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 +1360 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: large_crafting_sft_fail
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# large_crafting_sft_fail
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.3223
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: large_crafting_sft_fail
|
|
|
|
| 16 |
|
| 17 |
# large_crafting_sft_fail
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the identity and the large_crafting_sft_fail datasets.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.3223
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995964161756397,
|
| 3 |
+
"eval_loss": 0.32232195138931274,
|
| 4 |
+
"eval_runtime": 111.5863,
|
| 5 |
+
"eval_samples_per_second": 36.259,
|
| 6 |
+
"eval_steps_per_second": 2.267,
|
| 7 |
+
"total_flos": 836493551075328.0,
|
| 8 |
+
"train_loss": 0.4527231248466235,
|
| 9 |
+
"train_runtime": 23130.6046,
|
| 10 |
+
"train_samples_per_second": 8.569,
|
| 11 |
+
"train_steps_per_second": 0.067
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995964161756397,
|
| 3 |
+
"eval_loss": 0.32232195138931274,
|
| 4 |
+
"eval_runtime": 111.5863,
|
| 5 |
+
"eval_samples_per_second": 36.259,
|
| 6 |
+
"eval_steps_per_second": 2.267
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995964161756397,
|
| 3 |
+
"total_flos": 836493551075328.0,
|
| 4 |
+
"train_loss": 0.4527231248466235,
|
| 5 |
+
"train_runtime": 23130.6046,
|
| 6 |
+
"train_samples_per_second": 8.569,
|
| 7 |
+
"train_steps_per_second": 0.067
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1360 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9995964161756397,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 1548,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.006457341189765114,
|
| 13 |
+
"grad_norm": 36.13093813298851,
|
| 14 |
+
"learning_rate": 6.451612903225807e-07,
|
| 15 |
+
"loss": 1.4776,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.012914682379530229,
|
| 20 |
+
"grad_norm": 10.88271660121199,
|
| 21 |
+
"learning_rate": 1.2903225806451614e-06,
|
| 22 |
+
"loss": 1.0088,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.019372023569295342,
|
| 27 |
+
"grad_norm": 8.349376848130536,
|
| 28 |
+
"learning_rate": 1.935483870967742e-06,
|
| 29 |
+
"loss": 0.7032,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.025829364759060457,
|
| 34 |
+
"grad_norm": 7.565511440200043,
|
| 35 |
+
"learning_rate": 2.580645161290323e-06,
|
| 36 |
+
"loss": 0.6113,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03228670594882557,
|
| 41 |
+
"grad_norm": 6.9547450559973605,
|
| 42 |
+
"learning_rate": 3.225806451612903e-06,
|
| 43 |
+
"loss": 0.5429,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03228670594882557,
|
| 48 |
+
"eval_loss": 0.4979822635650635,
|
| 49 |
+
"eval_runtime": 111.9712,
|
| 50 |
+
"eval_samples_per_second": 36.134,
|
| 51 |
+
"eval_steps_per_second": 2.26,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.038744047138590684,
|
| 56 |
+
"grad_norm": 5.37755461346713,
|
| 57 |
+
"learning_rate": 3.870967741935484e-06,
|
| 58 |
+
"loss": 0.5324,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0452013883283558,
|
| 63 |
+
"grad_norm": 5.944625000599463,
|
| 64 |
+
"learning_rate": 4.516129032258065e-06,
|
| 65 |
+
"loss": 0.5465,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.051658729518120915,
|
| 70 |
+
"grad_norm": 5.188224377415384,
|
| 71 |
+
"learning_rate": 5.161290322580646e-06,
|
| 72 |
+
"loss": 0.5395,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.058116070707886026,
|
| 77 |
+
"grad_norm": 5.29650815819046,
|
| 78 |
+
"learning_rate": 5.806451612903226e-06,
|
| 79 |
+
"loss": 0.5142,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.06457341189765115,
