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 +1921 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: gemma
|
|
| 4 |
base_model: google/gemma-2-9b
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: hp_ablations_gemma_bsz256
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# hp_ablations_gemma_bsz256
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.6163
|
| 21 |
|
|
|
|
| 4 |
base_model: google/gemma-2-9b
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: hp_ablations_gemma_bsz256
|
|
|
|
| 16 |
|
| 17 |
# hp_ablations_gemma_bsz256
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6163
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9991537376586743,
|
| 3 |
+
"eval_loss": 0.6162799000740051,
|
| 4 |
+
"eval_runtime": 697.6766,
|
| 5 |
+
"eval_samples_per_second": 17.115,
|
| 6 |
+
"eval_steps_per_second": 0.536,
|
| 7 |
+
"total_flos": 5064195066298368.0,
|
| 8 |
+
"train_loss": 0.5339989464833739,
|
| 9 |
+
"train_runtime": 122516.7944,
|
| 10 |
+
"train_samples_per_second": 5.555,
|
| 11 |
+
"train_steps_per_second": 0.022
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9991537376586743,
|
| 3 |
+
"eval_loss": 0.6162799000740051,
|
| 4 |
+
"eval_runtime": 697.6766,
|
| 5 |
+
"eval_samples_per_second": 17.115,
|
| 6 |
+
"eval_steps_per_second": 0.536
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9991537376586743,
|
| 3 |
+
"total_flos": 5064195066298368.0,
|
| 4 |
+
"train_loss": 0.5339989464833739,
|
| 5 |
+
"train_runtime": 122516.7944,
|
| 6 |
+
"train_samples_per_second": 5.555,
|
| 7 |
+
"train_steps_per_second": 0.022
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1921 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9991537376586743,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2658,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.011283497884344146,
|
| 13 |
+
"grad_norm": 1.3125232159346416,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.7474,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.022566995768688293,
|
| 20 |
+
"grad_norm": 0.9167355748966123,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.6794,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03385049365303244,
|
| 27 |
+
"grad_norm": 0.8469930147086754,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.6697,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.045133991537376586,
|
| 34 |
+
"grad_norm": 0.8935332426600987,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.6592,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.056417489421720736,
|
| 41 |
+
"grad_norm": 0.7558955578947845,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.6527,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06770098730606489,
|
| 48 |
+
"grad_norm": 0.8864690987221431,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.6546,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07898448519040903,
|
| 55 |
+
"grad_norm": 0.7695810970926475,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.632,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.09026798307475317,
|
| 62 |
+
"grad_norm": 0.7714248271685794,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.636,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.10155148095909731,
|
| 69 |
+
"grad_norm": 0.8886760851072192,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.6225,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.11283497884344147,
|
| 76 |
+
"grad_norm": 0.8974890384086033,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6362,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.12411847672778561,
|
| 83 |
+
"grad_norm": 0.8819677575312233,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.6325,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.13540197461212977,
|
| 90 |
+
"grad_norm": 0.9251296507200821,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.6271,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1466854724964739,
|
| 97 |
+
"grad_norm": 0.7702797791218077,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.6273,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.15796897038081806,
|
| 104 |
+
"grad_norm": 0.8095360026454328,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.6252,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1692524682651622,
|
| 111 |
+
"grad_norm": 0.8204620911060526,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6287,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.18053596614950634,
|
| 118 |
+
"grad_norm": 0.8182785549342615,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.6284,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1918194640338505,
|
| 125 |
+
"grad_norm": 0.7445113899986885,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6264,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.20310296191819463,
|
| 132 |
+
"grad_norm": 0.7873061135697372,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6253,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2143864598025388,
|
| 139 |
+
"grad_norm": 0.7956486177510658,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6264,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.22566995768688294,
|
| 146 |
+
"grad_norm": 0.7746629467371798,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6238,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.23695345557122707,
|
| 153 |
+
"grad_norm": 0.7345245715769874,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.619,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.24823695345557123,
|
| 160 |
+
"grad_norm": 0.8349914408696147,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6145,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.25952045133991536,
|
| 167 |
+
"grad_norm": 0.7331223816734604,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6179,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.27080394922425954,
|
| 174 |
+
"grad_norm": 0.7535227854265615,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.615,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2820874471086037,
|
| 181 |
+
"grad_norm": 0.9217132891288368,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.614,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2933709449929478,
|
| 188 |
+
"grad_norm": 0.7626220728005123,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.6207,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.304654442877292,
|
| 195 |
+
"grad_norm": 0.7567534233021369,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6138,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3159379407616361,
|
| 202 |
+
"grad_norm": 0.7740686670455319,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.6107,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.32722143864598024,
|
| 209 |
+
"grad_norm": 0.7577709244521811,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.614,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3385049365303244,
|
| 216 |
+
