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 +1144 -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_14_ranking_stackexchange
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# top_14_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: 0.8005
|
| 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_14_ranking_stackexchange
|
|
|
|
| 16 |
|
| 17 |
# top_14_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_14_ranking_stackexchange dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.8005
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.997084548104956,
|
| 3 |
+
"eval_loss": 0.8005240559577942,
|
| 4 |
+
"eval_runtime": 555.4162,
|
| 5 |
+
"eval_samples_per_second": 24.96,
|
| 6 |
+
"eval_steps_per_second": 0.391,
|
| 7 |
+
"total_flos": 2582698052812800.0,
|
| 8 |
+
"train_loss": 0.7834810720498151,
|
| 9 |
+
"train_runtime": 91136.0835,
|
| 10 |
+
"train_samples_per_second": 8.67,
|
| 11 |
+
"train_steps_per_second": 0.017
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.997084548104956,
|
| 3 |
+
"eval_loss": 0.8005240559577942,
|
| 4 |
+
"eval_runtime": 555.4162,
|
| 5 |
+
"eval_samples_per_second": 24.96,
|
| 6 |
+
"eval_steps_per_second": 0.391
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.997084548104956,
|
| 3 |
+
"total_flos": 2582698052812800.0,
|
| 4 |
+
"train_loss": 0.7834810720498151,
|
| 5 |
+
"train_runtime": 91136.0835,
|
| 6 |
+
"train_samples_per_second": 8.67,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.997084548104956,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1542,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.019436345966958212,
|
| 13 |
+
"grad_norm": 3.5477320746078096,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 1.0532,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.038872691933916424,
|
| 20 |
+
"grad_norm": 2.8209235996953512,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.9684,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05830903790087463,
|
| 27 |
+
"grad_norm": 1.1257852692164845,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.9294,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07774538386783285,
|
| 34 |
+
"grad_norm": 0.888481539231949,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.9201,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.09718172983479106,
|
| 41 |
+
"grad_norm": 0.6469537614046023,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.8971,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11661807580174927,
|
| 48 |
+
"grad_norm": 0.592544408615531,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.8837,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1360544217687075,
|
| 55 |
+
"grad_norm": 0.6433313667438364,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.8749,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1554907677356657,
|
| 62 |
+
"grad_norm": 1.344429915972531,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.867,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1749271137026239,
|
| 69 |
+
"grad_norm": 0.8707935340603853,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.8623,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.19436345966958213,
|
| 76 |
+
"grad_norm": 0.7828161719097383,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.8624,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.21379980563654033,
|
| 83 |
+
"grad_norm": 0.682126021781355,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.8611,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.23323615160349853,
|
| 90 |
+
"grad_norm": 0.8081328723422389,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.8551,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.25267249757045673,
|
| 97 |
+
"grad_norm": 0.6691994077909735,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.8583,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.272108843537415,
|
| 104 |
+
"grad_norm": 0.586140300081327,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.8523,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2915451895043732,
|
| 111 |
+
"grad_norm": 0.8552001050583659,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.8497,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3109815354713314,
|
| 118 |
+
"grad_norm": 0.501523965918074,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.8464,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3304178814382896,
|
