End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +759 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3.1
|
|
| 4 |
base_model: meta-llama/Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: OH_original_wo_cot_alpaca
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# OH_original_wo_cot_alpaca
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.6004
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: OH_original_wo_cot_alpaca
|
|
|
|
| 16 |
|
| 17 |
# OH_original_wo_cot_alpaca
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the mlfoundations-dev/OH_original_wo_cot_alpaca dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6004
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.993238166791886,
|
| 3 |
+
"eval_loss": 0.6004215478897095,
|
| 4 |
+
"eval_runtime": 112.6152,
|
| 5 |
+
"eval_samples_per_second": 79.607,
|
| 6 |
+
"eval_steps_per_second": 0.63,
|
| 7 |
+
"total_flos": 1667918337146880.0,
|
| 8 |
+
"train_loss": 0.5658263341490045,
|
| 9 |
+
"train_runtime": 16943.5847,
|
| 10 |
+
"train_samples_per_second": 30.156,
|
| 11 |
+
"train_steps_per_second": 0.059
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.993238166791886,
|
| 3 |
+
"eval_loss": 0.6004215478897095,
|
| 4 |
+
"eval_runtime": 112.6152,
|
| 5 |
+
"eval_samples_per_second": 79.607,
|
| 6 |
+
"eval_steps_per_second": 0.63
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.993238166791886,
|
| 3 |
+
"total_flos": 1667918337146880.0,
|
| 4 |
+
"train_loss": 0.5658263341490045,
|
| 5 |
+
"train_runtime": 16943.5847,
|
| 6 |
+
"train_samples_per_second": 30.156,
|
| 7 |
+
"train_steps_per_second": 0.059
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,759 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.993238166791886,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 996,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03005259203606311,
|
| 13 |
+
"grad_norm": 4.810495218440688,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.7926,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06010518407212622,
|
| 20 |
+
"grad_norm": 3.155508530359899,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.722,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09015777610818933,
|
| 27 |
+
"grad_norm": 1.225544271167285,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.7085,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12021036814425244,
|
| 34 |
+
"grad_norm": 0.9265761014813488,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.6829,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.15026296018031554,
|
| 41 |
+
"grad_norm": 1.2106246073988878,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.6706,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.18031555221637866,
|
| 48 |
+
"grad_norm": 1.9380737235516812,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.6637,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21036814425244177,
|
| 55 |
+
"grad_norm": 0.8111060604176487,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.6536,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.24042073628850488,
|
| 62 |
+
"grad_norm": 0.9088296756504328,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.6441,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.270473328324568,
|
| 69 |
+
"grad_norm": 0.6375258367082703,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.636,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3005259203606311,
|
| 76 |
+
"grad_norm": 1.2329946577337598,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6293,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3305785123966942,
|
| 83 |
+
"grad_norm": 0.5905978981231776,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.6255,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3606311044327573,
|
| 90 |
+
"grad_norm": 0.5247850741074309,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.6275,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.39068369646882045,
|
| 97 |
+
"grad_norm": 0.6903136425418634,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.635,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.42073628850488354,
|
| 104 |
+
"grad_norm": 0.5428640707055408,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.6283,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4507888805409467,
|
| 111 |
+
"grad_norm": 0.7725320921008048,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6265,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.48084147257700977,
|
| 118 |
+
"grad_norm": 0.6353293754243331,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.6219,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5108940646130729,
|
| 125 |
+
"grad_norm": 0.696998211557625,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6222,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.540946656649136,
|
| 132 |
+
"grad_norm": 0.5725933318808639,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6233,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5709992486851991,
|
| 139 |
+
"grad_norm": 0.5406370000400791,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6141,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6010518407212622,
|
| 146 |
+