"grad_norm": 0.7294703403964556,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.6113,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.34978843441466856,
|
| 223 |
+
"grad_norm": 0.7503750502849057,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6122,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3610719322990127,
|
| 230 |
+
"grad_norm": 0.7103206649111901,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6167,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.3723554301833568,
|
| 237 |
+
"grad_norm": 0.7626842348184225,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.606,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.383638928067701,
|
| 244 |
+
"grad_norm": 0.7621571567885804,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.6155,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.39492242595204513,
|
| 251 |
+
"grad_norm": 0.7549313486626996,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.6172,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.40620592383638926,
|
| 258 |
+
"grad_norm": 0.782988336813104,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.5985,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.41748942172073344,
|
| 265 |
+
"grad_norm": 0.7863471438503445,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.6154,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4287729196050776,
|
| 272 |
+
"grad_norm": 0.7640237197989878,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.5897,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.4400564174894217,
|
| 279 |
+
"grad_norm": 0.8024119449518029,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.6157,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4513399153737659,
|
| 286 |
+
"grad_norm": 0.720556179289527,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.603,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.46262341325811,
|
| 293 |
+
"grad_norm": 0.76294955883197,
|
| 294 |
+
"learning_rate": 5e-06,
|
| 295 |
+
"loss": 0.6061,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.47390691114245415,
|
| 300 |
+
"grad_norm": 0.8156507807690674,
|
| 301 |
+
"learning_rate": 5e-06,
|
| 302 |
+
"loss": 0.6051,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.48519040902679833,
|
| 307 |
+
"grad_norm": 0.7521066252629773,
|
| 308 |
+
"learning_rate": 5e-06,
|
| 309 |
+
"loss": 0.5976,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.49647390691114246,
|
| 314 |
+
"grad_norm": 0.7133025964230046,
|
| 315 |
+
"learning_rate": 5e-06,
|
| 316 |
+
"loss": 0.5968,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5077574047954866,
|
| 321 |
+
"grad_norm": 0.7925716834523774,
|
| 322 |
+
"learning_rate": 5e-06,
|
| 323 |
+
"loss": 0.6096,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5190409026798307,
|
| 328 |
+
"grad_norm": 0.7100847121605542,
|
| 329 |
+
"learning_rate": 5e-06,
|
| 330 |
+
"loss": 0.6032,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5303244005641748,
|
| 335 |
+
"grad_norm": 0.6929396371646737,
|
| 336 |
+
"learning_rate": 5e-06,
|
| 337 |
+
"loss": 0.6002,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5416078984485191,
|
| 342 |
+
"grad_norm": 0.6977506618129865,
|
| 343 |
+
"learning_rate": 5e-06,
|
| 344 |
+
"loss": 0.6104,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5528913963328632,
|
| 349 |
+
"grad_norm": 0.7147611855456376,
|
| 350 |
+
"learning_rate": 5e-06,
|
| 351 |
+
"loss": 0.5912,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5641748942172073,
|
| 356 |
+
"grad_norm": 0.7042203040407636,
|
| 357 |
+
"learning_rate": 5e-06,
|
| 358 |
+
"loss": 0.6079,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.5754583921015515,
|
| 363 |
+
"grad_norm": 0.7309189788815705,
|
| 364 |
+
"learning_rate": 5e-06,
|
| 365 |
+
"loss": 0.6036,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5867418899858956,
|
| 370 |
+
"grad_norm": 0.7248169421227385,
|
| 371 |
+
"learning_rate": 5e-06,
|
| 372 |
+
"loss": 0.6003,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5980253878702397,
|
| 377 |
+
"grad_norm": 0.7572409467891201,
|
| 378 |
+
"learning_rate": 5e-06,
|
| 379 |
+
"loss": 0.5916,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.609308885754584,
|
| 384 |
+
"grad_norm": 0.733437644851395,
|
| 385 |
+
"learning_rate": 5e-06,
|
| 386 |
+
"loss": 0.6036,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.6205923836389281,
|
| 391 |
+
"grad_norm": 0.7131751072814058,
|
| 392 |
+
"learning_rate": 5e-06,
|
| 393 |
+
"loss": 0.6034,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6318758815232722,
|
| 398 |
+
"grad_norm": 0.7360178195388309,
|
| 399 |
+
"learning_rate": 5e-06,
|
| 400 |
+
"loss": 0.605,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6431593794076164,
|
| 405 |
+
"grad_norm": 1.1495804042684488,
|
| 406 |
+
"learning_rate": 5e-06,
|
| 407 |
+
"loss": 0.5974,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.6544428772919605,
|
| 412 |
+
"grad_norm": 0.6817754751813853,
|
| 413 |
+
"learning_rate": 5e-06,
|
| 414 |
+
"loss": 0.5977,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.6657263751763046,
|
| 419 |
+
"grad_norm": 0.7044965353014948,
|
| 420 |
+
"learning_rate": 5e-06,
|
| 421 |
+
"loss": 0.607,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6770098730606487,
|
| 426 |
+
"grad_norm": 0.7308565798791333,
|
| 427 |
+
"learning_rate": 5e-06,
|
| 428 |
+
"loss": 0.6015,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.688293370944993,
|
| 433 |
+
"grad_norm": 0.758452633023999,
|
| 434 |
+
"learning_rate": 5e-06,
|
| 435 |
+
"loss": 0.603,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.6995768688293371,
|
| 440 |
+
"grad_norm": 0.7778955204205954,
|
| 441 |
+
"learning_rate": 5e-06,
|
| 442 |
+
"loss": 0.5924,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.7108603667136812,
|
| 447 |
+
"grad_norm": 0.6757727892125893,
|
| 448 |
+
"learning_rate": 5e-06,
|
| 449 |
+
"loss": 0.5999,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7221438645980254,
|
| 454 |
+
"grad_norm": 0.7690880111005869,
|
| 455 |
+
"learning_rate": 5e-06,
|
| 456 |
+
"loss": 0.6008,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7334273624823695,
|
| 461 |
+
"grad_norm": 0.780886462765786,
|
| 462 |
+
"learning_rate": 5e-06,
|
| 463 |
+
"loss": 0.5954,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.7447108603667136,
|
| 468 |
+
"grad_norm": 0.7683226572424213,
|
| 469 |
+
"learning_rate": 5e-06,
|
| 470 |
+
"loss": 0.5975,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.7559943582510579,
|
| 475 |
+
"grad_norm": 0.6840538894373641,
|
| 476 |
+
"learning_rate": 5e-06,
|
| 477 |
+
"loss": 0.6023,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.767277856135402,
|
| 482 |
+
"grad_norm": 0.6771027958757195,
|
| 483 |
+
"learning_rate": 5e-06,
|
| 484 |
+
"loss": 0.59,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.7785613540197461,
|
| 489 |
+
"grad_norm": 0.6681056791937571,
|
| 490 |
+
"learning_rate": 5e-06,
|
| 491 |
+
"loss": 0.5931,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7898448519040903,
