0.9169,
+      "step": 135
+    },
+    {
+      "epoch": 0.39785470502194054,
+      "grad_norm": 0.7590457981077249,
+      "learning_rate": 9.700404489051974e-06,
+      "loss": 0.9451,
+      "step": 136
+    },
+    {
+      "epoch": 0.4007801072647489,
+      "grad_norm": 0.6735223362511448,
+      "learning_rate": 9.69162043770435e-06,
+      "loss": 0.9099,
+      "step": 137
+    },
+    {
+      "epoch": 0.4037055095075573,
+      "grad_norm": 0.6866553871773976,
+      "learning_rate": 9.682713561879275e-06,
+      "loss": 0.9114,
+      "step": 138
+    },
+    {
+      "epoch": 0.4066309117503657,
+      "grad_norm": 0.6661362317941144,
+      "learning_rate": 9.673684094754686e-06,
+      "loss": 0.9263,
+      "step": 139
+    },
+    {
+      "epoch": 0.40955631399317405,
+      "grad_norm": 0.6773611746763274,
+      "learning_rate": 9.664532272717902e-06,
+      "loss": 0.9119,
+      "step": 140
+    },
+    {
+      "epoch": 0.41248171623598245,
+      "grad_norm": 0.6330232345134237,
+      "learning_rate": 9.655258335359438e-06,
+      "loss": 0.9235,
+      "step": 141
+    },
+    {
+      "epoch": 0.41540711847879086,
+      "grad_norm": 0.6364881510059489,
+      "learning_rate": 9.645862525466734e-06,
+      "loss": 0.9299,
+      "step": 142
+    },
+    {
+      "epoch": 0.4183325207215992,
+      "grad_norm": 0.7507102668694946,
+      "learning_rate": 9.636345089017795e-06,
+      "loss": 0.9526,
+      "step": 143
+    },
+    {
+      "epoch": 0.4212579229644076,
+      "grad_norm": 0.6526196555099488,
+      "learning_rate": 9.626706275174754e-06,
+      "loss": 0.9398,
+      "step": 144
+    },
+    {
+      "epoch": 0.42418332520721597,
+      "grad_norm": 0.6700118261014734,
+      "learning_rate": 9.61694633627735e-06,
+      "loss": 0.9124,
+      "step": 145
+    },
+    {
+      "epoch": 0.4271087274500244,
+      "grad_norm": 0.6335057158130035,
+      "learning_rate": 9.607065527836324e-06,
+      "loss": 0.9603,
+      "step": 146
+    },
+    {
+      "epoch": 0.4300341296928328,
+      "grad_norm": 0.6277095717664852,
+      "learning_rate": 9.597064108526715e-06,
+      "loss": 0.9221,
+      "step": 147
+    },
+    {
+      "epoch": 0.43295953193564113,
+      "grad_norm": 0.6712875310890567,
+      "learning_rate": 9.58694234018111e-06,
+      "loss": 0.9204,
+      "step": 148
+    },
+    {
+      "epoch": 0.43588493417844953,
+      "grad_norm": 0.6592731934180556,
+      "learning_rate": 9.576700487782775e-06,
+      "loss": 0.9438,
+      "step": 149
+    },
+    {
+      "epoch": 0.43881033642125794,
+      "grad_norm": 0.6479345778232325,
+      "learning_rate": 9.566338819458726e-06,
+      "loss": 0.937,
+      "step": 150
+    },
+    {
+      "epoch": 0.4417357386640663,
+      "grad_norm": 0.6617896622163715,
+      "learning_rate": 9.555857606472692e-06,
+      "loss": 0.9499,
+      "step": 151
+    },
+    {
+      "epoch": 0.4446611409068747,
+      "grad_norm": 0.6245931528735381,
+      "learning_rate": 9.545257123218043e-06,
+      "loss": 0.9215,
+      "step": 152
+    },
+    {
+      "epoch": 0.4475865431496831,
+      "grad_norm": 0.6579890487283353,
+      "learning_rate": 9.534537647210582e-06,
+      "loss": 0.9517,
+      "step": 153
+    },
+    {
+      "epoch": 0.45051194539249145,
+      "grad_norm": 0.695847847970159,
+      "learning_rate": 9.523699459081285e-06,
+      "loss": 0.9305,
+      "step": 154
+    },
+    {
+      "epoch": 0.45343734763529986,
+      "grad_norm": 0.5946097480044219,
+      "learning_rate": 9.512742842568964e-06,
+      "loss": 0.9141,
+      "step": 155
+    },
+    {
+      "epoch": 0.45636274987810826,
+      "grad_norm": 0.6524432888789063,
+      "learning_rate": 9.501668084512827e-06,
+      "loss": 0.9122,
+      "step": 156
+    },
+    {
+      "epoch": 0.4592881521209166,
+      "grad_norm": 0.6715958526339862,
+      "learning_rate": 9.490475474844976e-06,
+      "loss": 0.9336,
+      "step": 157
+    },
+    {
+      "epoch": 0.462213554363725,
+      "grad_norm": 0.6010391743428036,
+      "learning_rate": 9.479165306582811e-06,
+      "loss": 0.9139,
+      "step": 158
+    },
+    {
+      "epoch": 0.46513895660653337,
+      "grad_norm": 0.7089381455175933,
+      "learning_rate": 9.467737875821368e-06,
+      "loss": 0.9295,
+      "step": 159
+    },
+    {
+      "epoch": 0.4680643588493418,
+      "grad_norm": 0.7289713827153292,
+      "learning_rate": 9.456193481725555e-06,
+      "loss": 0.9095,
+      "step": 160
+    },
+    {
+      "epoch": 0.4709897610921502,
+      "grad_norm": 0.6768392933447552,
+      "learning_rate": 9.444532426522334e-06,
+      "loss": 0.916,
+      "step": 161
+    },
+    {
+      "epoch": 0.47391516333495853,
+      "grad_norm": 0.6859161203017968,
+      "learning_rate": 9.432755015492794e-06,
+      "loss": 0.9191,
+      "step": 162
+    },
+    {
+      "epoch": 0.47684056557776694,
+      "grad_norm": 0.6293363193961834,
+      "learning_rate": 9.42086155696417e-06,
+      "loss": 0.9315,
+      "step": 163
+    },
+    {
+      "epoch": 0.47976596782057535,
+      "grad_norm": 0.6705616648771443,
+      "learning_rate": 9.408852362301768e-06,
+      "loss": 0.9252,
+      "step": 164
+    },
+    {
+      "epoch": 0.4826913700633837,
+      "grad_norm": 0.5708431906967768,
+      "learning_rate": 9.396727745900811e-06,
+      "loss": 0.9251,
+      "step": 165
+    },
+    {
+      "epoch": 0.4856167723061921,
+      "grad_norm": 0.6083895665414887,
+      "learning_rate": 9.384488025178214e-06,
+      "loss": 0.9294,
+      "step": 166
+    },
+    {
+      "epoch": 0.4885421745490005,
+      "grad_norm": 0.6313624264612219,
+      "learning_rate": 9.372133520564264e-06,
+      "loss": 0.934,
+      "step": 167
+    },
+    {
+      "epoch": 0.49146757679180886,
+      "grad_norm": 0.6152317431277435,
+      "learning_rate": 9.359664555494244e-06,
+      "loss": 0.9426,
+      "step": 168
+    },
+    {
+      "epoch": 0.49439297903461726,
+      "grad_norm": 0.5950351172049964,
+      "learning_rate": 9.347081456399958e-06,
+      "loss": 0.92,
+      "step": 169
+    },
+    {
+      "epoch": 0.49731838127742567,
+      "grad_norm": 0.6063209229661293,
+      "learning_rate": 9.334384552701183e-06,
+      "loss": 0.9158,
+      "step": 170
+    },
+    {
+      "epoch": 0.500243783520234,
+      "grad_norm": 0.654811581491953,
+      "learning_rate": 9.321574176797055e-06,
+      "loss": 0.9137,
+      "step": 171
+    },
+    {
+      "epoch": 0.5031691857630424,
+      "grad_norm": 0.6443091025598243,
+      "learning_rate": 9.308650664057352e-06,
+      "loss": 0.9347,
+      "step": 172
+    },
+    {
+      "epoch": 0.5031691857630424,
+      "eval_loss": 1.382827877998352,
+      "eval_runtime": 175.4317,
+      "eval_samples_per_second": 5.524,
+      "eval_steps_per_second": 0.923,
+      "step": 172
+    },
+    {
+      "epoch": 0.5060945880058508,
+      "grad_norm": 0.6026207581703545,
+      "learning_rate": 9.295614352813732e-06,
+      "loss": 0.9563,
+      "step": 173
+    },
+    {
+      "epoch": 0.5090199902486592,
+      "grad_norm": 0.6335528865651444,
+      "learning_rate": 9.282465584350856e-06,
+      "loss": 0.9351,
+      "step": 174
+    },
+    {
+      "epoch": 0.5119453924914675,
+      "grad_norm": 0.6241890440961206,
+      "learning_rate": 9.269204702897476e-06,
+      "loss": 0.9218,
+      "step": 175
+    },
+    {
+      "epoch": 0.514870794734276,
+      "grad_norm": 0.6159111786845223,
+      "learning_rate": 9.2558320556174e-06,
+      "loss": 0.929,
+      "step": 176
+    },
+    {
+      "epoch": 0.5177961969770843,
+      "grad_norm": 0.5980336848061285,
+      "learning_rate": 9.242347992600416e-06,
+      "loss": 0.9304,
+      "step": 177
+    },
+    {
+      "epoch": 0.5207215992198927,
+      "grad_norm": 0.6410233986431451,
+      "learning_rate": 9.22875286685313e-06,
+      "loss": 0.9122,
+      "step": 178
+    },
+    {
+      "epoch": 0.5236470014627012,
+      "grad_norm": 0.6597655503440497,
+      "learning_rate": 9.215047034289716e-06,
+      "loss": 0.9097,
+      "step": 179
+    },
+    {
+      "epoch": 0.5265724037055095,
+      "grad_norm": 0.6154485141199222,
+      "learning_rate": 9.201230853722603e-06,
+      "loss": 0.9153,
+      "step": 180
+    },
+    {
+      "epoch": 0.5294978059483179,
+      "grad_norm": 0.6414319139886607,
+      "learning_rate": 9.187304686853078e-06,
+      "loss": 0.9176,
+      "step": 181
+    },
+    {
+      "epoch": 0.5324232081911263,
+      "grad_norm": 0.6454394793945475,
+      "learning_rate": 9.173268898261822e-06,
