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 +1501 -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_19_ranking_stackexchange
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# top_19_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: 0.8026
|
| 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_19_ranking_stackexchange
|
|
|
|
| 16 |
|
| 17 |
# top_19_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_19_ranking_stackexchange dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.8026
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9961671837926627,
|
| 3 |
+
"eval_loss": 0.8026307821273804,
|
| 4 |
+
"eval_runtime": 735.7112,
|
| 5 |
+
"eval_samples_per_second": 25.085,
|
| 6 |
+
"eval_steps_per_second": 0.393,
|
| 7 |
+
"total_flos": 3436967047987200.0,
|
| 8 |
+
"train_loss": 0.7862561077286161,
|
| 9 |
+
"train_runtime": 121149.8135,
|
| 10 |
+
"train_samples_per_second": 8.683,
|
| 11 |
+
"train_steps_per_second": 0.017
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9961671837926627,
|
| 3 |
+
"eval_loss": 0.8026307821273804,
|
| 4 |
+
"eval_runtime": 735.7112,
|
| 5 |
+
"eval_samples_per_second": 25.085,
|
| 6 |
+
"eval_steps_per_second": 0.393
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9961671837926627,
|
| 3 |
+
"total_flos": 3436967047987200.0,
|
| 4 |
+
"train_loss": 0.7862561077286161,
|
| 5 |
+
"train_runtime": 121149.8135,
|
| 6 |
+
"train_samples_per_second": 8.683,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1501 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9961671837926627,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2052,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.014601204599379448,
|
| 13 |
+
"grad_norm": 31.200588193935076,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 1.0665,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.029202409198758897,
|
| 20 |
+
"grad_norm": 2.1030174817289726,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.9851,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.043803613798138345,
|
| 27 |
+
"grad_norm": 1.7889745137305164,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.9413,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.058404818397517794,
|
| 34 |
+
"grad_norm": 0.7798640642359425,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.9234,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07300602299689725,
|
| 41 |
+
"grad_norm": 2.7003950764835163,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.9077,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.08760722759627669,
|
| 48 |
+
"grad_norm": 6.611494407685939,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.9045,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.10220843219565615,
|
| 55 |
+
"grad_norm": 1.081246334652253,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.8965,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.11680963679503559,
|
| 62 |
+
"grad_norm": 0.8101716177472186,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.8855,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.13141084139441503,
|
| 69 |
+
"grad_norm": 0.8801376249396373,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.8827,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1460120459937945,
|
| 76 |
+
"grad_norm": 0.6385442821205225,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.8714,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.16061325059317394,
|
| 83 |
+
"grad_norm": 0.6872556086848158,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.8735,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.17521445519255338,
|
| 90 |
+
"grad_norm": 0.6992499417358933,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.8682,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.18981565979193282,
|
| 97 |
+
"grad_norm": 0.6013577080845172,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.8662,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2044168643913123,
|
| 104 |
+
"grad_norm": 0.5988600270173734,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.8649,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.21901806899069173,
|
| 111 |
+
"grad_norm": 0.6460225651419232,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.8647,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.23361927359007117,
|
| 118 |
+
"grad_norm": 0.5603551860244527,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.8533,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.24822047818945062,
|
| 125 |
+
"grad_norm": 0.5553710866489995,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.8544,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.26282168278883006,
|
| 132 |
+
"grad_norm": 0.6554387689230537,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.8592,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2774228873882095,
|
| 139 |
+
"grad_norm": 0.6786037864304745,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.8518,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.292024091987589,
|
| 146 |
+
"grad_norm": 0.5561181889312125,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.8505,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3066252965869684,
|
| 153 |
+
"grad_norm": 0.7917259340608006,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.8475,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3212265011863479,