|
| 84 |
+
"grad_norm": 5.545565219468533,
|
| 85 |
+
"learning_rate": 6.451612903225806e-06,
|
| 86 |
+
"loss": 0.5398,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06457341189765115,
|
| 91 |
+
"eval_loss": 0.4740481972694397,
|
| 92 |
+
"eval_runtime": 111.8977,
|
| 93 |
+
"eval_samples_per_second": 36.158,
|
| 94 |
+
"eval_steps_per_second": 2.261,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.07103075308741626,
|
| 99 |
+
"grad_norm": 4.49931443330707,
|
| 100 |
+
"learning_rate": 7.096774193548388e-06,
|
| 101 |
+
"loss": 0.5428,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.07748809427718137,
|
| 106 |
+
"grad_norm": 4.966057668727009,
|
| 107 |
+
"learning_rate": 7.741935483870968e-06,
|
| 108 |
+
"loss": 0.5282,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.08394543546694648,
|
| 113 |
+
"grad_norm": 4.829422007611953,
|
| 114 |
+
"learning_rate": 8.387096774193549e-06,
|
| 115 |
+
"loss": 0.559,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.0904027766567116,
|
| 120 |
+
"grad_norm": 5.817474181181473,
|
| 121 |
+
"learning_rate": 9.03225806451613e-06,
|
| 122 |
+
"loss": 0.5582,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.09686011784647672,
|
| 127 |
+
"grad_norm": 8.02692271099152,
|
| 128 |
+
"learning_rate": 9.67741935483871e-06,
|
| 129 |
+
"loss": 0.5484,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.09686011784647672,
|
| 134 |
+
"eval_loss": 0.4832856059074402,
|
| 135 |
+
"eval_runtime": 111.9347,
|
| 136 |
+
"eval_samples_per_second": 36.146,
|
| 137 |
+
"eval_steps_per_second": 2.26,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.10331745903624183,
|
| 142 |
+
"grad_norm": 4.3413736033416725,
|
| 143 |
+
"learning_rate": 9.999682112882774e-06,
|
| 144 |
+
"loss": 0.5607,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.10977480022600694,
|
| 149 |
+
"grad_norm": 4.586183180211225,
|
| 150 |
+
"learning_rate": 9.997139258465151e-06,
|
| 151 |
+
"loss": 0.5586,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.11623214141577205,
|
| 156 |
+
"grad_norm": 4.268945193260488,
|
| 157 |
+
"learning_rate": 9.992054842933846e-06,
|
| 158 |
+
"loss": 0.5564,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.12268948260553716,
|
| 163 |
+
"grad_norm": 3.817348542603216,
|
| 164 |
+
"learning_rate": 9.984431452238968e-06,
|
| 165 |
+
"loss": 0.5253,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.1291468237953023,
|
| 170 |
+
"grad_norm": 3.7920034076935067,
|
| 171 |
+
"learning_rate": 9.974272963661561e-06,
|
| 172 |
+
"loss": 0.5265,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.1291468237953023,
|
| 177 |
+
"eval_loss": 0.47804030776023865,
|
| 178 |
+
"eval_runtime": 111.9585,
|
| 179 |
+
"eval_samples_per_second": 36.138,
|
| 180 |
+
"eval_steps_per_second": 2.26,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.1356041649850674,
|
| 185 |
+
"grad_norm": 3.459834130945297,
|
| 186 |
+
"learning_rate": 9.961584543841625e-06,
|
| 187 |
+
"loss": 0.5329,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.1420615061748325,
|
| 192 |
+
"grad_norm": 3.5341352790273883,
|
| 193 |
+
"learning_rate": 9.946372646150322e-06,
|
| 194 |
+
"loss": 0.5534,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.14851884736459764,
|
| 199 |
+
"grad_norm": 3.6130657979533707,
|
| 200 |
+
"learning_rate": 9.928645007407791e-06,
|
| 201 |
+
"loss": 0.5365,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.15497618855436274,
|
| 206 |
+
"grad_norm": 4.682242996257105,
|
| 207 |
+
"learning_rate": 9.908410643948162e-06,
|
| 208 |
+
"loss": 0.5118,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.16143352974412786,
|
| 213 |
+
"grad_norm": 3.959992480881294,
|
| 214 |
+