+      "loss": 0.9532,
+      "step": 182
+    },
+    {
+      "epoch": 0.5353486104339347,
+      "grad_norm": 0.6318137898521786,
+      "learning_rate": 9.159123855399364e-06,
+      "loss": 0.9154,
+      "step": 183
+    },
+    {
+      "epoch": 0.538274012676743,
+      "grad_norm": 0.673121635478712,
+      "learning_rate": 9.144869928576451e-06,
+      "loss": 0.9205,
+      "step": 184
+    },
+    {
+      "epoch": 0.5411994149195515,
+      "grad_norm": 0.69673708523528,
+      "learning_rate": 9.130507490954375e-06,
+      "loss": 0.8939,
+      "step": 185
+    },
+    {
+      "epoch": 0.5441248171623598,
+      "grad_norm": 0.6235430793813558,
+      "learning_rate": 9.11603691853518e-06,
+      "loss": 0.9286,
+      "step": 186
+    },
+    {
+      "epoch": 0.5470502194051682,
+      "grad_norm": 0.671802703912287,
+      "learning_rate": 9.101458590151837e-06,
+      "loss": 0.917,
+      "step": 187
+    },
+    {
+      "epoch": 0.5499756216479766,
+      "grad_norm": 0.7068672175457833,
+      "learning_rate": 9.086772887458314e-06,
+      "loss": 0.9066,
+      "step": 188
+    },
+    {
+      "epoch": 0.552901023890785,
+      "grad_norm": 0.6408445103986982,
+      "learning_rate": 9.071980194919592e-06,
+      "loss": 0.9104,
+      "step": 189
+    },
+    {
+      "epoch": 0.5558264261335933,
+      "grad_norm": 0.6433394608747284,
+      "learning_rate": 9.057080899801598e-06,
+      "loss": 0.888,
+      "step": 190
+    },
+    {
+      "epoch": 0.5587518283764018,
+      "grad_norm": 0.5837415931981027,
+      "learning_rate": 9.042075392161062e-06,
+      "loss": 0.9336,
+      "step": 191
+    },
+    {
+      "epoch": 0.5616772306192102,
+      "grad_norm": 0.6199039250762649,
+      "learning_rate": 9.026964064835312e-06,
+      "loss": 0.9328,
+      "step": 192
+    },
+    {
+      "epoch": 0.5646026328620185,
+      "grad_norm": 0.6319233508882481,
+      "learning_rate": 9.011747313431988e-06,
+      "loss": 0.905,
+      "step": 193
+    },
+    {
+      "epoch": 0.567528035104827,
+      "grad_norm": 0.601081786670075,
+      "learning_rate": 8.996425536318683e-06,
+      "loss": 0.9074,
+      "step": 194
+    },
+    {
+      "epoch": 0.5704534373476353,
+      "grad_norm": 0.6033456681131416,
+      "learning_rate": 8.980999134612512e-06,
+      "loss": 0.8969,
+      "step": 195
+    },
+    {
+      "epoch": 0.5733788395904437,
+      "grad_norm": 0.5954276802274396,
+      "learning_rate": 8.96546851216962e-06,
+      "loss": 0.8876,
+      "step": 196
+    },
+    {
+      "epoch": 0.576304241833252,
+      "grad_norm": 0.5790973908218665,
+      "learning_rate": 8.949834075574595e-06,
+      "loss": 0.9295,
+      "step": 197
+    },
+    {
+      "epoch": 0.5792296440760605,
+      "grad_norm": 0.6403087898665544,
+      "learning_rate": 8.934096234129843e-06,
+      "loss": 0.9303,
+      "step": 198
+    },
+    {
+      "epoch": 0.5821550463188688,
+      "grad_norm": 0.6474848524459008,
+      "learning_rate": 8.918255399844855e-06,
+      "loss": 0.9118,
+      "step": 199
+    },
+    {
+      "epoch": 0.5850804485616772,
+      "grad_norm": 0.6317608858369101,
+      "learning_rate": 8.902311987425422e-06,
+      "loss": 0.9259,
+      "step": 200
+    },
+    {
+      "epoch": 0.5880058508044856,
+      "grad_norm": 0.6299668796988298,
+      "learning_rate": 8.886266414262797e-06,
+      "loss": 0.9113,
+      "step": 201
+    },
+    {
+      "epoch": 0.590931253047294,
+      "grad_norm": 0.6478367513320172,
+      "learning_rate": 8.870119100422743e-06,
+      "loss": 0.9131,
+      "step": 202
+    },
+    {
+      "epoch": 0.5938566552901023,
+      "grad_norm": 0.6750176409365689,
+      "learning_rate": 8.853870468634554e-06,
+      "loss": 0.9136,
+      "step": 203
+    },
+    {
+      "epoch": 0.5967820575329108,
+      "grad_norm": 0.6034423133153598,
+      "learning_rate": 8.837520944279976e-06,
+      "loss": 0.9299,
+      "step": 204
+    },
+    {
+      "epoch": 0.5997074597757192,
+      "grad_norm": 0.7246936174658474,
+      "learning_rate": 8.821070955382082e-06,
+      "loss": 0.934,
+      "step": 205
+    },
+    {
+      "epoch": 0.6026328620185275,
+      "grad_norm": 0.5842207824302007,
+      "learning_rate": 8.804520932594061e-06,
+      "loss": 0.8955,
+      "step": 206
+    },
+    {
+      "epoch": 0.605558264261336,
+      "grad_norm": 0.6464732426728426,
+      "learning_rate": 8.787871309187936e-06,
+      "loss": 0.9143,
+      "step": 207
+    },
+    {
+      "epoch": 0.6084836665041443,
+      "grad_norm": 0.593796254274566,
+      "learning_rate": 8.771122521043236e-06,
+      "loss": 0.9366,
+      "step": 208
+    },
+    {
+      "epoch": 0.6114090687469527,
+      "grad_norm": 0.6413805961118216,
+      "learning_rate": 8.754275006635573e-06,
+      "loss": 0.9141,
+      "step": 209
+    },
+    {
+      "epoch": 0.6143344709897611,
+      "grad_norm": 0.5915119964358855,
+      "learning_rate": 8.737329207025172e-06,
+      "loss": 0.9263,
+      "step": 210
+    },
+    {
+      "epoch": 0.6172598732325695,
+      "grad_norm": 0.602387309046525,
+      "learning_rate": 8.720285565845313e-06,
+      "loss": 0.9252,
+      "step": 211
+    },
+    {
+      "epoch": 0.6201852754753778,
+      "grad_norm": 0.5724972842726512,
+      "learning_rate": 8.703144529290733e-06,
+      "loss": 0.9126,
+      "step": 212
+    },
+    {
+      "epoch": 0.6231106777181863,
+      "grad_norm": 0.6072757135591695,
+      "learning_rate": 8.685906546105925e-06,
+      "loss": 0.9132,
+      "step": 213
+    },
+    {
+      "epoch": 0.6260360799609946,
+      "grad_norm": 0.5918104303300601,
+      "learning_rate": 8.668572067573409e-06,
+      "loss": 0.9041,
+      "step": 214
+    },
+    {
+      "epoch": 0.628961482203803,
+      "grad_norm": 0.7069632584780451,
+      "learning_rate": 8.651141547501904e-06,
+      "loss": 0.9147,
+      "step": 215
+    },
+    {
+      "epoch": 0.6318868844466115,
+      "grad_norm": 0.5939488489914676,
+      "learning_rate": 8.633615442214452e-06,
+      "loss": 0.8861,
+      "step": 216
+    },
+    {
+      "epoch": 0.6348122866894198,
+      "grad_norm": 0.594163983383459,
+      "learning_rate": 8.615994210536479e-06,
+      "loss": 0.904,
+      "step": 217
+    },
+    {
+      "epoch": 0.6377376889322282,
+      "grad_norm": 0.6115411803684507,
+      "learning_rate": 8.598278313783765e-06,
+      "loss": 0.906,
+      "step": 218
+    },
+    {
+      "epoch": 0.6406630911750366,
+      "grad_norm": 0.6098845828745101,
+      "learning_rate": 8.580468215750392e-06,
+      "loss": 0.9144,
+      "step": 219
+    },
+    {
+      "epoch": 0.643588493417845,
+      "grad_norm": 0.655945088038022,
+      "learning_rate": 8.562564382696578e-06,
+      "loss": 0.9141,
+      "step": 220
+    },
+    {
+      "epoch": 0.6465138956606533,
+      "grad_norm": 0.6384785223163155,
+      "learning_rate": 8.544567283336484e-06,
+      "loss": 0.9107,
+      "step": 221
+    },
+    {
+      "epoch": 0.6494392979034618,
+      "grad_norm": 0.6868191616720155,
+      "learning_rate": 8.52647738882594e-06,
+      "loss": 0.893,
+      "step": 222
+    },
+    {
+      "epoch": 0.6523647001462701,
+      "grad_norm": 0.626480892609364,
+      "learning_rate": 8.508295172750116e-06,
+      "loss": 0.9305,
+      "step": 223
+    },
+    {
+      "epoch": 0.6552901023890785,
+      "grad_norm": 0.6699010228701286,
+      "learning_rate": 8.490021111111108e-06,
+      "loss": 0.9023,
+      "step": 224
+    },
+    {
+      "epoch": 0.6582155046318869,
+      "grad_norm": 0.5986398715684018,
+      "learning_rate": 8.471655682315496e-06,
+      "loss": 0.905,
+      "step": 225
+    },
+    {
+      "epoch": 0.6611409068746953,
+      "grad_norm": 0.6561568745480283,
+      "learning_rate": 8.453199367161804e-06,
+      "loss": 0.9048,
+      "step": 226
+    },
+    {
+      "epoch": 0.6640663091175036,
+      "grad_norm": 0.6270511738126053,
+      "learning_rate": 8.434652648827925e-06,
+      "loss": 0.8712,
+      "step": 227
+    },
+    {
+      "epoch": 0.666991711360312,
+      "grad_norm": 0.6107362295918622,
+      "learning_rate": 8.41601601285846e-06,
+      "loss": 0.9044,
+      "step": 228
+    },
+    {
+      "epoch": 0.6699171136031205,
+      "grad_norm": 0.6799488575081768,
+      "learning_rate": 8.397289947152021e-06,
+      "loss": 0.8803,
+      "step": 229
+    },
+    {
+      "epoch": 0.6728425158459288,
+      "grad_norm": 0.5784070848804973,
+      "learning_rate": 8.378474941948437e-06,
+      "loss": 0.9148,
+      "step": 230