|
| 160 |
+
"grad_norm": 0.5838972916992158,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.8468,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.33582770578572735,
|
| 167 |
+
"grad_norm": 0.5415756077794452,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.8478,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.35042891038510676,
|
| 174 |
+
"grad_norm": 0.561460816685303,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.8471,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.36503011498448623,
|
| 181 |
+
"grad_norm": 0.5431016015146285,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.845,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.37963131958386565,
|
| 188 |
+
"grad_norm": 0.5777928639036234,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.8427,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3942325241832451,
|
| 195 |
+
"grad_norm": 0.6855206088461627,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.8406,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4088337287826246,
|
| 202 |
+
"grad_norm": 0.5959537867792327,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.843,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.423434933382004,
|
| 209 |
+
"grad_norm": 0.5787987185587301,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.842,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.43803613798138347,
|
| 216 |
+
"grad_norm": 0.9829016985861171,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.841,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.45263734258076294,
|
| 223 |
+
"grad_norm": 0.7109664833342627,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.8376,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.46723854718014235,
|
| 230 |
+
"grad_norm": 0.5953929615896101,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.8352,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4818397517795218,
|
| 237 |
+
"grad_norm": 0.6459745420821242,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.8322,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.49644095637890123,
|
| 244 |
+
"grad_norm": 0.7286780710714444,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.833,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5110421609782807,
|
| 251 |
+
"grad_norm": 0.8624769767543123,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.8326,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5256433655776601,
|
| 258 |
+
"grad_norm": 0.7489286697832975,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.8344,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5402445701770396,
|
| 265 |
+
"grad_norm": 0.6965027768353624,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.8329,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.554845774776419,
|
| 272 |
+
"grad_norm": 0.5898605613508874,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.8396,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5694469793757985,
|
| 279 |
+
"grad_norm": 0.669429389652064,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.8318,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.584048183975178,
|
| 286 |
+
"grad_norm": 0.6580798841963941,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.8314,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5986493885745574,
|
| 293 |
+
"grad_norm": 0.624128356604639,
|
| 294 |
+
"learning_rate": 5e-06,
|
| 295 |
+
"loss": 0.8282,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6132505931739368,
|
| 300 |
+
"grad_norm": 0.5755522646670556,
|
| 301 |
+
"learning_rate": 5e-06,
|
| 302 |
+
"loss": 0.8321,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6278517977733163,
|
| 307 |
+
"grad_norm": 0.8196980265974857,
|
| 308 |
+
"learning_rate": 5e-06,
|
| 309 |
+
"loss": 0.8313,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6424530023726958,
|
| 314 |
+
"grad_norm": 0.48261475886925087,
|
| 315 |
+
"learning_rate": 5e-06,
|
| 316 |
+
"loss": 0.8238,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.6570542069720752,
|
| 321 |
+
"grad_norm": 0.5343014097762563,
|
| 322 |
+
"learning_rate": 5e-06,
|
| 323 |
+
"loss": 0.8296,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6716554115714547,
|
| 328 |
+
"grad_norm": 0.8585815714707374,
|
| 329 |
+
"learning_rate": 5e-06,
|
| 330 |
+
"loss": 0.823,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6862566161708341,
|
| 335 |
+
"grad_norm": 0.7315620836524508,
|
| 336 |
+
"learning_rate": 5e-06,
|
| 337 |
+
"loss": 0.8331,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7008578207702135,
|
| 342 |
+
"grad_norm": 0.4711661790189355,
|
| 343 |
+
"learning_rate": 5e-06,
|
| 344 |
+
"loss": 0.8245,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7154590253695929,
|
| 349 |
+
"grad_norm": 0.546263482109446,
|
| 350 |
+
"learning_rate": 5e-06,
|
| 351 |
+
"loss": 0.8212,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.7300602299689725,
|
| 356 |
+
"grad_norm": 0.5757304431326317,
|
| 357 |
+
"learning_rate": 5e-06,
|
| 358 |
+
"loss": 0.8252,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.7446614345683519,
|
| 363 |
+
"grad_norm": 0.5563752904399338,
|
| 364 |
+
"learning_rate": 5e-06,
|
| 365 |
+
"loss": 0.8251,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.7592626391677313,
|
| 370 |
+
"grad_norm": 0.48890029763799747,
|