"learning_rate": 9.885679847033832e-06,
|
| 215 |
+
"loss": 0.5278,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.16143352974412786,
|
| 220 |
+
"eval_loss": 0.47931385040283203,
|
| 221 |
+
"eval_runtime": 111.8916,
|
| 222 |
+
"eval_samples_per_second": 36.16,
|
| 223 |
+
"eval_steps_per_second": 2.261,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.16789087093389296,
|
| 228 |
+
"grad_norm": 3.7322960692063765,
|
| 229 |
+
"learning_rate": 9.860464177621286e-06,
|
| 230 |
+
"loss": 0.5422,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.1743482121236581,
|
| 235 |
+
"grad_norm": 3.0954290376577713,
|
| 236 |
+
"learning_rate": 9.832776460481162e-06,
|
| 237 |
+
"loss": 0.4994,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.1808055533134232,
|
| 242 |
+
"grad_norm": 3.5660372393672395,
|
| 243 |
+
"learning_rate": 9.802630777675528e-06,
|
| 244 |
+
"loss": 0.5331,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.1872628945031883,
|
| 249 |
+
"grad_norm": 3.5180745275377667,
|
| 250 |
+
"learning_rate": 9.770042461395705e-06,
|
| 251 |
+
"loss": 0.5277,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.19372023569295344,
|
| 256 |
+
"grad_norm": 3.307637994501876,
|
| 257 |
+
"learning_rate": 9.735028086164265e-06,
|
| 258 |
+
"loss": 0.5259,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.19372023569295344,
|
| 263 |
+
"eval_loss": 0.45192769169807434,
|
| 264 |
+
"eval_runtime": 111.9272,
|
| 265 |
+
"eval_samples_per_second": 36.148,
|
| 266 |
+
"eval_steps_per_second": 2.26,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.20017757688271853,
|
| 271 |
+
"grad_norm": 3.618284262141084,
|
| 272 |
+
"learning_rate": 9.697605460405162e-06,
|
| 273 |
+
"loss": 0.5184,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.20663491807248366,
|
| 278 |
+
"grad_norm": 3.961931490949851,
|
| 279 |
+
"learning_rate": 9.657793617386337e-06,
|
| 280 |
+
"loss": 0.5183,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.21309225926224876,
|
| 285 |
+
"grad_norm": 3.3007761861884823,
|
| 286 |
+
"learning_rate": 9.615612805539305e-06,
|
| 287 |
+
"loss": 0.5109,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.21954960045201388,
|
| 292 |
+
"grad_norm": 3.2893563007794673,
|
| 293 |
+
"learning_rate": 9.571084478160763e-06,
|
| 294 |
+
"loss": 0.5056,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.226006941641779,
|
| 299 |
+
"grad_norm": 3.363703184254249,
|
| 300 |
+
"learning_rate": 9.524231282501362e-06,
|
| 301 |
+
"loss": 0.5293,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.226006941641779,
|
| 306 |
+
"eval_loss": 0.4497073292732239,
|
| 307 |
+
"eval_runtime": 111.9003,
|
| 308 |
+
"eval_samples_per_second": 36.157,
|
| 309 |
+
"eval_steps_per_second": 2.261,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.2324642828315441,
|
| 314 |
+
"grad_norm": 3.5950061797093453,
|
| 315 |
+
"learning_rate": 9.475077048247243e-06,
|
| 316 |
+
"loss": 0.4857,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23892162402130923,
|
| 321 |
+
"grad_norm": 4.195317979395103,
|
| 322 |
+
"learning_rate": 9.423646775400186e-06,
|
| 323 |
+
"loss": 0.5132,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.24537896521107433,
|
| 328 |
+
"grad_norm": 3.3932901420797026,
|
| 329 |
+
"learning_rate": 9.369966621562525e-06,
|
| 330 |
+
"loss": 0.494,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2518363064008394,
|
| 335 |
+
"grad_norm": 3.201620850435473,
|
| 336 |
+
"learning_rate": 9.314063888633312e-06,
|
| 337 |
+
"loss": 0.5045,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.2582936475906046,
|
| 342 |
+
"grad_norm": 3.0140805846591756,
|
| 343 |
+
"learning_rate": 9.255967008922475e-06,
|
| 344 |
+