+    },
+    {
+      "epoch": 0.6757679180887372,
+      "grad_norm": 0.6629135318112295,
+      "learning_rate": 8.359571489815946e-06,
+      "loss": 0.9213,
+      "step": 231
+    },
+    {
+      "epoch": 0.6786933203315456,
+      "grad_norm": 0.5852740864772179,
+      "learning_rate": 8.340580085638275e-06,
+      "loss": 0.9095,
+      "step": 232
+    },
+    {
+      "epoch": 0.681618722574354,
+      "grad_norm": 0.64996093688458,
+      "learning_rate": 8.321501226601702e-06,
+      "loss": 0.9169,
+      "step": 233
+    },
+    {
+      "epoch": 0.6845441248171623,
+      "grad_norm": 0.5694164027851655,
+      "learning_rate": 8.302335412182034e-06,
+      "loss": 0.891,
+      "step": 234
+    },
+    {
+      "epoch": 0.6874695270599708,
+      "grad_norm": 0.6356418602057949,
+      "learning_rate": 8.283083144131523e-06,
+      "loss": 0.9105,
+      "step": 235
+    },
+    {
+      "epoch": 0.6903949293027791,
+      "grad_norm": 0.6154729150264902,
+      "learning_rate": 8.263744926465744e-06,
+      "loss": 0.9277,
+      "step": 236
+    },
+    {
+      "epoch": 0.6933203315455875,
+      "grad_norm": 0.6117307726030774,
+      "learning_rate": 8.24432126545039e-06,
+      "loss": 0.9106,
+      "step": 237
+    },
+    {
+      "epoch": 0.6962457337883959,
+      "grad_norm": 0.5948671774603161,
+      "learning_rate": 8.224812669588028e-06,
+      "loss": 0.9091,
+      "step": 238
+    },
+    {
+      "epoch": 0.6991711360312043,
+      "grad_norm": 0.6747894010908736,
+      "learning_rate": 8.20521964960477e-06,
+      "loss": 0.9099,
+      "step": 239
+    },
+    {
+      "epoch": 0.7020965382740126,
+      "grad_norm": 0.6067781389366469,
+      "learning_rate": 8.185542718436923e-06,
+      "loss": 0.8824,
+      "step": 240
+    },
+    {
+      "epoch": 0.7050219405168211,
+      "grad_norm": 0.6218954056208628,
+      "learning_rate": 8.165782391217543e-06,
+      "loss": 0.9268,
+      "step": 241
+    },
+    {
+      "epoch": 0.7079473427596294,
+      "grad_norm": 0.6047649631286887,
+      "learning_rate": 8.145939185262963e-06,
+      "loss": 0.9068,
+      "step": 242
+    },
+    {
+      "epoch": 0.7108727450024378,
+      "grad_norm": 0.6627849155859088,
+      "learning_rate": 8.126013620059236e-06,
+      "loss": 0.8658,
+      "step": 243
+    },
+    {
+      "epoch": 0.7137981472452463,
+      "grad_norm": 0.5743150371347046,
+      "learning_rate": 8.106006217248552e-06,
+      "loss": 0.9165,
+      "step": 244
+    },
+    {
+      "epoch": 0.7167235494880546,
+      "grad_norm": 0.6372225785944298,
+      "learning_rate": 8.08591750061556e-06,
+      "loss": 0.8766,
+      "step": 245
+    },
+    {
+      "epoch": 0.719648951730863,
+      "grad_norm": 0.622673683239682,
+      "learning_rate": 8.065747996073681e-06,
+      "loss": 0.8979,
+      "step": 246
+    },
+    {
+      "epoch": 0.7225743539736714,
+      "grad_norm": 0.6078854821295643,
+      "learning_rate": 8.045498231651314e-06,
+      "loss": 0.894,
+      "step": 247
+    },
+    {
+      "epoch": 0.7254997562164798,
+      "grad_norm": 0.6137768530335086,
+      "learning_rate": 8.025168737478034e-06,
+      "loss": 0.9017,
+      "step": 248
+    },
+    {
+      "epoch": 0.7284251584592881,
+      "grad_norm": 0.5890466187531522,
+      "learning_rate": 8.004760045770702e-06,
+      "loss": 0.9028,
+      "step": 249
+    },
+    {
+      "epoch": 0.7313505607020966,
+      "grad_norm": 0.6534358893635163,
+      "learning_rate": 7.98427269081953e-06,
+      "loss": 0.9123,
+      "step": 250
+    },
+    {
+      "epoch": 0.7342759629449049,
+      "grad_norm": 0.5810190162761808,
+      "learning_rate": 7.963707208974103e-06,
+      "loss": 0.8841,
+      "step": 251
+    },
+    {
+      "epoch": 0.7372013651877133,
+      "grad_norm": 0.65324837663941,
+      "learning_rate": 7.943064138629332e-06,
+      "loss": 0.8962,
+      "step": 252
+    },
+    {
+      "epoch": 0.7401267674305217,
+      "grad_norm": 0.6566544273903392,
+      "learning_rate": 7.922344020211357e-06,
+      "loss": 0.8839,
+      "step": 253
+    },
+    {
+      "epoch": 0.7430521696733301,
+      "grad_norm": 0.6238544855656891,
+      "learning_rate": 7.9015473961634e-06,
+      "loss": 0.8777,
+      "step": 254
+    },
+    {
+      "epoch": 0.7459775719161384,
+      "grad_norm": 0.6095828534395317,
+      "learning_rate": 7.880674810931572e-06,
+      "loss": 0.9006,
+      "step": 255
+    },
+    {
+      "epoch": 0.7489029741589469,
+      "grad_norm": 0.6434213102088783,
+      "learning_rate": 7.859726810950606e-06,
+      "loss": 0.9302,
+      "step": 256
+    },
+    {
+      "epoch": 0.7518283764017553,
+      "grad_norm": 0.6997507230121648,
+      "learning_rate": 7.83870394462956e-06,
+      "loss": 0.8709,
+      "step": 257
+    },
+    {
+      "epoch": 0.7547537786445636,
+      "grad_norm": 0.6092872815949443,
+      "learning_rate": 7.817606762337465e-06,
+      "loss": 0.9142,
+      "step": 258
+    },
+    {
+      "epoch": 0.7547537786445636,
+      "eval_loss": 1.3693060874938965,
+      "eval_runtime": 65.5257,
+      "eval_samples_per_second": 14.788,
+      "eval_steps_per_second": 2.472,
+      "step": 258
+    },
+    {
+      "epoch": 0.757679180887372,
+      "grad_norm": 0.6246678441323336,
+      "learning_rate": 7.796435816388899e-06,
+      "loss": 0.9005,
+      "step": 259
+    },
+    {
+      "epoch": 0.7606045831301804,
+      "grad_norm": 0.5912377668528622,
+      "learning_rate": 7.77519166102955e-06,
+      "loss": 0.9017,
+      "step": 260
+    },
+    {
+      "epoch": 0.7635299853729888,
+      "grad_norm": 0.6053057054784722,
+      "learning_rate": 7.753874852421685e-06,
+      "loss": 0.8919,
+      "step": 261
+    },
+    {
+      "epoch": 0.7664553876157971,
+      "grad_norm": 0.5744146885343826,
+      "learning_rate": 7.73248594862961e-06,
+      "loss": 0.9064,
+      "step": 262
+    },
+    {
+      "epoch": 0.7693807898586056,
+      "grad_norm": 0.6319612148391044,
+      "learning_rate": 7.711025509605041e-06,
+      "loss": 0.9031,
+      "step": 263
+    },
+    {
+      "epoch": 0.7723061921014139,
+      "grad_norm": 0.5912614698781004,
+      "learning_rate": 7.689494097172457e-06,
+      "loss": 0.901,
+      "step": 264
+    },
+    {
+      "epoch": 0.7752315943442223,
+      "grad_norm": 0.6664929332095557,
+      "learning_rate": 7.66789227501439e-06,
+      "loss": 0.899,
+      "step": 265
+    },
+    {
+      "epoch": 0.7781569965870307,
+      "grad_norm": 0.6153709745040032,
+      "learning_rate": 7.646220608656662e-06,
+      "loss": 0.8814,
+      "step": 266
+    },
+    {
+      "epoch": 0.7810823988298391,
+      "grad_norm": 0.6256834772904273,
+      "learning_rate": 7.624479665453593e-06,
+      "loss": 0.898,
+      "step": 267
+    },
+    {
+      "epoch": 0.7840078010726474,
+      "grad_norm": 0.629527156196636,
+      "learning_rate": 7.602670014573128e-06,
+      "loss": 0.8804,
+      "step": 268
+    },
+    {
+      "epoch": 0.7869332033154559,
+      "grad_norm": 0.6326221554834266,
+      "learning_rate": 7.580792226981954e-06,
+      "loss": 0.8719,
+      "step": 269
+    },
+    {
+      "epoch": 0.7898586055582643,
+      "grad_norm": 0.6228147000647801,
+      "learning_rate": 7.558846875430548e-06,
+      "loss": 0.8951,
+      "step": 270
+    },
+    {
+      "epoch": 0.7927840078010726,
+      "grad_norm": 0.6300762602114698,
+      "learning_rate": 7.536834534438174e-06,
+      "loss": 0.8786,
+      "step": 271
+    },
+    {
+      "epoch": 0.7957094100438811,
+      "grad_norm": 0.602370277875063,
+      "learning_rate": 7.514755780277854e-06,
+      "loss": 0.899,
+      "step": 272
+    },
+    {
+      "epoch": 0.7986348122866894,
+      "grad_norm": 0.668424013856032,
+      "learning_rate": 7.492611190961272e-06,
+      "loss": 0.922,
+      "step": 273
+    },
+    {
+      "epoch": 0.8015602145294978,
+      "grad_norm": 0.643421950775731,
+      "learning_rate": 7.470401346223653e-06,
+      "loss": 0.9129,
+      "step": 274
+    },
+    {
+      "epoch": 0.8044856167723062,
+      "grad_norm": 0.6598339736650571,
+      "learning_rate": 7.448126827508573e-06,
+      "loss": 0.8857,
+      "step": 275
+    },
+    {
+      "epoch": 0.8074110190151146,
+      "grad_norm": 0.5798833085074291,
+      "learning_rate": 7.425788217952744e-06,
+      "loss": 0.9137,
+      "step": 276
+    },
+    {
+      "epoch": 0.8103364212579229,
+      "grad_norm": 0.6402512533541488,
+      "learning_rate": 7.403386102370751e-06,
+      "loss": 0.9064,
+      "step": 277
+    },