| 371 |
+
"learning_rate": 5e-06,
|
| 372 |
+
"loss": 0.8244,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7738638437671108,
|
| 377 |
+
"grad_norm": 0.6121148728397559,
|
| 378 |
+
"learning_rate": 5e-06,
|
| 379 |
+
"loss": 0.8219,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.7884650483664902,
|
| 384 |
+
"grad_norm": 0.651565586948898,
|
| 385 |
+
"learning_rate": 5e-06,
|
| 386 |
+
"loss": 0.8203,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.8030662529658696,
|
| 391 |
+
"grad_norm": 0.5365587518038645,
|
| 392 |
+
"learning_rate": 5e-06,
|
| 393 |
+
"loss": 0.8244,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8176674575652492,
|
| 398 |
+
"grad_norm": 0.5585874614674294,
|
| 399 |
+
"learning_rate": 5e-06,
|
| 400 |
+
"loss": 0.8261,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.8322686621646286,
|
| 405 |
+
"grad_norm": 0.48225482309598716,
|
| 406 |
+
"learning_rate": 5e-06,
|
| 407 |
+
"loss": 0.828,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.846869866764008,
|
| 412 |
+
"grad_norm": 0.6379018399000604,
|
| 413 |
+
"learning_rate": 5e-06,
|
| 414 |
+
"loss": 0.8187,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.8614710713633875,
|
| 419 |
+
"grad_norm": 0.8248757003628987,
|
| 420 |
+
"learning_rate": 5e-06,
|
| 421 |
+
"loss": 0.8245,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.8760722759627669,
|
| 426 |
+
"grad_norm": 0.7072642911500023,
|
| 427 |
+
"learning_rate": 5e-06,
|
| 428 |
+
"loss": 0.8199,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.8906734805621463,
|
| 433 |
+
"grad_norm": 0.6066965111128374,
|
| 434 |
+
"learning_rate": 5e-06,
|
| 435 |
+
"loss": 0.821,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.9052746851615259,
|
| 440 |
+
"grad_norm": 0.49608072224953953,
|
| 441 |
+
"learning_rate": 5e-06,
|
| 442 |
+
"loss": 0.8263,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.9198758897609053,
|
| 447 |
+
"grad_norm": 0.6053461220096085,
|
| 448 |
+
"learning_rate": 5e-06,
|
| 449 |
+
"loss": 0.8225,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.9344770943602847,
|
| 454 |
+
"grad_norm": 0.5575666035835788,
|
| 455 |
+
"learning_rate": 5e-06,
|
| 456 |
+
"loss": 0.8211,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.9490782989596642,
|
| 461 |
+
"grad_norm": 0.5170427420902555,
|
| 462 |
+
"learning_rate": 5e-06,
|
| 463 |
+
"loss": 0.8202,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.9636795035590436,
|
| 468 |
+
"grad_norm": 0.5652214016440857,
|
| 469 |
+
"learning_rate": 5e-06,
|
| 470 |
+
"loss": 0.8219,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.978280708158423,
|
| 475 |
+
"grad_norm": 0.5065476265832586,
|
| 476 |
+
"learning_rate": 5e-06,
|
| 477 |
+
"loss": 0.8121,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.9928819127578025,
|
| 482 |
+
"grad_norm": 0.5713479763199619,
|
| 483 |
+
"learning_rate": 5e-06,
|
| 484 |
+
"loss": 0.8154,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.9987223945975543,
|
| 489 |
+
"eval_loss": 0.8185040950775146,
|
| 490 |
+
"eval_runtime": 729.2812,
|
| 491 |
+
"eval_samples_per_second": 25.306,
|
| 492 |
+
"eval_steps_per_second": 0.396,
|
| 493 |
+
"step": 684
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.0074831173571819,
|
| 497 |
+
"grad_norm": 0.5659100587324225,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.8068,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.0220843219565614,
|
| 504 |
+
"grad_norm": 0.5725390345160268,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.7796,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.036685526555941,
|
| 511 |
+
"grad_norm": 0.5067331567131128,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.7784,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.0512867311553202,
|
| 518 |
+
"grad_norm": 0.5633875492368658,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.7789,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.0658879357546998,
|
| 525 |
+
"grad_norm": 0.6503391798526155,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.7785,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.0804891403540793,
|
| 532 |
+
"grad_norm": 0.6157238494098765,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.7788,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.0950903449534586,
|
| 539 |
+
"grad_norm": 0.6692246242398756,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.7791,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.109691549552838,
|
| 546 |
+
"grad_norm": 0.772994893504376,
|
| 547 |
+
"learning_rate": 5e-06,
|
| 548 |
+
"loss": 0.7772,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.1242927541522176,
|
| 553 |
+
"grad_norm": 0.5654007018077802,
|
| 554 |
+
"learning_rate": 5e-06,
|
| 555 |
+
"loss": 0.778,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.138893958751597,
|
| 560 |
+
"grad_norm": 0.5871850769943243,
|
| 561 |
+
"learning_rate": 5e-06,
|
| 562 |
+
"loss": 0.7797,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.1534951633509765,
|
| 567 |
+
"grad_norm": 0.6081431556291285,
|
| 568 |
+
"learning_rate": 5e-06,
|
| 569 |
+
"loss": 0.7776,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.168096367950356,
|
| 574 |
+
"grad_norm": 0.5943447291419969,
|
| 575 |
+
"learning_rate": 5e-06,
|
| 576 |
+
"loss": 0.7812,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.1826975725497353,