"loss": 0.5098,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.2582936475906046,
|
| 349 |
+
"eval_loss": 0.43027767539024353,
|
| 350 |
+
"eval_runtime": 111.936,
|
| 351 |
+
"eval_samples_per_second": 36.146,
|
| 352 |
+
"eval_steps_per_second": 2.26,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2647509887803697,
|
| 357 |
+
"grad_norm": 2.947263578735693,
|
| 358 |
+
"learning_rate": 9.19570553069006e-06,
|
| 359 |
+
"loss": 0.5018,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.2712083299701348,
|
| 364 |
+
"grad_norm": 3.27976180101635,
|
| 365 |
+
"learning_rate": 9.133310103117891e-06,
|
| 366 |
+
"loss": 0.4794,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.27766567115989993,
|
| 371 |
+
"grad_norm": 3.028690497485754,
|
| 372 |
+
"learning_rate": 9.068812460721296e-06,
|
| 373 |
+
"loss": 0.477,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.284123012349665,
|
| 378 |
+
"grad_norm": 9.22472978885445,
|
| 379 |
+
"learning_rate": 9.002245407208831e-06,
|
| 380 |
+
"loss": 0.5121,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.2905803535394301,
|
| 385 |
+
"grad_norm": 3.2389742570843487,
|
| 386 |
+
"learning_rate": 8.9336427987982e-06,
|
| 387 |
+
"loss": 0.482,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.2905803535394301,
|
| 392 |
+
"eval_loss": 0.4249188303947449,
|
| 393 |
+
"eval_runtime": 111.8946,
|
| 394 |
+
"eval_samples_per_second": 36.159,
|
| 395 |
+
"eval_steps_per_second": 2.261,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.2970376947291953,
|
| 400 |
+
"grad_norm": 2.732994123391758,
|
| 401 |
+
"learning_rate": 8.863039526996891e-06,
|
| 402 |
+
"loss": 0.4717,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.3034950359189604,
|
| 407 |
+
"grad_norm": 3.0988687687698677,
|
| 408 |
+
"learning_rate": 8.790471500856229e-06,
|
| 409 |
+
"loss": 0.4905,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.3099523771087255,
|
| 414 |
+
"grad_norm": 3.0947098221576197,
|
| 415 |
+
"learning_rate": 8.715975628707917e-06,
|
| 416 |
+
"loss": 0.5077,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.31640971829849057,
|
| 421 |
+
"grad_norm": 2.94319414282237,
|
| 422 |
+
"learning_rate": 8.63958979939235e-06,
|
| 423 |
+
"loss": 0.485,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.3228670594882557,
|
| 428 |
+
"grad_norm": 3.16584229914845,
|
| 429 |
+
"learning_rate": 8.56135286298822e-06,
|
| 430 |
+
"loss": 0.4683,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.3228670594882557,
|
| 435 |
+
"eval_loss": 0.4224134683609009,
|
| 436 |
+
"eval_runtime": 111.9514,
|
| 437 |
+
"eval_samples_per_second": 36.141,
|
| 438 |
+
"eval_steps_per_second": 2.26,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.3293244006780208,
|
| 443 |
+
"grad_norm": 2.800609243217591,
|
| 444 |
+
"learning_rate": 8.48130461105324e-06,
|
| 445 |
+
"loss": 0.4983,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.3357817418677859,
|
| 450 |
+
"grad_norm": 3.071948165652889,
|
| 451 |
+
"learning_rate": 8.399485756386038e-06,
|
| 452 |
+
"loss": 0.4568,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.3422390830575511,
|
| 457 |
+
"grad_norm": 3.0648029677410675,
|
| 458 |
+
"learning_rate": 8.315937912319493e-06,
|
| 459 |
+
"loss": 0.47,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.3486964242473162,
|
| 464 |
+
"grad_norm": 2.851989726691387,
|
| 465 |
+
"learning_rate": 8.23070357155605e-06,
|
| 466 |
+
"loss": 0.4703,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.35515376543708127,
|
| 471 |
+
"grad_norm": 3.050910633248402,
|
| 472 |
+
"learning_rate": 8.143826084555809e-06,
|
| 473 |
+
"loss": 0.4572,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.35515376543708127,
|
| 478 |
+
"eval_loss": 0.4135887324810028,
|
| 479 |
