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 +941 -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/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: llama3-1_8b_oh_v3.1_wo_gpt4_llm
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# llama3-1_8b_oh_v3.1_wo_gpt4_llm
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.6390
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: llama3-1_8b_oh_v3.1_wo_gpt4_llm
|
|
|
|
| 16 |
|
| 17 |
# llama3-1_8b_oh_v3.1_wo_gpt4_llm
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/oh_v3.1_wo_gpt4_llm dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6390
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6389971375465393,
|
| 4 |
+
"eval_runtime": 41.2263,
|
| 5 |
+
"eval_samples_per_second": 273.491,
|
| 6 |
+
"eval_steps_per_second": 1.092,
|
| 7 |
+
"total_flos": 2105521817518080.0,
|
| 8 |
+
"train_loss": 0.6169646524112189,
|
| 9 |
+
"train_runtime": 7810.9265,
|
| 10 |
+
"train_samples_per_second": 82.273,
|
| 11 |
+
"train_steps_per_second": 0.161
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6389971375465393,
|
| 4 |
+
"eval_runtime": 41.2263,
|
| 5 |
+
"eval_samples_per_second": 273.491,
|
| 6 |
+
"eval_steps_per_second": 1.092
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2105521817518080.0,
|
| 4 |
+
"train_loss": 0.6169646524112189,
|
| 5 |
+
"train_runtime": 7810.9265,
|
| 6 |
+
"train_samples_per_second": 82.273,
|
| 7 |
+
"train_steps_per_second": 0.161
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,941 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1257,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02386634844868735,
|
| 13 |
+
"grad_norm": 2.8815478378979726,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.8847,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0477326968973747,
|
| 20 |
+
"grad_norm": 2.1111681660055823,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.7795,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07159904534606205,
|
| 27 |
+
"grad_norm": 0.7661989040642819,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.7503,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0954653937947494,
|
| 34 |
+
"grad_norm": 0.9394058763103804,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.7339,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11933174224343675,
|
| 41 |
+
"grad_norm": 0.8225402898620612,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.7135,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1431980906921241,
|
| 48 |
+
"grad_norm": 0.7799933213085141,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.7122,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.16706443914081145,
|
| 55 |
+
"grad_norm": 0.5800160564456466,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.6973,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1909307875894988,
|
| 62 |
+
"grad_norm": 0.597063104491002,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.6903,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.21479713603818615,
|
| 69 |
+
"grad_norm": 0.5997913835782436,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.6808,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2386634844868735,
|
| 76 |
+
"grad_norm": 0.9361461454403766,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6882,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.26252983293556087,
|
| 83 |
+
"grad_norm": 0.6783993996639943,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.6836,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2863961813842482,
|
| 90 |
+
"grad_norm": 0.5795802549448508,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.6806,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.31026252983293556,
|
| 97 |
+
"grad_norm": 0.5386116555684645,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.6786,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.3341288782816229,
|
| 104 |
+
"grad_norm": 1.1955667749232783,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.673,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.35799522673031026,
|
| 111 |
+
"grad_norm": 0.963473662374355,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6791,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3818615751789976,
|
| 118 |
+
"grad_norm": 0.5375818632492324,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.6715,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.40572792362768495,
|
| 125 |
+
"grad_norm": 0.5122467752567826,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6672,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.4295942720763723,
|
| 132 |
+
"grad_norm": 0.5438018622021655,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6696,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.45346062052505964,
|
| 139 |
+
"grad_norm": 0.5443450875717797,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6707,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.477326968973747,
|
| 146 |
+
"grad_norm": 0.5591666330075007,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6629,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5011933174224343,