|
| 581 |
+
"grad_norm": 0.5174382592861106,
|
| 582 |
+
"learning_rate": 5e-06,
|
| 583 |
+
"loss": 0.7742,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.1972987771491148,
|
| 588 |
+
"grad_norm": 0.5335467085784507,
|
| 589 |
+
"learning_rate": 5e-06,
|
| 590 |
+
"loss": 0.7821,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.2118999817484943,
|
| 595 |
+
"grad_norm": 0.5424184832410203,
|
| 596 |
+
"learning_rate": 5e-06,
|
| 597 |
+
"loss": 0.7832,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.2265011863478736,
|
| 602 |
+
"grad_norm": 0.5401853269685924,
|
| 603 |
+
"learning_rate": 5e-06,
|
| 604 |
+
"loss": 0.7764,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.2411023909472532,
|
| 609 |
+
"grad_norm": 0.5532297607385643,
|
| 610 |
+
"learning_rate": 5e-06,
|
| 611 |
+
"loss": 0.776,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.2557035955466325,
|
| 616 |
+
"grad_norm": 0.4600563956098031,
|
| 617 |
+
"learning_rate": 5e-06,
|
| 618 |
+
"loss": 0.7746,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.270304800146012,
|
| 623 |
+
"grad_norm": 0.5135474289282321,
|
| 624 |
+
"learning_rate": 5e-06,
|
| 625 |
+
"loss": 0.7725,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.2849060047453915,
|
| 630 |
+
"grad_norm": 0.6354802982105713,
|
| 631 |
+
"learning_rate": 5e-06,
|
| 632 |
+
"loss": 0.7787,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.299507209344771,
|
| 637 |
+
"grad_norm": 0.5869839476501474,
|
| 638 |
+
"learning_rate": 5e-06,
|
| 639 |
+
"loss": 0.7712,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.3141084139441503,
|
| 644 |
+
"grad_norm": 0.49495760536344496,
|
| 645 |
+
"learning_rate": 5e-06,
|
| 646 |
+
"loss": 0.777,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.3287096185435299,
|
| 651 |
+
"grad_norm": 0.5322628773610525,
|
| 652 |
+
"learning_rate": 5e-06,
|
| 653 |
+
"loss": 0.7791,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.3433108231429092,
|
| 658 |
+
"grad_norm": 0.6394355119269733,
|
| 659 |
+
"learning_rate": 5e-06,
|
| 660 |
+
"loss": 0.7813,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.3579120277422887,
|
| 665 |
+
"grad_norm": 0.6150475948115007,
|
| 666 |
+
"learning_rate": 5e-06,
|
| 667 |
+
"loss": 0.7718,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.3725132323416682,
|
| 672 |
+
"grad_norm": 0.6284466998832495,
|
| 673 |
+
"learning_rate": 5e-06,
|
| 674 |
+
"loss": 0.7716,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.3871144369410477,
|
| 679 |
+
"grad_norm": 0.4995594773156744,
|
| 680 |
+
"learning_rate": 5e-06,
|
| 681 |
+
"loss": 0.7801,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.401715641540427,
|
| 686 |
+
"grad_norm": 0.5533231758658743,
|
| 687 |
+
"learning_rate": 5e-06,
|
| 688 |
+
"loss": 0.7749,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.4163168461398066,
|
| 693 |
+
"grad_norm": 0.5566318311264558,
|
| 694 |
+
"learning_rate": 5e-06,
|
| 695 |
+
"loss": 0.7809,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.4309180507391859,
|
| 700 |
+
"grad_norm": 0.5996092713965696,
|
| 701 |
+
"learning_rate": 5e-06,
|
| 702 |
+
"loss": 0.7769,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.4455192553385654,
|
| 707 |
+
"grad_norm": 0.4923370749506076,
|
| 708 |
+
"learning_rate": 5e-06,
|
| 709 |
+
"loss": 0.7733,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.460120459937945,
|
| 714 |
+
"grad_norm": 0.5718051545730899,
|
| 715 |
+
"learning_rate": 5e-06,
|
| 716 |
+
"loss": 0.778,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.4747216645373245,
|
| 721 |
+
"grad_norm": 0.4966605100244046,
|
| 722 |
+
"learning_rate": 5e-06,
|
| 723 |
+
"loss": 0.7755,
|
| 724 |
+
"step": 1010
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.4893228691367038,
|
| 728 |
+
"grad_norm": 0.5104108866561695,
|
| 729 |
+
"learning_rate": 5e-06,
|
| 730 |
+
"loss": 0.7762,
|
| 731 |
+
"step": 1020
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.5039240737360833,
|
| 735 |
+
"grad_norm": 0.5790841364965528,
|
| 736 |
+
"learning_rate": 5e-06,
|
| 737 |
+
"loss": 0.775,
|
| 738 |
+
"step": 1030
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.5185252783354626,
|
| 742 |
+
"grad_norm": 0.5079205962955746,
|
| 743 |
+
"learning_rate": 5e-06,
|
| 744 |
+
"loss": 0.7791,
|
| 745 |
+
"step": 1040
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.533126482934842,
|
| 749 |
+
"grad_norm": 0.4897829483446737,
|
| 750 |
+
"learning_rate": 5e-06,
|
| 751 |
+
"loss": 0.7732,
|
| 752 |
+
"step": 1050
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.5477276875342216,
|
| 756 |
+
"grad_norm": 0.5375326427308407,
|
| 757 |
+
"learning_rate": 5e-06,
|
| 758 |
+
"loss": 0.7734,
|
| 759 |
+
"step": 1060
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.5623288921336012,
|
| 763 |
+
"grad_norm": 0.4714533263773857,
|
| 764 |
+
"learning_rate": 5e-06,
|
| 765 |
+
"loss": 0.7786,
|
| 766 |
+
"step": 1070
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.5769300967329805,
|
| 770 |
+
"grad_norm": 0.5170403858384673,
|
| 771 |
+
"learning_rate": 5e-06,
|
| 772 |
+
"loss": 0.772,
|
| 773 |
+
"step": 1080
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.5915313013323598,
|
| 777 |
+
"grad_norm": 0.5584745095875884,
|
| 778 |
+
"learning_rate": 5e-06,
|
| 779 |
