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 +983 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: hp_ablations_qwen_lr1e-5
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# hp_ablations_qwen_lr1e-5
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.6266
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: hp_ablations_qwen_lr1e-5
|
|
|
|
| 16 |
|
| 17 |
# hp_ablations_qwen_lr1e-5
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6266
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.996011396011396,
|
| 3 |
+
"eval_loss": 0.6266428232192993,
|
| 4 |
+
"eval_runtime": 442.8791,
|
| 5 |
+
"eval_samples_per_second": 26.696,
|
| 6 |
+
"eval_steps_per_second": 0.418,
|
| 7 |
+
"total_flos": 2755219238682624.0,
|
| 8 |
+
"train_loss": 0.5826670261641435,
|
| 9 |
+
"train_runtime": 70447.3802,
|
| 10 |
+
"train_samples_per_second": 9.565,
|
| 11 |
+
"train_steps_per_second": 0.019
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.996011396011396,
|
| 3 |
+
"eval_loss": 0.6266428232192993,
|
| 4 |
+
"eval_runtime": 442.8791,
|
| 5 |
+
"eval_samples_per_second": 26.696,
|
| 6 |
+
"eval_steps_per_second": 0.418
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.996011396011396,
|
| 3 |
+
"total_flos": 2755219238682624.0,
|
| 4 |
+
"train_loss": 0.5826670261641435,
|
| 5 |
+
"train_runtime": 70447.3802,
|
| 6 |
+
"train_samples_per_second": 9.565,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,983 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.996011396011396,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1314,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.022792022792022793,
|
| 13 |
+
"grad_norm": 1.0146420064637809,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 0.7412,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.045584045584045586,
|
| 20 |
+
"grad_norm": 0.7912257831574413,
|
| 21 |
+
"learning_rate": 1e-05,
|
| 22 |
+
"loss": 0.6876,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06837606837606838,
|
| 27 |
+
"grad_norm": 0.8690010677441243,
|
| 28 |
+
"learning_rate": 1e-05,
|
| 29 |
+
"loss": 0.666,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09116809116809117,
|
| 34 |
+
"grad_norm": 0.505631934162416,
|
| 35 |
+
"learning_rate": 1e-05,
|
| 36 |
+
"loss": 0.6638,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11396011396011396,
|
| 41 |
+
"grad_norm": 0.33858449719431943,
|
| 42 |
+
"learning_rate": 1e-05,
|
| 43 |
+
"loss": 0.6608,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13675213675213677,
|
| 48 |
+
"grad_norm": 0.3902928439357306,
|
| 49 |
+
"learning_rate": 1e-05,
|
| 50 |
+
"loss": 0.6445,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.15954415954415954,
|
| 55 |
+
"grad_norm": 0.32811851282307186,
|
| 56 |
+
"learning_rate": 1e-05,
|
| 57 |
+
"loss": 0.6448,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.18233618233618235,
|
| 62 |
+
"grad_norm": 0.34238369327660734,
|
| 63 |
+
"learning_rate": 1e-05,
|
| 64 |
+
"loss": 0.6497,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.20512820512820512,
|
| 69 |
+
"grad_norm": 0.31623988973775263,
|
| 70 |
+
"learning_rate": 1e-05,
|
| 71 |
+
"loss": 0.6353,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.22792022792022792,
|
| 76 |
+
"grad_norm": 0.31093405606619007,
|
| 77 |
+
"learning_rate": 1e-05,
|
| 78 |
+
"loss": 0.6368,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.25071225071225073,
|
| 83 |
+
"grad_norm": 0.36187170115633943,
|
| 84 |
+
"learning_rate": 1e-05,
|
| 85 |
+
"loss": 0.6284,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.27350427350427353,
|
| 90 |
+
"grad_norm": 0.3233998336839521,
|
| 91 |
+
"learning_rate": 1e-05,
|
| 92 |
+
"loss": 0.6366,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2962962962962963,
|
| 97 |
+
"grad_norm": 0.3913907420956762,
|
| 98 |
+
"learning_rate": 1e-05,
