Model save
Browse files- README.md +69 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +435 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Meta-Llama-3-8B
|
| 3 |
+
datasets:
|
| 4 |
+
- generator
|
| 5 |
+
library_name: peft
|
| 6 |
+
license: llama3
|
| 7 |
+
tags:
|
| 8 |
+
- trl
|
| 9 |
+
- sft
|
| 10 |
+
- generated_from_trainer
|
| 11 |
+
model-index:
|
| 12 |
+
- name: llama3.1-8b-gpt4o_100k_coding-lora
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# llama3.1-8b-gpt4o_100k_coding-lora
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.2769
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0003
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 4
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 8
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 64
|
| 50 |
+
- total_eval_batch_size: 32
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 1
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 60 |
+
| 0.5385 | 1.0 | 270 | 1.2769 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.13.0
|
| 66 |
+
- Transformers 4.45.1
|
| 67 |
+
- Pytorch 2.4.1+cu121
|
| 68 |
+
- Datasets 3.0.1
|
| 69 |
+
- Tokenizers 0.20.0
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 7.971478934745252e+17,
|
| 4 |
+
"train_loss": 0.6237873245168615,
|
| 5 |
+
"train_runtime": 2852.5229,
|
| 6 |
+
"train_samples": 116368,
|
| 7 |
+
"train_samples_per_second": 6.048,
|
| 8 |
+
"train_steps_per_second": 0.095
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 7.971478934745252e+17,
|
| 4 |
+
"train_loss": 0.6237873245168615,
|
| 5 |
+
"train_runtime": 2852.5229,
|
| 6 |
+
"train_samples": 116368,
|
| 7 |
+
"train_samples_per_second": 6.048,
|
| 8 |
+
"train_steps_per_second": 0.095
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,435 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 270,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.003703703703703704,
|
| 13 |
+
"grad_norm": 0.6600888967514038,
|
| 14 |
+
"learning_rate": 1.111111111111111e-05,
|
| 15 |
+
"loss": 1.6547,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.018518518518518517,
|
| 20 |
+
"grad_norm": 1.0668487548828125,
|
| 21 |
+
"learning_rate": 5.5555555555555545e-05,
|
| 22 |
+
"loss": 1.6004,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.037037037037037035,
|
| 27 |
+
"grad_norm": 0.8215888142585754,
|
| 28 |
+
"learning_rate": 0.00011111111111111109,
|
| 29 |
+
"loss": 1.5361,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05555555555555555,
|
| 34 |
+
"grad_norm": 1.627755045890808,
|
| 35 |
+
"learning_rate": 0.00016666666666666666,
|
| 36 |
+
"loss": 1.3368,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07407407407407407,
|
| 41 |
+
"grad_norm": 1.0417497158050537,
|
| 42 |
+
"learning_rate": 0.00022222222222222218,
|
| 43 |
+
"loss": 0.9318,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09259259259259259,
|
| 48 |
+
"grad_norm": 0.45057186484336853,
|
| 49 |
+
"learning_rate": 0.0002777777777777778,
|
| 50 |
+
"loss": 0.7995,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1111111111111111,
|
| 55 |
+
"grad_norm": 0.3393832743167877,
|
| 56 |
+
"learning_rate": 0.0002998871928756345,
|
| 57 |
+
"loss": 0.7298,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.12962962962962962,
|
| 62 |
+
"grad_norm": 0.2655043601989746,
|
| 63 |
+
"learning_rate": 0.0002991984303609902,
|
| 64 |
+
"loss": 0.6803,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14814814814814814,
