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 +1340 -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: top_17_ranking_stackexchange
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# top_17_ranking_stackexchange
|
| 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: 0.7988
|
| 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: top_17_ranking_stackexchange
|
|
|
|
| 16 |
|
| 17 |
# top_17_ranking_stackexchange
|
| 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/top_17_ranking_stackexchange dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.7988
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.998768978251949,
|
| 3 |
+
"eval_loss": 0.7988426685333252,
|
| 4 |
+
"eval_runtime": 652.4279,
|
| 5 |
+
"eval_samples_per_second": 25.163,
|
| 6 |
+
"eval_steps_per_second": 0.394,
|
| 7 |
+
"total_flos": 3060083667763200.0,
|
| 8 |
+
"train_loss": 0.7828072778631836,
|
| 9 |
+
"train_runtime": 108782.0419,
|
| 10 |
+
"train_samples_per_second": 8.602,
|
| 11 |
+
"train_steps_per_second": 0.017
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.998768978251949,
|
| 3 |
+
"eval_loss": 0.7988426685333252,
|
| 4 |
+
"eval_runtime": 652.4279,
|
| 5 |
+
"eval_samples_per_second": 25.163,
|
| 6 |
+
"eval_steps_per_second": 0.394
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.998768978251949,
|
| 3 |
+
"total_flos": 3060083667763200.0,
|
| 4 |
+
"train_loss": 0.7828072778631836,
|
| 5 |
+
"train_runtime": 108782.0419,
|
| 6 |
+
"train_samples_per_second": 8.602,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1340 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.998768978251949,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1827,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016413623307345096,
|
| 13 |
+
"grad_norm": 8.99270138013034,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 1.0659,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03282724661469019,
|
| 20 |
+
"grad_norm": 3.053529266595301,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.9734,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04924086992203529,
|
| 27 |
+
"grad_norm": 2.633730745764626,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.9341,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06565449322938038,
|
| 34 |
+
"grad_norm": 0.7908528977431902,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.9191,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08206811653672548,
|
| 41 |
+
"grad_norm": 1.0408150537576215,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.9013,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09848173984407058,
|
| 48 |
+
"grad_norm": 1.0009107528629961,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.8956,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11489536315141567,
|
| 55 |
+
"grad_norm": 0.8433960502782532,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.8783,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13130898645876077,
|
| 62 |
+
"grad_norm": 1.2184758422903226,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.8776,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14772260976610588,
|
| 69 |
+
"grad_norm": 0.7980413481780791,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.8707,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16413623307345096,
|
| 76 |
+
"grad_norm": 0.5562074295693149,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.8672,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.18054985638079607,
|
| 83 |
+
"grad_norm": 0.5260694903772933,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.8611,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.19696347968814115,
|
| 90 |
+
"grad_norm": 0.6264931158468416,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.8621,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.21337710299548626,
|
| 97 |
+
"grad_norm": 0.6191079265416527,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.8541,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.22979072630283134,
|
| 104 |
+
"grad_norm": 0.5921376117856568,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.8535,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.24620434961017645,
|
| 111 |
+
"grad_norm": 0.5621484849345678,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.8548,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.26261797291752154,
|
| 118 |
+
"grad_norm": 0.5294016331059697,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.8538,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2790315962248666,
|
| 125 |
+
"grad_norm": 0.5007519115014486,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.849,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.29544521953221176,