| 125 |
+
"grad_norm": 0.6785445153206255,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.848,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3498542274052478,
|
| 132 |
+
"grad_norm": 0.6494060293856031,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.8459,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.369290573372206,
|
| 139 |
+
"grad_norm": 0.6020737926390343,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.8484,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.38872691933916426,
|
| 146 |
+
"grad_norm": 0.48912875825316915,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.8449,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.40816326530612246,
|
| 153 |
+
"grad_norm": 0.8781137047011839,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.8395,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.42759961127308066,
|
| 160 |
+
"grad_norm": 0.5879468826056136,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.8387,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.44703595724003886,
|
| 167 |
+
"grad_norm": 0.6017675792916065,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.8363,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.46647230320699706,
|
| 174 |
+
"grad_norm": 0.616647981494789,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.8336,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4859086491739553,
|
| 181 |
+
"grad_norm": 0.855268617382177,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.8336,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5053449951409135,
|
| 188 |
+
"grad_norm": 0.780188445457583,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.831,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5247813411078717,
|
| 195 |
+
"grad_norm": 0.5840816004625115,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.8319,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.54421768707483,
|
| 202 |
+
"grad_norm": 0.6535257947752856,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.833,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5636540330417882,
|
| 209 |
+
"grad_norm": 0.6710102563759031,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.8354,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5830903790087464,
|
| 216 |
+
"grad_norm": 0.5947252085113186,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.8315,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6025267249757046,
|
| 223 |
+
"grad_norm": 0.5902161171422673,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.83,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6219630709426628,
|
| 230 |
+
"grad_norm": 0.5757165816873938,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.8299,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.641399416909621,
|
| 237 |
+
"grad_norm": 0.6751753868245474,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.827,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6608357628765792,
|
| 244 |
+
"grad_norm": 0.535560817394151,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.8264,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6802721088435374,
|
| 251 |
+
"grad_norm": 0.6183377886108462,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.8243,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6997084548104956,
|
| 258 |
+
"grad_norm": 0.6200501825686097,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.828,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.7191448007774538,
|
| 265 |
+
"grad_norm": 0.5622254912052161,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.8287,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.738581146744412,
|
| 272 |
+
"grad_norm": 0.6720527159909909,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.8234,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7580174927113703,
|
| 279 |
+
"grad_norm": 0.5315560166276624,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.824,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.7774538386783285,
|
| 286 |
+
"grad_norm": 0.6413527148042328,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.8194,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7968901846452867,
|
| 293 |
+
"grad_norm": 0.6402327795437167,
|
| 294 |
+
"learning_rate": 5e-06,
|
| 295 |
+
"loss": 0.8243,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8163265306122449,
|
| 300 |
+
"grad_norm": 0.6290935177044384,
|
| 301 |
+
"learning_rate": 5e-06,
|