|
| 153 |
+
"grad_norm": 0.7316386056094906,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.6601,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5250596658711217,
|
| 160 |
+
"grad_norm": 0.8169771743047101,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.666,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.548926014319809,
|
| 167 |
+
"grad_norm": 0.5023436573258486,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6655,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5727923627684964,
|
| 174 |
+
"grad_norm": 0.5715922888425466,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.6621,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5966587112171837,
|
| 181 |
+
"grad_norm": 0.5978492051245125,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.6606,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6205250596658711,
|
| 188 |
+
"grad_norm": 0.5562863722589444,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.6646,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6443914081145584,
|
| 195 |
+
"grad_norm": 0.5933691995834427,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6583,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.6682577565632458,
|
| 202 |
+
"grad_norm": 0.5981641076306046,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.6557,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6921241050119332,
|
| 209 |
+
"grad_norm": 0.8109530838139422,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6582,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.7159904534606205,
|
| 216 |
+
"grad_norm": 0.5965206875329182,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.6621,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7398568019093079,
|
| 223 |
+
"grad_norm": 0.486222749934066,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6549,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.7637231503579952,
|
| 230 |
+
"grad_norm": 0.5522832083975265,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6496,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7875894988066826,
|
| 237 |
+
"grad_norm": 0.5396338578678825,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.6431,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.8114558472553699,
|
| 244 |
+
"grad_norm": 0.509360104131435,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.6458,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.8353221957040573,
|
| 251 |
+
"grad_norm": 0.5620324892726529,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.6564,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.8591885441527446,
|
| 258 |
+
"grad_norm": 0.6119146933240237,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.6534,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.883054892601432,
|
| 265 |
+
"grad_norm": 0.5839021797409776,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.6565,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.9069212410501193,
|
| 272 |
+
"grad_norm": 0.43401159052073285,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.6535,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.9307875894988067,
|
| 279 |
+
"grad_norm": 0.5668890229094246,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.6462,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.954653937947494,
|
| 286 |
+
"grad_norm": 0.5782226624956547,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.6546,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9785202863961814,
|
| 293 |
+
"grad_norm": 0.6579659643852935,
|
| 294 |
+
"learning_rate": 5e-06,
|
| 295 |
+
"loss": 0.641,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.0,
|
| 300 |
+
"eval_loss": 0.6449207663536072,
|
| 301 |
+
"eval_runtime": 41.1778,
|
| 302 |
+
"eval_samples_per_second": 273.813,
|
| 303 |
+
"eval_steps_per_second": 1.093,
|
| 304 |
+
"step": 419
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.0023866348448687,
|
| 308 |
+
"grad_norm": 0.7827774952972171,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.6431,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.026252983293556,
|
| 315 |
+
"grad_norm": 0.6329747383963555,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.6134,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.0501193317422435,
|
| 322 |
+
"grad_norm": 0.5281801985221292,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.6083,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.0739856801909309,
|
| 329 |
+
"grad_norm": 0.7577758408944637,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.6061,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.097852028639618,
|
| 336 |
+
"grad_norm": 0.5351677292156073,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.6031,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.1217183770883055,
|
| 343 |
+
"grad_norm": 0.5015989972497082,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.6059,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.1455847255369929,
|
| 350 |
+