+    {
+      "epoch": 0.8132618235007314,
+      "grad_norm": 0.5779865664446158,
+      "learning_rate": 7.380921067239732e-06,
+      "loss": 0.8877,
+      "step": 278
+    },
+    {
+      "epoch": 0.8161872257435397,
+      "grad_norm": 0.6252271460860866,
+      "learning_rate": 7.3583937006840335e-06,
+      "loss": 0.887,
+      "step": 279
+    },
+    {
+      "epoch": 0.8191126279863481,
+      "grad_norm": 0.5885152139853308,
+      "learning_rate": 7.335804592459811e-06,
+      "loss": 0.8857,
+      "step": 280
+    },
+    {
+      "epoch": 0.8220380302291566,
+      "grad_norm": 0.6246237578334921,
+      "learning_rate": 7.313154333939587e-06,
+      "loss": 0.8807,
+      "step": 281
+    },
+    {
+      "epoch": 0.8249634324719649,
+      "grad_norm": 0.6141579913787804,
+      "learning_rate": 7.2904435180967695e-06,
+      "loss": 0.8912,
+      "step": 282
+    },
+    {
+      "epoch": 0.8278888347147733,
+      "grad_norm": 0.6181601204601509,
+      "learning_rate": 7.26767273949013e-06,
+      "loss": 0.884,
+      "step": 283
+    },
+    {
+      "epoch": 0.8308142369575817,
+      "grad_norm": 0.5658821051405528,
+      "learning_rate": 7.244842594248244e-06,
+      "loss": 0.8924,
+      "step": 284
+    },
+    {
+      "epoch": 0.8337396392003901,
+      "grad_norm": 0.598596513563131,
+      "learning_rate": 7.221953680053867e-06,
+      "loss": 0.8869,
+      "step": 285
+    },
+    {
+      "epoch": 0.8366650414431984,
+      "grad_norm": 0.5757584762578442,
+      "learning_rate": 7.1990065961283075e-06,
+      "loss": 0.8883,
+      "step": 286
+    },
+    {
+      "epoch": 0.8395904436860068,
+      "grad_norm": 0.6121626641719572,
+      "learning_rate": 7.1760019432157295e-06,
+      "loss": 0.9127,
+      "step": 287
+    },
+    {
+      "epoch": 0.8425158459288152,
+      "grad_norm": 0.6040818769702724,
+      "learning_rate": 7.1529403235674236e-06,
+      "loss": 0.8925,
+      "step": 288
+    },
+    {
+      "epoch": 0.8454412481716236,
+      "grad_norm": 0.6694613001668741,
+      "learning_rate": 7.129822340926045e-06,
+      "loss": 0.8911,
+      "step": 289
+    },
+    {
+      "epoch": 0.8483666504144319,
+      "grad_norm": 0.6263429758841262,
+      "learning_rate": 7.106648600509809e-06,
+      "loss": 0.8704,
+      "step": 290
+    },
+    {
+      "epoch": 0.8512920526572404,
+      "grad_norm": 0.6284317810383815,
+      "learning_rate": 7.083419708996641e-06,
+      "loss": 0.93,
+      "step": 291
+    },
+    {
+      "epoch": 0.8542174549000487,
+      "grad_norm": 0.6255860929144157,
+      "learning_rate": 7.060136274508296e-06,
+      "loss": 0.9188,
+      "step": 292
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.6875778643587599,
+      "learning_rate": 7.036798906594442e-06,
+      "loss": 0.8848,
+      "step": 293
+    },
+    {
+      "epoch": 0.8600682593856656,
+      "grad_norm": 0.6292538167195054,
+      "learning_rate": 7.0134082162167e-06,
+      "loss": 0.8798,
+      "step": 294
+    },
+    {
+      "epoch": 0.8629936616284739,
+      "grad_norm": 0.6780000891153708,
+      "learning_rate": 6.989964815732643e-06,
+      "loss": 0.8935,
+      "step": 295
+    },
+    {
+      "epoch": 0.8659190638712823,
+      "grad_norm": 0.590176250826063,
+      "learning_rate": 6.9664693188797776e-06,
+      "loss": 0.9009,
+      "step": 296
+    },
+    {
+      "epoch": 0.8688444661140907,
+      "grad_norm": 0.5785779594775584,
+      "learning_rate": 6.942922340759465e-06,
+      "loss": 0.9051,
+      "step": 297
+    },
+    {
+      "epoch": 0.8717698683568991,
+      "grad_norm": 0.5978845535479155,
+      "learning_rate": 6.9193244978208226e-06,
+      "loss": 0.9006,
+      "step": 298
+    },
+    {
+      "epoch": 0.8746952705997074,
+      "grad_norm": 0.5859143049414189,
+      "learning_rate": 6.895676407844587e-06,
+      "loss": 0.9037,
+      "step": 299
+    },
+    {
+      "epoch": 0.8776206728425159,
+      "grad_norm": 0.5839240106472464,
+      "learning_rate": 6.8719786899269426e-06,
+      "loss": 0.8989,
+      "step": 300
+    },
+    {
+      "epoch": 0.8805460750853242,
+      "grad_norm": 0.6103420392295683,
+      "learning_rate": 6.848231964463301e-06,
+      "loss": 0.8953,
+      "step": 301
+    },
+    {
+      "epoch": 0.8834714773281326,
+      "grad_norm": 0.5686560770840599,
+      "learning_rate": 6.8244368531320795e-06,
+      "loss": 0.8766,
+      "step": 302
+    },
+    {
+      "epoch": 0.886396879570941,
+      "grad_norm": 0.61072247574655,
+      "learning_rate": 6.800593978878407e-06,
+      "loss": 0.8762,
+      "step": 303
+    },
+    {
+      "epoch": 0.8893222818137494,
+      "grad_norm": 0.6158369105071173,
+      "learning_rate": 6.776703965897831e-06,
+      "loss": 0.9028,
+      "step": 304
+    },
+    {
+      "epoch": 0.8922476840565577,
+      "grad_norm": 0.5937764317875888,
+      "learning_rate": 6.752767439619961e-06,
+      "loss": 0.9047,
+      "step": 305
+    },
+    {
+      "epoch": 0.8951730862993662,
+      "grad_norm": 0.5936048944160339,
+      "learning_rate": 6.728785026692113e-06,
+      "loss": 0.9093,
+      "step": 306
+    },
+    {
+      "epoch": 0.8980984885421746,
+      "grad_norm": 0.5761666127145109,
+      "learning_rate": 6.704757354962888e-06,
+      "loss": 0.8963,
+      "step": 307
+    },
+    {
+      "epoch": 0.9010238907849829,
+      "grad_norm": 0.5698243858767273,
+      "learning_rate": 6.680685053465743e-06,
+      "loss": 0.889,
+      "step": 308
+    },
+    {
+      "epoch": 0.9039492930277914,
+      "grad_norm": 0.6187986831036327,
+      "learning_rate": 6.656568752402521e-06,
+      "loss": 0.8793,
+      "step": 309
+    },
+    {
+      "epoch": 0.9068746952705997,
+      "grad_norm": 0.599039810186881,
+      "learning_rate": 6.632409083126959e-06,
+      "loss": 0.9014,
+      "step": 310
+    },
+    {
+      "epoch": 0.9098000975134081,
+      "grad_norm": 0.5965723397933764,
+      "learning_rate": 6.608206678128143e-06,
+      "loss": 0.9036,
+      "step": 311
+    },
+    {
+      "epoch": 0.9127254997562165,
+      "grad_norm": 0.5993919939223842,
+      "learning_rate": 6.583962171013974e-06,
+      "loss": 0.8921,
+      "step": 312
+    },
+    {
+      "epoch": 0.9156509019990249,
+      "grad_norm": 0.5924590487598618,
+      "learning_rate": 6.559676196494555e-06,
+      "loss": 0.9203,
+      "step": 313
+    },
+    {
+      "epoch": 0.9185763042418332,
+      "grad_norm": 0.5637168699409383,
+      "learning_rate": 6.535349390365597e-06,
+      "loss": 0.8827,
+      "step": 314
+    },
+    {
+      "epoch": 0.9215017064846417,
+      "grad_norm": 0.6068559586638762,
+      "learning_rate": 6.510982389491756e-06,
+      "loss": 0.9011,
+      "step": 315
+    },
+    {
+      "epoch": 0.92442710872745,
+      "grad_norm": 0.5818145636426237,
+      "learning_rate": 6.486575831789974e-06,
+      "loss": 0.8927,
+      "step": 316
+    },
+    {
+      "epoch": 0.9273525109702584,
+      "grad_norm": 0.6129278738869518,
+      "learning_rate": 6.462130356212768e-06,
+      "loss": 0.9059,
+      "step": 317
+    },
+    {
+      "epoch": 0.9302779132130667,
+      "grad_norm": 0.5842516474759907,
+      "learning_rate": 6.437646602731509e-06,
+      "loss": 0.8781,
+      "step": 318
+    },
+    {
+      "epoch": 0.9332033154558752,
+      "grad_norm": 0.5740360820130547,
+      "learning_rate": 6.413125212319664e-06,
+      "loss": 0.9031,
+      "step": 319
+    },
+    {
+      "epoch": 0.9361287176986836,
+      "grad_norm": 0.6305695619214373,
+      "learning_rate": 6.388566826936025e-06,
+      "loss": 0.9111,
+      "step": 320
+    },
+    {
+      "epoch": 0.9390541199414919,
+      "grad_norm": 0.6403885483257377,
+      "learning_rate": 6.363972089507886e-06,
+      "loss": 0.8765,
+      "step": 321
+    },
+    {
+      "epoch": 0.9419795221843004,
+      "grad_norm": 0.634525294542331,
+      "learning_rate": 6.3393416439142255e-06,
+      "loss": 0.9096,
+      "step": 322
+    },
+    {
+      "epoch": 0.9449049244271087,
+      "grad_norm": 0.629802499730145,
+      "learning_rate": 6.314676134968845e-06,
+      "loss": 0.8842,
+      "step": 323
+    },
+    {
+      "epoch": 0.9478303266699171,
+      "grad_norm": 0.6138154866450481,
+      "learning_rate": 6.28997620840349e-06,
+      "loss": 0.9042,
+      "step": 324
+    },
+    {
+      "epoch": 0.9507557289127255,
+      "grad_norm": 0.5889081155134466,
+      "learning_rate": 6.26524251085094e-06,
+      "loss": 0.8978,
+      "step": 325
+    },
+    {
+      "epoch": 0.9536811311555339,