| 302 |
+
"loss": 0.8201,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.8357628765792031,
|
| 307 |
+
"grad_norm": 0.6137598310285064,
|
| 308 |
+
"learning_rate": 5e-06,
|
| 309 |
+
"loss": 0.8187,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8551992225461613,
|
| 314 |
+
"grad_norm": 0.6137894354862566,
|
| 315 |
+
"learning_rate": 5e-06,
|
| 316 |
+
"loss": 0.8217,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8746355685131195,
|
| 321 |
+
"grad_norm": 0.7376542092364302,
|
| 322 |
+
"learning_rate": 5e-06,
|
| 323 |
+
"loss": 0.8191,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8940719144800777,
|
| 328 |
+
"grad_norm": 0.5443940007812901,
|
| 329 |
+
"learning_rate": 5e-06,
|
| 330 |
+
"loss": 0.8179,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.9135082604470359,
|
| 335 |
+
"grad_norm": 0.6778023088897194,
|
| 336 |
+
"learning_rate": 5e-06,
|
| 337 |
+
"loss": 0.8158,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.9329446064139941,
|
| 342 |
+
"grad_norm": 0.6040677193471313,
|
| 343 |
+
"learning_rate": 5e-06,
|
| 344 |
+
"loss": 0.8176,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.9523809523809523,
|
| 349 |
+
"grad_norm": 0.5741967517130403,
|
| 350 |
+
"learning_rate": 5e-06,
|
| 351 |
+
"loss": 0.8215,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.9718172983479106,
|
| 356 |
+
"grad_norm": 0.5184977635424605,
|
| 357 |
+
"learning_rate": 5e-06,
|
| 358 |
+
"loss": 0.8218,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.9912536443148688,
|
| 363 |
+
"grad_norm": 0.5484601778792662,
|
| 364 |
+
"learning_rate": 5e-06,
|
| 365 |
+
"loss": 0.8158,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.9990281827016521,
|
| 370 |
+
"eval_loss": 0.8152287006378174,
|
| 371 |
+
"eval_runtime": 547.9504,
|
| 372 |
+
"eval_samples_per_second": 25.3,
|
| 373 |
+
"eval_steps_per_second": 0.396,
|
| 374 |
+
"step": 514
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.010689990281827,
|
| 378 |
+
"grad_norm": 0.6821565020818955,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.8355,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.0301263362487851,
|
| 385 |
+
"grad_norm": 0.6277981964271326,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.7749,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.0495626822157433,
|
| 392 |
+
"grad_norm": 0.6114756472079457,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.7751,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.0689990281827018,
|
| 399 |
+
"grad_norm": 0.8259615966427586,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.7756,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.08843537414966,
|
| 406 |
+
"grad_norm": 0.6113352198439804,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.7789,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.1078717201166182,
|
| 413 |
+
"grad_norm": 0.5269512429419262,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.7784,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.1273080660835764,
|
| 420 |
+
"grad_norm": 0.5792710933468033,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.7757,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.1467444120505346,
|
| 427 |
+
"grad_norm": 0.5467198449481481,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.7757,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.1661807580174928,
|
| 434 |
+
"grad_norm": 0.6190447420364188,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.7754,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.185617103984451,
|
| 441 |
+
"grad_norm": 0.7074708178383962,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.7738,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.2050534499514092,
|
| 448 |
+
"grad_norm": 0.5708793884696434,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.7675,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.2244897959183674,
|
| 455 |
+
"grad_norm": 0.5278424041049065,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.7724,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.2439261418853256,
|
| 462 |
+
"grad_norm": 0.48269223376284837,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.7678,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.2633624878522838,
|
| 469 |
+
"grad_norm": 0.6628438951702088,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.772,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.282798833819242,
|
| 476 |
+