+
"eval_runtime": 111.8521,
|
| 480 |
+
"eval_samples_per_second": 36.173,
|
| 481 |
+
"eval_steps_per_second": 2.262,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.3616111066268464,
|
| 486 |
+
"grad_norm": 2.981485417190354,
|
| 487 |
+
"learning_rate": 8.055349637488336e-06,
|
| 488 |
+
"loss": 0.4639,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.3680684478166115,
|
| 493 |
+
"grad_norm": 2.9699353695800745,
|
| 494 |
+
"learning_rate": 7.965319229759435e-06,
|
| 495 |
+
"loss": 0.4606,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.3745257890063766,
|
| 500 |
+
"grad_norm": 2.7984725950234433,
|
| 501 |
+
"learning_rate": 7.873780651124302e-06,
|
| 502 |
+
"loss": 0.4764,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.3809831301961417,
|
| 507 |
+
"grad_norm": 2.616017681487916,
|
| 508 |
+
"learning_rate": 7.78078045839871e-06,
|
| 509 |
+
"loss": 0.4473,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.38744047138590687,
|
| 514 |
+
"grad_norm": 2.826757920966078,
|
| 515 |
+
"learning_rate": 7.686365951780071e-06,
|
| 516 |
+
"loss": 0.456,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.38744047138590687,
|
| 521 |
+
"eval_loss": 0.4034173786640167,
|
| 522 |
+
"eval_runtime": 111.9212,
|
| 523 |
+
"eval_samples_per_second": 36.15,
|
| 524 |
+
"eval_steps_per_second": 2.261,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.39389781257567197,
|
| 529 |
+
"grad_norm": 2.825465317099364,
|
| 530 |
+
"learning_rate": 7.590585150790388e-06,
|
| 531 |
+
"loss": 0.4416,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.40035515376543707,
|
| 536 |
+
"grad_norm": 2.9443179257564385,
|
| 537 |
+
"learning_rate": 7.493486769853383e-06,
|
| 538 |
+
"loss": 0.4652,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.4068124949552022,
|
| 543 |
+
"grad_norm": 2.7289719580286893,
|
| 544 |
+
"learning_rate": 7.39512019351818e-06,
|
| 545 |
+
"loss": 0.4558,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.4132698361449673,
|
| 550 |
+
"grad_norm": 2.66796889335289,
|
| 551 |
+
"learning_rate": 7.295535451342166e-06,
|
| 552 |
+
"loss": 0.4351,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.4197271773347324,
|
| 557 |
+
"grad_norm": 3.07324590421804,
|
| 558 |
+
"learning_rate": 7.194783192445795e-06,
|
| 559 |
+
"loss": 0.4606,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.4197271773347324,
|
| 564 |
+
"eval_loss": 0.39828598499298096,
|
| 565 |
+
"eval_runtime": 111.8888,
|
| 566 |
+
"eval_samples_per_second": 36.161,
|
| 567 |
+
"eval_steps_per_second": 2.261,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.4261845185244975,
|
| 572 |
+
"grad_norm": 2.728311440018257,
|
| 573 |
+
"learning_rate": 7.092914659752286e-06,
|
| 574 |
+
"loss": 0.4533,
|
| 575 |
+
"step": 660
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.43264185971426267,
|
| 579 |
+
"grad_norm": 3.053431956925498,
|
| 580 |
+
"learning_rate": 6.989981663925301e-06,
|
| 581 |
+
"loss": 0.4521,
|
| 582 |
+
"step": 670
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.43909920090402776,
|
| 586 |
+
"grad_norm": 2.692808749624645,
|
| 587 |
+
"learning_rate": 6.886036557017881e-06,
|
| 588 |
+
"loss": 0.4658,
|
| 589 |
+
"step": 680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.44555654209379286,
|
| 593 |
+
"grad_norm": 2.8255493961476144,
|
| 594 |
+
"learning_rate": 6.781132205846019e-06,
|
| 595 |
+
"loss": 0.4476,
|
| 596 |
+
"step": 690
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.452013883283558,
|
| 600 |
+
"grad_norm": 2.9302657855607612,
|
| 601 |
+
"learning_rate": 6.675321965100431e-06,
|
| 602 |
+
"loss": 0.4285,
|
| 603 |
+
"step": 700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.452013883283558,
|
| 607 |
+