|
| 132 |
+
"grad_norm": 0.5887354661692235,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.8488,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.31185884283955684,
|
| 139 |
+
"grad_norm": 0.5081716506810537,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.8484,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3282724661469019,
|
| 146 |
+
"grad_norm": 0.6188657430216449,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.8426,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.344686089454247,
|
| 153 |
+
"grad_norm": 1.0610412603180521,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.8399,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.36109971276159214,
|
| 160 |
+
"grad_norm": 0.7317657510287235,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.8455,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3775133360689372,
|
| 167 |
+
"grad_norm": 0.5199899282009807,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.8437,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3939269593762823,
|
| 174 |
+
"grad_norm": 0.701918684276049,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.8391,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4103405826836274,
|
| 181 |
+
"grad_norm": 0.5559902755445636,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.8358,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4267542059909725,
|
| 188 |
+
"grad_norm": 0.5581199955306168,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.8394,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4431678292983176,
|
| 195 |
+
"grad_norm": 0.6690583184335058,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.8373,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4595814526056627,
|
| 202 |
+
"grad_norm": 0.505413325131573,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.8321,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.47599507591300777,
|
| 209 |
+
"grad_norm": 0.4902726775641345,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.8407,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.4924086992203529,
|
| 216 |
+
"grad_norm": 0.7023706220694934,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.8309,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.508822322527698,
|
| 223 |
+
"grad_norm": 0.5762877961049813,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.8318,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5252359458350431,
|
| 230 |
+
"grad_norm": 0.47853098636746905,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.8332,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5416495691423882,
|
| 237 |
+
"grad_norm": 0.5281284739639729,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.83,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5580631924497332,
|
| 244 |
+
"grad_norm": 0.5794359727324211,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.827,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5744768157570784,
|
| 251 |
+
"grad_norm": 0.542547522553918,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.8289,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5908904390644235,
|
| 258 |
+
"grad_norm": 0.5615169892984633,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.8261,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6073040623717686,
|
| 265 |
+
"grad_norm": 0.5992859282011177,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.8265,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6237176856791137,
|
| 272 |
+
"grad_norm": 0.6682966476034522,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.8272,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6401313089864588,
|
| 279 |
+
"grad_norm": 0.5419933138601745,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.8258,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6565449322938038,
|
| 286 |
+
"grad_norm": 0.49991773880492635,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.8249,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6729585556011489,
|
| 293 |
+
"grad_norm": 0.6878795353167779,
|
| 294 |
+
"learning_rate": 5e-06,
|
| 295 |
+
"loss": 0.8222,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.689372178908494,
|
| 300 |
+
"grad_norm": 0.4911573402330116,
|
| 301 |
+
"learning_rate": 5e-06,
|
| 302 |
+
"loss": 0.825,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7057858022158392,
|
| 307 |
+
"grad_norm": 0.5697346305894231,
|
| 308 |
+
"learning_rate": 5e-06,
|
| 309 |
+
"loss": 0.825,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7221994255231843,
|
| 314 |
+
"grad_norm": 0.5513743964148584,
|
| 315 |
+
"learning_rate": 5e-06,
|
| 316 |
+