+      "grad_norm": 0.5885045686141304,
+      "learning_rate": 6.240475689828087e-06,
+      "loss": 0.8669,
+      "step": 326
+    },
+    {
+      "epoch": 0.9566065333983422,
+      "grad_norm": 0.5813834952894164,
+      "learning_rate": 6.21567639371898e-06,
+      "loss": 0.8573,
+      "step": 327
+    },
+    {
+      "epoch": 0.9595319356411507,
+      "grad_norm": 0.6297897811406099,
+      "learning_rate": 6.190845271757846e-06,
+      "loss": 0.901,
+      "step": 328
+    },
+    {
+      "epoch": 0.962457337883959,
+      "grad_norm": 0.5833991294096019,
+      "learning_rate": 6.165982974012104e-06,
+      "loss": 0.9206,
+      "step": 329
+    },
+    {
+      "epoch": 0.9653827401267674,
+      "grad_norm": 0.5693519759193476,
+      "learning_rate": 6.141090151365341e-06,
+      "loss": 0.8581,
+      "step": 330
+    },
+    {
+      "epoch": 0.9683081423695759,
+      "grad_norm": 0.6086478543119002,
+      "learning_rate": 6.116167455500265e-06,
+      "loss": 0.8945,
+      "step": 331
+    },
+    {
+      "epoch": 0.9712335446123842,
+      "grad_norm": 0.5650924803920132,
+      "learning_rate": 6.0912155388816584e-06,
+      "loss": 0.8941,
+      "step": 332
+    },
+    {
+      "epoch": 0.9741589468551926,
+      "grad_norm": 0.5903130575046514,
+      "learning_rate": 6.066235054739289e-06,
+      "loss": 0.8899,
+      "step": 333
+    },
+    {
+      "epoch": 0.977084349098001,
+      "grad_norm": 0.5975948126480749,
+      "learning_rate": 6.041226657050804e-06,
+      "loss": 0.8607,
+      "step": 334
+    },
+    {
+      "epoch": 0.9800097513408094,
+      "grad_norm": 0.6025105840404439,
+      "learning_rate": 6.01619100052462e-06,
+      "loss": 0.8885,
+      "step": 335
+    },
+    {
+      "epoch": 0.9829351535836177,
+      "grad_norm": 0.6046007091634541,
+      "learning_rate": 5.991128740582774e-06,
+      "loss": 0.8897,
+      "step": 336
+    },
+    {
+      "epoch": 0.9858605558264262,
+      "grad_norm": 0.5434521802533933,
+      "learning_rate": 5.966040533343772e-06,
+      "loss": 0.8844,
+      "step": 337
+    },
+    {
+      "epoch": 0.9887859580692345,
+      "grad_norm": 0.6303574796088046,
+      "learning_rate": 5.9409270356054025e-06,
+      "loss": 0.8802,
+      "step": 338
+    },
+    {
+      "epoch": 0.9917113603120429,
+      "grad_norm": 0.5819203211883127,
+      "learning_rate": 5.915788904827553e-06,
+      "loss": 0.8948,
+      "step": 339
+    },
+    {
+      "epoch": 0.9946367625548513,
+      "grad_norm": 0.5729927595936578,
+      "learning_rate": 5.890626799114991e-06,
+      "loss": 0.9198,
+      "step": 340
+    },
+    {
+      "epoch": 0.9975621647976597,
+      "grad_norm": 0.5643044236514093,
+      "learning_rate": 5.865441377200137e-06,
+      "loss": 0.8738,
+      "step": 341
+    },
+    {
+      "epoch": 1.000487567040468,
+      "grad_norm": 0.5893972684647703,
+      "learning_rate": 5.840233298425818e-06,
+      "loss": 0.8821,
+      "step": 342
+    },
+    {
+      "epoch": 1.0007308160779538,
+      "grad_norm": 0.68110454506424,
+      "learning_rate": 5.815003222728007e-06,
+      "loss": 0.8728,
+      "step": 343
+    },
+    {
+      "epoch": 1.0036540803897687,
+      "grad_norm": 0.8602651253070958,
+      "learning_rate": 5.789751810618551e-06,
+      "loss": 0.7967,
+      "step": 344
+    },
+    {
+      "epoch": 1.0036540803897687,
+      "eval_loss": 1.365891695022583,
+      "eval_runtime": 65.455,
+      "eval_samples_per_second": 14.804,
+      "eval_steps_per_second": 2.475,
+      "step": 344
+    },
+    {
+      "epoch": 1.0065773447015833,
+      "grad_norm": 0.6693783832444782,
+      "learning_rate": 5.764479723167867e-06,
+      "loss": 0.8162,
+      "step": 345
+    },
+    {
+      "epoch": 1.0095006090133982,
+      "grad_norm": 0.8649026077052362,
+      "learning_rate": 5.739187621987649e-06,
+      "loss": 0.7811,
+      "step": 346
+    },
+    {
+      "epoch": 1.012423873325213,
+      "grad_norm": 0.7283056665598604,
+      "learning_rate": 5.713876169213538e-06,
+      "loss": 0.8023,
+      "step": 347
+    },
+    {
+      "epoch": 1.015347137637028,
+      "grad_norm": 0.6464070682314531,
+      "learning_rate": 5.688546027487793e-06,
+      "loss": 0.8299,
+      "step": 348
+    },
+    {
+      "epoch": 1.0182704019488429,
+      "grad_norm": 0.7459265332536604,
+      "learning_rate": 5.663197859941938e-06,
+      "loss": 0.7923,
+      "step": 349
+    },
+    {
+      "epoch": 1.0211936662606578,
+      "grad_norm": 0.6961432197550056,
+      "learning_rate": 5.637832330179409e-06,
+      "loss": 0.7985,
+      "step": 350
+    },
+    {
+      "epoch": 1.0241169305724727,
+      "grad_norm": 0.6700485502738509,
+      "learning_rate": 5.612450102258175e-06,
+      "loss": 0.7976,
+      "step": 351
+    },
+    {
+      "epoch": 1.0270401948842875,
+      "grad_norm": 0.7702215817383979,
+      "learning_rate": 5.587051840673356e-06,
+      "loss": 0.8131,
+      "step": 352
+    },
+    {
+      "epoch": 1.0299634591961022,
+      "grad_norm": 0.6852662863129292,
+      "learning_rate": 5.56163821033982e-06,
+      "loss": 0.8029,
+      "step": 353
+    },
+    {
+      "epoch": 1.032886723507917,
+      "grad_norm": 0.7217757781141521,
+      "learning_rate": 5.536209876574793e-06,
+      "loss": 0.7978,
+      "step": 354
+    },
+    {
+      "epoch": 1.035809987819732,
+      "grad_norm": 0.7300263042947811,
+      "learning_rate": 5.510767505080419e-06,
+      "loss": 0.8166,
+      "step": 355
+    },
+    {
+      "epoch": 1.0387332521315469,
+      "grad_norm": 0.6920161152507025,
+      "learning_rate": 5.4853117619263496e-06,
+      "loss": 0.8128,
+      "step": 356
+    },
+    {
+      "epoch": 1.0416565164433618,
+      "grad_norm": 0.7747760542004816,
+      "learning_rate": 5.4598433135323015e-06,
+      "loss": 0.8232,
+      "step": 357
+    },
+    {
+      "epoch": 1.0445797807551767,
+      "grad_norm": 0.6763340836215797,
+      "learning_rate": 5.434362826650603e-06,
+      "loss": 0.8125,
+      "step": 358
+    },
+    {
+      "epoch": 1.0475030450669915,
+      "grad_norm": 0.6209130990558949,
+      "learning_rate": 5.4088709683487494e-06,
+      "loss": 0.808,
+      "step": 359
+    },
+    {
+      "epoch": 1.0504263093788064,
+      "grad_norm": 0.6893839443256197,
+      "learning_rate": 5.383368405991932e-06,
+      "loss": 0.8136,
+      "step": 360
+    },
+    {
+      "epoch": 1.053349573690621,
+      "grad_norm": 0.6233006238408513,
+      "learning_rate": 5.357855807225573e-06,
+      "loss": 0.8202,
+      "step": 361
+    },
+    {
+      "epoch": 1.056272838002436,
+      "grad_norm": 0.6163295638238943,
+      "learning_rate": 5.332333839957835e-06,
+      "loss": 0.7972,
+      "step": 362
+    },
+    {
+      "epoch": 1.0591961023142509,
+      "grad_norm": 0.6239471219126078,
+      "learning_rate": 5.3068031723421545e-06,
+      "loss": 0.7933,
+      "step": 363
+    },
+    {
+      "epoch": 1.0621193666260658,
+      "grad_norm": 0.6491549577786548,
+      "learning_rate": 5.281264472759731e-06,
+      "loss": 0.8144,
+      "step": 364
+    },
+    {
+      "epoch": 1.0650426309378807,
+      "grad_norm": 0.6527091363470504,
+      "learning_rate": 5.255718409802041e-06,
+      "loss": 0.7687,
+      "step": 365
+    },
+    {
+      "epoch": 1.0679658952496955,
+      "grad_norm": 0.6385672567759509,
+      "learning_rate": 5.230165652253329e-06,
+      "loss": 0.8159,
+      "step": 366
+    },
+    {
+      "epoch": 1.0708891595615104,
+      "grad_norm": 0.5864111560675286,
+      "learning_rate": 5.2046068690731035e-06,
+      "loss": 0.7831,
+      "step": 367
+    },
+    {
+      "epoch": 1.0738124238733253,
+      "grad_norm": 0.6194785781749127,
+      "learning_rate": 5.179042729378616e-06,
+      "loss": 0.8052,
+      "step": 368
+    },
+    {
+      "epoch": 1.07673568818514,
+      "grad_norm": 0.6362356799862054,
+      "learning_rate": 5.153473902427355e-06,
+      "loss": 0.8196,
+      "step": 369
+    },
+    {
+      "epoch": 1.0796589524969549,
+      "grad_norm": 0.5942323267279191,
+      "learning_rate": 5.127901057599517e-06,
+      "loss": 0.8161,
+      "step": 370
+    },
+    {
+      "epoch": 1.0825822168087698,
+      "grad_norm": 0.5742483554036059,
+      "learning_rate": 5.1023248643804845e-06,
+      "loss": 0.8228,
+      "step": 371
+    },
+    {
+      "epoch": 1.0855054811205846,
+      "grad_norm": 0.5860306244571696,
+      "learning_rate": 5.076745992343297e-06,
+      "loss": 0.8212,
+      "step": 372
+    },
+    {
+      "epoch": 1.0884287454323995,