+
"loss": 0.7788,
|
| 780 |
+
"step": 1090
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.6061325059317393,
|
| 784 |
+
"grad_norm": 0.5632792125524021,
|
| 785 |
+
"learning_rate": 5e-06,
|
| 786 |
+
"loss": 0.7764,
|
| 787 |
+
"step": 1100
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.6207337105311188,
|
| 791 |
+
"grad_norm": 0.5303585273369582,
|
| 792 |
+
"learning_rate": 5e-06,
|
| 793 |
+
"loss": 0.7698,
|
| 794 |
+
"step": 1110
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.6353349151304983,
|
| 798 |
+
"grad_norm": 0.5292556194617752,
|
| 799 |
+
"learning_rate": 5e-06,
|
| 800 |
+
"loss": 0.7754,
|
| 801 |
+
"step": 1120
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.6499361197298779,
|
| 805 |
+
"grad_norm": 0.5319736770394399,
|
| 806 |
+
"learning_rate": 5e-06,
|
| 807 |
+
"loss": 0.7754,
|
| 808 |
+
"step": 1130
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.6645373243292572,
|
| 812 |
+
"grad_norm": 0.5409862397072692,
|
| 813 |
+
"learning_rate": 5e-06,
|
| 814 |
+
"loss": 0.7732,
|
| 815 |
+
"step": 1140
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.6791385289286365,
|
| 819 |
+
"grad_norm": 0.5347398767131228,
|
| 820 |
+
"learning_rate": 5e-06,
|
| 821 |
+
"loss": 0.775,
|
| 822 |
+
"step": 1150
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.693739733528016,
|
| 826 |
+
"grad_norm": 0.5887598823053857,
|
| 827 |
+
"learning_rate": 5e-06,
|
| 828 |
+
"loss": 0.7734,
|
| 829 |
+
"step": 1160
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.7083409381273955,
|
| 833 |
+
"grad_norm": 0.588980481311897,
|
| 834 |
+
"learning_rate": 5e-06,
|
| 835 |
+
"loss": 0.7776,
|
| 836 |
+
"step": 1170
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.722942142726775,
|
| 840 |
+
"grad_norm": 0.5476017973657227,
|
| 841 |
+
"learning_rate": 5e-06,
|
| 842 |
+
"loss": 0.7718,
|
| 843 |
+
"step": 1180
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.7375433473261546,
|
| 847 |
+
"grad_norm": 0.5548638443373327,
|
| 848 |
+
"learning_rate": 5e-06,
|
| 849 |
+
"loss": 0.778,
|
| 850 |
+
"step": 1190
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.7521445519255339,
|
| 854 |
+
"grad_norm": 0.5443995408512653,
|
| 855 |
+
"learning_rate": 5e-06,
|
| 856 |
+
"loss": 0.7731,
|
| 857 |
+
"step": 1200
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.7667457565249132,
|
| 861 |
+
"grad_norm": 0.5134399032378028,
|
| 862 |
+
"learning_rate": 5e-06,
|
| 863 |
+
"loss": 0.7762,
|
| 864 |
+
"step": 1210
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.7813469611242927,
|
| 868 |
+
"grad_norm": 0.5143443520325698,
|
| 869 |
+
"learning_rate": 5e-06,
|
| 870 |
+
"loss": 0.7737,
|
| 871 |
+
"step": 1220
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.7959481657236722,
|
| 875 |
+
"grad_norm": 0.5712512301925389,
|
| 876 |
+
"learning_rate": 5e-06,
|
| 877 |
+
"loss": 0.7752,
|
| 878 |
+
"step": 1230
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.8105493703230517,
|
| 882 |
+
"grad_norm": 0.5022436155237929,
|
| 883 |
+
"learning_rate": 5e-06,
|
| 884 |
+
"loss": 0.7746,
|
| 885 |
+
"step": 1240
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.825150574922431,
|
| 889 |
+
"grad_norm": 0.5183607046169039,
|
| 890 |
+
"learning_rate": 5e-06,
|
| 891 |
+
"loss": 0.7758,
|
| 892 |
+
"step": 1250
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.8397517795218106,
|
| 896 |
+
"grad_norm": 0.5327048894936923,
|
| 897 |
+
"learning_rate": 5e-06,
|
| 898 |
+
"loss": 0.7737,
|
| 899 |
+
"step": 1260
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.8543529841211899,
|
| 903 |
+
"grad_norm": 0.4828373941208032,
|
| 904 |
+
"learning_rate": 5e-06,
|
| 905 |
+
"loss": 0.7734,
|
| 906 |
+
"step": 1270
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.8689541887205694,
|
| 910 |
+
"grad_norm": 0.4692396568766125,
|
| 911 |
+
"learning_rate": 5e-06,
|
| 912 |
+
"loss": 0.7702,
|
| 913 |
+
"step": 1280
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.883555393319949,
|
| 917 |
+
"grad_norm": 0.5272353821412613,
|
| 918 |
+
"learning_rate": 5e-06,
|
| 919 |
+
"loss": 0.7738,
|
| 920 |
+
"step": 1290
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.8981565979193284,
|
| 924 |
+
"grad_norm": 0.5974378803453756,
|
| 925 |
+
"learning_rate": 5e-06,
|
| 926 |
+
"loss": 0.7744,
|
| 927 |
+
"step": 1300
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.9127578025187078,
|
| 931 |
+
"grad_norm": 0.45897414900404526,
|
| 932 |
+
"learning_rate": 5e-06,
|
| 933 |
+
"loss": 0.7707,
|
| 934 |
+
"step": 1310
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.9273590071180873,
|
| 938 |
+
"grad_norm": 0.5661797189222842,
|
| 939 |
+
"learning_rate": 5e-06,
|
| 940 |
+
"loss": 0.7729,
|
| 941 |
+
"step": 1320
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.9419602117174666,
|
| 945 |
+
"grad_norm": 0.5291159788169262,
|
| 946 |
+
"learning_rate": 5e-06,
|
| 947 |
+
"loss": 0.7704,
|
| 948 |
+
"step": 1330
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.956561416316846,
|
| 952 |
+
"grad_norm": 0.5803039839795054,
|
| 953 |
+
"learning_rate": 5e-06,
|
| 954 |
+
"loss": 0.7711,
|
| 955 |
+
"step": 1340
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.9711626209162256,
|
| 959 |
+
"grad_norm": 0.5668430658536179,
|
| 960 |
+
"learning_rate": 5e-06,
|
| 961 |
+