"loss": 0.8246,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7386130488305294,
|
| 321 |
+
"grad_norm": 0.688660194802024,
|
| 322 |
+
"learning_rate": 5e-06,
|
| 323 |
+
"loss": 0.8222,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.7550266721378744,
|
| 328 |
+
"grad_norm": 0.511273977957526,
|
| 329 |
+
"learning_rate": 5e-06,
|
| 330 |
+
"loss": 0.8213,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.7714402954452195,
|
| 335 |
+
"grad_norm": 0.5063886517354912,
|
| 336 |
+
"learning_rate": 5e-06,
|
| 337 |
+
"loss": 0.8222,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7878539187525646,
|
| 342 |
+
"grad_norm": 0.5454872366957495,
|
| 343 |
+
"learning_rate": 5e-06,
|
| 344 |
+
"loss": 0.8193,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8042675420599097,
|
| 349 |
+
"grad_norm": 0.565210030152154,
|
| 350 |
+
"learning_rate": 5e-06,
|
| 351 |
+
"loss": 0.8177,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8206811653672548,
|
| 356 |
+
"grad_norm": 0.6047647526413709,
|
| 357 |
+
"learning_rate": 5e-06,
|
| 358 |
+
"loss": 0.8184,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8370947886746,
|
| 363 |
+
"grad_norm": 0.4922366597743525,
|
| 364 |
+
"learning_rate": 5e-06,
|
| 365 |
+
"loss": 0.8172,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.853508411981945,
|
| 370 |
+
"grad_norm": 0.5659941668447491,
|
| 371 |
+
"learning_rate": 5e-06,
|
| 372 |
+
"loss": 0.8204,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8699220352892901,
|
| 377 |
+
"grad_norm": 0.7936193835249891,
|
| 378 |
+
"learning_rate": 5e-06,
|
| 379 |
+
"loss": 0.8156,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.8863356585966352,
|
| 384 |
+
"grad_norm": 0.635704407895363,
|
| 385 |
+
"learning_rate": 5e-06,
|
| 386 |
+
"loss": 0.8168,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.9027492819039803,
|
| 391 |
+
"grad_norm": 0.5271560225642157,
|
| 392 |
+
"learning_rate": 5e-06,
|
| 393 |
+
"loss": 0.8154,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.9191629052113254,
|
| 398 |
+
"grad_norm": 0.4819325527832828,
|
| 399 |
+
"learning_rate": 5e-06,
|
| 400 |
+
"loss": 0.818,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9355765285186705,
|
| 405 |
+
"grad_norm": 0.5777651614118724,
|
| 406 |
+
"learning_rate": 5e-06,
|
| 407 |
+
"loss": 0.8168,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.9519901518260155,
|
| 412 |
+
"grad_norm": 0.7370846415410045,
|
| 413 |
+
"learning_rate": 5e-06,
|
| 414 |
+
"loss": 0.8152,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.9684037751333607,
|
| 419 |
+
"grad_norm": 0.6007353019630401,
|
| 420 |
+
"learning_rate": 5e-06,
|
| 421 |
+
"loss": 0.8173,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.9848173984407058,
|
| 426 |
+
"grad_norm": 0.56593529564363,
|
| 427 |
+
"learning_rate": 5e-06,
|
| 428 |
+
"loss": 0.8157,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.9995896594173164,
|
| 433 |
+
"eval_loss": 0.8145917654037476,
|
| 434 |
+
"eval_runtime": 649.6437,
|
| 435 |
+
"eval_samples_per_second": 25.271,
|
| 436 |
+
"eval_steps_per_second": 0.396,
|
| 437 |
+
"step": 609
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.001231021748051,
|
| 441 |
+
"grad_norm": 1.5425883939459828,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.8731,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.017644645055396,
|
| 448 |
+
"grad_norm": 0.7619005303987774,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.7758,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.034058268362741,
|
| 455 |
+
"grad_norm": 0.6185096912027249,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.7704,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.0504718916700861,
|
| 462 |
+
"grad_norm": 0.5425736459453947,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.774,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.0668855149774312,
|
| 469 |
+
"grad_norm": 0.5336001597783918,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.7706,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.0832991382847763,
|
| 476 |
+
"grad_norm": 0.5273934170840361,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.7812,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.0997127615921214,
|
| 483 |
+
"grad_norm": 0.49999784470967323,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.7786,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.1161263848994665,
|
| 490 |
+
"grad_norm": 0.5332221891356449,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.7749,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.1325400082068118,
|
| 497 |
+
"grad_norm": 0.5733836629913084,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.7782,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.1489536315141566,
