Hugging Face's logo

zerozeroz
/
Qwen2.5-Coder-7B

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
Generated from Trainer
trl
grpo
conversational
text-generation-inference
Model card Files
xet
Metrics Community
zerozeroz commited on
Commit
3097beb
·
verified ·
1 Parent(s): f87c4cb

Model save

Browse files
Files changed (4) hide show
  1. all_results.json +4 -4
  2. config.json +1 -1
  3. train_results.json +4 -4
  4. trainer_state.json +21 -8
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 2.596636219443127e-05,
4
- "train_runtime": 4869.9523,
5
  "train_samples": 374,
6
- "train_samples_per_second": 0.154,
7
- "train_steps_per_second": 0.026
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 5.371543848591428e-07,
4
+ "train_runtime": 142.6302,
5
  "train_samples": 374,
6
+ "train_samples_per_second": 5.258,
7
+ "train_steps_per_second": 0.876
8
  }
config.json CHANGED
@@ -23,7 +23,7 @@
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.48.1",
26
- "use_cache": false,
27
  "use_sliding_window": false,
28
  "vocab_size": 152064
29
  }
 
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.48.1",
26
+ "use_cache": true,
27
  "use_sliding_window": false,
28
  "vocab_size": 152064
29
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 2.596636219443127e-05,
4
- "train_runtime": 4869.9523,
5
  "train_samples": 374,
6
- "train_samples_per_second": 0.154,
7
- "train_steps_per_second": 0.026
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 5.371543848591428e-07,
4
+ "train_runtime": 142.6302,
5
  "train_samples": 374,
6
+ "train_samples_per_second": 5.258,
7
+ "train_steps_per_second": 0.876
8
  }
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.992,
5
  "eval_steps": 500,
6
- "global_step": 125,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1634,13 +1634,26 @@
1634
  "step": 125
1635
  },
1636
  {
1637
- "epoch": 1.992,
1638
- "step": 125,
 
 
 
 
 
 
 
 
 
 
 
 
 
1639
  "total_flos": 0.0,
1640
- "train_loss": 2.596636219443127e-05,
1641
- "train_runtime": 4869.9523,
1642
- "train_samples_per_second": 0.154,
1643
- "train_steps_per_second": 0.026
1644
  }
1645
  ],
1646
  "logging_steps": 1,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.032,
5
  "eval_steps": 500,
6
+ "global_step": 126,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1634
  "step": 125
1635
  },
1636
  {
1637
+ "completion_length": 70.72916984558105,
1638
+ "epoch": 2.032,
1639
+ "grad_norm": 0.921072382478298,
1640
+ "kl": 0.067626953125,
1641
+ "learning_rate": 8.425867412190091e-11,
1642
+ "loss": 0.0001,
1643
+ "reward": 0.8045242130756378,
1644
+ "reward_std": 0.41052111983299255,
1645
+ "rewards/correct_code_reward_func": 0.3750000149011612,
1646
+ "rewards/len_reward_func": 0.42952418327331543,
1647
+ "step": 126
1648
+ },
1649
+ {
1650
+ "epoch": 2.032,
1651
+ "step": 126,
1652
  "total_flos": 0.0,
1653
+ "train_loss": 5.371543848591428e-07,
1654
+ "train_runtime": 142.6302,
1655
+ "train_samples_per_second": 5.258,
1656
+ "train_steps_per_second": 0.876
1657
  }
1658
  ],
1659
  "logging_steps": 1,