|
| 69 |
+
"grad_norm": 0.1693999469280243,
|
| 70 |
+
"learning_rate": 0.0002978864495017194,
|
| 71 |
+
"loss": 0.65,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16666666666666666,
|
| 76 |
+
"grad_norm": 0.1550581008195877,
|
| 77 |
+
"learning_rate": 0.00029595673058697357,
|
| 78 |
+
"loss": 0.6344,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.18518518518518517,
|
| 83 |
+
"grad_norm": 0.13547781109809875,
|
| 84 |
+
"learning_rate": 0.0002934173342660819,
|
| 85 |
+
"loss": 0.6189,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2037037037037037,
|
| 90 |
+
"grad_norm": 0.12479308992624283,
|
| 91 |
+
"learning_rate": 0.00029027886787832844,
|
| 92 |
+
"loss": 0.6105,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2222222222222222,
|
| 97 |
+
"grad_norm": 0.14283517003059387,
|
| 98 |
+
"learning_rate": 0.000286554441144922,
|
| 99 |
+
"loss": 0.6005,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.24074074074074073,
|
| 104 |
+
"grad_norm": 0.15204459428787231,
|
| 105 |
+
"learning_rate": 0.0002822596114082412,
|
| 106 |
+
"loss": 0.6063,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.25925925925925924,
|
| 111 |
+
"grad_norm": 0.1366046667098999,
|
| 112 |
+
"learning_rate": 0.0002774123186470946,
|
| 113 |
+
"loss": 0.5926,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2777777777777778,
|
| 118 |
+
"grad_norm": 0.13155071437358856,
|
| 119 |
+
"learning_rate": 0.0002720328105394451,
|
| 120 |
+
"loss": 0.5877,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2962962962962963,
|
| 125 |
+
"grad_norm": 0.14542943239212036,
|
| 126 |
+
"learning_rate": 0.00026614355788561985,
|
| 127 |
+
"loss": 0.5688,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3148148148148148,
|
| 132 |
+
"grad_norm": 0.14441293478012085,
|
| 133 |
+
"learning_rate": 0.00025976916074529183,
|
| 134 |
+
"loss": 0.5706,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3333333333333333,
|
| 139 |
+
"grad_norm": 0.13577958941459656,
|
| 140 |
+
"learning_rate": 0.00025293624568031,
|
| 141 |
+
"loss": 0.5717,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.35185185185185186,
|
| 146 |
+
"grad_norm": 0.16319440305233002,
|
| 147 |
+
"learning_rate": 0.0002456733545326059,
|
| 148 |
+
"loss": 0.5709,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.37037037037037035,
|
| 153 |
+
"grad_norm": 0.13978739082813263,
|
| 154 |
+
"learning_rate": 0.00023801082520176267,
|
| 155 |
+
"loss": 0.5565,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3888888888888889,
|
| 160 |
+
"grad_norm": 0.16405534744262695,
|
| 161 |
+
"learning_rate": 0.0002299806649202537,
|
| 162 |
+
"loss": 0.5682,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.4074074074074074,
|
| 167 |
+
"grad_norm": 0.14882802963256836,
|
| 168 |
+
"learning_rate": 0.00022161641655569234,
|
| 169 |
+
"loss": 0.5525,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.42592592592592593,
|
| 174 |
+
"grad_norm": 0.15766838192939758,
|
| 175 |
+
"learning_rate": 0.00021295301849856435,
|
| 176 |
+
"loss": 0.5525,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4444444444444444,
|
| 181 |
+
"grad_norm": 0.16089104115962982,
|
| 182 |
+
"learning_rate": 0.00020402665872070654,
|
| 183 |
+
"loss": 0.5477,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.46296296296296297,
|
| 188 |
+
"grad_norm": 0.1631491482257843,
|
| 189 |
+
"learning_rate": 0.00019487462361414626,
|
| 190 |
+