"grad_norm": 0.5967761959033508,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.6144,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.1694510739856803,
|
| 357 |
+
"grad_norm": 0.6199769517789647,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.6089,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.1933174224343674,
|
| 364 |
+
"grad_norm": 0.5989234321280023,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.6079,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.2171837708830548,
|
| 371 |
+
"grad_norm": 0.48214122296698664,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.6106,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.2410501193317423,
|
| 378 |
+
"grad_norm": 0.500906885639557,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.6114,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.2649164677804297,
|
| 385 |
+
"grad_norm": 0.5055182485221988,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.6073,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.288782816229117,
|
| 392 |
+
"grad_norm": 0.5890740590556416,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.6074,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.3126491646778042,
|
| 399 |
+
"grad_norm": 0.48236044063151085,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.6128,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.3365155131264916,
|
| 406 |
+
"grad_norm": 0.5202514925506149,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.6058,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.360381861575179,
|
| 413 |
+
"grad_norm": 0.5228316664959745,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.6091,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.3842482100238662,
|
| 420 |
+
"grad_norm": 0.51530770994292,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.6087,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.4081145584725536,
|
| 427 |
+
"grad_norm": 0.6386559379894787,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.6116,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.431980906921241,
|
| 434 |
+
"grad_norm": 0.4779744600855222,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.6033,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.4558472553699284,
|
| 441 |
+
"grad_norm": 0.4819600928038827,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.6077,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.4797136038186158,
|
| 448 |
+
"grad_norm": 0.45917275315096606,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.6094,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.503579952267303,
|
| 455 |
+
"grad_norm": 0.5010113270578477,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.6055,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.5274463007159904,
|
| 462 |
+
"grad_norm": 0.7579117243752399,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.6159,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.5513126491646778,
|
| 469 |
+
"grad_norm": 0.6420792800924288,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.6058,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.575178997613365,
|
| 476 |
+
"grad_norm": 0.55940882824889,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.5961,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.5990453460620526,
|
| 483 |
+
"grad_norm": 0.4983792149426302,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.6083,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.6229116945107398,
|
| 490 |
+
"grad_norm": 0.5263299595036224,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.6053,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.6467780429594272,
|
| 497 |
+
"grad_norm": 0.5149484039474402,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.6079,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.6706443914081146,
|
| 504 |
+
"grad_norm": 0.4685802940879146,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.6041,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.6945107398568018,
|
| 511 |
+
"grad_norm": 0.4639317334767733,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.6012,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.7183770883054894,
|
| 518 |
+
"grad_norm": 0.48774835965978913,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.6117,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.7422434367541766,
|
| 525 |
+
"grad_norm": 0.4895883070209168,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.6066,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.766109785202864,
|
| 532 |
+
"grad_norm": 0.45180400146140737,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.6031,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.7899761336515514,
|
| 539 |
+
"grad_norm": 0.5197512123710193,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.6018,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.8138424821002386,
|
| 546 |
+
"grad_norm": 0.45816712660411146,
|
| 547 |
+
"learning_rate": 5e-06,
|
| 548 |
+
"loss": 0.6024,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.837708830548926,
|
| 553 |
+
"grad_norm": 0.45318755220959944,
|
| 554 |
+
"learning_rate": 5e-06,