"grad_norm": 0.5328195355513519,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6135,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6311044327573253,
|
| 153 |
+
"grad_norm": 0.5757875631327323,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.6177,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.6611570247933884,
|
| 160 |
+
"grad_norm": 0.511696604236356,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6221,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.6912096168294516,
|
| 167 |
+
"grad_norm": 0.5535745253744225,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6093,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7212622088655146,
|
| 174 |
+
"grad_norm": 0.5080323201706937,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.6198,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7513148009015778,
|
| 181 |
+
"grad_norm": 0.7440297135028378,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.6141,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.7813673929376409,
|
| 188 |
+
"grad_norm": 0.5240609426616543,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.6001,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8114199849737039,
|
| 195 |
+
"grad_norm": 0.5170330245787976,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6077,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8414725770097671,
|
| 202 |
+
"grad_norm": 0.469645994556069,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.6158,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.8715251690458302,
|
| 209 |
+
"grad_norm": 0.48882124388027265,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6114,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9015777610818934,
|
| 216 |
+
"grad_norm": 0.5404896464902132,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.6075,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9316303531179564,
|
| 223 |
+
"grad_norm": 0.5064337097380566,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.5973,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9616829451540195,
|
| 230 |
+
"grad_norm": 0.5395666354340096,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6142,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.9917355371900827,
|
| 237 |
+
"grad_norm": 0.5443646281574408,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.6024,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.9977460555972952,
|
| 244 |
+
"eval_loss": 0.602512001991272,
|
| 245 |
+
"eval_runtime": 115.6071,
|
| 246 |
+
"eval_samples_per_second": 77.547,
|
| 247 |
+
"eval_steps_per_second": 0.614,
|
| 248 |
+
"step": 332
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.0217881292261457,
|
| 252 |
+
"grad_norm": 0.6043688308355755,
|
| 253 |
+
"learning_rate": 5e-06,
|
| 254 |
+
"loss": 0.5718,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.051840721262209,
|
| 259 |
+
"grad_norm": 0.5742469748119633,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.5559,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.081893313298272,
|
| 266 |
+
"grad_norm": 0.5641150930410421,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.5565,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.111945905334335,
|
| 273 |
+
"grad_norm": 0.5251750994837489,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.5559,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.1419984973703983,
|
| 280 |
+
"grad_norm": 0.5594749881743232,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.5548,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.1720510894064613,
|
| 287 |
+
"grad_norm": 0.5192017193387347,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.5616,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.2021036814425243,
|
| 294 |
+
"grad_norm": 0.5006444275848907,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.553,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.2321562734785876,
|
| 301 |
+
"grad_norm": 0.5182596004381461,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.5534,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.2622088655146506,
|
| 308 |
+
"grad_norm": 0.48792630443547186,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.5596,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.2922614575507136,
|
| 315 |
+
"grad_norm": 0.4971407424850785,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.5559,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.322314049586777,
|
| 322 |
+
"grad_norm": 0.4769582306533125,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.559,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.35236664162284,
|
| 329 |
+
"grad_norm": 0.5696514756007727,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.559,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.382419233658903,
|
| 336 |
+
"grad_norm": 0.47028266891611087,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.5552,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.4124718256949662,
|
| 343 |
+
"grad_norm": 0.5142628164984128,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.5562,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.4425244177310292,
|
| 350 |
+
"grad_norm": 0.4298738340578577,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.5444,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.4725770097670925,