|
| 504 |
+
"grad_norm": 0.49502621904597705,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.771,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.165367254821502,
|
| 511 |
+
"grad_norm": 0.527378879948705,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.769,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.181780878128847,
|
| 518 |
+
"grad_norm": 0.6092891531058294,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.7735,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.198194501436192,
|
| 525 |
+
"grad_norm": 0.7409709215243082,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.7735,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.2146081247435372,
|
| 532 |
+
"grad_norm": 0.5407098999014308,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.7735,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.2310217480508823,
|
| 539 |
+
"grad_norm": 0.558991862523269,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.7773,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.2474353713582274,
|
| 546 |
+
"grad_norm": 0.5542175525118204,
|
| 547 |
+
"learning_rate": 5e-06,
|
| 548 |
+
"loss": 0.7776,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.2638489946655724,
|
| 553 |
+
"grad_norm": 0.5783902400184568,
|
| 554 |
+
"learning_rate": 5e-06,
|
| 555 |
+
"loss": 0.7746,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.2802626179729175,
|
| 560 |
+
"grad_norm": 0.5521887369776995,
|
| 561 |
+
"learning_rate": 5e-06,
|
| 562 |
+
"loss": 0.7707,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.2966762412802626,
|
| 567 |
+
"grad_norm": 0.8444645957997873,
|
| 568 |
+
"learning_rate": 5e-06,
|
| 569 |
+
"loss": 0.7725,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.3130898645876077,
|
| 574 |
+
"grad_norm": 0.5736975526122204,
|
| 575 |
+
"learning_rate": 5e-06,
|
| 576 |
+
"loss": 0.7744,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.3295034878949528,
|
| 581 |
+
"grad_norm": 0.48292249290479,
|
| 582 |
+
"learning_rate": 5e-06,
|
| 583 |
+
"loss": 0.7733,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.3459171112022978,
|
| 588 |
+
"grad_norm": 0.5049987037399899,
|
| 589 |
+
"learning_rate": 5e-06,
|
| 590 |
+
"loss": 0.7714,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.362330734509643,
|
| 595 |
+
"grad_norm": 0.5062380261284263,
|
| 596 |
+
"learning_rate": 5e-06,
|
| 597 |
+
"loss": 0.7715,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.3787443578169882,
|
| 602 |
+
"grad_norm": 0.5278903296959995,
|
| 603 |
+
"learning_rate": 5e-06,
|
| 604 |
+
"loss": 0.7726,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.395157981124333,
|
| 609 |
+
"grad_norm": 0.5450750708926599,
|
| 610 |
+
"learning_rate": 5e-06,
|
| 611 |
+
"loss": 0.7747,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.4115716044316784,
|
| 616 |
+
"grad_norm": 0.6396261396718704,
|
| 617 |
+
"learning_rate": 5e-06,
|
| 618 |
+
"loss": 0.7744,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.4279852277390233,
|
| 623 |
+
"grad_norm": 0.5482394718697263,
|
| 624 |
+
"learning_rate": 5e-06,
|
| 625 |
+
"loss": 0.7727,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.4443988510463686,
|
| 630 |
+
"grad_norm": 0.46959189800427537,
|
| 631 |
+
"learning_rate": 5e-06,
|
| 632 |
+
"loss": 0.7744,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.4608124743537136,
|
| 637 |
+
"grad_norm": 0.5691557302620813,
|
| 638 |
+
"learning_rate": 5e-06,
|
| 639 |
+
"loss": 0.77,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.4772260976610587,
|
| 644 |
+
"grad_norm": 0.5438893971371171,
|
| 645 |
+
"learning_rate": 5e-06,
|
| 646 |
+
"loss": 0.7742,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.4936397209684038,
|
| 651 |
+
"grad_norm": 0.515108075044442,
|
| 652 |
+
"learning_rate": 5e-06,
|
| 653 |
+
"loss": 0.7674,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.5100533442757489,
|
| 658 |
+
"grad_norm": 0.535062525509266,
|
| 659 |
+
"learning_rate": 5e-06,
|
| 660 |
+
"loss": 0.7716,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.526466967583094,
|
| 665 |
+
"grad_norm": 0.48864573799251787,
|
| 666 |
+
"learning_rate": 5e-06,
|
| 667 |
+
"loss": 0.7711,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.542880590890439,
|
| 672 |
+
"grad_norm": 0.512031098496549,
|
| 673 |
+
"learning_rate": 5e-06,
|
| 674 |
+
"loss": 0.7724,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.5592942141977841,
|
| 679 |
+
"grad_norm": 0.5349855948928464,
|
| 680 |
+
"learning_rate": 5e-06,
|
| 681 |
+
"loss": 0.7693,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.5757078375051292,
|
| 686 |
+