|
| 496 |
+
"grad_norm": 0.7086908628376102,
|
| 497 |
+
"learning_rate": 5e-06,
|
| 498 |
+
"loss": 0.6005,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8011283497884344,
|
| 503 |
+
"grad_norm": 0.6592220118037463,
|
| 504 |
+
"learning_rate": 5e-06,
|
| 505 |
+
"loss": 0.5888,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8124118476727785,
|
| 510 |
+
"grad_norm": 0.7384276235727564,
|
| 511 |
+
"learning_rate": 5e-06,
|
| 512 |
+
"loss": 0.6029,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8236953455571228,
|
| 517 |
+
"grad_norm": 0.7153557202506454,
|
| 518 |
+
"learning_rate": 5e-06,
|
| 519 |
+
"loss": 0.6004,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8349788434414669,
|
| 524 |
+
"grad_norm": 0.7412356079152558,
|
| 525 |
+
"learning_rate": 5e-06,
|
| 526 |
+
"loss": 0.6062,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.846262341325811,
|
| 531 |
+
"grad_norm": 0.8186167983419891,
|
| 532 |
+
"learning_rate": 5e-06,
|
| 533 |
+
"loss": 0.6012,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.8575458392101551,
|
| 538 |
+
"grad_norm": 0.6956555496968945,
|
| 539 |
+
"learning_rate": 5e-06,
|
| 540 |
+
"loss": 0.5986,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.8688293370944993,
|
| 545 |
+
"grad_norm": 0.6972125762170825,
|
| 546 |
+
"learning_rate": 5e-06,
|
| 547 |
+
"loss": 0.598,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8801128349788434,
|
| 552 |
+
"grad_norm": 0.6554398016756771,
|
| 553 |
+
"learning_rate": 5e-06,
|
| 554 |
+
"loss": 0.5899,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.8913963328631875,
|
| 559 |
+
"grad_norm": 0.6816513719411913,
|
| 560 |
+
"learning_rate": 5e-06,
|
| 561 |
+
"loss": 0.5959,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.9026798307475318,
|
| 566 |
+
"grad_norm": 0.6802192397813065,
|
| 567 |
+
"learning_rate": 5e-06,
|
| 568 |
+
"loss": 0.5966,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.9139633286318759,
|
| 573 |
+
"grad_norm": 0.7297229988637639,
|
| 574 |
+
"learning_rate": 5e-06,
|
| 575 |
+
"loss": 0.5977,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.92524682651622,
|
| 580 |
+
"grad_norm": 0.6910581824985036,
|
| 581 |
+
"learning_rate": 5e-06,
|
| 582 |
+
"loss": 0.5903,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.9365303244005642,
|
| 587 |
+
"grad_norm": 0.7038633597805812,
|
| 588 |
+
"learning_rate": 5e-06,
|
| 589 |
+
"loss": 0.5926,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.9478138222849083,
|
| 594 |
+
"grad_norm": 0.7006043004126095,
|
| 595 |
+
"learning_rate": 5e-06,
|
| 596 |
+
"loss": 0.5968,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9590973201692524,
|
| 601 |
+
"grad_norm": 0.7196243633360835,
|
| 602 |
+
"learning_rate": 5e-06,
|
| 603 |
+
"loss": 0.5946,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.9703808180535967,
|
| 608 |
+
"grad_norm": 1.0955172142857887,
|
| 609 |
+
"learning_rate": 5e-06,
|
| 610 |
+
"loss": 0.5837,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.9816643159379408,
|
| 615 |
+
"grad_norm": 0.6592667550168434,
|
| 616 |
+
"learning_rate": 5e-06,
|
| 617 |
+
"loss": 0.5998,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.9929478138222849,
|
| 622 |
+
"grad_norm": 0.7854190040474681,
|
| 623 |
+
"learning_rate": 5e-06,
|
| 624 |
+
"loss": 0.5875,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.9997179125528914,
|
| 629 |
+
"eval_loss": 0.5916627049446106,
|
| 630 |
+
"eval_runtime": 700.0009,
|
| 631 |
+
"eval_samples_per_second": 17.059,
|
| 632 |
+
"eval_steps_per_second": 0.534,
|
| 633 |
+
"step": 886
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.004231311706629,
|
| 637 |
+
"grad_norm": 1.3251196950195474,
|
| 638 |
+
"learning_rate": 5e-06,
|
| 639 |
+
"loss": 0.6038,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.0155148095909732,
|
| 644 |
+
"grad_norm": 0.833678301438908,
|
| 645 |
+
"learning_rate": 5e-06,
|
| 646 |
+
"loss": 0.5204,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.0267983074753173,
|
| 651 |
+
"grad_norm": 0.7372319799588725,
|
| 652 |
+
"learning_rate": 5e-06,
|
| 653 |
+
"loss": 0.5098,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.0380818053596614,
|
| 658 |
+
"grad_norm": 0.710656408718745,
|
| 659 |
+
"learning_rate": 5e-06,
|
| 660 |
+
"loss": 0.5147,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.0493653032440056,
|
| 665 |
+
"grad_norm": 0.7035392178179493,
|
| 666 |
+
"learning_rate": 5e-06,
|
| 667 |
+
"loss": 0.532,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.0606488011283497,
|
| 672 |
+
"grad_norm": 0.7419000790657035,
|
| 673 |
+
"learning_rate": 5e-06,
|
| 674 |
+
"loss": 0.5232,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.071932299012694,
|
| 679 |
+
"grad_norm": 0.7507810642090355,
|
| 680 |
+
"learning_rate": 5e-06,
|
| 681 |
+
"loss": 0.5182,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.0832157968970382,
|
| 686 |
+
"grad_norm": 0.7365569865429179,
|
| 687 |
+
"learning_rate": 5e-06,
|
| 688 |
+
"loss": 0.5156,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.0944992947813823,
|
| 693 |
+
"grad_norm": 0.6971352350986588,
|
| 694 |
+
"learning_rate": 5e-06,
|
| 695 |
+
"loss": 0.5255,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.1057827926657264,
|
| 700 |
+
"grad_norm": 0.769651560789747,
|
| 701 |
+
"learning_rate": 5e-06,
|
| 702 |
+
"loss": 0.5275,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.1170662905500706,
|
| 707 |
+
"grad_norm": 0.6835338919436766,
|
| 708 |
+
"learning_rate": 5e-06,
|
| 709 |
+
"loss": 0.5266,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.1283497884344147,
|
| 714 |
+
"grad_norm": 0.7080901866255427,
|
| 715 |
+
"learning_rate": 5e-06,
|
| 716 |
+
"loss": 0.5245,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.1396332863187588,
|
| 721 |
+
"grad_norm": 0.6973746558937527,
|
| 722 |
+
"learning_rate": 5e-06,
|
| 723 |
+
"loss": 0.5272,
|
| 724 |
+
"step": 1010
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.150916784203103,
|
| 728 |
+
"grad_norm": 0.7328115120631007,
|
| 729 |
+
"learning_rate": 5e-06,
|
| 730 |
+
"loss": 0.5269,
|
| 731 |
+
"step": 1020
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.162200282087447,
|
| 735 |
+
"grad_norm": 0.8161495623001298,
|
| 736 |
+
"learning_rate": 5e-06,
|
| 737 |
+
"loss": 0.5226,
|
| 738 |
+
"step": 1030
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.1734837799717912,
|
| 742 |
+
"grad_norm": 0.8517029792820613,
|
| 743 |
+
"learning_rate": 5e-06,
|
| 744 |
+
"loss": 0.5175,
|
| 745 |
+
"step": 1040
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.1847672778561353,
|
| 749 |
+
"grad_norm": 0.8438046028102798,
|
| 750 |
+
"learning_rate": 5e-06,
|
| 751 |
+
"loss": 0.5241,
|
| 752 |
+
"step": 1050
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.1960507757404795,
|
| 756 |
+
"grad_norm": 0.7099751086024491,
|
| 757 |
+
"learning_rate": 5e-06,
|
| 758 |
+
"loss": 0.5291,