|
| 555 |
+
"loss": 0.6101,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.8615751789976134,
|
| 560 |
+
"grad_norm": 0.48227944198410183,
|
| 561 |
+
"learning_rate": 5e-06,
|
| 562 |
+
"loss": 0.6084,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.8854415274463006,
|
| 567 |
+
"grad_norm": 0.5498211459609608,
|
| 568 |
+
"learning_rate": 5e-06,
|
| 569 |
+
"loss": 0.6014,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.9093078758949882,
|
| 574 |
+
"grad_norm": 0.5272792947894827,
|
| 575 |
+
"learning_rate": 5e-06,
|
| 576 |
+
"loss": 0.6035,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.9331742243436754,
|
| 581 |
+
"grad_norm": 0.4520775749202011,
|
| 582 |
+
"learning_rate": 5e-06,
|
| 583 |
+
"loss": 0.6023,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.9570405727923628,
|
| 588 |
+
"grad_norm": 0.48624457536560756,
|
| 589 |
+
"learning_rate": 5e-06,
|
| 590 |
+
"loss": 0.6022,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.9809069212410502,
|
| 595 |
+
"grad_norm": 0.5488566572359053,
|
| 596 |
+
"learning_rate": 5e-06,
|
| 597 |
+
"loss": 0.6068,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.0,
|
| 602 |
+
"eval_loss": 0.6355295777320862,
|
| 603 |
+
"eval_runtime": 40.6265,
|
| 604 |
+
"eval_samples_per_second": 277.529,
|
| 605 |
+
"eval_steps_per_second": 1.108,
|
| 606 |
+
"step": 838
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.0047732696897373,
|
| 610 |
+
"grad_norm": 0.6658281603460572,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.5955,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.028639618138425,
|
| 617 |
+
"grad_norm": 0.7098614483793992,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.5701,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.052505966587112,
|
| 624 |
+
"grad_norm": 0.6533616500153973,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.5634,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.0763723150357993,
|
| 631 |
+
"grad_norm": 0.6126417325021997,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.5639,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.100238663484487,
|
| 638 |
+
"grad_norm": 0.44612672152357774,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.5671,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.124105011933174,
|
| 645 |
+
"grad_norm": 0.5379973514690706,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.562,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.1479713603818618,
|
| 652 |
+
"grad_norm": 0.442404391317877,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.5728,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.171837708830549,
|
| 659 |
+
"grad_norm": 0.5754078775127957,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.5613,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.195704057279236,
|
| 666 |
+
"grad_norm": 0.6586173018673331,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.5654,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.2195704057279237,
|
| 673 |
+
"grad_norm": 0.5439510862576353,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.5614,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.243436754176611,
|
| 680 |
+
"grad_norm": 0.5740630674331443,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.565,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.2673031026252985,
|
| 687 |
+
"grad_norm": 0.48777976586303107,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.561,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.2911694510739857,
|
| 694 |
+
"grad_norm": 0.4461443532364416,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.5582,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.315035799522673,
|
| 701 |
+
"grad_norm": 0.487505257972905,
|
| 702 |
+
"learning_rate": 5e-06,
|
| 703 |
+
"loss": 0.5692,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.3389021479713605,
|
| 708 |
+
"grad_norm": 0.48305958679617367,
|
| 709 |
+
"learning_rate": 5e-06,
|
| 710 |
+
"loss": 0.5694,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.3627684964200477,
|
| 715 |
+
"grad_norm": 0.503359166301003,
|
| 716 |
+
"learning_rate": 5e-06,
|
| 717 |
+
"loss": 0.5609,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.386634844868735,
|
| 722 |
+
"grad_norm": 0.5256679194745039,
|
| 723 |
+
"learning_rate": 5e-06,
|
| 724 |
+
"loss": 0.5632,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.4105011933174225,
|
| 729 |
+
"grad_norm": 0.5732669619119689,
|
| 730 |
+
"learning_rate": 5e-06,
|
| 731 |
+
"loss": 0.5666,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.4343675417661097,
|
| 736 |
+
"grad_norm": 0.4506151186524362,
|
| 737 |
+
"learning_rate": 5e-06,
|
| 738 |
+
"loss": 0.5762,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.4582338902147973,
|
| 743 |
+
"grad_norm": 0.4746241123968773,
|
| 744 |
+
"learning_rate": 5e-06,
|
| 745 |
+
"loss": 0.5652,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.4821002386634845,
|
| 750 |
+
"grad_norm": 0.46349902513638275,
|
| 751 |
+
"learning_rate": 5e-06,
|
| 752 |
+