"grad_norm": 0.662086219432035,
|
| 687 |
+
"learning_rate": 5e-06,
|
| 688 |
+
"loss": 0.7712,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.5921214608124743,
|
| 693 |
+
"grad_norm": 0.5526444522821828,
|
| 694 |
+
"learning_rate": 5e-06,
|
| 695 |
+
"loss": 0.7709,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.6085350841198194,
|
| 700 |
+
"grad_norm": 0.55082436990172,
|
| 701 |
+
"learning_rate": 5e-06,
|
| 702 |
+
"loss": 0.7772,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.6249487074271647,
|
| 707 |
+
"grad_norm": 0.5815245751790243,
|
| 708 |
+
"learning_rate": 5e-06,
|
| 709 |
+
"loss": 0.7722,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.6413623307345095,
|
| 714 |
+
"grad_norm": 0.5154000934765319,
|
| 715 |
+
"learning_rate": 5e-06,
|
| 716 |
+
"loss": 0.7694,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.6577759540418548,
|
| 721 |
+
"grad_norm": 0.6023290973410581,
|
| 722 |
+
"learning_rate": 5e-06,
|
| 723 |
+
"loss": 0.7673,
|
| 724 |
+
"step": 1010
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.6741895773491997,
|
| 728 |
+
"grad_norm": 0.600577558938854,
|
| 729 |
+
"learning_rate": 5e-06,
|
| 730 |
+
"loss": 0.7713,
|
| 731 |
+
"step": 1020
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.690603200656545,
|
| 735 |
+
"grad_norm": 0.6079065129634816,
|
| 736 |
+
"learning_rate": 5e-06,
|
| 737 |
+
"loss": 0.7687,
|
| 738 |
+
"step": 1030
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.7070168239638899,
|
| 742 |
+
"grad_norm": 0.693841170522645,
|
| 743 |
+
"learning_rate": 5e-06,
|
| 744 |
+
"loss": 0.7697,
|
| 745 |
+
"step": 1040
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.7234304472712352,
|
| 749 |
+
"grad_norm": 0.48888900591836165,
|
| 750 |
+
"learning_rate": 5e-06,
|
| 751 |
+
"loss": 0.7691,
|
| 752 |
+
"step": 1050
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.7398440705785803,
|
| 756 |
+
"grad_norm": 0.7010501927100856,
|
| 757 |
+
"learning_rate": 5e-06,
|
| 758 |
+
"loss": 0.7741,
|
| 759 |
+
"step": 1060
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.7562576938859253,
|
| 763 |
+
"grad_norm": 0.4911843241601219,
|
| 764 |
+
"learning_rate": 5e-06,
|
| 765 |
+
"loss": 0.7661,
|
| 766 |
+
"step": 1070
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.7726713171932704,
|
| 770 |
+
"grad_norm": 0.5931976251774361,
|
| 771 |
+
"learning_rate": 5e-06,
|
| 772 |
+
"loss": 0.7689,
|
| 773 |
+
"step": 1080
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.7890849405006155,
|
| 777 |
+
"grad_norm": 0.6443181893958313,
|
| 778 |
+
"learning_rate": 5e-06,
|
| 779 |
+
"loss": 0.7705,
|
| 780 |
+
"step": 1090
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.8054985638079606,
|
| 784 |
+
"grad_norm": 0.470844146128102,
|
| 785 |
+
"learning_rate": 5e-06,
|
| 786 |
+
"loss": 0.7726,
|
| 787 |
+
"step": 1100
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.8219121871153057,
|
| 791 |
+
"grad_norm": 0.6664878595725717,
|
| 792 |
+
"learning_rate": 5e-06,
|
| 793 |
+
"loss": 0.7698,
|
| 794 |
+
"step": 1110
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.8383258104226508,
|
| 798 |
+
"grad_norm": 0.507697225304388,
|
| 799 |
+
"learning_rate": 5e-06,
|
| 800 |
+
"loss": 0.767,
|
| 801 |
+
"step": 1120
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.8547394337299958,
|
| 805 |
+
"grad_norm": 0.5439425837704747,
|
| 806 |
+
"learning_rate": 5e-06,
|
| 807 |
+
"loss": 0.7686,
|
| 808 |
+
"step": 1130
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.8711530570373411,
|
| 812 |
+
"grad_norm": 0.8621901744125671,
|
| 813 |
+
"learning_rate": 5e-06,
|
| 814 |
+
"loss": 0.7717,
|
| 815 |
+
"step": 1140
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.887566680344686,
|
| 819 |
+
"grad_norm": 0.5511696877991991,
|
| 820 |
+
"learning_rate": 5e-06,
|
| 821 |
+
"loss": 0.7715,
|
| 822 |
+
"step": 1150
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.9039803036520313,
|
| 826 |
+
"grad_norm": 0.4950879715118595,
|
| 827 |
+
"learning_rate": 5e-06,
|
| 828 |
+
"loss": 0.7719,
|
| 829 |
+
"step": 1160
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.9203939269593762,
|
| 833 |
+
"grad_norm": 0.48824900399092436,
|
| 834 |
+
"learning_rate": 5e-06,
|
| 835 |
+
"loss": 0.7715,
|
| 836 |
+
"step": 1170
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.9368075502667215,
|
| 840 |
+
"grad_norm": 0.5450863319774812,
|
| 841 |
+
"learning_rate": 5e-06,
|
| 842 |
+
"loss": 0.7653,
|
| 843 |
+
"step": 1180
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.9532211735740663,
|
| 847 |
+
"grad_norm": 0.5501310306692955,
|
| 848 |
+
"learning_rate": 5e-06,
|
| 849 |
+
"loss": 0.7678,
|
| 850 |
+