|
| 759 |
+
"step": 1060
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.2073342736248236,
|
| 763 |
+
"grad_norm": 0.7580945476663854,
|
| 764 |
+
"learning_rate": 5e-06,
|
| 765 |
+
"loss": 0.5249,
|
| 766 |
+
"step": 1070
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.2186177715091677,
|
| 770 |
+
"grad_norm": 0.7667303387873934,
|
| 771 |
+
"learning_rate": 5e-06,
|
| 772 |
+
"loss": 0.5235,
|
| 773 |
+
"step": 1080
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.229901269393512,
|
| 777 |
+
"grad_norm": 0.8114242325537707,
|
| 778 |
+
"learning_rate": 5e-06,
|
| 779 |
+
"loss": 0.5283,
|
| 780 |
+
"step": 1090
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.2411847672778562,
|
| 784 |
+
"grad_norm": 0.7131407385877792,
|
| 785 |
+
"learning_rate": 5e-06,
|
| 786 |
+
"loss": 0.5288,
|
| 787 |
+
"step": 1100
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.2524682651622003,
|
| 791 |
+
"grad_norm": 0.685086959113009,
|
| 792 |
+
"learning_rate": 5e-06,
|
| 793 |
+
"loss": 0.5195,
|
| 794 |
+
"step": 1110
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.2637517630465445,
|
| 798 |
+
"grad_norm": 0.7053119373842179,
|
| 799 |
+
"learning_rate": 5e-06,
|
| 800 |
+
"loss": 0.542,
|
| 801 |
+
"step": 1120
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.2750352609308886,
|
| 805 |
+
"grad_norm": 0.7644874615248024,
|
| 806 |
+
"learning_rate": 5e-06,
|
| 807 |
+
"loss": 0.5287,
|
| 808 |
+
"step": 1130
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.2863187588152327,
|
| 812 |
+
"grad_norm": 0.6883885545058486,
|
| 813 |
+
"learning_rate": 5e-06,
|
| 814 |
+
"loss": 0.5267,
|
| 815 |
+
"step": 1140
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.2976022566995769,
|
| 819 |
+
"grad_norm": 0.7306504262086587,
|
| 820 |
+
"learning_rate": 5e-06,
|
| 821 |
+
"loss": 0.5289,
|
| 822 |
+
"step": 1150
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.308885754583921,
|
| 826 |
+
"grad_norm": 0.9640801871844217,
|
| 827 |
+
"learning_rate": 5e-06,
|
| 828 |
+
"loss": 0.5267,
|
| 829 |
+
"step": 1160
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.320169252468265,
|
| 833 |
+
"grad_norm": 0.661755370313437,
|
| 834 |
+
"learning_rate": 5e-06,
|
| 835 |
+
"loss": 0.5305,
|
| 836 |
+
"step": 1170
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.3314527503526092,
|
| 840 |
+
"grad_norm": 0.6875142102900156,
|
| 841 |
+
"learning_rate": 5e-06,
|
| 842 |
+
"loss": 0.5262,
|
| 843 |
+
"step": 1180
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.3427362482369536,
|
| 847 |
+
"grad_norm": 0.7205563505642903,
|
| 848 |
+
"learning_rate": 5e-06,
|
| 849 |
+
"loss": 0.5391,
|
| 850 |
+
"step": 1190
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.3540197461212977,
|
| 854 |
+
"grad_norm": 0.6599447213858599,
|
| 855 |
+
"learning_rate": 5e-06,
|
| 856 |
+
"loss": 0.5272,
|
| 857 |
+
"step": 1200
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.3653032440056418,
|
| 861 |
+
"grad_norm": 0.6674411183277559,
|
| 862 |
+
"learning_rate": 5e-06,
|
| 863 |
+
"loss": 0.5294,
|
| 864 |
+
"step": 1210
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.376586741889986,
|
| 868 |
+
"grad_norm": 0.6760191535339451,
|
| 869 |
+
"learning_rate": 5e-06,
|
| 870 |
+
"loss": 0.5237,
|
| 871 |
+
"step": 1220
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.38787023977433,
|
| 875 |
+
"grad_norm": 0.699499504851807,
|
| 876 |
+
"learning_rate": 5e-06,
|
| 877 |
+
"loss": 0.5239,
|
| 878 |
+
"step": 1230
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.3991537376586742,
|
| 882 |
+
"grad_norm": 0.6949474979507084,
|
| 883 |
+
"learning_rate": 5e-06,
|
| 884 |
+
"loss": 0.5371,
|
| 885 |
+
"step": 1240
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.4104372355430184,
|
| 889 |
+
"grad_norm": 0.6871033689397662,
|
| 890 |
+
"learning_rate": 5e-06,
|
| 891 |
+
"loss": 0.5346,
|
| 892 |
+
"step": 1250
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.4217207334273625,
|
| 896 |
+
"grad_norm": 0.6742402949788701,
|
| 897 |
+
"learning_rate": 5e-06,
|
| 898 |
+
"loss": 0.5239,
|
| 899 |
+
"step": 1260
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.4330042313117066,
|
| 903 |
+
"grad_norm": 0.6751463140934231,
|
| 904 |
+
"learning_rate": 5e-06,
|
| 905 |
+
"loss": 0.5266,
|
| 906 |
+
"step": 1270
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.4442877291960508,
|
| 910 |
+
"grad_norm": 0.7142787617460878,
|
| 911 |
+
"learning_rate": 5e-06,
|
| 912 |
+
"loss": 0.5315,
|
| 913 |
+
"step": 1280
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.4555712270803949,
|
| 917 |
+
"grad_norm": 0.7226332853252287,
|
| 918 |
+
"learning_rate": 5e-06,
|
| 919 |
+
"loss": 0.5275,
|
| 920 |
+
"step": 1290
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.466854724964739,
|
| 924 |
+
"grad_norm": 0.7145272993925487,
|
| 925 |
+
"learning_rate": 5e-06,
|
| 926 |
+
"loss": 0.5322,
|
| 927 |
+
"step": 1300
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.4781382228490831,
|
| 931 |
+
"grad_norm": 0.6768426299144826,
|
| 932 |
+
"learning_rate": 5e-06,
|
| 933 |
+
"loss": 0.538,
|
| 934 |
+
"step": 1310
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.4894217207334273,
|
| 938 |
+
"grad_norm": 0.7123747155692624,
|
| 939 |
+
"learning_rate": 5e-06,
|
| 940 |
+
"loss": 0.5289,
|
| 941 |
+
"step": 1320
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.5007052186177714,
|
| 945 |
+
"grad_norm": 0.6786058643003756,
|
| 946 |
+
"learning_rate": 5e-06,
|
| 947 |
+
"loss": 0.5253,
|
| 948 |
+
"step": 1330
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.5119887165021155,
|
| 952 |
+
"grad_norm": 0.7110831777325413,
|
| 953 |
+
"learning_rate": 5e-06,
|
| 954 |
+
"loss": 0.5324,
|
| 955 |
+
"step": 1340
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.5232722143864597,
|
| 959 |
+
"grad_norm": 0.6695015578694526,
|
| 960 |
+
"learning_rate": 5e-06,
|
| 961 |
+
"loss": 0.5214,
|
| 962 |
+
"step": 1350
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.5345557122708038,
|
| 966 |
+
"grad_norm": 0.7459448089167867,
|
| 967 |
+
"learning_rate": 5e-06,
|
| 968 |
+
"loss": 0.5252,
|
| 969 |
+
"step": 1360
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.5458392101551481,
|
| 973 |
+
"grad_norm": 0.6753928189856611,
|
| 974 |
+
"learning_rate": 5e-06,
|
| 975 |
+
"loss": 0.5251,
|
| 976 |
+
"step": 1370
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.5571227080394923,
|
| 980 |
+
"grad_norm": 0.6996235594913326,
|
| 981 |
+
"learning_rate": 5e-06,
|
| 982 |
+
"loss": 0.5248,
|
| 983 |
+
"step": 1380
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.5684062059238364,
|
| 987 |
+
"grad_norm": 0.7079009762601143,
|
| 988 |
+
"learning_rate": 5e-06,
|
| 989 |
+
"loss": 0.5323,
|
| 990 |
+
"step": 1390
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.5796897038081805,
|
| 994 |
+
"grad_norm": 0.6924093724518422,
|
| 995 |
+
"learning_rate": 5e-06,
|
| 996 |
+
"loss": 0.5255,
|