|
| 357 |
+
"grad_norm": 0.5886177624554544,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.553,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.5026296018031555,
|
| 364 |
+
"grad_norm": 0.479969456761664,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.5615,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.5326821938392188,
|
| 371 |
+
"grad_norm": 0.546008279918396,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.5588,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.5627347858752816,
|
| 378 |
+
"grad_norm": 0.5113023466894115,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.5515,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.5927873779113448,
|
| 385 |
+
"grad_norm": 0.4638757502509985,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.5602,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.622839969947408,
|
| 392 |
+
"grad_norm": 0.5396179709473905,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.5687,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.6528925619834711,
|
| 399 |
+
"grad_norm": 0.5307757961312712,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.5522,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.6829451540195342,
|
| 406 |
+
"grad_norm": 0.5717833229926992,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.5539,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.7129977460555974,
|
| 413 |
+
"grad_norm": 0.5148441797108223,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.5486,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.7430503380916604,
|
| 420 |
+
"grad_norm": 0.4744973222154149,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.5515,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.7731029301277235,
|
| 427 |
+
"grad_norm": 0.4644006036526441,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.5529,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.8031555221637867,
|
| 434 |
+
"grad_norm": 0.5742071808595426,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.5563,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.8332081141998497,
|
| 441 |
+
"grad_norm": 0.524857373914898,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.5548,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.8632607062359128,
|
| 448 |
+
"grad_norm": 0.5108979951578987,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.5517,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.893313298271976,
|
| 455 |
+
"grad_norm": 0.5651055404638835,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.5566,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.923365890308039,
|
| 462 |
+
"grad_norm": 0.4596795240284601,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.5565,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.953418482344102,
|
| 469 |
+
"grad_norm": 0.5231843841522166,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.5543,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.9834710743801653,
|
| 476 |
+
"grad_norm": 0.4613490632623934,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.5526,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.998497370398197,
|
| 483 |
+
"eval_loss": 0.5943902730941772,
|
| 484 |
+
"eval_runtime": 116.0841,
|
| 485 |
+
"eval_samples_per_second": 77.229,
|
| 486 |
+
"eval_steps_per_second": 0.612,
|
| 487 |
+
"step": 665
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.0135236664162286,
|
| 491 |
+
"grad_norm": 1.0151560958110475,
|
| 492 |
+
"learning_rate": 5e-06,
|
| 493 |
+
"loss": 0.5296,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.0435762584522914,
|
| 498 |
+
"grad_norm": 0.5753358656630801,
|
| 499 |
+
"learning_rate": 5e-06,
|
| 500 |
+
"loss": 0.5029,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.0736288504883547,
|
| 505 |
+
"grad_norm": 0.535229224584348,
|
| 506 |
+
"learning_rate": 5e-06,
|
| 507 |
+
"loss": 0.5033,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.103681442524418,
|
| 512 |
+
"grad_norm": 0.5308477913499555,
|
| 513 |
+
"learning_rate": 5e-06,
|
| 514 |
+
"loss": 0.4981,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.1337340345604807,
|
| 519 |
+
"grad_norm": 0.5032127296654162,
|
| 520 |
+
"learning_rate": 5e-06,
|
| 521 |
+
"loss": 0.5025,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.163786626596544,
|
| 526 |
+
"grad_norm": 0.5692227883516503,
|
| 527 |
+
"learning_rate": 5e-06,
|
| 528 |
+
"loss": 0.5052,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.1938392186326072,
|
| 533 |
+
"grad_norm": 0.5408850500925536,
|
| 534 |
+
"learning_rate": 5e-06,
|
| 535 |
+
"loss": 0.4995,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.22389181066867,
|
| 540 |
+
"grad_norm": 0.47006049113767784,
|
| 541 |
+
"learning_rate": 5e-06,
|
| 542 |
+
"loss": 0.5053,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.2539444027047333,
|
| 547 |
+
"grad_norm": 0.6577893214388708,
|
| 548 |
+
"learning_rate": 5e-06,
|
| 549 |
+
"loss": 0.5068,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.2839969947407965,
|
| 554 |
+
"grad_norm": 0.5453995235461279,
|
| 555 |
+
"learning_rate": 5e-06,
|
| 556 |
+
"loss": 0.5025,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.3140495867768593,
|
| 561 |
+
"grad_norm": 0.5111820993930344,
|