"loss": 0.5503,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.48148148148148145,
|
| 195 |
+
"grad_norm": 0.15596701204776764,
|
| 196 |
+
"learning_rate": 0.00018553514224171783,
|
| 197 |
+
"loss": 0.5469,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5,
|
| 202 |
+
"grad_norm": 0.1614404171705246,
|
| 203 |
+
"learning_rate": 0.00017604722665003956,
|
| 204 |
+
"loss": 0.5532,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5185185185185185,
|
| 209 |
+
"grad_norm": 0.15226240456104279,
|
| 210 |
+
"learning_rate": 0.00016645050891187974,
|
| 211 |
+
"loss": 0.5432,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5370370370370371,
|
| 216 |
+
"grad_norm": 0.16388216614723206,
|
| 217 |
+
"learning_rate": 0.00015678507557860595,
|
| 218 |
+
"loss": 0.542,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5555555555555556,
|
| 223 |
+
"grad_norm": 0.15366673469543457,
|
| 224 |
+
"learning_rate": 0.00014709130023422633,
|
| 225 |
+
"loss": 0.5475,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5740740740740741,
|
| 230 |
+
"grad_norm": 0.16850697994232178,
|
| 231 |
+
"learning_rate": 0.00013740967485046393,
|
| 232 |
+
"loss": 0.5516,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5925925925925926,
|
| 237 |
+
"grad_norm": 0.16164420545101166,
|
| 238 |
+
"learning_rate": 0.0001277806406473127,
|
| 239 |
+
"loss": 0.5372,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6111111111111112,
|
| 244 |
+
"grad_norm": 0.16969184577465057,
|
| 245 |
+
"learning_rate": 0.00011824441916558842,
|
| 246 |
+
"loss": 0.5324,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6296296296296297,
|
| 251 |
+
"grad_norm": 0.17503169178962708,
|
| 252 |
+
"learning_rate": 0.00010884084425710479,
|
| 253 |
+
"loss": 0.5372,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6481481481481481,
|
| 258 |
+
"grad_norm": 0.17154920101165771,
|
| 259 |
+
"learning_rate": 9.960919569426869e-05,
|
| 260 |
+
"loss": 0.5339,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6666666666666666,
|
| 265 |
+
"grad_norm": 0.16324155032634735,
|
| 266 |
+
"learning_rate": 9.058803509412646e-05,
|
| 267 |
+
"loss": 0.5415,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6851851851851852,
|
| 272 |
+
"grad_norm": 0.1716451346874237,
|
| 273 |
+
"learning_rate": 8.18150448422249e-05,
|
| 274 |
+
"loss": 0.5329,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7037037037037037,
|
| 279 |
+
"grad_norm": 0.15859860181808472,
|
| 280 |
+
"learning_rate": 7.332687068911903e-05,
|
| 281 |
+
"loss": 0.5368,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.7222222222222222,
|
| 286 |
+
"grad_norm": 0.16680656373500824,
|
| 287 |
+
"learning_rate": 6.515896867701923e-05,
|
| 288 |
+
"loss": 0.538,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7407407407407407,
|
| 293 |
+
"grad_norm": 0.1692035049200058,
|
| 294 |
+
"learning_rate": 5.734545703598145e-05,
|
| 295 |
+
"loss": 0.5323,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7592592592592593,
|
| 300 |
+
"grad_norm": 0.1742638200521469,
|
| 301 |
+
"learning_rate": 4.991897366828704e-05,
|
| 302 |
+
"loss": 0.5375,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7777777777777778,
|
| 307 |
+
"grad_norm": 0.1706262081861496,
|
| 308 |
+
"learning_rate": 4.2910539816315164e-05,
|
| 309 |
+
"loss": 0.5286,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7962962962962963,
|
| 314 |
+
"grad_norm": 0.15826331079006195,
|
| 315 |
+