|
| 99 |
+
"loss": 0.6377,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.3190883190883191,
|
| 104 |
+
"grad_norm": 0.3360481444653111,
|
| 105 |
+
"learning_rate": 1e-05,
|
| 106 |
+
"loss": 0.6398,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3418803418803419,
|
| 111 |
+
"grad_norm": 0.3175168014145369,
|
| 112 |
+
"learning_rate": 1e-05,
|
| 113 |
+
"loss": 0.6323,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3646723646723647,
|
| 118 |
+
"grad_norm": 0.37657481652603003,
|
| 119 |
+
"learning_rate": 1e-05,
|
| 120 |
+
"loss": 0.6376,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.38746438746438744,
|
| 125 |
+
"grad_norm": 0.35292598832747574,
|
| 126 |
+
"learning_rate": 1e-05,
|
| 127 |
+
"loss": 0.6294,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.41025641025641024,
|
| 132 |
+
"grad_norm": 0.3020552424319043,
|
| 133 |
+
"learning_rate": 1e-05,
|
| 134 |
+
"loss": 0.635,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.43304843304843305,
|
| 139 |
+
"grad_norm": 0.3439921293702071,
|
| 140 |
+
"learning_rate": 1e-05,
|
| 141 |
+
"loss": 0.6276,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.45584045584045585,
|
| 146 |
+
"grad_norm": 0.3327414470872692,
|
| 147 |
+
"learning_rate": 1e-05,
|
| 148 |
+
"loss": 0.6356,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.47863247863247865,
|
| 153 |
+
"grad_norm": 0.34684235410854686,
|
| 154 |
+
"learning_rate": 1e-05,
|
| 155 |
+
"loss": 0.6319,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5014245014245015,
|
| 160 |
+
"grad_norm": 0.3407250677678901,
|
| 161 |
+
"learning_rate": 1e-05,
|
| 162 |
+
"loss": 0.6357,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5242165242165242,
|
| 167 |
+
"grad_norm": 0.357024472193329,
|
| 168 |
+
"learning_rate": 1e-05,
|
| 169 |
+
"loss": 0.6314,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5470085470085471,
|
| 174 |
+
"grad_norm": 0.30797227810550154,
|
| 175 |
+
"learning_rate": 1e-05,
|
| 176 |
+
"loss": 0.6271,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5698005698005698,
|
| 181 |
+
"grad_norm": 0.33312179990469154,
|
| 182 |
+
"learning_rate": 1e-05,
|
| 183 |
+
"loss": 0.6321,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5925925925925926,
|
| 188 |
+
"grad_norm": 0.3367120191713227,
|
| 189 |
+
"learning_rate": 1e-05,
|
| 190 |
+
"loss": 0.6303,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6153846153846154,
|
| 195 |
+
"grad_norm": 0.33627122083313027,
|
| 196 |
+
"learning_rate": 1e-05,
|
| 197 |
+
"loss": 0.6274,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.6381766381766382,
|
| 202 |
+
"grad_norm": 0.362508172904337,
|
| 203 |
+
"learning_rate": 1e-05,
|
| 204 |
+
"loss": 0.6382,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6609686609686609,
|
| 209 |
+
"grad_norm": 0.34361915555957834,
|
| 210 |
+
"learning_rate": 1e-05,
|
| 211 |
+
"loss": 0.6269,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6837606837606838,
|
| 216 |
+
"grad_norm": 0.3287032976695359,
|
| 217 |
+
"learning_rate": 1e-05,
|
| 218 |
+
"loss": 0.6249,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7065527065527065,
|
| 223 |
+
"grad_norm": 0.3191486869355932,
|
| 224 |
+
"learning_rate": 1e-05,
|
| 225 |
+
"loss": 0.6248,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.7293447293447294,
|
| 230 |
+
"grad_norm": 0.31860851089180897,
|
| 231 |
+
"learning_rate": 1e-05,
|
| 232 |
+
"loss": 0.6254,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7521367521367521,
|
| 237 |
+
"grad_norm": 0.3846001822856447,
|
| 238 |
+
"learning_rate": 1e-05,
|
| 239 |
+
"loss": 0.622,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7749287749287749,
|
| 244 |
+
"grad_norm": 0.3477286187132196,
|
| 245 |
+
"learning_rate": 1e-05,
|
| 246 |
+
"loss": 0.6277,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7977207977207977,