| 997 |
+
"step": 1400
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.5909732016925247,
|
| 1001 |
+
"grad_norm": 0.6761094320283147,
|
| 1002 |
+
"learning_rate": 5e-06,
|
| 1003 |
+
"loss": 0.5339,
|
| 1004 |
+
"step": 1410
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.6022566995768688,
|
| 1008 |
+
"grad_norm": 0.6809745203094293,
|
| 1009 |
+
"learning_rate": 5e-06,
|
| 1010 |
+
"loss": 0.5298,
|
| 1011 |
+
"step": 1420
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.6135401974612131,
|
| 1015 |
+
"grad_norm": 0.7106432021864519,
|
| 1016 |
+
"learning_rate": 5e-06,
|
| 1017 |
+
"loss": 0.5478,
|
| 1018 |
+
"step": 1430
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.6248236953455573,
|
| 1022 |
+
"grad_norm": 0.7187158548818587,
|
| 1023 |
+
"learning_rate": 5e-06,
|
| 1024 |
+
"loss": 0.531,
|
| 1025 |
+
"step": 1440
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.6361071932299014,
|
| 1029 |
+
"grad_norm": 0.6596453734369295,
|
| 1030 |
+
"learning_rate": 5e-06,
|
| 1031 |
+
"loss": 0.5225,
|
| 1032 |
+
"step": 1450
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.6473906911142455,
|
| 1036 |
+
"grad_norm": 0.7093693747872939,
|
| 1037 |
+
"learning_rate": 5e-06,
|
| 1038 |
+
"loss": 0.5257,
|
| 1039 |
+
"step": 1460
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.6586741889985896,
|
| 1043 |
+
"grad_norm": 0.6944427657225931,
|
| 1044 |
+
"learning_rate": 5e-06,
|
| 1045 |
+
"loss": 0.5412,
|
| 1046 |
+
"step": 1470
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.6699576868829338,
|
| 1050 |
+
"grad_norm": 0.6955533636685318,
|
| 1051 |
+
"learning_rate": 5e-06,
|
| 1052 |
+
"loss": 0.5367,
|
| 1053 |
+
"step": 1480
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.681241184767278,
|
| 1057 |
+
"grad_norm": 0.6624317919452952,
|
| 1058 |
+
"learning_rate": 5e-06,
|
| 1059 |
+
"loss": 0.5293,
|
| 1060 |
+
"step": 1490
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.692524682651622,
|
| 1064 |
+
"grad_norm": 0.6778095946034755,
|
| 1065 |
+
"learning_rate": 5e-06,
|
| 1066 |
+
"loss": 0.5323,
|
| 1067 |
+
"step": 1500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.7038081805359662,
|
| 1071 |
+
"grad_norm": 0.7341427766426889,
|
| 1072 |
+
"learning_rate": 5e-06,
|
| 1073 |
+
"loss": 0.5263,
|
| 1074 |
+
"step": 1510
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.7150916784203103,
|
| 1078 |
+
"grad_norm": 0.7432696239071007,
|
| 1079 |
+
"learning_rate": 5e-06,
|
| 1080 |
+
"loss": 0.5334,
|
| 1081 |
+
"step": 1520
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.7263751763046544,
|
| 1085 |
+
"grad_norm": 0.6491261448207155,
|
| 1086 |
+
"learning_rate": 5e-06,
|
| 1087 |
+
"loss": 0.5305,
|
| 1088 |
+
"step": 1530
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.7376586741889986,
|
| 1092 |
+
"grad_norm": 0.7486777638151452,
|
| 1093 |
+
"learning_rate": 5e-06,
|
| 1094 |
+
"loss": 0.5304,
|
| 1095 |
+
"step": 1540
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.7489421720733427,
|
| 1099 |
+
"grad_norm": 0.7118918086770966,
|
| 1100 |
+
"learning_rate": 5e-06,
|
| 1101 |
+
"loss": 0.5216,
|
| 1102 |
+
"step": 1550
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.7602256699576868,
|
| 1106 |
+
"grad_norm": 0.7038340173438765,
|
| 1107 |
+
"learning_rate": 5e-06,
|
| 1108 |
+
"loss": 0.5322,
|
| 1109 |
+
"step": 1560
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.771509167842031,
|
| 1113 |
+
"grad_norm": 0.6539818459517368,
|
| 1114 |
+
"learning_rate": 5e-06,
|
| 1115 |
+
"loss": 0.5321,
|
| 1116 |
+
"step": 1570
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.782792665726375,
|
| 1120 |
+
"grad_norm": 0.658011536602541,
|
| 1121 |
+
"learning_rate": 5e-06,
|
| 1122 |
+
"loss": 0.5288,
|
| 1123 |
+
"step": 1580
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.7940761636107192,
|
| 1127 |
+
"grad_norm": 0.6572168627274099,
|
| 1128 |
+
"learning_rate": 5e-06,
|
| 1129 |
+
"loss": 0.5219,
|
| 1130 |
+
"step": 1590
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.8053596614950633,
|
| 1134 |
+
"grad_norm": 0.6648318139285605,
|
| 1135 |
+
"learning_rate": 5e-06,
|
| 1136 |
+
"loss": 0.5292,
|
| 1137 |
+
"step": 1600
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.8166431593794075,
|
| 1141 |
+
"grad_norm": 0.6932570407391014,
|
| 1142 |
+
"learning_rate": 5e-06,
|
| 1143 |
+
"loss": 0.5381,
|
| 1144 |
+
"step": 1610
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.8279266572637518,
|
| 1148 |
+
"grad_norm": 0.6710478896264537,
|
| 1149 |
+
"learning_rate": 5e-06,
|
| 1150 |
+
"loss": 0.5344,
|
| 1151 |
+
"step": 1620
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.839210155148096,
|
| 1155 |
+
"grad_norm": 0.6710698360135149,
|
| 1156 |
+
"learning_rate": 5e-06,
|
| 1157 |
+
"loss": 0.5201,
|
| 1158 |
+
"step": 1630
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.85049365303244,
|
| 1162 |
+
"grad_norm": 0.6664339220436462,
|
| 1163 |
+
"learning_rate": 5e-06,
|
| 1164 |
+
"loss": 0.5272,
|
| 1165 |
+
"step": 1640
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.8617771509167842,
|
| 1169 |
+
"grad_norm": 0.679324908548248,
|
| 1170 |
+
"learning_rate": 5e-06,
|
| 1171 |
+
"loss": 0.5381,
|
| 1172 |
+
"step": 1650
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.8730606488011283,
|
| 1176 |
+
"grad_norm": 0.7203049853389839,
|
| 1177 |
+
"learning_rate": 5e-06,
|
| 1178 |
+
"loss": 0.5325,
|
| 1179 |
+
"step": 1660
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.8843441466854725,
|
| 1183 |
+
"grad_norm": 0.671958846252959,
|
| 1184 |
+
"learning_rate": 5e-06,
|
| 1185 |
+
"loss": 0.5308,
|
| 1186 |
+
"step": 1670
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.8956276445698168,
|
| 1190 |
+
"grad_norm": 0.6756200949168255,
|
| 1191 |
+
"learning_rate": 5e-06,
|
| 1192 |
+
"loss": 0.5401,
|
| 1193 |
+
"step": 1680
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.906911142454161,
|
| 1197 |
+
"grad_norm": 0.6795733118816987,
|
| 1198 |
+
"learning_rate": 5e-06,
|
| 1199 |
+
"loss": 0.5209,
|
| 1200 |
+
"step": 1690
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.918194640338505,
|
| 1204 |
+
"grad_norm": 0.6875411881069398,
|
| 1205 |
+
"learning_rate": 5e-06,
|
| 1206 |
+
"loss": 0.5274,
|
| 1207 |
+
"step": 1700
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.9294781382228492,
|
| 1211 |
+
"grad_norm": 0.6539417007788165,
|
| 1212 |
+
"learning_rate": 5e-06,
|
| 1213 |
+
"loss": 0.5293,
|
| 1214 |
+
"step": 1710
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.9407616361071933,
|
| 1218 |
+
"grad_norm": 0.7131644844536464,
|
| 1219 |
+
"learning_rate": 5e-06,
|
| 1220 |
+
"loss": 0.5288,
|
| 1221 |
+
"step": 1720
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.9520451339915375,
|
| 1225 |
+
"grad_norm": 0.6498878256598866,
|
| 1226 |
+
"learning_rate": 5e-06,
|
| 1227 |
+
"loss": 0.5289,
|
| 1228 |
+
"step": 1730
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.9633286318758816,