"learning_rate": 3.6349430483382306e-05,
|
| 316 |
+
"loss": 0.5273,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8148148148148148,
|
| 321 |
+
"grad_norm": 0.15241724252700806,
|
| 322 |
+
"learning_rate": 3.0263052148816046e-05,
|
| 323 |
+
"loss": 0.5285,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8333333333333334,
|
| 328 |
+
"grad_norm": 0.1507098227739334,
|
| 329 |
+
"learning_rate": 2.4676828288059558e-05,
|
| 330 |
+
"loss": 0.5356,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8518518518518519,
|
| 335 |
+
"grad_norm": 0.15940095484256744,
|
| 336 |
+
"learning_rate": 1.9614093176002828e-05,
|
| 337 |
+
"loss": 0.5417,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8703703703703703,
|
| 342 |
+
"grad_norm": 0.16012977063655853,
|
| 343 |
+
"learning_rate": 1.5095994417136053e-05,
|
| 344 |
+
"loss": 0.5323,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8888888888888888,
|
| 349 |
+
"grad_norm": 0.1607007086277008,
|
| 350 |
+
"learning_rate": 1.1141404609666449e-05,
|
| 351 |
+
"loss": 0.5234,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.9074074074074074,
|
| 356 |
+
"grad_norm": 0.15569806098937988,
|
| 357 |
+
"learning_rate": 7.766842512588529e-06,
|
| 358 |
+
"loss": 0.5293,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.9259259259259259,
|
| 363 |
+
"grad_norm": 0.15847626328468323,
|
| 364 |
+
"learning_rate": 4.986404045000697e-06,
|
| 365 |
+
"loss": 0.5286,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.9444444444444444,
|
| 370 |
+
"grad_norm": 0.16243720054626465,
|
| 371 |
+
"learning_rate": 2.811703405892296e-06,
|
| 372 |
+
"loss": 0.525,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.9629629629629629,
|
| 377 |
+
"grad_norm": 0.1597120612859726,
|
| 378 |
+
"learning_rate": 1.2518245603498345e-06,
|
| 379 |
+
"loss": 0.5295,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.9814814814814815,
|
| 384 |
+
"grad_norm": 0.15212252736091614,
|
| 385 |
+
"learning_rate": 3.1328329483019663e-07,
|
| 386 |
+
"loss": 0.5356,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.0,
|
| 391 |
+
"grad_norm": 0.15848107635974884,
|
| 392 |
+
"learning_rate": 0.0,
|
| 393 |
+
"loss": 0.5385,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.0,
|
| 398 |
+
"eval_loss": 1.2769262790679932,
|
| 399 |
+
"eval_runtime": 1.0983,
|
| 400 |
+
"eval_samples_per_second": 3.642,
|
| 401 |
+
"eval_steps_per_second": 0.911,
|
| 402 |
+
"step": 270
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.0,
|
| 406 |
+
"step": 270,
|
| 407 |
+
"total_flos": 7.971478934745252e+17,
|
| 408 |
+
"train_loss": 0.6237873245168615,
|
| 409 |
+
"train_runtime": 2852.5229,
|
| 410 |
+
"train_samples_per_second": 6.048,
|
| 411 |
+
"train_steps_per_second": 0.095
|
| 412 |
+
}
|
| 413 |
+
],
|
| 414 |
+
"logging_steps": 5,
|
| 415 |
+
"max_steps": 270,
|
| 416 |
+
"num_input_tokens_seen": 0,
|
| 417 |
+
"num_train_epochs": 1,
|
| 418 |
+
"save_steps": 100,
|
| 419 |
+
"stateful_callbacks": {
|
| 420 |
+
"TrainerControl": {
|
| 421 |
+
"args": {
|
| 422 |
+
"should_epoch_stop": false,
|
| 423 |
+
"should_evaluate": false,
|
| 424 |
+
"should_log": false,
|
| 425 |
+
"should_save": true,
|
| 426 |
+
"should_training_stop": true
|
| 427 |
+
},
|
| 428 |
+
"attributes": {}
|
| 429 |
+
}
|
| 430 |
+
},
|
| 431 |
+
"total_flos": 7.971478934745252e+17,
|
| 432 |
+
"train_batch_size": 4,
|
| 433 |
+
"trial_name": null,
|
| 434 |
+
"trial_params": null
|
| 435 |
+
}
|