| 562 |
+
"learning_rate": 5e-06,
|
| 563 |
+
"loss": 0.5025,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.3441021788129226,
|
| 568 |
+
"grad_norm": 0.5019244840316214,
|
| 569 |
+
"learning_rate": 5e-06,
|
| 570 |
+
"loss": 0.5059,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.374154770848986,
|
| 575 |
+
"grad_norm": 0.4860932571878682,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.5057,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.4042073628850487,
|
| 582 |
+
"grad_norm": 0.5105307181041621,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.5104,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.434259954921112,
|
| 589 |
+
"grad_norm": 0.4985867132406256,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.5078,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.464312546957175,
|
| 596 |
+
"grad_norm": 0.5460937499191226,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.5091,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.494365138993238,
|
| 603 |
+
"grad_norm": 0.4887915411999051,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.5084,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.5244177310293012,
|
| 610 |
+
"grad_norm": 0.48194363042727245,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.5041,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.5544703230653645,
|
| 617 |
+
"grad_norm": 0.5346871895488505,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.5041,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.5845229151014273,
|
| 624 |
+
"grad_norm": 0.5741375180255713,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.5044,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.6145755071374905,
|
| 631 |
+
"grad_norm": 0.5215520764416209,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.5113,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.644628099173554,
|
| 638 |
+
"grad_norm": 0.5134970783379779,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.5037,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.674680691209617,
|
| 645 |
+
"grad_norm": 0.5673341470254984,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.5126,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.70473328324568,
|
| 652 |
+
"grad_norm": 0.5345905680232906,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.5071,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.734785875281743,
|
| 659 |
+
"grad_norm": 0.6651222249433006,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.5069,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.764838467317806,
|
| 666 |
+
"grad_norm": 0.5593066350235659,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.5105,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.794891059353869,
|
| 673 |
+
"grad_norm": 0.45810869599006515,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.5058,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.8249436513899324,
|
| 680 |
+
"grad_norm": 0.5097170540621323,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.5086,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.8549962434259957,
|
| 687 |
+
"grad_norm": 0.61115109062032,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.5097,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.8850488354620585,
|
| 694 |
+
"grad_norm": 0.5416071063853659,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.506,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.9151014274981217,
|
| 701 |
+
"grad_norm": 0.5010400411025377,
|
| 702 |
+
"learning_rate": 5e-06,
|
| 703 |
+
"loss": 0.5084,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.945154019534185,
|
| 708 |
+
"grad_norm": 0.505134630851122,
|
| 709 |
+
"learning_rate": 5e-06,
|
| 710 |
+
"loss": 0.5054,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.975206611570248,
|
| 715 |
+
"grad_norm": 0.5247938588776304,
|
| 716 |
+
"learning_rate": 5e-06,
|
| 717 |
+
"loss": 0.5067,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.993238166791886,
|
| 722 |
+
"eval_loss": 0.6004215478897095,
|
| 723 |
+
"eval_runtime": 113.1633,
|
| 724 |
+
"eval_samples_per_second": 79.222,
|
| 725 |
+
"eval_steps_per_second": 0.627,
|
| 726 |
+
"step": 996
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 2.993238166791886,
|
| 730 |
+
"step": 996,
|
| 731 |
+
"total_flos": 1667918337146880.0,
|
| 732 |
+
"train_loss": 0.5658263341490045,
|
| 733 |
+
"train_runtime": 16943.5847,
|
| 734 |
+
"train_samples_per_second": 30.156,
|
| 735 |
+
"train_steps_per_second": 0.059
|
| 736 |
+
}
|
| 737 |
+
],
|
| 738 |
+
"logging_steps": 10,
|
| 739 |
+
"max_steps": 996,
|
| 740 |
+
"num_input_tokens_seen": 0,
|
| 741 |
+
"num_train_epochs": 3,
|
| 742 |
+
"save_steps": 500,
|
| 743 |
+
"stateful_callbacks": {
|
| 744 |
+
"TrainerControl": {
|
| 745 |
+
"args": {
|
| 746 |
+
"should_epoch_stop": false,
|
| 747 |
+
"should_evaluate": false,
|
| 748 |
+
"should_log": false,
|
| 749 |
+
"should_save": true,
|
| 750 |
+
"should_training_stop": true
|
| 751 |
+
},
|
| 752 |
+
"attributes": {}
|
| 753 |
+
}
|
| 754 |
+
},
|
| 755 |
+
"total_flos": 1667918337146880.0,
|
| 756 |
+
"train_batch_size": 8,
|
| 757 |
+
"trial_name": null,
|
| 758 |
+
"trial_params": null
|
| 759 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|