"step": 1190
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.9696347968814116,
|
| 854 |
+
"grad_norm": 0.5175687374091981,
|
| 855 |
+
"learning_rate": 5e-06,
|
| 856 |
+
"loss": 0.7687,
|
| 857 |
+
"step": 1200
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.9860484201887567,
|
| 861 |
+
"grad_norm": 0.5729581338876775,
|
| 862 |
+
"learning_rate": 5e-06,
|
| 863 |
+
"loss": 0.7667,
|
| 864 |
+
"step": 1210
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.9991793188346327,
|
| 868 |
+
"eval_loss": 0.8003594875335693,
|
| 869 |
+
"eval_runtime": 649.053,
|
| 870 |
+
"eval_samples_per_second": 25.294,
|
| 871 |
+
"eval_steps_per_second": 0.396,
|
| 872 |
+
"step": 1218
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.002462043496102,
|
| 876 |
+
"grad_norm": 0.6463781219114217,
|
| 877 |
+
"learning_rate": 5e-06,
|
| 878 |
+
"loss": 0.8157,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.0188756668034467,
|
| 883 |
+
"grad_norm": 0.5511864743662498,
|
| 884 |
+
"learning_rate": 5e-06,
|
| 885 |
+
"loss": 0.7226,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.035289290110792,
|
| 890 |
+
"grad_norm": 0.5903816264405134,
|
| 891 |
+
"learning_rate": 5e-06,
|
| 892 |
+
"loss": 0.723,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.0517029134181373,
|
| 897 |
+
"grad_norm": 0.6048277468103348,
|
| 898 |
+
"learning_rate": 5e-06,
|
| 899 |
+
"loss": 0.7279,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.068116536725482,
|
| 904 |
+
"grad_norm": 0.6180095343734895,
|
| 905 |
+
"learning_rate": 5e-06,
|
| 906 |
+
"loss": 0.7231,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.0845301600328274,
|
| 911 |
+
"grad_norm": 0.5510967685128281,
|
| 912 |
+
"learning_rate": 5e-06,
|
| 913 |
+
"loss": 0.7251,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.1009437833401723,
|
| 918 |
+
"grad_norm": 0.5188988483266073,
|
| 919 |
+
"learning_rate": 5e-06,
|
| 920 |
+
"loss": 0.721,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.1173574066475176,
|
| 925 |
+
"grad_norm": 0.5609918054348771,
|
| 926 |
+
"learning_rate": 5e-06,
|
| 927 |
+
"loss": 0.7247,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.1337710299548625,
|
| 932 |
+
"grad_norm": 0.5166068490722786,
|
| 933 |
+
"learning_rate": 5e-06,
|
| 934 |
+
"loss": 0.7239,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.1501846532622078,
|
| 939 |
+
"grad_norm": 0.5214337691948149,
|
| 940 |
+
"learning_rate": 5e-06,
|
| 941 |
+
"loss": 0.7265,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.1665982765695526,
|
| 946 |
+
"grad_norm": 0.5346119768256951,
|
| 947 |
+
"learning_rate": 5e-06,
|
| 948 |
+
"loss": 0.7271,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.183011899876898,
|
| 953 |
+
"grad_norm": 0.5300060629839389,
|
| 954 |
+
"learning_rate": 5e-06,
|
| 955 |
+
"loss": 0.728,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.199425523184243,
|
| 960 |
+
"grad_norm": 0.6130748309683199,
|
| 961 |
+
"learning_rate": 5e-06,
|
| 962 |
+
"loss": 0.7304,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.215839146491588,
|
| 967 |
+
"grad_norm": 0.5131757232254592,
|
| 968 |
+
"learning_rate": 5e-06,
|
| 969 |
+
"loss": 0.7289,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.232252769798933,
|
| 974 |
+
"grad_norm": 0.5452450696684072,
|
| 975 |
+
"learning_rate": 5e-06,
|
| 976 |
+
"loss": 0.7279,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.2486663931062782,
|
| 981 |
+
"grad_norm": 0.5644129980449457,
|
| 982 |
+
"learning_rate": 5e-06,
|
| 983 |
+
"loss": 0.7294,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.2650800164136236,
|
| 988 |
+
"grad_norm": 0.5723600015296851,
|
| 989 |
+
"learning_rate": 5e-06,
|
| 990 |
+
"loss": 0.7282,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.2814936397209684,
|
| 995 |
+
"grad_norm": 0.5745168828163788,
|
| 996 |
+
"learning_rate": 5e-06,
|
| 997 |
+
"loss": 0.7241,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.2979072630283133,
|
| 1002 |
+
"grad_norm": 0.6316489371250509,
|
| 1003 |
+
"learning_rate": 5e-06,
|
| 1004 |
+
"loss": 0.7318,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.3143208863356586,
|
| 1009 |
+
"grad_norm": 0.5884122209110337,
|
| 1010 |
+
"learning_rate": 5e-06,
|
| 1011 |
+
"loss": 0.726,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.330734509643004,
|
| 1016 |
+
"grad_norm": 0.5694563289563384,
|
| 1017 |
+
"learning_rate": 5e-06,
|
| 1018 |
+
"loss": 0.7303,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.3471481329503487,
|
| 1023 |
+
"grad_norm": 0.5726932495181197,
|
| 1024 |
+
"learning_rate": 5e-06,
|
| 1025 |
+
"loss": 0.7288,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.363561756257694,