"grad_norm": 0.49956285734450795,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.78,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.3022351797862002,
|
| 483 |
+
"grad_norm": 0.4482989241465936,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.7712,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.3216715257531584,
|
| 490 |
+
"grad_norm": 0.515252608881534,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.7712,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.3411078717201166,
|
| 497 |
+
"grad_norm": 0.5392787594093453,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.7733,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.3605442176870748,
|
| 504 |
+
"grad_norm": 0.5239288581769422,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.7744,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.379980563654033,
|
| 511 |
+
"grad_norm": 0.5368087860350439,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.7721,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.3994169096209912,
|
| 518 |
+
"grad_norm": 0.5331498843832938,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.7702,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.4188532555879494,
|
| 525 |
+
"grad_norm": 0.5840718481917428,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.7755,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.4382896015549078,
|
| 532 |
+
"grad_norm": 0.537679455083028,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.7719,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.4577259475218658,
|
| 539 |
+
"grad_norm": 0.7948828701245976,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.7717,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.4771622934888242,
|
| 546 |
+
"grad_norm": 0.5813227807421696,
|
| 547 |
+
"learning_rate": 5e-06,
|
| 548 |
+
"loss": 0.7763,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.4965986394557822,
|
| 553 |
+
"grad_norm": 0.6049608273143411,
|
| 554 |
+
"learning_rate": 5e-06,
|
| 555 |
+
"loss": 0.7719,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.5160349854227406,
|
| 560 |
+
"grad_norm": 0.6057676712274179,
|
| 561 |
+
"learning_rate": 5e-06,
|
| 562 |
+
"loss": 0.7742,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.5354713313896986,
|
| 567 |
+
"grad_norm": 0.625042201984692,
|
| 568 |
+
"learning_rate": 5e-06,
|
| 569 |
+
"loss": 0.7767,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.554907677356657,
|
| 574 |
+
"grad_norm": 0.5502470811006085,
|
| 575 |
+
"learning_rate": 5e-06,
|
| 576 |
+
"loss": 0.769,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.574344023323615,
|
| 581 |
+
"grad_norm": 0.5857965121292225,
|
| 582 |
+
"learning_rate": 5e-06,
|
| 583 |
+
"loss": 0.7709,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.5937803692905734,
|
| 588 |
+
"grad_norm": 0.613513782295781,
|
| 589 |
+
"learning_rate": 5e-06,
|
| 590 |
+
"loss": 0.7755,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.6132167152575316,
|
| 595 |
+
"grad_norm": 0.583240417199926,
|
| 596 |
+
"learning_rate": 5e-06,
|
| 597 |
+
"loss": 0.7738,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.6326530612244898,
|
| 602 |
+
"grad_norm": 0.5231701163074167,
|
| 603 |
+
"learning_rate": 5e-06,
|
| 604 |
+
"loss": 0.7731,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.652089407191448,
|
| 609 |
+
"grad_norm": 0.4914609295920534,
|
| 610 |
+
"learning_rate": 5e-06,
|
| 611 |
+
"loss": 0.7714,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.6715257531584062,
|
| 616 |
+
"grad_norm": 0.5250445862469549,
|
| 617 |
+
"learning_rate": 5e-06,
|
| 618 |
+
"loss": 0.7747,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.6909620991253644,
|
| 623 |
+
"grad_norm": 0.5415316148110199,
|
| 624 |
+
"learning_rate": 5e-06,
|
| 625 |
+
"loss": 0.7685,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.7103984450923226,
|
| 630 |
+
"grad_norm": 0.5426871063126633,
|
| 631 |
+
"learning_rate": 5e-06,
|
| 632 |
+
"loss": 0.7687,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.7298347910592808,
|
| 637 |
+
"grad_norm": 0.5573890854917875,
|
| 638 |
+
"learning_rate": 5e-06,
|
| 639 |
+
"loss": 0.7732,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.749271137026239,
|
| 644 |
+
"grad_norm": 0.5966240890058521,
|
| 645 |
+
"learning_rate": 5e-06,
|
| 646 |
+
"loss": 0.7695,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.7687074829931972,
|
| 651 |