"loss": 0.7714,
|
| 962 |
+
"step": 1350
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.9857638255156052,
|
| 966 |
+
"grad_norm": 0.5292288364377395,
|
| 967 |
+
"learning_rate": 5e-06,
|
| 968 |
+
"loss": 0.7681,
|
| 969 |
+
"step": 1360
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.9989049096550464,
|
| 973 |
+
"eval_loss": 0.8045554161071777,
|
| 974 |
+
"eval_runtime": 732.5889,
|
| 975 |
+
"eval_samples_per_second": 25.191,
|
| 976 |
+
"eval_steps_per_second": 0.394,
|
| 977 |
+
"step": 1369
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.0003650301149847,
|
| 981 |
+
"grad_norm": 0.5917011918049785,
|
| 982 |
+
"learning_rate": 5e-06,
|
| 983 |
+
"loss": 0.7813,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.0149662347143638,
|
| 988 |
+
"grad_norm": 0.6437888983866474,
|
| 989 |
+
"learning_rate": 5e-06,
|
| 990 |
+
"loss": 0.7275,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.0295674393137433,
|
| 995 |
+
"grad_norm": 0.5993159674827806,
|
| 996 |
+
"learning_rate": 5e-06,
|
| 997 |
+
"loss": 0.7301,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.044168643913123,
|
| 1002 |
+
"grad_norm": 0.6004688564094799,
|
| 1003 |
+
"learning_rate": 5e-06,
|
| 1004 |
+
"loss": 0.7279,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.0587698485125023,
|
| 1009 |
+
"grad_norm": 0.5968765010977406,
|
| 1010 |
+
"learning_rate": 5e-06,
|
| 1011 |
+
"loss": 0.732,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.073371053111882,
|
| 1016 |
+
"grad_norm": 0.6368286520923802,
|
| 1017 |
+
"learning_rate": 5e-06,
|
| 1018 |
+
"loss": 0.7327,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.0879722577112614,
|
| 1023 |
+
"grad_norm": 0.5121224799191383,
|
| 1024 |
+
"learning_rate": 5e-06,
|
| 1025 |
+
"loss": 0.7289,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.1025734623106405,
|
| 1030 |
+
"grad_norm": 0.5426488835411897,
|
| 1031 |
+
"learning_rate": 5e-06,
|
| 1032 |
+
"loss": 0.729,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.11717466691002,
|
| 1037 |
+
"grad_norm": 0.5360711433495,
|
| 1038 |
+
"learning_rate": 5e-06,
|
| 1039 |
+
"loss": 0.7321,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.1317758715093995,
|
| 1044 |
+
"grad_norm": 0.570345866307846,
|
| 1045 |
+
"learning_rate": 5e-06,
|
| 1046 |
+
"loss": 0.7283,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.146377076108779,
|
| 1051 |
+
"grad_norm": 0.5646482286111343,
|
| 1052 |
+
"learning_rate": 5e-06,
|
| 1053 |
+
"loss": 0.7341,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.1609782807081586,
|
| 1058 |
+
"grad_norm": 0.6170916412089019,
|
| 1059 |
+
"learning_rate": 5e-06,
|
| 1060 |
+
"loss": 0.7273,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 2.175579485307538,
|
| 1065 |
+
"grad_norm": 0.5669820051659463,
|
| 1066 |
+
"learning_rate": 5e-06,
|
| 1067 |
+
"loss": 0.7327,
|
| 1068 |
+
"step": 1490
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 2.190180689906917,
|
| 1072 |
+
"grad_norm": 0.5032603903192315,
|
| 1073 |
+
"learning_rate": 5e-06,
|
| 1074 |
+
"loss": 0.7259,
|
| 1075 |
+
"step": 1500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 2.2047818945062967,
|
| 1079 |
+
"grad_norm": 0.536250519862031,
|
| 1080 |
+
"learning_rate": 5e-06,
|
| 1081 |
+
"loss": 0.7309,
|
| 1082 |
+
"step": 1510
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 2.219383099105676,
|
| 1086 |
+
"grad_norm": 0.4989195000116721,
|
| 1087 |
+
"learning_rate": 5e-06,
|
| 1088 |
+
"loss": 0.7351,
|
| 1089 |
+
"step": 1520
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.2339843037050557,
|
| 1093 |
+
"grad_norm": 0.48084465295135953,
|
| 1094 |
+
"learning_rate": 5e-06,
|
| 1095 |
+
"loss": 0.7319,
|
| 1096 |
+
"step": 1530
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.2485855083044353,
|
| 1100 |
+
"grad_norm": 0.6041492880249871,
|
| 1101 |
+
"learning_rate": 5e-06,
|
| 1102 |
+
"loss": 0.7331,
|
| 1103 |
+
"step": 1540
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.2631867129038143,
|
| 1107 |
+
"grad_norm": 0.48501706414438883,
|
| 1108 |
+
"learning_rate": 5e-06,
|
| 1109 |
+
"loss": 0.7364,
|
| 1110 |
+
"step": 1550
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.277787917503194,
|
| 1114 |
+
"grad_norm": 0.486621431249399,
|
| 1115 |
+
"learning_rate": 5e-06,
|
| 1116 |
+
"loss": 0.7336,
|
| 1117 |
+
"step": 1560
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.2923891221025734,
|
| 1121 |
+
"grad_norm": 0.6249224122437264,
|
| 1122 |
+
"learning_rate": 5e-06,
|
| 1123 |
+
"loss": 0.7335,
|
| 1124 |
+
"step": 1570
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 2.306990326701953,
|
| 1128 |
+
"grad_norm": 0.6255968466832591,
|
| 1129 |
+
"learning_rate": 5e-06,
|
| 1130 |
+
"loss": 0.7315,
|
| 1131 |
+
"step": 1580
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.3215915313013324,
|
| 1135 |
+
"grad_norm": 0.5271636183137467,
|
| 1136 |
+
"learning_rate": 5e-06,
|
| 1137 |
+
"loss": 0.7322,
|
| 1138 |
+
"step": 1590
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.336192735900712,
|
| 1142 |
+
"grad_norm": 0.5924207573496902,
|
| 1143 |
+
"learning_rate": 5e-06,
|
| 1144 |
+
"loss": 0.7345,
|
| 1145 |
+
"step": 1600
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 2.3507939405000915,
|
| 1149 |
+
"grad_norm": 0.5587622345452513,
|
| 1150 |
+
"learning_rate": 5e-06,