|
| 1232 |
+
"grad_norm": 0.6843667341548544,
|
| 1233 |
+
"learning_rate": 5e-06,
|
| 1234 |
+
"loss": 0.5418,
|
| 1235 |
+
"step": 1740
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.9746121297602257,
|
| 1239 |
+
"grad_norm": 0.6650168678603656,
|
| 1240 |
+
"learning_rate": 5e-06,
|
| 1241 |
+
"loss": 0.5402,
|
| 1242 |
+
"step": 1750
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.9858956276445698,
|
| 1246 |
+
"grad_norm": 0.6825312514425923,
|
| 1247 |
+
"learning_rate": 5e-06,
|
| 1248 |
+
"loss": 0.5268,
|
| 1249 |
+
"step": 1760
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.997179125528914,
|
| 1253 |
+
"grad_norm": 0.6765862874969008,
|
| 1254 |
+
"learning_rate": 5e-06,
|
| 1255 |
+
"loss": 0.5215,
|
| 1256 |
+
"step": 1770
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.9994358251057829,
|
| 1260 |
+
"eval_loss": 0.5913873910903931,
|
| 1261 |
+
"eval_runtime": 698.2566,
|
| 1262 |
+
"eval_samples_per_second": 17.101,
|
| 1263 |
+
"eval_steps_per_second": 0.536,
|
| 1264 |
+
"step": 1772
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 2.008462623413258,
|
| 1268 |
+
"grad_norm": 0.9398660673562257,
|
| 1269 |
+
"learning_rate": 5e-06,
|
| 1270 |
+
"loss": 0.5208,
|
| 1271 |
+
"step": 1780
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 2.0197461212976022,
|
| 1275 |
+
"grad_norm": 0.7762940970041788,
|
| 1276 |
+
"learning_rate": 5e-06,
|
| 1277 |
+
"loss": 0.4524,
|
| 1278 |
+
"step": 1790
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 2.0310296191819464,
|
| 1282 |
+
"grad_norm": 0.8552156108609141,
|
| 1283 |
+
"learning_rate": 5e-06,
|
| 1284 |
+
"loss": 0.4428,
|
| 1285 |
+
"step": 1800
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 2.0423131170662905,
|
| 1289 |
+
"grad_norm": 0.7759834543073888,
|
| 1290 |
+
"learning_rate": 5e-06,
|
| 1291 |
+
"loss": 0.4497,
|
| 1292 |
+
"step": 1810
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 2.0535966149506346,
|
| 1296 |
+
"grad_norm": 0.813460157749594,
|
| 1297 |
+
"learning_rate": 5e-06,
|
| 1298 |
+
"loss": 0.4501,
|
| 1299 |
+
"step": 1820
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.0648801128349787,
|
| 1303 |
+
"grad_norm": 0.7555915322851285,
|
| 1304 |
+
"learning_rate": 5e-06,
|
| 1305 |
+
"loss": 0.4366,
|
| 1306 |
+
"step": 1830
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.076163610719323,
|
| 1310 |
+
"grad_norm": 0.778910984127173,
|
| 1311 |
+
"learning_rate": 5e-06,
|
| 1312 |
+
"loss": 0.45,
|
| 1313 |
+
"step": 1840
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.087447108603667,
|
| 1317 |
+
"grad_norm": 0.7823483784772997,
|
| 1318 |
+
"learning_rate": 5e-06,
|
| 1319 |
+
"loss": 0.4487,
|
| 1320 |
+
"step": 1850
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.098730606488011,
|
| 1324 |
+
"grad_norm": 0.7451819548464573,
|
| 1325 |
+
"learning_rate": 5e-06,
|
| 1326 |
+
"loss": 0.4524,
|
| 1327 |
+
"step": 1860
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.1100141043723553,
|
| 1331 |
+
"grad_norm": 0.7366797047615511,
|
| 1332 |
+
"learning_rate": 5e-06,
|
| 1333 |
+
"loss": 0.4554,
|
| 1334 |
+
"step": 1870
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.1212976022566994,
|
| 1338 |
+
"grad_norm": 0.7739116377396993,
|
| 1339 |
+
"learning_rate": 5e-06,
|
| 1340 |
+
"loss": 0.4545,
|
| 1341 |
+
"step": 1880
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 2.1325811001410435,
|
| 1345 |
+
"grad_norm": 0.7393809355678413,
|
| 1346 |
+
"learning_rate": 5e-06,
|
| 1347 |
+
"loss": 0.4576,
|
| 1348 |
+
"step": 1890
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 2.143864598025388,
|
| 1352 |
+
"grad_norm": 0.7783700395003256,
|
| 1353 |
+
"learning_rate": 5e-06,
|
| 1354 |
+
"loss": 0.456,
|
| 1355 |
+
"step": 1900
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 2.155148095909732,
|
| 1359 |
+
"grad_norm": 0.7655026275655048,
|
| 1360 |
+
"learning_rate": 5e-06,
|
| 1361 |
+
"loss": 0.4555,
|
| 1362 |
+
"step": 1910
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.1664315937940763,
|
| 1366 |
+
"grad_norm": 0.7308671453948609,
|
| 1367 |
+
"learning_rate": 5e-06,
|
| 1368 |
+
"loss": 0.4516,
|
| 1369 |
+
"step": 1920
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 2.1777150916784205,
|
| 1373 |
+
"grad_norm": 0.7548898417368491,
|
| 1374 |
+
"learning_rate": 5e-06,
|
| 1375 |
+
"loss": 0.4554,
|
| 1376 |
+
"step": 1930
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 2.1889985895627646,
|
| 1380 |
+
"grad_norm": 0.7422727245259925,
|
| 1381 |
+
"learning_rate": 5e-06,
|
| 1382 |
+
"loss": 0.4501,
|
| 1383 |
+
"step": 1940
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 2.2002820874471087,
|
| 1387 |
+
"grad_norm": 0.787975192132044,
|
| 1388 |
+
"learning_rate": 5e-06,
|
| 1389 |
+
"loss": 0.4439,
|
| 1390 |
+
"step": 1950
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 2.211565585331453,
|
| 1394 |
+
"grad_norm": 0.7365878952628802,
|
| 1395 |
+
"learning_rate": 5e-06,
|
| 1396 |
+
"loss": 0.4514,
|
| 1397 |
+
"step": 1960
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 2.222849083215797,
|
| 1401 |
+
"grad_norm": 0.7259152335914627,
|
| 1402 |
+
"learning_rate": 5e-06,
|
| 1403 |
+
"loss": 0.4443,
|
| 1404 |
+
"step": 1970
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.234132581100141,
|
| 1408 |
+
"grad_norm": 0.7305442934832262,
|
| 1409 |
+
"learning_rate": 5e-06,
|
| 1410 |
+
"loss": 0.4508,
|
| 1411 |
+
"step": 1980
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 2.2454160789844853,
|
| 1415 |
+
"grad_norm": 0.752378808107532,
|
| 1416 |
+
"learning_rate": 5e-06,
|
| 1417 |
+
"loss": 0.4533,
|
| 1418 |
+
"step": 1990
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 2.2566995768688294,
|
| 1422 |
+
"grad_norm": 0.7662288679828292,
|
| 1423 |
+
"learning_rate": 5e-06,
|
| 1424 |
+
"loss": 0.4591,
|
| 1425 |
+
"step": 2000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.2679830747531735,
|
| 1429 |
+
"grad_norm": 0.7571986629865566,
|
| 1430 |
+
"learning_rate": 5e-06,
|
| 1431 |
+
"loss": 0.4583,
|
| 1432 |
+
"step": 2010
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 2.2792665726375176,
|
| 1436 |
+
"grad_norm": 0.7853445680318998,
|
| 1437 |
+
"learning_rate": 5e-06,
|
| 1438 |
+
"loss": 0.4665,
|
| 1439 |
+
"step": 2020
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 2.2905500705218618,
|
| 1443 |
+
"grad_norm": 0.8056666478419078,
|
| 1444 |
+
"learning_rate": 5e-06,
|
| 1445 |
+
"loss": 0.4626,
|
| 1446 |
+
"step": 2030
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 2.301833568406206,
|
| 1450 |
+
"grad_norm": 0.7705827370447227,
|
| 1451 |
+
"learning_rate": 5e-06,
|
| 1452 |
+
"loss": 0.4529,
|
| 1453 |
+
"step": 2040
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 2.31311706629055,
|
| 1457 |
+
"grad_norm": 0.952209351698993,
|
| 1458 |
+
"learning_rate": 5e-06,
|
| 1459 |
+
"loss": 0.4533,
|
| 1460 |
+
"step": 2050
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 2.324400564174894,