+
"grad_norm": 0.48852508189672406,
|
| 652 |
+
"learning_rate": 5e-06,
|
| 653 |
+
"loss": 0.7716,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.7881438289601554,
|
| 658 |
+
"grad_norm": 0.510423049422432,
|
| 659 |
+
"learning_rate": 5e-06,
|
| 660 |
+
"loss": 0.7695,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.8075801749271136,
|
| 665 |
+
"grad_norm": 0.5128362713697912,
|
| 666 |
+
"learning_rate": 5e-06,
|
| 667 |
+
"loss": 0.768,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.8270165208940718,
|
| 672 |
+
"grad_norm": 0.5100892708497722,
|
| 673 |
+
"learning_rate": 5e-06,
|
| 674 |
+
"loss": 0.7721,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.8464528668610303,
|
| 679 |
+
"grad_norm": 0.5050841552954286,
|
| 680 |
+
"learning_rate": 5e-06,
|
| 681 |
+
"loss": 0.7703,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.8658892128279883,
|
| 686 |
+
"grad_norm": 0.5100122636839687,
|
| 687 |
+
"learning_rate": 5e-06,
|
| 688 |
+
"loss": 0.7675,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.8853255587949467,
|
| 693 |
+
"grad_norm": 0.5858103448907649,
|
| 694 |
+
"learning_rate": 5e-06,
|
| 695 |
+
"loss": 0.7719,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.9047619047619047,
|
| 700 |
+
"grad_norm": 0.7186164442084766,
|
| 701 |
+
"learning_rate": 5e-06,
|
| 702 |
+
"loss": 0.7704,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.924198250728863,
|
| 707 |
+
"grad_norm": 0.49187325414902705,
|
| 708 |
+
"learning_rate": 5e-06,
|
| 709 |
+
"loss": 0.7744,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.943634596695821,
|
| 714 |
+
"grad_norm": 0.48132179189009133,
|
| 715 |
+
"learning_rate": 5e-06,
|
| 716 |
+
"loss": 0.7666,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.9630709426627795,
|
| 721 |
+
"grad_norm": 0.6042950330363083,
|
| 722 |
+
"learning_rate": 5e-06,
|
| 723 |
+
"loss": 0.7682,
|
| 724 |
+
"step": 1010
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.9825072886297375,
|
| 728 |
+
"grad_norm": 0.5107563561120851,
|
| 729 |
+
"learning_rate": 5e-06,
|
| 730 |
+
"loss": 0.7688,
|
| 731 |
+
"step": 1020
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.0,
|
| 735 |
+
"eval_loss": 0.8017936944961548,
|
| 736 |
+
"eval_runtime": 549.3546,
|
| 737 |
+
"eval_samples_per_second": 25.235,
|
| 738 |
+
"eval_steps_per_second": 0.395,
|
| 739 |
+
"step": 1029
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.001943634596696,
|
| 743 |
+
"grad_norm": 0.8520236880105687,
|
| 744 |
+
"learning_rate": 5e-06,
|
| 745 |
+
"loss": 0.8065,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.021379980563654,
|
| 750 |
+
"grad_norm": 0.6759369335284802,
|
| 751 |
+
"learning_rate": 5e-06,
|
| 752 |
+
"loss": 0.7247,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.0408163265306123,
|
| 757 |
+
"grad_norm": 0.6810404313004184,
|
| 758 |
+
"learning_rate": 5e-06,
|
| 759 |
+
"loss": 0.7257,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.0602526724975703,
|
| 764 |
+
"grad_norm": 0.5976865962159595,
|
| 765 |
+
"learning_rate": 5e-06,
|
| 766 |
+
"loss": 0.7266,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.0796890184645287,
|
| 771 |
+
"grad_norm": 0.5170299538250477,
|
| 772 |
+
"learning_rate": 5e-06,
|
| 773 |
+
"loss": 0.7262,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.0991253644314867,
|
| 778 |
+
"grad_norm": 0.636746039057963,
|
| 779 |
+
"learning_rate": 5e-06,
|
| 780 |
+
"loss": 0.7271,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.118561710398445,
|
| 785 |
+
"grad_norm": 0.7347207445428233,
|
| 786 |
+
"learning_rate": 5e-06,
|
| 787 |
+
"loss": 0.7221,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.1379980563654035,
|
| 792 |
+
"grad_norm": 0.6669755018146,
|
| 793 |
+
"learning_rate": 5e-06,
|
| 794 |
+
"loss": 0.7277,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.1574344023323615,
|
| 799 |
+
"grad_norm": 0.5653238227925762,
|
| 800 |
+
"learning_rate": 5e-06,
|
| 801 |
+
"loss": 0.726,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.17687074829932,
|
| 806 |
+
"grad_norm": 0.5720425000083328,
|
| 807 |
+
"learning_rate": 5e-06,
|
| 808 |
+
"loss": 0.7271,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.196307094266278,
|
| 813 |
+
"grad_norm": 0.5494809428119856,
|
| 814 |
+
"learning_rate": 5e-06,
|
| 815 |
+
"loss": 0.727,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.2157434402332363,
|
| 820 |