|
| 251 |
+
"grad_norm": 0.366357630454119,
|
| 252 |
+
"learning_rate": 1e-05,
|
| 253 |
+
"loss": 0.6348,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.8205128205128205,
|
| 258 |
+
"grad_norm": 0.3609953342647578,
|
| 259 |
+
"learning_rate": 1e-05,
|
| 260 |
+
"loss": 0.6267,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.8433048433048433,
|
| 265 |
+
"grad_norm": 0.41707694363193043,
|
| 266 |
+
"learning_rate": 1e-05,
|
| 267 |
+
"loss": 0.6203,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.8660968660968661,
|
| 272 |
+
"grad_norm": 0.3638258217776452,
|
| 273 |
+
"learning_rate": 1e-05,
|
| 274 |
+
"loss": 0.6326,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8888888888888888,
|
| 279 |
+
"grad_norm": 0.36073013889545996,
|
| 280 |
+
"learning_rate": 1e-05,
|
| 281 |
+
"loss": 0.6312,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9116809116809117,
|
| 286 |
+
"grad_norm": 0.3707654840473297,
|
| 287 |
+
"learning_rate": 1e-05,
|
| 288 |
+
"loss": 0.6343,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9344729344729344,
|
| 293 |
+
"grad_norm": 0.34309367527787005,
|
| 294 |
+
"learning_rate": 1e-05,
|
| 295 |
+
"loss": 0.6306,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.9572649572649573,
|
| 300 |
+
"grad_norm": 0.35582985450029564,
|
| 301 |
+
"learning_rate": 1e-05,
|
| 302 |
+
"loss": 0.6176,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.98005698005698,
|
| 307 |
+
"grad_norm": 0.4461192998565824,
|
| 308 |
+
"learning_rate": 1e-05,
|
| 309 |
+
"loss": 0.6304,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.9982905982905983,
|
| 314 |
+
"eval_loss": 0.621112048625946,
|
| 315 |
+
"eval_runtime": 440.3517,
|
| 316 |
+
"eval_samples_per_second": 26.849,
|
| 317 |
+
"eval_steps_per_second": 0.42,
|
| 318 |
+
"step": 438
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.0034188034188034,
|
| 322 |
+
"grad_norm": 0.40599764408780503,
|
| 323 |
+
"learning_rate": 1e-05,
|
| 324 |
+
"loss": 0.6403,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.0262108262108263,
|
| 329 |
+
"grad_norm": 0.33824605577756234,
|
| 330 |
+
"learning_rate": 1e-05,
|
| 331 |
+
"loss": 0.5777,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.049002849002849,
|
| 336 |
+
"grad_norm": 0.32924589697953344,
|
| 337 |
+
"learning_rate": 1e-05,
|
| 338 |
+
"loss": 0.5713,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.0717948717948718,
|
| 343 |
+
"grad_norm": 0.3390857296918303,
|
| 344 |
+
"learning_rate": 1e-05,
|
| 345 |
+
"loss": 0.5722,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.0945868945868946,
|
| 350 |
+
"grad_norm": 0.35001642645281617,
|
| 351 |
+
"learning_rate": 1e-05,
|
| 352 |
+
"loss": 0.5799,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.1173789173789175,
|
| 357 |
+
"grad_norm": 0.35554307229590787,
|
| 358 |
+
"learning_rate": 1e-05,
|
| 359 |
+
"loss": 0.5849,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.1401709401709401,
|
| 364 |
+
"grad_norm": 0.31083370576221864,
|
| 365 |
+
"learning_rate": 1e-05,
|
| 366 |
+
"loss": 0.5755,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.162962962962963,
|
| 371 |
+
"grad_norm": 0.31553364890263425,
|
| 372 |
+
"learning_rate": 1e-05,
|
| 373 |
+
"loss": 0.5736,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.1857549857549858,
|
| 378 |
+
"grad_norm": 0.2987072829265303,
|
| 379 |
+
"learning_rate": 1e-05,
|
| 380 |
+
"loss": 0.5794,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.2085470085470085,
|
| 385 |
+
"grad_norm": 0.3357868380230108,
|
| 386 |
+
"learning_rate": 1e-05,
|
| 387 |
+
"loss": 0.5731,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.2313390313390313,
|
| 392 |
+
"grad_norm": 0.3424754214162845,
|
| 393 |
+
"learning_rate": 1e-05,
|
| 394 |
+
"loss": 0.5831,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.2541310541310542,