|
| 1030 |
+
"grad_norm": 0.5879297609823882,
|
| 1031 |
+
"learning_rate": 5e-06,
|
| 1032 |
+
"loss": 0.7296,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.379975379565039,
|
| 1037 |
+
"grad_norm": 0.5883121862822648,
|
| 1038 |
+
"learning_rate": 5e-06,
|
| 1039 |
+
"loss": 0.733,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.396389002872384,
|
| 1044 |
+
"grad_norm": 0.5536017215166609,
|
| 1045 |
+
"learning_rate": 5e-06,
|
| 1046 |
+
"loss": 0.7273,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.412802626179729,
|
| 1051 |
+
"grad_norm": 0.5153804582312451,
|
| 1052 |
+
"learning_rate": 5e-06,
|
| 1053 |
+
"loss": 0.7315,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.4292162494870744,
|
| 1058 |
+
"grad_norm": 0.5281531288573597,
|
| 1059 |
+
"learning_rate": 5e-06,
|
| 1060 |
+
"loss": 0.7276,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 2.4456298727944192,
|
| 1065 |
+
"grad_norm": 0.5456727623872021,
|
| 1066 |
+
"learning_rate": 5e-06,
|
| 1067 |
+
"loss": 0.7303,
|
| 1068 |
+
"step": 1490
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 2.4620434961017645,
|
| 1072 |
+
"grad_norm": 0.6682595967854461,
|
| 1073 |
+
"learning_rate": 5e-06,
|
| 1074 |
+
"loss": 0.7268,
|
| 1075 |
+
"step": 1500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 2.4784571194091094,
|
| 1079 |
+
"grad_norm": 0.5277543058901882,
|
| 1080 |
+
"learning_rate": 5e-06,
|
| 1081 |
+
"loss": 0.7308,
|
| 1082 |
+
"step": 1510
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 2.4948707427164547,
|
| 1086 |
+
"grad_norm": 0.5377911403023388,
|
| 1087 |
+
"learning_rate": 5e-06,
|
| 1088 |
+
"loss": 0.7307,
|
| 1089 |
+
"step": 1520
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.5112843660237996,
|
| 1093 |
+
"grad_norm": 0.5405851958754275,
|
| 1094 |
+
"learning_rate": 5e-06,
|
| 1095 |
+
"loss": 0.7276,
|
| 1096 |
+
"step": 1530
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.527697989331145,
|
| 1100 |
+
"grad_norm": 0.5939416097504914,
|
| 1101 |
+
"learning_rate": 5e-06,
|
| 1102 |
+
"loss": 0.7276,
|
| 1103 |
+
"step": 1540
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.54411161263849,
|
| 1107 |
+
"grad_norm": 0.4915672499433413,
|
| 1108 |
+
"learning_rate": 5e-06,
|
| 1109 |
+
"loss": 0.7302,
|
| 1110 |
+
"step": 1550
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.560525235945835,
|
| 1114 |
+
"grad_norm": 0.5714622711240627,
|
| 1115 |
+
"learning_rate": 5e-06,
|
| 1116 |
+
"loss": 0.7304,
|
| 1117 |
+
"step": 1560
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.57693885925318,
|
| 1121 |
+
"grad_norm": 0.5369778418982702,
|
| 1122 |
+
"learning_rate": 5e-06,
|
| 1123 |
+
"loss": 0.7288,
|
| 1124 |
+
"step": 1570
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 2.593352482560525,
|
| 1128 |
+
"grad_norm": 0.6119186113930412,
|
| 1129 |
+
"learning_rate": 5e-06,
|
| 1130 |
+
"loss": 0.7292,
|
| 1131 |
+
"step": 1580
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.6097661058678705,
|
| 1135 |
+
"grad_norm": 0.6419697927822549,
|
| 1136 |
+
"learning_rate": 5e-06,
|
| 1137 |
+
"loss": 0.7329,
|
| 1138 |
+
"step": 1590
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.6261797291752154,
|
| 1142 |
+
"grad_norm": 0.519894007258766,
|
| 1143 |
+
"learning_rate": 5e-06,
|
| 1144 |
+
"loss": 0.7289,
|
| 1145 |
+
"step": 1600
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 2.6425933524825607,
|
| 1149 |
+
"grad_norm": 0.5472253996087528,
|
| 1150 |
+
"learning_rate": 5e-06,
|
| 1151 |
+
"loss": 0.7331,
|
| 1152 |
+
"step": 1610
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 2.6590069757899055,
|
| 1156 |
+
"grad_norm": 0.516270579267269,
|
| 1157 |
+
"learning_rate": 5e-06,
|
| 1158 |
+
"loss": 0.73,
|
| 1159 |
+
"step": 1620
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 2.675420599097251,
|
| 1163 |
+
"grad_norm": 0.6435228852860398,
|
| 1164 |
+
"learning_rate": 5e-06,
|
| 1165 |
+
"loss": 0.7302,
|
| 1166 |
+
"step": 1630
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 2.6918342224045957,
|
| 1170 |
+
"grad_norm": 0.5501601501281529,
|
| 1171 |
+
"learning_rate": 5e-06,
|
| 1172 |
+
"loss": 0.7326,
|
| 1173 |
+
"step": 1640
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 2.708247845711941,
|
| 1177 |
+
"grad_norm": 0.5949109159278116,
|
| 1178 |
+
"learning_rate": 5e-06,
|
| 1179 |
+
"loss": 0.7316,
|
| 1180 |
+
"step": 1650
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 2.724661469019286,
|
| 1184 |
+
"grad_norm": 0.6480843118367907,
|
| 1185 |
+
"learning_rate": 5e-06,
|
| 1186 |
+
"loss": 0.7309,
|
| 1187 |
+
"step": 1660
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 2.741075092326631,