+      "grad_norm": 0.5773619726397791,
+      "learning_rate": 5.0511651111311285e-06,
+      "loss": 0.8018,
+      "step": 373
+    },
+    {
+      "epoch": 1.0913520097442144,
+      "grad_norm": 0.6105870953754982,
+      "learning_rate": 5.025582890439752e-06,
+      "loss": 0.8227,
+      "step": 374
+    },
+    {
+      "epoch": 1.0942752740560293,
+      "grad_norm": 0.608222048968305,
+      "learning_rate": 5e-06,
+      "loss": 0.7955,
+      "step": 375
+    },
+    {
+      "epoch": 1.0971985383678442,
+      "grad_norm": 0.602520252718154,
+      "learning_rate": 4.97441710956025e-06,
+      "loss": 0.8038,
+      "step": 376
+    },
+    {
+      "epoch": 1.1001218026796589,
+      "grad_norm": 0.647759737480258,
+      "learning_rate": 4.948834888868872e-06,
+      "loss": 0.7891,
+      "step": 377
+    },
+    {
+      "epoch": 1.1030450669914738,
+      "grad_norm": 0.6466942994000808,
+      "learning_rate": 4.9232540076567034e-06,
+      "loss": 0.838,
+      "step": 378
+    },
+    {
+      "epoch": 1.1059683313032886,
+      "grad_norm": 0.7597398060034541,
+      "learning_rate": 4.897675135619517e-06,
+      "loss": 0.7992,
+      "step": 379
+    },
+    {
+      "epoch": 1.1088915956151035,
+      "grad_norm": 0.5916241197525671,
+      "learning_rate": 4.872098942400484e-06,
+      "loss": 0.834,
+      "step": 380
+    },
+    {
+      "epoch": 1.1118148599269184,
+      "grad_norm": 0.7488543256724444,
+      "learning_rate": 4.846526097572646e-06,
+      "loss": 0.8056,
+      "step": 381
+    },
+    {
+      "epoch": 1.1147381242387333,
+      "grad_norm": 0.6127152632610644,
+      "learning_rate": 4.820957270621385e-06,
+      "loss": 0.8152,
+      "step": 382
+    },
+    {
+      "epoch": 1.1176613885505482,
+      "grad_norm": 0.6772622229366005,
+      "learning_rate": 4.795393130926899e-06,
+      "loss": 0.8112,
+      "step": 383
+    },
+    {
+      "epoch": 1.1205846528623629,
+      "grad_norm": 0.6100582490809515,
+      "learning_rate": 4.769834347746672e-06,
+      "loss": 0.7971,
+      "step": 384
+    },
+    {
+      "epoch": 1.1235079171741778,
+      "grad_norm": 0.6138527497182587,
+      "learning_rate": 4.744281590197961e-06,
+      "loss": 0.8096,
+      "step": 385
+    },
+    {
+      "epoch": 1.1264311814859926,
+      "grad_norm": 0.5946729261402381,
+      "learning_rate": 4.71873552724027e-06,
+      "loss": 0.7972,
+      "step": 386
+    },
+    {
+      "epoch": 1.1293544457978075,
+      "grad_norm": 0.6272869943876259,
+      "learning_rate": 4.693196827657848e-06,
+      "loss": 0.8099,
+      "step": 387
+    },
+    {
+      "epoch": 1.1322777101096224,
+      "grad_norm": 0.6709827503445973,
+      "learning_rate": 4.667666160042166e-06,
+      "loss": 0.8035,
+      "step": 388
+    },
+    {
+      "epoch": 1.1352009744214373,
+      "grad_norm": 0.5802507520284231,
+      "learning_rate": 4.642144192774429e-06,
+      "loss": 0.8259,
+      "step": 389
+    },
+    {
+      "epoch": 1.1381242387332522,
+      "grad_norm": 0.5934148999822147,
+      "learning_rate": 4.616631594008069e-06,
+      "loss": 0.7784,
+      "step": 390
+    },
+    {
+      "epoch": 1.141047503045067,
+      "grad_norm": 0.670256603061476,
+      "learning_rate": 4.591129031651252e-06,
+      "loss": 0.7982,
+      "step": 391
+    },
+    {
+      "epoch": 1.143970767356882,
+      "grad_norm": 0.5729733544495296,
+      "learning_rate": 4.5656371733493986e-06,
+      "loss": 0.7902,
+      "step": 392
+    },
+    {
+      "epoch": 1.1468940316686966,
+      "grad_norm": 0.6506904279982785,
+      "learning_rate": 4.540156686467699e-06,
+      "loss": 0.8144,
+      "step": 393
+    },
+    {
+      "epoch": 1.1498172959805115,
+      "grad_norm": 0.6305703446057582,
+      "learning_rate": 4.514688238073651e-06,
+      "loss": 0.8346,
+      "step": 394
+    },
+    {
+      "epoch": 1.1527405602923264,
+      "grad_norm": 0.6207821437251902,
+      "learning_rate": 4.489232494919583e-06,
+      "loss": 0.814,
+      "step": 395
+    },
+    {
+      "epoch": 1.1556638246041413,
+      "grad_norm": 0.6326520891011468,
+      "learning_rate": 4.463790123425209e-06,
+      "loss": 0.8173,
+      "step": 396
+    },
+    {
+      "epoch": 1.1585870889159562,
+      "grad_norm": 0.6361956657928358,
+      "learning_rate": 4.438361789660182e-06,
+      "loss": 0.8024,
+      "step": 397
+    },
+    {
+      "epoch": 1.161510353227771,
+      "grad_norm": 0.6274266062590439,
+      "learning_rate": 4.412948159326647e-06,
+      "loss": 0.8029,
+      "step": 398
+    },
+    {
+      "epoch": 1.164433617539586,
+      "grad_norm": 0.5964467349901271,
+      "learning_rate": 4.3875498977418255e-06,
+      "loss": 0.8064,
+      "step": 399
+    },
+    {
+      "epoch": 1.1673568818514006,
+      "grad_norm": 0.7270366961339101,
+      "learning_rate": 4.362167669820593e-06,
+      "loss": 0.8061,
+      "step": 400
+    },
+    {
+      "epoch": 1.1702801461632155,
+      "grad_norm": 0.5862080854450132,
+      "learning_rate": 4.3368021400580635e-06,
+      "loss": 0.8113,
+      "step": 401
+    },
+    {
+      "epoch": 1.1732034104750304,
+      "grad_norm": 0.6141962978102556,
+      "learning_rate": 4.311453972512209e-06,
+      "loss": 0.8161,
+      "step": 402
+    },
+    {
+      "epoch": 1.1761266747868453,
+      "grad_norm": 0.6096769412968969,
+      "learning_rate": 4.286123830786463e-06,
+      "loss": 0.7977,
+      "step": 403
+    },
+    {
+      "epoch": 1.1790499390986602,
+      "grad_norm": 0.5895182827045679,
+      "learning_rate": 4.260812378012353e-06,
+      "loss": 0.8123,
+      "step": 404
+    },
+    {
+      "epoch": 1.181973203410475,
+      "grad_norm": 0.6004537708021467,
+      "learning_rate": 4.235520276832134e-06,
+      "loss": 0.797,
+      "step": 405
+    },
+    {
+      "epoch": 1.18489646772229,
+      "grad_norm": 0.5948518568661362,
+      "learning_rate": 4.2102481893814504e-06,
+      "loss": 0.8172,
+      "step": 406
+    },
+    {
+      "epoch": 1.1878197320341048,
+      "grad_norm": 0.5912718596576074,
+      "learning_rate": 4.1849967772719935e-06,
+      "loss": 0.7908,
+      "step": 407
+    },
+    {
+      "epoch": 1.1907429963459195,
+      "grad_norm": 0.5912188183434732,
+      "learning_rate": 4.159766701574184e-06,
+      "loss": 0.7847,
+      "step": 408
+    },
+    {
+      "epoch": 1.1936662606577344,
+      "grad_norm": 0.6458915180295917,
+      "learning_rate": 4.1345586227998645e-06,
+      "loss": 0.7956,
+      "step": 409
+    },
+    {
+      "epoch": 1.1965895249695493,
+      "grad_norm": 0.5860427146707542,
+      "learning_rate": 4.109373200885011e-06,
+      "loss": 0.8171,
+      "step": 410
+    },
+    {
+      "epoch": 1.1995127892813642,
+      "grad_norm": 0.5965859399277259,
+      "learning_rate": 4.084211095172448e-06,
+      "loss": 0.8057,
+      "step": 411
+    },
+    {
+      "epoch": 1.202436053593179,
+      "grad_norm": 0.6145061256713188,
+      "learning_rate": 4.059072964394599e-06,
+      "loss": 0.7856,
+      "step": 412
+    },
+    {
+      "epoch": 1.205359317904994,
+      "grad_norm": 0.5938060609434931,
+      "learning_rate": 4.0339594666562294e-06,
+      "loss": 0.8035,
+      "step": 413
+    },
+    {
+      "epoch": 1.2082825822168088,
+      "grad_norm": 0.6074730571618651,
+      "learning_rate": 4.008871259417227e-06,
+      "loss": 0.7978,
+      "step": 414
+    },
+    {
+      "epoch": 1.2112058465286237,
+      "grad_norm": 0.5955227016960192,
+      "learning_rate": 3.983808999475381e-06,
+      "loss": 0.8164,
+      "step": 415
+    },
+    {
+      "epoch": 1.2141291108404384,
+      "grad_norm": 0.5890660617212938,
+      "learning_rate": 3.958773342949196e-06,
+      "loss": 0.8189,
+      "step": 416
+    },
+    {
+      "epoch": 1.2170523751522533,
+      "grad_norm": 0.6069302365393437,
+      "learning_rate": 3.933764945260712e-06,
+      "loss": 0.8037,
+      "step": 417
+    },
+    {
+      "epoch": 1.2199756394640682,
+      "grad_norm": 0.596287098938014,
+      "learning_rate": 3.9087844611183415e-06,
+      "loss": 0.8057,
+      "step": 418
+    },
+    {
+      "epoch": 1.222898903775883,
+      "grad_norm": 0.6002784512679291,
+      "learning_rate": 3.883832544499735e-06,
+      "loss": 0.7997,
+      "step": 419
+    },
+    {
+      "epoch": 1.225822168087698,
+      "grad_norm": 0.6099781756811369,
+      "learning_rate": 3.858909848634661e-06,
+      "loss": 0.8128,
+      "step": 420
+    },
+    {
+      "epoch": 1.2287454323995128,
+      "grad_norm": 0.6974709875164911,