|
| 399 |
+
"grad_norm": 0.2994505023233895,
|
| 400 |
+
"learning_rate": 1e-05,
|
| 401 |
+
"loss": 0.5798,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.2769230769230768,
|
| 406 |
+
"grad_norm": 0.3261302844209219,
|
| 407 |
+
"learning_rate": 1e-05,
|
| 408 |
+
"loss": 0.5818,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.2997150997150997,
|
| 413 |
+
"grad_norm": 0.32160593176293023,
|
| 414 |
+
"learning_rate": 1e-05,
|
| 415 |
+
"loss": 0.5762,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.3225071225071225,
|
| 420 |
+
"grad_norm": 0.31343014468938596,
|
| 421 |
+
"learning_rate": 1e-05,
|
| 422 |
+
"loss": 0.5747,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.3452991452991454,
|
| 427 |
+
"grad_norm": 0.3029232044781107,
|
| 428 |
+
"learning_rate": 1e-05,
|
| 429 |
+
"loss": 0.5744,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.368091168091168,
|
| 434 |
+
"grad_norm": 0.3204205916615222,
|
| 435 |
+
"learning_rate": 1e-05,
|
| 436 |
+
"loss": 0.5801,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.390883190883191,
|
| 441 |
+
"grad_norm": 0.33901583811674174,
|
| 442 |
+
"learning_rate": 1e-05,
|
| 443 |
+
"loss": 0.5802,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.4136752136752135,
|
| 448 |
+
"grad_norm": 0.35647413040021203,
|
| 449 |
+
"learning_rate": 1e-05,
|
| 450 |
+
"loss": 0.5831,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.4364672364672364,
|
| 455 |
+
"grad_norm": 0.3926041011121538,
|
| 456 |
+
"learning_rate": 1e-05,
|
| 457 |
+
"loss": 0.5813,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.4592592592592593,
|
| 462 |
+
"grad_norm": 0.33806390127793345,
|
| 463 |
+
"learning_rate": 1e-05,
|
| 464 |
+
"loss": 0.5762,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.4820512820512821,
|
| 469 |
+
"grad_norm": 0.328698581982291,
|
| 470 |
+
"learning_rate": 1e-05,
|
| 471 |
+
"loss": 0.5744,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.504843304843305,
|
| 476 |
+
"grad_norm": 0.3395135859147101,
|
| 477 |
+
"learning_rate": 1e-05,
|
| 478 |
+
"loss": 0.5742,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.5276353276353276,
|
| 483 |
+
"grad_norm": 0.3885455805540249,
|
| 484 |
+
"learning_rate": 1e-05,
|
| 485 |
+
"loss": 0.5816,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.5504273504273505,
|
| 490 |
+
"grad_norm": 0.30996592095776465,
|
| 491 |
+
"learning_rate": 1e-05,
|
| 492 |
+
"loss": 0.5707,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.573219373219373,
|
| 497 |
+
"grad_norm": 0.3146912481858014,
|
| 498 |
+
"learning_rate": 1e-05,
|
| 499 |
+
"loss": 0.5744,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.596011396011396,
|
| 504 |
+
"grad_norm": 0.31588213782224217,
|
| 505 |
+
"learning_rate": 1e-05,
|
| 506 |
+
"loss": 0.59,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.6188034188034188,
|
| 511 |
+
"grad_norm": 0.32153673893804763,
|
| 512 |
+
"learning_rate": 1e-05,
|
| 513 |
+
"loss": 0.5774,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.6415954415954417,
|
| 518 |
+
"grad_norm": 0.31257504452618234,
|
| 519 |
+
"learning_rate": 1e-05,
|
| 520 |
+
"loss": 0.5818,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.6643874643874645,
|
| 525 |
+
"grad_norm": 0.3253370468338142,
|
| 526 |
+
"learning_rate": 1e-05,
|
| 527 |
+
"loss": 0.5752,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.6871794871794872,
|
| 532 |
+
"grad_norm": 0.35468087072518323,
|
| 533 |
+
"learning_rate": 1e-05,
|
| 534 |
+
"loss": 0.5765,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.7099715099715098,
|
| 539 |
+
"grad_norm": 0.2941502107066292,
|
| 540 |
+
"learning_rate": 1e-05,
|
| 541 |
+
"loss": 0.574,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.7327635327635327,
|
| 546 |
+
"grad_norm": 0.4040377978043082,