|
| 1191 |
+
"grad_norm": 0.6058791921384546,
|
| 1192 |
+
"learning_rate": 5e-06,
|
| 1193 |
+
"loss": 0.7348,
|
| 1194 |
+
"step": 1670
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.7574887156339765,
|
| 1198 |
+
"grad_norm": 0.5131902537364029,
|
| 1199 |
+
"learning_rate": 5e-06,
|
| 1200 |
+
"loss": 0.7286,
|
| 1201 |
+
"step": 1680
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.7739023389413213,
|
| 1205 |
+
"grad_norm": 0.6053781021635353,
|
| 1206 |
+
"learning_rate": 5e-06,
|
| 1207 |
+
"loss": 0.7342,
|
| 1208 |
+
"step": 1690
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 2.790315962248666,
|
| 1212 |
+
"grad_norm": 0.6434931495576977,
|
| 1213 |
+
"learning_rate": 5e-06,
|
| 1214 |
+
"loss": 0.7303,
|
| 1215 |
+
"step": 1700
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 2.8067295855560115,
|
| 1219 |
+
"grad_norm": 0.521875321768183,
|
| 1220 |
+
"learning_rate": 5e-06,
|
| 1221 |
+
"loss": 0.7292,
|
| 1222 |
+
"step": 1710
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 2.823143208863357,
|
| 1226 |
+
"grad_norm": 0.5213429202976669,
|
| 1227 |
+
"learning_rate": 5e-06,
|
| 1228 |
+
"loss": 0.7255,
|
| 1229 |
+
"step": 1720
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 2.8395568321707017,
|
| 1233 |
+
"grad_norm": 0.5054795512549872,
|
| 1234 |
+
"learning_rate": 5e-06,
|
| 1235 |
+
"loss": 0.7305,
|
| 1236 |
+
"step": 1730
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 2.8559704554780465,
|
| 1240 |
+
"grad_norm": 0.5445431336579684,
|
| 1241 |
+
"learning_rate": 5e-06,
|
| 1242 |
+
"loss": 0.7297,
|
| 1243 |
+
"step": 1740
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 2.872384078785392,
|
| 1247 |
+
"grad_norm": 0.4823512740461331,
|
| 1248 |
+
"learning_rate": 5e-06,
|
| 1249 |
+
"loss": 0.7274,
|
| 1250 |
+
"step": 1750
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 2.888797702092737,
|
| 1254 |
+
"grad_norm": 0.7211033918425558,
|
| 1255 |
+
"learning_rate": 5e-06,
|
| 1256 |
+
"loss": 0.7321,
|
| 1257 |
+
"step": 1760
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.905211325400082,
|
| 1261 |
+
"grad_norm": 0.4979306966545238,
|
| 1262 |
+
"learning_rate": 5e-06,
|
| 1263 |
+
"loss": 0.7315,
|
| 1264 |
+
"step": 1770
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 2.9216249487074273,
|
| 1268 |
+
"grad_norm": 0.5227086332578315,
|
| 1269 |
+
"learning_rate": 5e-06,
|
| 1270 |
+
"loss": 0.7266,
|
| 1271 |
+
"step": 1780
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 2.938038572014772,
|
| 1275 |
+
"grad_norm": 0.48731020276155895,
|
| 1276 |
+
"learning_rate": 5e-06,
|
| 1277 |
+
"loss": 0.7326,
|
| 1278 |
+
"step": 1790
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 2.9544521953221174,
|
| 1282 |
+
"grad_norm": 0.5441906751482174,
|
| 1283 |
+
"learning_rate": 5e-06,
|
| 1284 |
+
"loss": 0.7299,
|
| 1285 |
+
"step": 1800
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 2.9708658186294623,
|
| 1289 |
+
"grad_norm": 0.4959846025308401,
|
| 1290 |
+
"learning_rate": 5e-06,
|
| 1291 |
+
"loss": 0.7363,
|
| 1292 |
+
"step": 1810
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 2.9872794419368076,
|
| 1296 |
+
"grad_norm": 0.5582701492514177,
|
| 1297 |
+
"learning_rate": 5e-06,
|
| 1298 |
+
"loss": 0.7286,
|
| 1299 |
+
"step": 1820
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.998768978251949,
|
| 1303 |
+
"eval_loss": 0.7988426685333252,
|
| 1304 |
+
"eval_runtime": 652.5981,
|
| 1305 |
+
"eval_samples_per_second": 25.156,
|
| 1306 |
+
"eval_steps_per_second": 0.394,
|
| 1307 |
+
"step": 1827
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 2.998768978251949,
|
| 1311 |
+
"step": 1827,
|
| 1312 |
+
"total_flos": 3060083667763200.0,
|
| 1313 |
+
"train_loss": 0.7828072778631836,
|
| 1314 |
+
"train_runtime": 108782.0419,
|
| 1315 |
+
"train_samples_per_second": 8.602,
|
| 1316 |
+
"train_steps_per_second": 0.017
|
| 1317 |
+
}
|
| 1318 |
+
],
|
| 1319 |
+
"logging_steps": 10,
|
| 1320 |
+
"max_steps": 1827,
|
| 1321 |
+
"num_input_tokens_seen": 0,
|
| 1322 |
+
"num_train_epochs": 3,
|
| 1323 |
+
"save_steps": 500,
|
| 1324 |
+
"stateful_callbacks": {
|
| 1325 |
+
"TrainerControl": {
|
| 1326 |
+
"args": {
|
| 1327 |
+
"should_epoch_stop": false,
|
| 1328 |
+
"should_evaluate": false,
|
| 1329 |
+
"should_log": false,
|
| 1330 |
+
"should_save": true,
|
| 1331 |
+
"should_training_stop": true
|
| 1332 |
+
},
|
| 1333 |
+
"attributes": {}
|
| 1334 |
+
}
|
| 1335 |
+
},
|
| 1336 |
+
"total_flos": 3060083667763200.0,
|
| 1337 |
+
"train_batch_size": 8,
|
| 1338 |
+
"trial_name": null,
|
| 1339 |
+
"trial_params": null
|
| 1340 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|