+      "learning_rate": 3.8340170259878965e-06,
+      "loss": 0.7665,
+      "step": 421
+    },
+    {
+      "epoch": 1.2316686967113277,
+      "grad_norm": 0.5941348378805758,
+      "learning_rate": 3.8091547282421544e-06,
+      "loss": 0.8018,
+      "step": 422
+    },
+    {
+      "epoch": 1.2345919610231424,
+      "grad_norm": 0.6157891176270607,
+      "learning_rate": 3.7843236062810216e-06,
+      "loss": 0.7911,
+      "step": 423
+    },
+    {
+      "epoch": 1.2375152253349573,
+      "grad_norm": 0.6544854607872745,
+      "learning_rate": 3.7595243101719126e-06,
+      "loss": 0.8172,
+      "step": 424
+    },
+    {
+      "epoch": 1.2404384896467722,
+      "grad_norm": 0.5745985979840479,
+      "learning_rate": 3.7347574891490597e-06,
+      "loss": 0.804,
+      "step": 425
+    },
+    {
+      "epoch": 1.243361753958587,
+      "grad_norm": 0.6354083348942862,
+      "learning_rate": 3.71002379159651e-06,
+      "loss": 0.7796,
+      "step": 426
+    },
+    {
+      "epoch": 1.246285018270402,
+      "grad_norm": 0.620970843336737,
+      "learning_rate": 3.6853238650311553e-06,
+      "loss": 0.8224,
+      "step": 427
+    },
+    {
+      "epoch": 1.2492082825822168,
+      "grad_norm": 0.6232417871814647,
+      "learning_rate": 3.6606583560857757e-06,
+      "loss": 0.818,
+      "step": 428
+    },
+    {
+      "epoch": 1.2521315468940317,
+      "grad_norm": 0.6127780408174556,
+      "learning_rate": 3.636027910492115e-06,
+      "loss": 0.8117,
+      "step": 429
+    },
+    {
+      "epoch": 1.2550548112058466,
+      "grad_norm": 0.5789315663515364,
+      "learning_rate": 3.611433173063976e-06,
+      "loss": 0.7912,
+      "step": 430
+    },
+    {
+      "epoch": 1.2550548112058466,
+      "eval_loss": 1.3727632761001587,
+      "eval_runtime": 65.3881,
+      "eval_samples_per_second": 14.819,
+      "eval_steps_per_second": 2.478,
+      "step": 430
+    },
+    {
+      "epoch": 1.2579780755176615,
+      "grad_norm": 0.6009615498767048,
+      "learning_rate": 3.5868747876803356e-06,
+      "loss": 0.7952,
+      "step": 431
+    },
+    {
+      "epoch": 1.2609013398294762,
+      "grad_norm": 0.6045746410233208,
+      "learning_rate": 3.562353397268492e-06,
+      "loss": 0.7934,
+      "step": 432
+    },
+    {
+      "epoch": 1.263824604141291,
+      "grad_norm": 0.5931695254070988,
+      "learning_rate": 3.5378696437872334e-06,
+      "loss": 0.8137,
+      "step": 433
+    },
+    {
+      "epoch": 1.266747868453106,
+      "grad_norm": 0.6149684612885844,
+      "learning_rate": 3.5134241682100266e-06,
+      "loss": 0.7945,
+      "step": 434
+    },
+    {
+      "epoch": 1.2696711327649208,
+      "grad_norm": 0.572462214001696,
+      "learning_rate": 3.4890176105082436e-06,
+      "loss": 0.8232,
+      "step": 435
+    },
+    {
+      "epoch": 1.2725943970767357,
+      "grad_norm": 0.5900294807807364,
+      "learning_rate": 3.464650609634403e-06,
+      "loss": 0.812,
+      "step": 436
+    },
+    {
+      "epoch": 1.2755176613885506,
+      "grad_norm": 0.5719536650263874,
+      "learning_rate": 3.4403238035054453e-06,
+      "loss": 0.7951,
+      "step": 437
+    },
+    {
+      "epoch": 1.2784409257003655,
+      "grad_norm": 0.5654407271189463,
+      "learning_rate": 3.4160378289860272e-06,
+      "loss": 0.8344,
+      "step": 438
+    },
+    {
+      "epoch": 1.2813641900121802,
+      "grad_norm": 0.6141919442543494,
+      "learning_rate": 3.391793321871857e-06,
+      "loss": 0.8152,
+      "step": 439
+    },
+    {
+      "epoch": 1.284287454323995,
+      "grad_norm": 0.5873637470479766,
+      "learning_rate": 3.3675909168730435e-06,
+      "loss": 0.7867,
+      "step": 440
+    },
+    {
+      "epoch": 1.28721071863581,
+      "grad_norm": 0.5902445618697549,
+      "learning_rate": 3.343431247597479e-06,
+      "loss": 0.7765,
+      "step": 441
+    },
+    {
+      "epoch": 1.2901339829476248,
+      "grad_norm": 0.6015910173648741,
+      "learning_rate": 3.319314946534258e-06,
+      "loss": 0.8018,
+      "step": 442
+    },
+    {
+      "epoch": 1.2930572472594397,
+      "grad_norm": 0.5712364823565985,
+      "learning_rate": 3.295242645037112e-06,
+      "loss": 0.8085,
+      "step": 443
+    },
+    {
+      "epoch": 1.2959805115712546,
+      "grad_norm": 0.5562180227854343,
+      "learning_rate": 3.271214973307887e-06,
+      "loss": 0.8129,
+      "step": 444
+    },
+    {
+      "epoch": 1.2989037758830695,
+      "grad_norm": 0.5839696563715857,
+      "learning_rate": 3.2472325603800382e-06,
+      "loss": 0.7825,
+      "step": 445
+    },
+    {
+      "epoch": 1.3018270401948842,
+      "grad_norm": 0.5749209131454011,
+      "learning_rate": 3.2232960341021703e-06,
+      "loss": 0.7829,
+      "step": 446
+    },
+    {
+      "epoch": 1.3047503045066993,
+      "grad_norm": 0.5833897427603767,
+      "learning_rate": 3.1994060211215936e-06,
+      "loss": 0.7875,
+      "step": 447
+    },
+    {
+      "epoch": 1.307673568818514,
+      "grad_norm": 0.5642135859057068,
+      "learning_rate": 3.1755631468679217e-06,
+      "loss": 0.7904,
+      "step": 448
+    },
+    {
+      "epoch": 1.3105968331303288,
+      "grad_norm": 0.644206424516224,
+      "learning_rate": 3.1517680355366985e-06,
+      "loss": 0.7944,
+      "step": 449
+    },
+    {
+      "epoch": 1.3135200974421437,
+      "grad_norm": 0.6001327772482385,
+      "learning_rate": 3.1280213100730595e-06,
+      "loss": 0.805,
+      "step": 450
+    },
+    {
+      "epoch": 1.3164433617539586,
+      "grad_norm": 0.5813006153323479,
+      "learning_rate": 3.104323592155413e-06,
+      "loss": 0.8016,
+      "step": 451
+    },
+    {
+      "epoch": 1.3193666260657735,
+      "grad_norm": 0.5928090466919959,
+      "learning_rate": 3.08067550217918e-06,
+      "loss": 0.7969,
+      "step": 452
+    },
+    {
+      "epoch": 1.3222898903775884,
+      "grad_norm": 0.5908564631070854,
+      "learning_rate": 3.057077659240538e-06,
+      "loss": 0.8087,
+      "step": 453
+    },
+    {
+      "epoch": 1.3252131546894033,
+      "grad_norm": 0.5768938363404773,
+      "learning_rate": 3.033530681120225e-06,
+      "loss": 0.7975,
+      "step": 454
+    },
+    {
+      "epoch": 1.328136419001218,
+      "grad_norm": 0.5898657463165522,
+      "learning_rate": 3.0100351842673593e-06,
+      "loss": 0.8066,
+      "step": 455
+    },
+    {
+      "epoch": 1.3310596833130328,
+      "grad_norm": 0.6028044807784166,
+      "learning_rate": 2.9865917837833025e-06,
+      "loss": 0.792,
+      "step": 456
+    },
+    {
+      "epoch": 1.3339829476248477,
+      "grad_norm": 0.5902269088580138,
+      "learning_rate": 2.963201093405559e-06,
+      "loss": 0.7963,
+      "step": 457
+    },
+    {
+      "epoch": 1.3369062119366626,
+      "grad_norm": 0.570908075119228,
+      "learning_rate": 2.939863725491706e-06,
+      "loss": 0.7971,
+      "step": 458
+    },
+    {
+      "epoch": 1.3398294762484775,
+      "grad_norm": 0.6173543812499931,
+      "learning_rate": 2.916580291003361e-06,
+      "loss": 0.8191,
+      "step": 459
+    },
+    {
+      "epoch": 1.3427527405602924,
+      "grad_norm": 0.6343832043531719,
+      "learning_rate": 2.893351399490194e-06,
+      "loss": 0.8074,
+      "step": 460
+    },
+    {
+      "epoch": 1.3456760048721073,
+      "grad_norm": 0.5782617555335829,
+      "learning_rate": 2.870177659073958e-06,
+      "loss": 0.7978,
+      "step": 461
+    },
+    {
+      "epoch": 1.348599269183922,
+      "grad_norm": 0.6172015597729136,
+      "learning_rate": 2.84705967643258e-06,
+      "loss": 0.7965,
+      "step": 462
+    },
+    {
+      "epoch": 1.351522533495737,
+      "grad_norm": 0.6359340039521935,
+      "learning_rate": 2.8239980567842734e-06,
+      "loss": 0.8076,
+      "step": 463
+    },
+    {
+      "epoch": 1.3544457978075517,
+      "grad_norm": 0.6717197639966513,
+      "learning_rate": 2.800993403871694e-06,
+      "loss": 0.7873,
+      "step": 464
+    },
+    {
+      "epoch": 1.3573690621193666,
+      "grad_norm": 0.5964892377721963,
+      "learning_rate": 2.778046319946135e-06,
+      "loss": 0.7964,
+      "step": 465
+    },
+    {
+      "epoch": 1.3602923264311815,
+      "grad_norm": 0.6014805489255499,
+      "learning_rate": 2.75515740575176e-06,
+      "loss": 0.785,
+      "step": 466
+    },
+    {
+      "epoch": 1.3632155907429964,
+      "grad_norm": 0.59722861045332,
+      "learning_rate": 2.7323272605098718e-06,
+      "loss": 0.8169,
+      "step": 467
+    },
+    {
+      "epoch": 1.3661388550548113,
+      "grad_norm": 0.5872035783585831,