"loss": 0.5644,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.5059665871121717,
|
| 757 |
+
"grad_norm": 0.45976906873116374,
|
| 758 |
+
"learning_rate": 5e-06,
|
| 759 |
+
"loss": 0.5686,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.5298329355608593,
|
| 764 |
+
"grad_norm": 0.4662220401853357,
|
| 765 |
+
"learning_rate": 5e-06,
|
| 766 |
+
"loss": 0.5686,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.5536992840095465,
|
| 771 |
+
"grad_norm": 0.4951436398512421,
|
| 772 |
+
"learning_rate": 5e-06,
|
| 773 |
+
"loss": 0.5702,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.577565632458234,
|
| 778 |
+
"grad_norm": 0.4502698747379483,
|
| 779 |
+
"learning_rate": 5e-06,
|
| 780 |
+
"loss": 0.5719,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.6014319809069213,
|
| 785 |
+
"grad_norm": 0.5079705723721918,
|
| 786 |
+
"learning_rate": 5e-06,
|
| 787 |
+
"loss": 0.5671,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.6252983293556085,
|
| 792 |
+
"grad_norm": 0.5140346872907439,
|
| 793 |
+
"learning_rate": 5e-06,
|
| 794 |
+
"loss": 0.5671,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.649164677804296,
|
| 799 |
+
"grad_norm": 0.5358331120197253,
|
| 800 |
+
"learning_rate": 5e-06,
|
| 801 |
+
"loss": 0.5633,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.6730310262529833,
|
| 806 |
+
"grad_norm": 0.4907309631164768,
|
| 807 |
+
"learning_rate": 5e-06,
|
| 808 |
+
"loss": 0.5644,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.6968973747016705,
|
| 813 |
+
"grad_norm": 0.5049970936550133,
|
| 814 |
+
"learning_rate": 5e-06,
|
| 815 |
+
"loss": 0.5692,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.720763723150358,
|
| 820 |
+
"grad_norm": 0.5553567091902175,
|
| 821 |
+
"learning_rate": 5e-06,
|
| 822 |
+
"loss": 0.5658,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.7446300715990453,
|
| 827 |
+
"grad_norm": 0.49261752142359677,
|
| 828 |
+
"learning_rate": 5e-06,
|
| 829 |
+
"loss": 0.5742,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.7684964200477324,
|
| 834 |
+
"grad_norm": 0.5018759977401656,
|
| 835 |
+
"learning_rate": 5e-06,
|
| 836 |
+
"loss": 0.5645,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.79236276849642,
|
| 841 |
+
"grad_norm": 0.45826106825699625,
|
| 842 |
+
"learning_rate": 5e-06,
|
| 843 |
+
"loss": 0.5641,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.8162291169451072,
|
| 848 |
+
"grad_norm": 0.5072976091618316,
|
| 849 |
+
"learning_rate": 5e-06,
|
| 850 |
+
"loss": 0.5676,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.840095465393795,
|
| 855 |
+
"grad_norm": 0.651235919618626,
|
| 856 |
+
"learning_rate": 5e-06,
|
| 857 |
+
"loss": 0.5681,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.863961813842482,
|
| 862 |
+
"grad_norm": 0.5113781250941779,
|
| 863 |
+
"learning_rate": 5e-06,
|
| 864 |
+
"loss": 0.5669,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.8878281622911697,
|
| 869 |
+
"grad_norm": 0.4949601222660754,
|
| 870 |
+
"learning_rate": 5e-06,
|
| 871 |
+
"loss": 0.5581,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.911694510739857,
|
| 876 |
+
"grad_norm": 0.5748654481884351,
|
| 877 |
+
"learning_rate": 5e-06,
|
| 878 |
+
"loss": 0.5678,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.935560859188544,
|
| 883 |
+
"grad_norm": 0.5793617800123868,
|
| 884 |
+
"learning_rate": 5e-06,
|
| 885 |
+
"loss": 0.5649,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.9594272076372317,
|
| 890 |
+
"grad_norm": 0.4514242707013011,
|
| 891 |
+
"learning_rate": 5e-06,
|
| 892 |
+
"loss": 0.5652,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.983293556085919,
|
| 897 |
+
"grad_norm": 0.4744906861925991,
|
| 898 |
+
"learning_rate": 5e-06,
|
| 899 |
+
"loss": 0.5638,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 3.0,
|
| 904 |
+
"eval_loss": 0.6389971375465393,
|
| 905 |
+
"eval_runtime": 41.4704,
|
| 906 |
+
"eval_samples_per_second": 271.881,
|
| 907 |
+
"eval_steps_per_second": 1.085,
|
| 908 |
+
"step": 1257
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 3.0,
|
| 912 |
+
"step": 1257,
|
| 913 |
+
"total_flos": 2105521817518080.0,
|
| 914 |
+
"train_loss": 0.6169646524112189,
|
| 915 |
+
"train_runtime": 7810.9265,
|
| 916 |
+
"train_samples_per_second": 82.273,
|
| 917 |
+
"train_steps_per_second": 0.161
|
| 918 |
+
}
|
| 919 |
+
],
|
| 920 |
+
"logging_steps": 10,
|
| 921 |
+
"max_steps": 1257,
|
| 922 |
+
"num_input_tokens_seen": 0,
|
| 923 |
+
"num_train_epochs": 3,
|
| 924 |
+
"save_steps": 500,
|
| 925 |
+
"stateful_callbacks": {
|
| 926 |
+
"TrainerControl": {
|
| 927 |
+
"args": {
|
| 928 |
+
"should_epoch_stop": false,
|
| 929 |
+
"should_evaluate": false,
|
| 930 |
+
"should_log": false,
|
| 931 |
+
"should_save": true,
|
| 932 |
+
"should_training_stop": true
|
| 933 |
+
},
|
| 934 |
+
"attributes": {}
|
| 935 |
+
}
|
| 936 |
+
},
|
| 937 |
+
"total_flos": 2105521817518080.0,
|
| 938 |
+
"train_batch_size": 16,
|
| 939 |
+
"trial_name": null,
|
| 940 |
+
"trial_params": null
|
| 941 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|