|
| 547 |
+
"learning_rate": 1e-05,
|
| 548 |
+
"loss": 0.5776,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.7555555555555555,
|
| 553 |
+
"grad_norm": 0.3335681103789512,
|
| 554 |
+
"learning_rate": 1e-05,
|
| 555 |
+
"loss": 0.5743,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.7783475783475784,
|
| 560 |
+
"grad_norm": 0.30226629822048895,
|
| 561 |
+
"learning_rate": 1e-05,
|
| 562 |
+
"loss": 0.5816,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.8011396011396013,
|
| 567 |
+
"grad_norm": 0.3339556013176704,
|
| 568 |
+
"learning_rate": 1e-05,
|
| 569 |
+
"loss": 0.5793,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.823931623931624,
|
| 574 |
+
"grad_norm": 0.3269246369063951,
|
| 575 |
+
"learning_rate": 1e-05,
|
| 576 |
+
"loss": 0.5666,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.8467236467236468,
|
| 581 |
+
"grad_norm": 0.3224956260584643,
|
| 582 |
+
"learning_rate": 1e-05,
|
| 583 |
+
"loss": 0.5742,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.8695156695156694,
|
| 588 |
+
"grad_norm": 0.3655123174434984,
|
| 589 |
+
"learning_rate": 1e-05,
|
| 590 |
+
"loss": 0.5721,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.8923076923076922,
|
| 595 |
+
"grad_norm": 0.33531337558262225,
|
| 596 |
+
"learning_rate": 1e-05,
|
| 597 |
+
"loss": 0.5758,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.915099715099715,
|
| 602 |
+
"grad_norm": 0.33279895151242517,
|
| 603 |
+
"learning_rate": 1e-05,
|
| 604 |
+
"loss": 0.5803,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.937891737891738,
|
| 609 |
+
"grad_norm": 0.31841085542396463,
|
| 610 |
+
"learning_rate": 1e-05,
|
| 611 |
+
"loss": 0.5786,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.9606837606837608,
|
| 616 |
+
"grad_norm": 0.3656774559080548,
|
| 617 |
+
"learning_rate": 1e-05,
|
| 618 |
+
"loss": 0.5798,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.9834757834757835,
|
| 623 |
+
"grad_norm": 0.32129389800623026,
|
| 624 |
+
"learning_rate": 1e-05,
|
| 625 |
+
"loss": 0.5774,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.9994301994301993,
|
| 630 |
+
"eval_loss": 0.6186357736587524,
|
| 631 |
+
"eval_runtime": 442.4653,
|
| 632 |
+
"eval_samples_per_second": 26.721,
|
| 633 |
+
"eval_steps_per_second": 0.418,
|
| 634 |
+
"step": 877
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.006837606837607,
|
| 638 |
+
"grad_norm": 0.40023961081016884,
|
| 639 |
+
"learning_rate": 1e-05,
|
| 640 |
+
"loss": 0.5896,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.0296296296296297,
|
| 645 |
+
"grad_norm": 0.3934269207415266,
|
| 646 |
+
"learning_rate": 1e-05,
|
| 647 |
+
"loss": 0.5143,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.0524216524216525,
|
| 652 |
+
"grad_norm": 0.3372672329666936,
|
| 653 |
+
"learning_rate": 1e-05,
|
| 654 |
+
"loss": 0.5277,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.0752136752136754,
|
| 659 |
+
"grad_norm": 0.3590605375051872,
|
| 660 |
+
"learning_rate": 1e-05,
|
| 661 |
+
"loss": 0.5262,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.098005698005698,
|
| 666 |
+
"grad_norm": 0.32027005855990875,
|
| 667 |
+
"learning_rate": 1e-05,
|
| 668 |
+
"loss": 0.529,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.1207977207977207,
|
| 673 |
+
"grad_norm": 0.3122240355891651,
|
| 674 |
+
"learning_rate": 1e-05,
|
| 675 |
+
"loss": 0.5279,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.1435897435897435,
|
| 680 |
+
"grad_norm": 0.306328979810517,
|
| 681 |
+
"learning_rate": 1e-05,
|
| 682 |
+
"loss": 0.523,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.1663817663817664,
|
| 687 |
+
"grad_norm": 0.2997763176691866,
|
| 688 |
+
"learning_rate": 1e-05,
|
| 689 |
+
"loss": 0.5239,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.1891737891737892,
|
| 694 |
+
"grad_norm": 0.30072443341331295,