|
| 1151 |
+
"loss": 0.7344,
|
| 1152 |
+
"step": 1610
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 2.3653951450994706,
|
| 1156 |
+
"grad_norm": 0.6269568570302153,
|
| 1157 |
+
"learning_rate": 5e-06,
|
| 1158 |
+
"loss": 0.7359,
|
| 1159 |
+
"step": 1620
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 2.37999634969885,
|
| 1163 |
+
"grad_norm": 0.6533009549527986,
|
| 1164 |
+
"learning_rate": 5e-06,
|
| 1165 |
+
"loss": 0.7368,
|
| 1166 |
+
"step": 1630
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 2.3945975542982296,
|
| 1170 |
+
"grad_norm": 0.5195452792704209,
|
| 1171 |
+
"learning_rate": 5e-06,
|
| 1172 |
+
"loss": 0.7355,
|
| 1173 |
+
"step": 1640
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 2.409198758897609,
|
| 1177 |
+
"grad_norm": 0.5528537289554203,
|
| 1178 |
+
"learning_rate": 5e-06,
|
| 1179 |
+
"loss": 0.7355,
|
| 1180 |
+
"step": 1650
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 2.4237999634969887,
|
| 1184 |
+
"grad_norm": 0.5434124551027695,
|
| 1185 |
+
"learning_rate": 5e-06,
|
| 1186 |
+
"loss": 0.7343,
|
| 1187 |
+
"step": 1660
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 2.4384011680963678,
|
| 1191 |
+
"grad_norm": 0.5166289013156083,
|
| 1192 |
+
"learning_rate": 5e-06,
|
| 1193 |
+
"loss": 0.7348,
|
| 1194 |
+
"step": 1670
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.4530023726957473,
|
| 1198 |
+
"grad_norm": 0.5085481998475664,
|
| 1199 |
+
"learning_rate": 5e-06,
|
| 1200 |
+
"loss": 0.7384,
|
| 1201 |
+
"step": 1680
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.467603577295127,
|
| 1205 |
+
"grad_norm": 0.47895714940004425,
|
| 1206 |
+
"learning_rate": 5e-06,
|
| 1207 |
+
"loss": 0.7319,
|
| 1208 |
+
"step": 1690
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 2.4822047818945063,
|
| 1212 |
+
"grad_norm": 0.6790087073589551,
|
| 1213 |
+
"learning_rate": 5e-06,
|
| 1214 |
+
"loss": 0.7344,
|
| 1215 |
+
"step": 1700
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 2.496805986493886,
|
| 1219 |
+
"grad_norm": 0.5337750367727961,
|
| 1220 |
+
"learning_rate": 5e-06,
|
| 1221 |
+
"loss": 0.7348,
|
| 1222 |
+
"step": 1710
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 2.511407191093265,
|
| 1226 |
+
"grad_norm": 0.578024943637955,
|
| 1227 |
+
"learning_rate": 5e-06,
|
| 1228 |
+
"loss": 0.7335,
|
| 1229 |
+
"step": 1720
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 2.526008395692645,
|
| 1233 |
+
"grad_norm": 0.5321237652992599,
|
| 1234 |
+
"learning_rate": 5e-06,
|
| 1235 |
+
"loss": 0.7341,
|
| 1236 |
+
"step": 1730
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 2.540609600292024,
|
| 1240 |
+
"grad_norm": 0.552250362014024,
|
| 1241 |
+
"learning_rate": 5e-06,
|
| 1242 |
+
"loss": 0.7345,
|
| 1243 |
+
"step": 1740
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 2.5552108048914035,
|
| 1247 |
+
"grad_norm": 0.47716769494866995,
|
| 1248 |
+
"learning_rate": 5e-06,
|
| 1249 |
+
"loss": 0.7364,
|
| 1250 |
+
"step": 1750
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 2.569812009490783,
|
| 1254 |
+
"grad_norm": 0.5382810891628738,
|
| 1255 |
+
"learning_rate": 5e-06,
|
| 1256 |
+
"loss": 0.7327,
|
| 1257 |
+
"step": 1760
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.5844132140901626,
|
| 1261 |
+
"grad_norm": 0.5291652309846363,
|
| 1262 |
+
"learning_rate": 5e-06,
|
| 1263 |
+
"loss": 0.734,
|
| 1264 |
+
"step": 1770
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 2.599014418689542,
|
| 1268 |
+
"grad_norm": 0.583404809051004,
|
| 1269 |
+
"learning_rate": 5e-06,
|
| 1270 |
+
"loss": 0.7309,
|
| 1271 |
+
"step": 1780
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 2.613615623288921,
|
| 1275 |
+
"grad_norm": 0.607832211058636,
|
| 1276 |
+
"learning_rate": 5e-06,
|
| 1277 |
+
"loss": 0.7352,
|
| 1278 |
+
"step": 1790
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 2.6282168278883007,
|
| 1282 |
+
"grad_norm": 0.5598928601891838,
|
| 1283 |
+
"learning_rate": 5e-06,
|
| 1284 |
+
"loss": 0.7356,
|
| 1285 |
+
"step": 1800
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 2.64281803248768,
|
| 1289 |
+
"grad_norm": 0.5949750898099526,
|
| 1290 |
+
"learning_rate": 5e-06,
|
| 1291 |
+
"loss": 0.7353,
|
| 1292 |
+
"step": 1810
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 2.6574192370870597,
|
| 1296 |
+
"grad_norm": 0.6066820856022053,
|
| 1297 |
+
"learning_rate": 5e-06,
|
| 1298 |
+
"loss": 0.7347,
|
| 1299 |
+
"step": 1820
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.6720204416864393,
|
| 1303 |
+
"grad_norm": 0.5198033507111653,
|
| 1304 |
+
"learning_rate": 5e-06,
|
| 1305 |
+
"loss": 0.7354,
|
| 1306 |
+
"step": 1830
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.6866216462858183,
|
| 1310 |
+
"grad_norm": 0.5040452692645214,
|
| 1311 |
+
"learning_rate": 5e-06,
|
| 1312 |
+
"loss": 0.7391,
|
| 1313 |
+
"step": 1840
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.701222850885198,
|
| 1317 |
+
"grad_norm": 0.5156854247429866,
|
| 1318 |
+
"learning_rate": 5e-06,
|
| 1319 |
+
"loss": 0.7388,
|
| 1320 |
+
"step": 1850
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.7158240554845774,
|
| 1324 |
+
"grad_norm": 0.5617334329140413,
|
| 1325 |
+
"learning_rate": 5e-06,
|
| 1326 |
+
"loss": 0.737,
|
| 1327 |
+
"step": 1860