+
"grad_norm": 0.6708852933316355,
|
| 821 |
+
"learning_rate": 5e-06,
|
| 822 |
+
"loss": 0.7286,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.2351797862001943,
|
| 827 |
+
"grad_norm": 0.5649904350477953,
|
| 828 |
+
"learning_rate": 5e-06,
|
| 829 |
+
"loss": 0.7253,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.2546161321671527,
|
| 834 |
+
"grad_norm": 0.6681152322447659,
|
| 835 |
+
"learning_rate": 5e-06,
|
| 836 |
+
"loss": 0.7227,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.2740524781341107,
|
| 841 |
+
"grad_norm": 0.7452957502891413,
|
| 842 |
+
"learning_rate": 5e-06,
|
| 843 |
+
"loss": 0.7271,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.293488824101069,
|
| 848 |
+
"grad_norm": 0.730891816162587,
|
| 849 |
+
"learning_rate": 5e-06,
|
| 850 |
+
"loss": 0.7297,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.312925170068027,
|
| 855 |
+
"grad_norm": 0.5422066002537126,
|
| 856 |
+
"learning_rate": 5e-06,
|
| 857 |
+
"loss": 0.7291,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.3323615160349855,
|
| 862 |
+
"grad_norm": 0.5368279161848004,
|
| 863 |
+
"learning_rate": 5e-06,
|
| 864 |
+
"loss": 0.7291,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.3517978620019435,
|
| 869 |
+
"grad_norm": 0.5831776325357405,
|
| 870 |
+
"learning_rate": 5e-06,
|
| 871 |
+
"loss": 0.7299,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.371234207968902,
|
| 876 |
+
"grad_norm": 0.4988880812457934,
|
| 877 |
+
"learning_rate": 5e-06,
|
| 878 |
+
"loss": 0.7286,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.39067055393586,
|
| 883 |
+
"grad_norm": 0.6745820300056689,
|
| 884 |
+
"learning_rate": 5e-06,
|
| 885 |
+
"loss": 0.7246,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.4101068999028183,
|
| 890 |
+
"grad_norm": 0.6502142374990822,
|
| 891 |
+
"learning_rate": 5e-06,
|
| 892 |
+
"loss": 0.7274,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.4295432458697763,
|
| 897 |
+
"grad_norm": 0.6686318012888572,
|
| 898 |
+
"learning_rate": 5e-06,
|
| 899 |
+
"loss": 0.7273,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.4489795918367347,
|
| 904 |
+
"grad_norm": 0.5959741098147713,
|
| 905 |
+
"learning_rate": 5e-06,
|
| 906 |
+
"loss": 0.7296,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.4684159378036927,
|
| 911 |
+
"grad_norm": 0.6933996442905096,
|
| 912 |
+
"learning_rate": 5e-06,
|
| 913 |
+
"loss": 0.7265,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.487852283770651,
|
| 918 |
+
"grad_norm": 0.5220203781381132,
|
| 919 |
+
"learning_rate": 5e-06,
|
| 920 |
+
"loss": 0.7279,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.5072886297376096,
|
| 925 |
+
"grad_norm": 0.5382425321528858,
|
| 926 |
+
"learning_rate": 5e-06,
|
| 927 |
+
"loss": 0.7305,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.5267249757045676,
|
| 932 |
+
"grad_norm": 0.5181218910911854,
|
| 933 |
+
"learning_rate": 5e-06,
|
| 934 |
+
"loss": 0.7249,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.5461613216715255,
|
| 939 |
+
"grad_norm": 0.6478067615615305,
|
| 940 |
+
"learning_rate": 5e-06,
|
| 941 |
+
"loss": 0.7319,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.565597667638484,
|
| 946 |
+
"grad_norm": 0.5078942293566884,
|
| 947 |
+
"learning_rate": 5e-06,
|
| 948 |
+
"loss": 0.7288,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.5850340136054424,
|
| 953 |
+
"grad_norm": 0.6268137880948265,
|
| 954 |
+
"learning_rate": 5e-06,
|
| 955 |
+
"loss": 0.7299,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.6044703595724004,
|
| 960 |
+
"grad_norm": 0.7996921164519973,
|
| 961 |
+
"learning_rate": 5e-06,
|
| 962 |
+
"loss": 0.7332,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.6239067055393583,
|
| 967 |
+
"grad_norm": 0.6835765316105765,
|
| 968 |
+
"learning_rate": 5e-06,
|
| 969 |
+
"loss": 0.7332,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.6433430515063168,
|
| 974 |
+
"grad_norm": 0.6208677881375628,
|
| 975 |
+
"learning_rate": 5e-06,
|
| 976 |
+
"loss": 0.7255,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.662779397473275,
|
| 981 |
+
"grad_norm": 0.5685215567462071,
|
| 982 |
+
"learning_rate": 5e-06,
|
| 983 |
+
"loss": 0.7311,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.682215743440233,
|
| 988 |
+
"grad_norm": 0.502556515949076,
|
| 989 |
+
"learning_rate": 5e-06,
|
| 990 |
+
"loss": 0.7288,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.7016520894071916,