|
| 695 |
+
"learning_rate": 1e-05,
|
| 696 |
+
"loss": 0.5291,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.211965811965812,
|
| 701 |
+
"grad_norm": 0.3659610909649348,
|
| 702 |
+
"learning_rate": 1e-05,
|
| 703 |
+
"loss": 0.529,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.234757834757835,
|
| 708 |
+
"grad_norm": 0.31170766785306336,
|
| 709 |
+
"learning_rate": 1e-05,
|
| 710 |
+
"loss": 0.5197,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.2575498575498574,
|
| 715 |
+
"grad_norm": 0.3107127824005287,
|
| 716 |
+
"learning_rate": 1e-05,
|
| 717 |
+
"loss": 0.5287,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.2803418803418802,
|
| 722 |
+
"grad_norm": 0.3077202897593116,
|
| 723 |
+
"learning_rate": 1e-05,
|
| 724 |
+
"loss": 0.5293,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.303133903133903,
|
| 729 |
+
"grad_norm": 0.3766294985445228,
|
| 730 |
+
"learning_rate": 1e-05,
|
| 731 |
+
"loss": 0.5269,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.325925925925926,
|
| 736 |
+
"grad_norm": 0.31670166754832074,
|
| 737 |
+
"learning_rate": 1e-05,
|
| 738 |
+
"loss": 0.5298,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.348717948717949,
|
| 743 |
+
"grad_norm": 0.3294563307726443,
|
| 744 |
+
"learning_rate": 1e-05,
|
| 745 |
+
"loss": 0.5311,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.3715099715099717,
|
| 750 |
+
"grad_norm": 0.33934557749302635,
|
| 751 |
+
"learning_rate": 1e-05,
|
| 752 |
+
"loss": 0.5299,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.394301994301994,
|
| 757 |
+
"grad_norm": 0.29973624613589284,
|
| 758 |
+
"learning_rate": 1e-05,
|
| 759 |
+
"loss": 0.5292,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.417094017094017,
|
| 764 |
+
"grad_norm": 0.30731911268155737,
|
| 765 |
+
"learning_rate": 1e-05,
|
| 766 |
+
"loss": 0.537,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.43988603988604,
|
| 771 |
+
"grad_norm": 0.3320184686838146,
|
| 772 |
+
"learning_rate": 1e-05,
|
| 773 |
+
"loss": 0.5397,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.4626780626780627,
|
| 778 |
+
"grad_norm": 0.33488791378484484,
|
| 779 |
+
"learning_rate": 1e-05,
|
| 780 |
+
"loss": 0.5354,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.4854700854700855,
|
| 785 |
+
"grad_norm": 0.29869988487306637,
|
| 786 |
+
"learning_rate": 1e-05,
|
| 787 |
+
"loss": 0.5339,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.5082621082621084,
|
| 792 |
+
"grad_norm": 0.3904880801438361,
|
| 793 |
+
"learning_rate": 1e-05,
|
| 794 |
+
"loss": 0.5394,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.5310541310541312,
|
| 799 |
+
"grad_norm": 0.38036081075155204,
|
| 800 |
+
"learning_rate": 1e-05,
|
| 801 |
+
"loss": 0.5341,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.5538461538461537,
|
| 806 |
+
"grad_norm": 0.30643406351346947,
|
| 807 |
+
"learning_rate": 1e-05,
|
| 808 |
+
"loss": 0.5322,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.5766381766381765,
|
| 813 |
+
"grad_norm": 0.2893340180647077,
|
| 814 |
+
"learning_rate": 1e-05,
|
| 815 |
+
"loss": 0.5319,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.5994301994301994,
|
| 820 |
+
"grad_norm": 0.29553745186992597,
|
| 821 |
+
"learning_rate": 1e-05,
|
| 822 |
+
"loss": 0.5318,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.6222222222222222,
|
| 827 |
+
"grad_norm": 0.3121235774200754,
|
| 828 |
+
"learning_rate": 1e-05,
|
| 829 |
+
"loss": 0.5324,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.645014245014245,
|
| 834 |
+
"grad_norm": 0.3537885981034807,
|
| 835 |
+
"learning_rate": 1e-05,
|
| 836 |
+
"loss": 0.5338,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.667806267806268,
|
| 841 |
+
"grad_norm": 0.3135782078081984,
|
| 842 |
+
"learning_rate": 1e-05,
|
| 843 |
+