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.730425260083957,
|
| 1331 |
+
"grad_norm": 0.4970472716656489,
|
| 1332 |
+
"learning_rate": 5e-06,
|
| 1333 |
+
"loss": 0.7359,
|
| 1334 |
+
"step": 1870
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.7450264646833364,
|
| 1338 |
+
"grad_norm": 0.6666729572656519,
|
| 1339 |
+
"learning_rate": 5e-06,
|
| 1340 |
+
"loss": 0.7349,
|
| 1341 |
+
"step": 1880
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 2.759627669282716,
|
| 1345 |
+
"grad_norm": 0.660456603270783,
|
| 1346 |
+
"learning_rate": 5e-06,
|
| 1347 |
+
"loss": 0.7363,
|
| 1348 |
+
"step": 1890
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 2.7742288738820955,
|
| 1352 |
+
"grad_norm": 0.5479397279932245,
|
| 1353 |
+
"learning_rate": 5e-06,
|
| 1354 |
+
"loss": 0.7359,
|
| 1355 |
+
"step": 1900
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 2.7888300784814746,
|
| 1359 |
+
"grad_norm": 0.5184737073351016,
|
| 1360 |
+
"learning_rate": 5e-06,
|
| 1361 |
+
"loss": 0.7383,
|
| 1362 |
+
"step": 1910
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.803431283080854,
|
| 1366 |
+
"grad_norm": 0.501451603194624,
|
| 1367 |
+
"learning_rate": 5e-06,
|
| 1368 |
+
"loss": 0.7344,
|
| 1369 |
+
"step": 1920
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 2.8180324876802336,
|
| 1373 |
+
"grad_norm": 0.5543991291124852,
|
| 1374 |
+
"learning_rate": 5e-06,
|
| 1375 |
+
"loss": 0.7382,
|
| 1376 |
+
"step": 1930
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 2.832633692279613,
|
| 1380 |
+
"grad_norm": 0.6053239113120223,
|
| 1381 |
+
"learning_rate": 5e-06,
|
| 1382 |
+
"loss": 0.7356,
|
| 1383 |
+
"step": 1940
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 2.8472348968789927,
|
| 1387 |
+
"grad_norm": 0.5618006505391813,
|
| 1388 |
+
"learning_rate": 5e-06,
|
| 1389 |
+
"loss": 0.7377,
|
| 1390 |
+
"step": 1950
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 2.8618361014783718,
|
| 1394 |
+
"grad_norm": 0.5815392261505143,
|
| 1395 |
+
"learning_rate": 5e-06,
|
| 1396 |
+
"loss": 0.7337,
|
| 1397 |
+
"step": 1960
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 2.8764373060777513,
|
| 1401 |
+
"grad_norm": 0.7488694605510656,
|
| 1402 |
+
"learning_rate": 5e-06,
|
| 1403 |
+
"loss": 0.7362,
|
| 1404 |
+
"step": 1970
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.891038510677131,
|
| 1408 |
+
"grad_norm": 0.5769073126410138,
|
| 1409 |
+
"learning_rate": 5e-06,
|
| 1410 |
+
"loss": 0.7359,
|
| 1411 |
+
"step": 1980
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 2.9056397152765103,
|
| 1415 |
+
"grad_norm": 0.5750570915989177,
|
| 1416 |
+
"learning_rate": 5e-06,
|
| 1417 |
+
"loss": 0.7331,
|
| 1418 |
+
"step": 1990
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 2.92024091987589,
|
| 1422 |
+
"grad_norm": 0.5354199731148004,
|
| 1423 |
+
"learning_rate": 5e-06,
|
| 1424 |
+
"loss": 0.7341,
|
| 1425 |
+
"step": 2000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.9348421244752694,
|
| 1429 |
+
"grad_norm": 0.5855570342179945,
|
| 1430 |
+
"learning_rate": 5e-06,
|
| 1431 |
+
"loss": 0.7404,
|
| 1432 |
+
"step": 2010
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 2.949443329074649,
|
| 1436 |
+
"grad_norm": 0.6261526281235102,
|
| 1437 |
+
"learning_rate": 5e-06,
|
| 1438 |
+
"loss": 0.7337,
|
| 1439 |
+
"step": 2020
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 2.964044533674028,
|
| 1443 |
+
"grad_norm": 0.5504549828167312,
|
| 1444 |
+
"learning_rate": 5e-06,
|
| 1445 |
+
"loss": 0.7348,
|
| 1446 |
+
"step": 2030
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 2.9786457382734075,
|
| 1450 |
+
"grad_norm": 0.529021801831048,
|
| 1451 |
+
"learning_rate": 5e-06,
|
| 1452 |
+
"loss": 0.7354,
|
| 1453 |
+
"step": 2040
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 2.993246942872787,
|
| 1457 |
+
"grad_norm": 0.5245972765419218,
|
| 1458 |
+
"learning_rate": 5e-06,
|
| 1459 |
+
"loss": 0.7372,
|
| 1460 |
+
"step": 2050
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 2.9961671837926627,
|
| 1464 |
+
"eval_loss": 0.8026307821273804,
|
| 1465 |
+
"eval_runtime": 732.5471,
|
| 1466 |
+
"eval_samples_per_second": 25.193,
|
| 1467 |
+
"eval_steps_per_second": 0.395,
|
| 1468 |
+
"step": 2052
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 2.9961671837926627,
|
| 1472 |
+
"step": 2052,
|
| 1473 |
+
"total_flos": 3436967047987200.0,
|
| 1474 |
+
"train_loss": 0.7862561077286161,
|
| 1475 |
+
"train_runtime": 121149.8135,
|
| 1476 |
+
"train_samples_per_second": 8.683,
|
| 1477 |
+
"train_steps_per_second": 0.017
|
| 1478 |
+
}
|
| 1479 |
+
],
|
| 1480 |
+
"logging_steps": 10,
|
| 1481 |
+
"max_steps": 2052,
|
| 1482 |
+
"num_input_tokens_seen": 0,
|
| 1483 |
+
"num_train_epochs": 3,
|
| 1484 |
+
"save_steps": 500,
|
| 1485 |
+
"stateful_callbacks": {
|
| 1486 |
+
"TrainerControl": {
|
| 1487 |
+
"args": {
|
| 1488 |
+
"should_epoch_stop": false,
|
| 1489 |
+
"should_evaluate": false,
|
| 1490 |
+
"should_log": false,
|
| 1491 |
+
"should_save": true,
|
| 1492 |
+
"should_training_stop": true
|
| 1493 |
+
},
|
| 1494 |
+
"attributes": {}
|
| 1495 |
+
}
|
| 1496 |
+
},
|
| 1497 |
+
"total_flos": 3436967047987200.0,
|
| 1498 |
+
"train_batch_size": 8,
|
| 1499 |
+
"trial_name": null,
|
| 1500 |
+
"trial_params": null
|
| 1501 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|