|
| 995 |
+
"grad_norm": 0.5557319329244653,
|
| 996 |
+
"learning_rate": 5e-06,
|
| 997 |
+
"loss": 0.7252,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.7210884353741496,
|
| 1002 |
+
"grad_norm": 0.5681474343567127,
|
| 1003 |
+
"learning_rate": 5e-06,
|
| 1004 |
+
"loss": 0.7324,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.740524781341108,
|
| 1009 |
+
"grad_norm": 0.5718856742663174,
|
| 1010 |
+
"learning_rate": 5e-06,
|
| 1011 |
+
"loss": 0.7314,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.759961127308066,
|
| 1016 |
+
"grad_norm": 0.5207890225289823,
|
| 1017 |
+
"learning_rate": 5e-06,
|
| 1018 |
+
"loss": 0.7327,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.7793974732750244,
|
| 1023 |
+
"grad_norm": 0.5610775317663003,
|
| 1024 |
+
"learning_rate": 5e-06,
|
| 1025 |
+
"loss": 0.7325,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.7988338192419824,
|
| 1030 |
+
"grad_norm": 0.49435740403271333,
|
| 1031 |
+
"learning_rate": 5e-06,
|
| 1032 |
+
"loss": 0.7306,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.818270165208941,
|
| 1037 |
+
"grad_norm": 0.5548340643212172,
|
| 1038 |
+
"learning_rate": 5e-06,
|
| 1039 |
+
"loss": 0.7248,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.837706511175899,
|
| 1044 |
+
"grad_norm": 0.8162943266425523,
|
| 1045 |
+
"learning_rate": 5e-06,
|
| 1046 |
+
"loss": 0.728,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.857142857142857,
|
| 1051 |
+
"grad_norm": 0.5605722072050826,
|
| 1052 |
+
"learning_rate": 5e-06,
|
| 1053 |
+
"loss": 0.7321,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.8765792031098156,
|
| 1058 |
+
"grad_norm": 0.5811312094740239,
|
| 1059 |
+
"learning_rate": 5e-06,
|
| 1060 |
+
"loss": 0.7312,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 2.8960155490767736,
|
| 1065 |
+
"grad_norm": 0.581575144969956,
|
| 1066 |
+
"learning_rate": 5e-06,
|
| 1067 |
+
"loss": 0.7321,
|
| 1068 |
+
"step": 1490
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 2.9154518950437316,
|
| 1072 |
+
"grad_norm": 0.5099095695816087,
|
| 1073 |
+
"learning_rate": 5e-06,
|
| 1074 |
+
"loss": 0.7334,
|
| 1075 |
+
"step": 1500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 2.93488824101069,
|
| 1079 |
+
"grad_norm": 0.5572721217938963,
|
| 1080 |
+
"learning_rate": 5e-06,
|
| 1081 |
+
"loss": 0.7308,
|
| 1082 |
+
"step": 1510
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 2.9543245869776484,
|
| 1086 |
+
"grad_norm": 0.522930114991094,
|
| 1087 |
+
"learning_rate": 5e-06,
|
| 1088 |
+
"loss": 0.7295,
|
| 1089 |
+
"step": 1520
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.9737609329446064,
|
| 1093 |
+
"grad_norm": 0.6436319992243297,
|
| 1094 |
+
"learning_rate": 5e-06,
|
| 1095 |
+
"loss": 0.7331,
|
| 1096 |
+
"step": 1530
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.9931972789115644,
|
| 1100 |
+
"grad_norm": 0.6235339876579238,
|
| 1101 |
+
"learning_rate": 5e-06,
|
| 1102 |
+
"loss": 0.7263,
|
| 1103 |
+
"step": 1540
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.997084548104956,
|
| 1107 |
+
"eval_loss": 0.8005240559577942,
|
| 1108 |
+
"eval_runtime": 550.1116,
|
| 1109 |
+
"eval_samples_per_second": 25.2,
|
| 1110 |
+
"eval_steps_per_second": 0.394,
|
| 1111 |
+
"step": 1542
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 2.997084548104956,
|
| 1115 |
+
"step": 1542,
|
| 1116 |
+
"total_flos": 2582698052812800.0,
|
| 1117 |
+
"train_loss": 0.7834810720498151,
|
| 1118 |
+
"train_runtime": 91136.0835,
|
| 1119 |
+
"train_samples_per_second": 8.67,
|
| 1120 |
+
"train_steps_per_second": 0.017
|
| 1121 |
+
}
|
| 1122 |
+
],
|
| 1123 |
+
"logging_steps": 10,
|
| 1124 |
+
"max_steps": 1542,
|
| 1125 |
+
"num_input_tokens_seen": 0,
|
| 1126 |
+
"num_train_epochs": 3,
|
| 1127 |
+
"save_steps": 500,
|
| 1128 |
+
"stateful_callbacks": {
|
| 1129 |
+
"TrainerControl": {
|
| 1130 |
+
"args": {
|
| 1131 |
+
"should_epoch_stop": false,
|
| 1132 |
+
"should_evaluate": false,
|
| 1133 |
+
"should_log": false,
|
| 1134 |
+
"should_save": true,
|
| 1135 |
+
"should_training_stop": true
|
| 1136 |
+
},
|
| 1137 |
+
"attributes": {}
|
| 1138 |
+
}
|
| 1139 |
+
},
|
| 1140 |
+
"total_flos": 2582698052812800.0,
|
| 1141 |
+
"train_batch_size": 8,
|
| 1142 |
+
"trial_name": null,
|
| 1143 |
+
"trial_params": null
|
| 1144 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|