|
| 1464 |
+
"grad_norm": 0.7437396447699182,
|
| 1465 |
+
"learning_rate": 5e-06,
|
| 1466 |
+
"loss": 0.4694,
|
| 1467 |
+
"step": 2060
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 2.3356840620592383,
|
| 1471 |
+
"grad_norm": 0.7507184464222211,
|
| 1472 |
+
"learning_rate": 5e-06,
|
| 1473 |
+
"loss": 0.4571,
|
| 1474 |
+
"step": 2070
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 2.3469675599435824,
|
| 1478 |
+
"grad_norm": 0.7538037629123275,
|
| 1479 |
+
"learning_rate": 5e-06,
|
| 1480 |
+
"loss": 0.4637,
|
| 1481 |
+
"step": 2080
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 2.3582510578279265,
|
| 1485 |
+
"grad_norm": 0.7207349348209307,
|
| 1486 |
+
"learning_rate": 5e-06,
|
| 1487 |
+
"loss": 0.454,
|
| 1488 |
+
"step": 2090
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 2.3695345557122707,
|
| 1492 |
+
"grad_norm": 0.7732963363098568,
|
| 1493 |
+
"learning_rate": 5e-06,
|
| 1494 |
+
"loss": 0.4621,
|
| 1495 |
+
"step": 2100
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 2.380818053596615,
|
| 1499 |
+
"grad_norm": 0.7733305143075813,
|
| 1500 |
+
"learning_rate": 5e-06,
|
| 1501 |
+
"loss": 0.4616,
|
| 1502 |
+
"step": 2110
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 2.392101551480959,
|
| 1506 |
+
"grad_norm": 0.7317816197062187,
|
| 1507 |
+
"learning_rate": 5e-06,
|
| 1508 |
+
"loss": 0.4544,
|
| 1509 |
+
"step": 2120
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 2.403385049365303,
|
| 1513 |
+
"grad_norm": 0.7387742831088012,
|
| 1514 |
+
"learning_rate": 5e-06,
|
| 1515 |
+
"loss": 0.4612,
|
| 1516 |
+
"step": 2130
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 2.414668547249647,
|
| 1520 |
+
"grad_norm": 0.7855904874369565,
|
| 1521 |
+
"learning_rate": 5e-06,
|
| 1522 |
+
"loss": 0.4567,
|
| 1523 |
+
"step": 2140
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 2.4259520451339913,
|
| 1527 |
+
"grad_norm": 0.7237436303435315,
|
| 1528 |
+
"learning_rate": 5e-06,
|
| 1529 |
+
"loss": 0.4624,
|
| 1530 |
+
"step": 2150
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 2.4372355430183354,
|
| 1534 |
+
"grad_norm": 0.8184805263780661,
|
| 1535 |
+
"learning_rate": 5e-06,
|
| 1536 |
+
"loss": 0.4621,
|
| 1537 |
+
"step": 2160
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 2.44851904090268,
|
| 1541 |
+
"grad_norm": 0.760755214994802,
|
| 1542 |
+
"learning_rate": 5e-06,
|
| 1543 |
+
"loss": 0.4602,
|
| 1544 |
+
"step": 2170
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 2.459802538787024,
|
| 1548 |
+
"grad_norm": 0.7634415569046652,
|
| 1549 |
+
"learning_rate": 5e-06,
|
| 1550 |
+
"loss": 0.461,
|
| 1551 |
+
"step": 2180
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 2.4710860366713683,
|
| 1555 |
+
"grad_norm": 0.725712122867678,
|
| 1556 |
+
"learning_rate": 5e-06,
|
| 1557 |
+
"loss": 0.4631,
|
| 1558 |
+
"step": 2190
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 2.4823695345557124,
|
| 1562 |
+
"grad_norm": 0.7540090450075305,
|
| 1563 |
+
"learning_rate": 5e-06,
|
| 1564 |
+
"loss": 0.4638,
|
| 1565 |
+
"step": 2200
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 2.4936530324400565,
|
| 1569 |
+
"grad_norm": 0.7217092577620574,
|
| 1570 |
+
"learning_rate": 5e-06,
|
| 1571 |
+
"loss": 0.4702,
|
| 1572 |
+
"step": 2210
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 2.5049365303244007,
|
| 1576 |
+
"grad_norm": 0.7316510601952371,
|
| 1577 |
+
"learning_rate": 5e-06,
|
| 1578 |
+
"loss": 0.4636,
|
| 1579 |
+
"step": 2220
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 2.516220028208745,
|
| 1583 |
+
"grad_norm": 0.7769888826201891,
|
| 1584 |
+
"learning_rate": 5e-06,
|
| 1585 |
+
"loss": 0.457,
|
| 1586 |
+
"step": 2230
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 2.527503526093089,
|
| 1590 |
+
"grad_norm": 0.6872130661688746,
|
| 1591 |
+
"learning_rate": 5e-06,
|
| 1592 |
+
"loss": 0.4603,
|
| 1593 |
+
"step": 2240
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 2.538787023977433,
|
| 1597 |
+
"grad_norm": 0.7809947622038785,
|
| 1598 |
+
"learning_rate": 5e-06,
|
| 1599 |
+
"loss": 0.4598,
|
| 1600 |
+
"step": 2250
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.550070521861777,
|
| 1604 |
+
"grad_norm": 0.7128936960294685,
|
| 1605 |
+
"learning_rate": 5e-06,
|
| 1606 |
+
"loss": 0.4665,
|
| 1607 |
+
"step": 2260
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.5613540197461213,
|
| 1611 |
+
"grad_norm": 0.7343811921788322,
|
| 1612 |
+
"learning_rate": 5e-06,
|
| 1613 |
+
"loss": 0.4612,
|
| 1614 |
+
"step": 2270
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.5726375176304654,
|
| 1618 |
+
"grad_norm": 0.7390667339205597,
|
| 1619 |
+
"learning_rate": 5e-06,
|
| 1620 |
+
"loss": 0.4607,
|
| 1621 |
+
"step": 2280
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.5839210155148096,
|
| 1625 |
+
"grad_norm": 0.726032460592344,
|
| 1626 |
+
"learning_rate": 5e-06,
|
| 1627 |
+
"loss": 0.4549,
|
| 1628 |
+
"step": 2290
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.5952045133991537,
|
| 1632 |
+
"grad_norm": 0.7524597049646161,
|
| 1633 |
+
"learning_rate": 5e-06,
|
| 1634 |
+
"loss": 0.4694,
|
| 1635 |
+
"step": 2300
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.606488011283498,
|
| 1639 |
+
"grad_norm": 0.7858250860151663,
|
| 1640 |
+
"learning_rate": 5e-06,
|
| 1641 |
+
"loss": 0.4663,
|
| 1642 |
+
"step": 2310
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 2.617771509167842,
|
| 1646 |
+
"grad_norm": 0.7293613916851106,
|
| 1647 |
+
"learning_rate": 5e-06,
|
| 1648 |
+
"loss": 0.4664,
|
| 1649 |
+
"step": 2320
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 2.629055007052186,
|
| 1653 |
+
"grad_norm": 0.7290633000536495,
|
| 1654 |
+
"learning_rate": 5e-06,
|
| 1655 |
+
"loss": 0.4543,
|
| 1656 |
+
"step": 2330
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 2.64033850493653,
|
| 1660 |
+
"grad_norm": 0.7091768581049495,
|
| 1661 |
+
"learning_rate": 5e-06,
|
| 1662 |
+
"loss": 0.4559,
|
| 1663 |
+
"step": 2340
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 2.6516220028208743,
|
| 1667 |
+
"grad_norm": 0.7087926245008993,
|
| 1668 |
+
"learning_rate": 5e-06,
|
| 1669 |
+
"loss": 0.4635,
|
| 1670 |
+
"step": 2350
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 2.6629055007052185,
|
| 1674 |
+
"grad_norm": 0.7590073933828212,
|
| 1675 |
+
"learning_rate": 5e-06,
|
| 1676 |
+
"loss": 0.4686,
|
| 1677 |
+
"step": 2360
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 2.6741889985895626,
|
| 1681 |
+
"grad_norm": 0.7267770663460916,
|
| 1682 |
+
"learning_rate": 5e-06,
|
| 1683 |
+
"loss": 0.46,
|
| 1684 |
+
"step": 2370
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 2.685472496473907,
|
| 1688 |
+
"grad_norm": 0.7248345474556908,
|
| 1689 |
+
"learning_rate": 5e-06,
|
| 1690 |
+
"loss": 0.4727,
|
| 1691 |
+
"step": 2380
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 2.6967559943582513,
|
| 1695 |
+