+      "learning_rate": 2.709556481903234e-06,
+      "loss": 0.7847,
+      "step": 468
+    },
+    {
+      "epoch": 1.3690621193666261,
+      "grad_norm": 0.5758494465266432,
+      "learning_rate": 2.686845666060416e-06,
+      "loss": 0.8166,
+      "step": 469
+    },
+    {
+      "epoch": 1.371985383678441,
+      "grad_norm": 0.5970395782412861,
+      "learning_rate": 2.6641954075401904e-06,
+      "loss": 0.7806,
+      "step": 470
+    },
+    {
+      "epoch": 1.3749086479902557,
+      "grad_norm": 0.5973735252514245,
+      "learning_rate": 2.6416062993159673e-06,
+      "loss": 0.8073,
+      "step": 471
+    },
+    {
+      "epoch": 1.3778319123020706,
+      "grad_norm": 0.6080027009026632,
+      "learning_rate": 2.6190789327602695e-06,
+      "loss": 0.8054,
+      "step": 472
+    },
+    {
+      "epoch": 1.3807551766138855,
+      "grad_norm": 0.575058281647644,
+      "learning_rate": 2.5966138976292525e-06,
+      "loss": 0.8219,
+      "step": 473
+    },
+    {
+      "epoch": 1.3836784409257004,
+      "grad_norm": 0.5511199798733908,
+      "learning_rate": 2.5742117820472585e-06,
+      "loss": 0.8058,
+      "step": 474
+    },
+    {
+      "epoch": 1.3866017052375152,
+      "grad_norm": 0.5894915190468311,
+      "learning_rate": 2.5518731724914296e-06,
+      "loss": 0.8003,
+      "step": 475
+    },
+    {
+      "epoch": 1.3895249695493301,
+      "grad_norm": 0.6008815228155614,
+      "learning_rate": 2.529598653776349e-06,
+      "loss": 0.7676,
+      "step": 476
+    },
+    {
+      "epoch": 1.392448233861145,
+      "grad_norm": 0.5582304902542878,
+      "learning_rate": 2.5073888090387288e-06,
+      "loss": 0.8153,
+      "step": 477
+    },
+    {
+      "epoch": 1.3953714981729597,
+      "grad_norm": 0.5361237402188473,
+      "learning_rate": 2.485244219722148e-06,
+      "loss": 0.7952,
+      "step": 478
+    },
+    {
+      "epoch": 1.3982947624847748,
+      "grad_norm": 0.5689438925320016,
+      "learning_rate": 2.4631654655618293e-06,
+      "loss": 0.8035,
+      "step": 479
+    },
+    {
+      "epoch": 1.4012180267965895,
+      "grad_norm": 0.5874254989274982,
+      "learning_rate": 2.4411531245694546e-06,
+      "loss": 0.7966,
+      "step": 480
+    },
+    {
+      "epoch": 1.4041412911084044,
+      "grad_norm": 0.5749456696437114,
+      "learning_rate": 2.4192077730180475e-06,
+      "loss": 0.8173,
+      "step": 481
+    },
+    {
+      "epoch": 1.4070645554202192,
+      "grad_norm": 0.5672450900355861,
+      "learning_rate": 2.3973299854268743e-06,
+      "loss": 0.7861,
+      "step": 482
+    },
+    {
+      "epoch": 1.4099878197320341,
+      "grad_norm": 0.5822534798540568,
+      "learning_rate": 2.3755203345464093e-06,
+      "loss": 0.8107,
+      "step": 483
+    },
+    {
+      "epoch": 1.412911084043849,
+      "grad_norm": 0.5735638363168305,
+      "learning_rate": 2.3537793913433386e-06,
+      "loss": 0.8111,
+      "step": 484
+    },
+    {
+      "epoch": 1.415834348355664,
+      "grad_norm": 0.5630609970931171,
+      "learning_rate": 2.3321077249856123e-06,
+      "loss": 0.8195,
+      "step": 485
+    },
+    {
+      "epoch": 1.4187576126674788,
+      "grad_norm": 0.5673965152389683,
+      "learning_rate": 2.3105059028275467e-06,
+      "loss": 0.7669,
+      "step": 486
+    },
+    {
+      "epoch": 1.4216808769792935,
+      "grad_norm": 0.5941423353872316,
+      "learning_rate": 2.288974490394962e-06,
+      "loss": 0.805,
+      "step": 487
+    },
+    {
+      "epoch": 1.4246041412911084,
+      "grad_norm": 0.583271460902054,
+      "learning_rate": 2.2675140513703924e-06,
+      "loss": 0.8062,
+      "step": 488
+    },
+    {
+      "epoch": 1.4275274056029232,
+      "grad_norm": 0.5569237007034656,
+      "learning_rate": 2.246125147578316e-06,
+      "loss": 0.8198,
+      "step": 489
+    },
+    {
+      "epoch": 1.4304506699147381,
+      "grad_norm": 0.556510419136389,
+      "learning_rate": 2.224808338970452e-06,
+      "loss": 0.8003,
+      "step": 490
+    },
+    {
+      "epoch": 1.433373934226553,
+      "grad_norm": 0.585029225572491,
+      "learning_rate": 2.2035641836111014e-06,
+      "loss": 0.8344,
+      "step": 491
+    },
+    {
+      "epoch": 1.436297198538368,
+      "grad_norm": 0.5623539594731303,
+      "learning_rate": 2.182393237662536e-06,
+      "loss": 0.795,
+      "step": 492
+    },
+    {
+      "epoch": 1.4392204628501828,
+      "grad_norm": 0.5730620202071608,
+      "learning_rate": 2.161296055370441e-06,
+      "loss": 0.8072,
+      "step": 493
+    },
+    {
+      "epoch": 1.4421437271619975,
+      "grad_norm": 0.5858480193047055,
+      "learning_rate": 2.140273189049396e-06,
+      "loss": 0.808,
+      "step": 494
+    },
+    {
+      "epoch": 1.4450669914738123,
+      "grad_norm": 0.5833871713302182,
+      "learning_rate": 2.1193251890684297e-06,
+      "loss": 0.7781,
+      "step": 495
+    },
+    {
+      "epoch": 1.4479902557856272,
+      "grad_norm": 0.5679251391544968,
+      "learning_rate": 2.0984526038366005e-06,
+      "loss": 0.7848,
+      "step": 496
+    },
+    {
+      "epoch": 1.4509135200974421,
+      "grad_norm": 0.5628769222538363,
+      "learning_rate": 2.0776559797886445e-06,
+      "loss": 0.8082,
+      "step": 497
+    },
+    {
+      "epoch": 1.453836784409257,
+      "grad_norm": 0.6023793540211936,
+      "learning_rate": 2.0569358613706685e-06,
+      "loss": 0.8097,
+      "step": 498
+    },
+    {
+      "epoch": 1.456760048721072,
+      "grad_norm": 0.5794155584920526,
+      "learning_rate": 2.036292791025899e-06,
+      "loss": 0.7773,
+      "step": 499
+    },
+    {
+      "epoch": 1.4596833130328868,
+      "grad_norm": 0.5696461615256238,
+      "learning_rate": 2.0157273091804725e-06,
+      "loss": 0.7882,
+      "step": 500
+    },
+    {
+      "epoch": 1.4626065773447015,
+      "grad_norm": 0.5827853659037967,
+      "learning_rate": 1.995239954229301e-06,
+      "loss": 0.7998,
+      "step": 501
+    },
+    {
+      "epoch": 1.4655298416565166,
+      "grad_norm": 0.5615811380760124,
+      "learning_rate": 1.9748312625219674e-06,
+      "loss": 0.7792,
+      "step": 502
+    },
+    {
+      "epoch": 1.4684531059683312,
+      "grad_norm": 0.5702951187471944,
+      "learning_rate": 1.954501768348687e-06,
+      "loss": 0.8027,
+      "step": 503
+    },
+    {
+      "epoch": 1.4713763702801461,
+      "grad_norm": 0.5859521759939277,
+      "learning_rate": 1.9342520039263206e-06,
+      "loss": 0.7939,
+      "step": 504
+    },
+    {
+      "epoch": 1.474299634591961,
+      "grad_norm": 0.5622948101159606,
+      "learning_rate": 1.9140824993844396e-06,
+      "loss": 0.8005,
+      "step": 505
+    },
+    {
+      "epoch": 1.477222898903776,
+      "grad_norm": 0.5709515740173828,
+      "learning_rate": 1.8939937827514509e-06,
+      "loss": 0.7931,
+      "step": 506
+    },
+    {
+      "epoch": 1.4801461632155908,
+      "grad_norm": 0.5744268405944757,
+      "learning_rate": 1.8739863799407644e-06,
+      "loss": 0.7715,
+      "step": 507
+    },
+    {
+      "epoch": 1.4830694275274057,
+      "grad_norm": 0.5658023138017119,
+      "learning_rate": 1.8540608147370386e-06,
+      "loss": 0.8154,
+      "step": 508
+    },
+    {
+      "epoch": 1.4859926918392206,
+      "grad_norm": 0.5683407498717216,
+      "learning_rate": 1.8342176087824576e-06,
+      "loss": 0.8085,
+      "step": 509
+    },
+    {
+      "epoch": 1.4889159561510352,
+      "grad_norm": 0.5689375651699262,
+      "learning_rate": 1.814457281563078e-06,
+      "loss": 0.8053,
+      "step": 510
+    },
+    {
+      "epoch": 1.4918392204628501,
+      "grad_norm": 0.5766874459611464,
+      "learning_rate": 1.7947803503952298e-06,
+      "loss": 0.8122,
+      "step": 511
+    },
+    {
+      "epoch": 1.494762484774665,
+      "grad_norm": 0.5738977689581138,
+      "learning_rate": 1.7751873304119743e-06,
+      "loss": 0.7907,
+      "step": 512
+    },
+    {
+      "epoch": 1.49768574908648,
+      "grad_norm": 0.5912437120374228,
+      "learning_rate": 1.7556787345496102e-06,
+      "loss": 0.7699,
+      "step": 513
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 682,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 171,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.560179872449167e+17,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-513/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe29fe7d020664051ae39aa007a84a5eb7b3ed3ad71b63536509945817e67e19
+size 8440

checkpoint-513/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)