"loss": 0.5361,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.690598290598291,
|
| 848 |
+
"grad_norm": 0.3120319160666968,
|
| 849 |
+
"learning_rate": 1e-05,
|
| 850 |
+
"loss": 0.5316,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.7133903133903132,
|
| 855 |
+
"grad_norm": 0.3721925648462127,
|
| 856 |
+
"learning_rate": 1e-05,
|
| 857 |
+
"loss": 0.5331,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.736182336182336,
|
| 862 |
+
"grad_norm": 0.35097259445904583,
|
| 863 |
+
"learning_rate": 1e-05,
|
| 864 |
+
"loss": 0.5362,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.758974358974359,
|
| 869 |
+
"grad_norm": 0.3191287188931511,
|
| 870 |
+
"learning_rate": 1e-05,
|
| 871 |
+
"loss": 0.5394,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.781766381766382,
|
| 876 |
+
"grad_norm": 0.3353550527181426,
|
| 877 |
+
"learning_rate": 1e-05,
|
| 878 |
+
"loss": 0.5301,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.8045584045584047,
|
| 883 |
+
"grad_norm": 0.3662461553840285,
|
| 884 |
+
"learning_rate": 1e-05,
|
| 885 |
+
"loss": 0.5286,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.827350427350427,
|
| 890 |
+
"grad_norm": 0.3582675691272763,
|
| 891 |
+
"learning_rate": 1e-05,
|
| 892 |
+
"loss": 0.5428,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.8501424501424504,
|
| 897 |
+
"grad_norm": 0.29421053202127245,
|
| 898 |
+
"learning_rate": 1e-05,
|
| 899 |
+
"loss": 0.5393,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.872934472934473,
|
| 904 |
+
"grad_norm": 0.3323816797271506,
|
| 905 |
+
"learning_rate": 1e-05,
|
| 906 |
+
"loss": 0.5369,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.8957264957264957,
|
| 911 |
+
"grad_norm": 0.34833626456933586,
|
| 912 |
+
"learning_rate": 1e-05,
|
| 913 |
+
"loss": 0.5381,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.9185185185185185,
|
| 918 |
+
"grad_norm": 0.3208962009280921,
|
| 919 |
+
"learning_rate": 1e-05,
|
| 920 |
+
"loss": 0.5288,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.9413105413105414,
|
| 925 |
+
"grad_norm": 0.3524250244854125,
|
| 926 |
+
"learning_rate": 1e-05,
|
| 927 |
+
"loss": 0.5293,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.9641025641025642,
|
| 932 |
+
"grad_norm": 0.31554960818197597,
|
| 933 |
+
"learning_rate": 1e-05,
|
| 934 |
+
"loss": 0.5303,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.9868945868945866,
|
| 939 |
+
"grad_norm": 0.33440739359228305,
|
| 940 |
+
"learning_rate": 1e-05,
|
| 941 |
+
"loss": 0.5394,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.996011396011396,
|
| 946 |
+
"eval_loss": 0.6266428232192993,
|
| 947 |
+
"eval_runtime": 446.7392,
|
| 948 |
+
"eval_samples_per_second": 26.465,
|
| 949 |
+
"eval_steps_per_second": 0.414,
|
| 950 |
+
"step": 1314
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.996011396011396,
|
| 954 |
+
"step": 1314,
|
| 955 |
+
"total_flos": 2755219238682624.0,
|
| 956 |
+
"train_loss": 0.5826670261641435,
|
| 957 |
+
"train_runtime": 70447.3802,
|
| 958 |
+
"train_samples_per_second": 9.565,
|
| 959 |
+
"train_steps_per_second": 0.019
|
| 960 |
+
}
|
| 961 |
+
],
|
| 962 |
+
"logging_steps": 10,
|
| 963 |
+
"max_steps": 1314,
|
| 964 |
+
"num_input_tokens_seen": 0,
|
| 965 |
+
"num_train_epochs": 3,
|
| 966 |
+
"save_steps": 500,
|
| 967 |
+
"stateful_callbacks": {
|
| 968 |
+
"TrainerControl": {
|
| 969 |
+
"args": {
|
| 970 |
+
"should_epoch_stop": false,
|
| 971 |
+
"should_evaluate": false,
|
| 972 |
+
"should_log": false,
|
| 973 |
+
"should_save": true,
|
| 974 |
+
"should_training_stop": true
|
| 975 |
+
},
|
| 976 |
+
"attributes": {}
|
| 977 |
+
}
|
| 978 |
+
},
|
| 979 |
+
"total_flos": 2755219238682624.0,
|
| 980 |
+
"train_batch_size": 8,
|
| 981 |
+
"trial_name": null,
|
| 982 |
+
"trial_params": null
|
| 983 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|