"grad_norm": 0.7498626285953574,
|
| 1696 |
+
"learning_rate": 5e-06,
|
| 1697 |
+
"loss": 0.4667,
|
| 1698 |
+
"step": 2390
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 2.7080394922425954,
|
| 1702 |
+
"grad_norm": 0.7438411024370735,
|
| 1703 |
+
"learning_rate": 5e-06,
|
| 1704 |
+
"loss": 0.465,
|
| 1705 |
+
"step": 2400
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 2.7193229901269396,
|
| 1709 |
+
"grad_norm": 0.7551882708372384,
|
| 1710 |
+
"learning_rate": 5e-06,
|
| 1711 |
+
"loss": 0.4659,
|
| 1712 |
+
"step": 2410
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 2.7306064880112837,
|
| 1716 |
+
"grad_norm": 0.7575954402507921,
|
| 1717 |
+
"learning_rate": 5e-06,
|
| 1718 |
+
"loss": 0.4679,
|
| 1719 |
+
"step": 2420
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 2.741889985895628,
|
| 1723 |
+
"grad_norm": 0.7276043657180276,
|
| 1724 |
+
"learning_rate": 5e-06,
|
| 1725 |
+
"loss": 0.4628,
|
| 1726 |
+
"step": 2430
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 2.753173483779972,
|
| 1730 |
+
"grad_norm": 0.7154984668294021,
|
| 1731 |
+
"learning_rate": 5e-06,
|
| 1732 |
+
"loss": 0.4654,
|
| 1733 |
+
"step": 2440
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 2.764456981664316,
|
| 1737 |
+
"grad_norm": 0.7203876412478339,
|
| 1738 |
+
"learning_rate": 5e-06,
|
| 1739 |
+
"loss": 0.4697,
|
| 1740 |
+
"step": 2450
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 2.77574047954866,
|
| 1744 |
+
"grad_norm": 0.7653450966118911,
|
| 1745 |
+
"learning_rate": 5e-06,
|
| 1746 |
+
"loss": 0.4705,
|
| 1747 |
+
"step": 2460
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 2.7870239774330043,
|
| 1751 |
+
"grad_norm": 0.7371256159182112,
|
| 1752 |
+
"learning_rate": 5e-06,
|
| 1753 |
+
"loss": 0.4641,
|
| 1754 |
+
"step": 2470
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 2.7983074753173485,
|
| 1758 |
+
"grad_norm": 0.7334765675316313,
|
| 1759 |
+
"learning_rate": 5e-06,
|
| 1760 |
+
"loss": 0.4726,
|
| 1761 |
+
"step": 2480
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 2.8095909732016926,
|
| 1765 |
+
"grad_norm": 0.7255504755388352,
|
| 1766 |
+
"learning_rate": 5e-06,
|
| 1767 |
+
"loss": 0.4734,
|
| 1768 |
+
"step": 2490
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 2.8208744710860367,
|
| 1772 |
+
"grad_norm": 0.721440148744813,
|
| 1773 |
+
"learning_rate": 5e-06,
|
| 1774 |
+
"loss": 0.4644,
|
| 1775 |
+
"step": 2500
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 2.832157968970381,
|
| 1779 |
+
"grad_norm": 0.748754622356668,
|
| 1780 |
+
"learning_rate": 5e-06,
|
| 1781 |
+
"loss": 0.4794,
|
| 1782 |
+
"step": 2510
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 2.843441466854725,
|
| 1786 |
+
"grad_norm": 0.7463238131630598,
|
| 1787 |
+
"learning_rate": 5e-06,
|
| 1788 |
+
"loss": 0.4628,
|
| 1789 |
+
"step": 2520
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 2.854724964739069,
|
| 1793 |
+
"grad_norm": 0.7220764644154523,
|
| 1794 |
+
"learning_rate": 5e-06,
|
| 1795 |
+
"loss": 0.4715,
|
| 1796 |
+
"step": 2530
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 2.8660084626234132,
|
| 1800 |
+
"grad_norm": 0.7116624476538259,
|
| 1801 |
+
"learning_rate": 5e-06,
|
| 1802 |
+
"loss": 0.4633,
|
| 1803 |
+
"step": 2540
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 2.8772919605077574,
|
| 1807 |
+
"grad_norm": 0.7567720887800601,
|
| 1808 |
+
"learning_rate": 5e-06,
|
| 1809 |
+
"loss": 0.4689,
|
| 1810 |
+
"step": 2550
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 2.8885754583921015,
|
| 1814 |
+
"grad_norm": 0.7311117433105612,
|
| 1815 |
+
"learning_rate": 5e-06,
|
| 1816 |
+
"loss": 0.4659,
|
| 1817 |
+
"step": 2560
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 2.8998589562764456,
|
| 1821 |
+
"grad_norm": 0.6857771399213093,
|
| 1822 |
+
"learning_rate": 5e-06,
|
| 1823 |
+
"loss": 0.4668,
|
| 1824 |
+
"step": 2570
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 2.9111424541607898,
|
| 1828 |
+
"grad_norm": 0.7603898848747829,
|
| 1829 |
+
"learning_rate": 5e-06,
|
| 1830 |
+
"loss": 0.4723,
|
| 1831 |
+
"step": 2580
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 2.922425952045134,
|
| 1835 |
+
"grad_norm": 0.7346850752363808,
|
| 1836 |
+
"learning_rate": 5e-06,
|
| 1837 |
+
"loss": 0.4631,
|
| 1838 |
+
"step": 2590
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 2.933709449929478,
|
| 1842 |
+
"grad_norm": 0.7524612932802797,
|
| 1843 |
+
"learning_rate": 5e-06,
|
| 1844 |
+
"loss": 0.4686,
|
| 1845 |
+
"step": 2600
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 2.944992947813822,
|
| 1849 |
+
"grad_norm": 0.7353041598333038,
|
| 1850 |
+
"learning_rate": 5e-06,
|
| 1851 |
+
"loss": 0.4641,
|
| 1852 |
+
"step": 2610
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 2.9562764456981663,
|
| 1856 |
+
"grad_norm": 0.7285422773911787,
|
| 1857 |
+
"learning_rate": 5e-06,
|
| 1858 |
+
"loss": 0.4748,
|
| 1859 |
+
"step": 2620
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 2.9675599435825104,
|
| 1863 |
+
"grad_norm": 0.7448074753267844,
|
| 1864 |
+
"learning_rate": 5e-06,
|
| 1865 |
+
"loss": 0.472,
|
| 1866 |
+
"step": 2630
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 2.9788434414668545,
|
| 1870 |
+
"grad_norm": 0.705662537995191,
|
| 1871 |
+
"learning_rate": 5e-06,
|
| 1872 |
+
"loss": 0.4627,
|
| 1873 |
+
"step": 2640
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 2.9901269393511987,
|
| 1877 |
+
"grad_norm": 0.7412402310259647,
|
| 1878 |
+
"learning_rate": 5e-06,
|
| 1879 |
+
"loss": 0.4672,
|
| 1880 |
+
"step": 2650
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 2.9991537376586743,
|
| 1884 |
+
"eval_loss": 0.6162799000740051,
|
| 1885 |
+
"eval_runtime": 701.2713,
|
| 1886 |
+
"eval_samples_per_second": 17.028,
|
| 1887 |
+
"eval_steps_per_second": 0.533,
|
| 1888 |
+
"step": 2658
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 2.9991537376586743,
|
| 1892 |
+
"step": 2658,
|
| 1893 |
+
"total_flos": 5064195066298368.0,
|
| 1894 |
+
"train_loss": 0.5339989464833739,
|
| 1895 |
+
"train_runtime": 122516.7944,
|
| 1896 |
+
"train_samples_per_second": 5.555,
|
| 1897 |
+
"train_steps_per_second": 0.022
|
| 1898 |
+
}
|
| 1899 |
+
],
|
| 1900 |
+
"logging_steps": 10,
|
| 1901 |
+
"max_steps": 2658,
|
| 1902 |
+
"num_input_tokens_seen": 0,
|
| 1903 |
+
"num_train_epochs": 3,
|
| 1904 |
+
"save_steps": 500,
|
| 1905 |
+
"stateful_callbacks": {
|
| 1906 |
+
"TrainerControl": {
|
| 1907 |
+
"args": {
|
| 1908 |
+
"should_epoch_stop": false,
|
| 1909 |
+
"should_evaluate": false,
|
| 1910 |
+
"should_log": false,
|
| 1911 |
+
"should_save": true,
|
| 1912 |
+
"should_training_stop": true
|
| 1913 |
+
},
|
| 1914 |
+
"attributes": {}
|
| 1915 |
+
}
|
| 1916 |
+
},
|
| 1917 |
+
"total_flos": 5064195066298368.0,
|
| 1918 |
+
"train_batch_size": 4,
|
| 1919 |
+
"trial_name": null,
|
| 1920 |
+
"trial_params": null
|
| 1921 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|