"eval_loss": 0.38738012313842773,
|
| 608 |
+
"eval_runtime": 111.8894,
|
| 609 |
+
"eval_samples_per_second": 36.161,
|
| 610 |
+
"eval_steps_per_second": 2.261,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.4584712244733231,
|
| 615 |
+
"grad_norm": 2.81795203028901,
|
| 616 |
+
"learning_rate": 6.568659650210184e-06,
|
| 617 |
+
"loss": 0.4381,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4649285656630882,
|
| 622 |
+
"grad_norm": 2.6773940869357764,
|
| 623 |
+
"learning_rate": 6.461199509972001e-06,
|
| 624 |
+
"loss": 0.4264,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47138590685285336,
|
| 629 |
+
"grad_norm": 2.5004598549233354,
|
| 630 |
+
"learning_rate": 6.35299619895914e-06,
|
| 631 |
+
"loss": 0.4143,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.47784324804261846,
|
| 636 |
+
"grad_norm": 2.8184324008176582,
|
| 637 |
+
"learning_rate": 6.244104749723916e-06,
|
| 638 |
+
"loss": 0.4364,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48430058923238356,
|
| 643 |
+
"grad_norm": 2.7733015055520718,
|
| 644 |
+
"learning_rate": 6.134580544807951e-06,
|
| 645 |
+
"loss": 0.4499,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.48430058923238356,
|
| 650 |
+
"eval_loss": 0.38058942556381226,
|
| 651 |
+
"eval_runtime": 111.8743,
|
| 652 |
+
"eval_samples_per_second": 36.166,
|
| 653 |
+
"eval_steps_per_second": 2.261,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.49075793042214866,
|
| 658 |
+
"grad_norm": 2.678406490336573,
|
| 659 |
+
"learning_rate": 6.024479288574448e-06,
|
| 660 |
+
"loss": 0.4374,
|
| 661 |
+
"step": 760
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.4972152716119138,
|
| 665 |
+
"grad_norm": 2.927553773587219,
|
| 666 |
+
"learning_rate": 5.9138569788767645e-06,
|
| 667 |
+
"loss": 0.4201,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.5036726128016789,
|
| 672 |
+
"grad_norm": 2.9320183431217166,
|
| 673 |
+
"learning_rate": 5.802769878577729e-06,
|
| 674 |
+
"loss": 0.4201,
|
| 675 |
+
"step": 780
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.510129953991444,
|
| 679 |
+
"grad_norm": 2.6304212034468875,
|
| 680 |
+
"learning_rate": 5.691274486934166e-06,
|
| 681 |
+
"loss": 0.4258,
|
| 682 |
+
"step": 790
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5165872951812092,
|
| 686 |
+
"grad_norm": 2.9033619402388475,
|
| 687 |
+
"learning_rate": 5.579427510861194e-06,
|
| 688 |
+
"loss": 0.4198,
|
| 689 |
+
"step": 800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.5165872951812092,
|
| 693 |
+
"eval_loss": 0.36852195858955383,
|
| 694 |
+
"eval_runtime": 111.8939,
|
| 695 |
+
"eval_samples_per_second": 36.159,
|
| 696 |
+
"eval_steps_per_second": 2.261,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.5230446363709742,
|
| 701 |
+
"grad_norm": 2.7380975946416615,
|
| 702 |
+
"learning_rate": 5.4672858360909e-06,
|
| 703 |
+
"loss": 0.4268,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.5295019775607394,
|
| 708 |
+
"grad_norm": 2.6318513335680525,
|
| 709 |
+
"learning_rate": 5.35490649824008e-06,
|
| 710 |
+
"loss": 0.4219,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.5359593187505045,
|
| 715 |
+
"grad_norm": 2.729811496006138,
|
| 716 |
+
"learning_rate": 5.242346653801739e-06,
|
| 717 |
+
"loss": 0.4447,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.5424166599402696,
|
| 722 |
+
"grad_norm": 2.8046958926916123,
|
| 723 |
+
"learning_rate": 5.129663551075109e-06,
|
| 724 |
+
"loss": 0.4225,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.5488740011300347,
|
| 729 |
+
"grad_norm": 2.479851593229805,
|
| 730 |
+
"learning_rate": 5.016914501048988e-06,
|
| 731 |
+
"loss": 0.4208,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.5488740011300347,
|
| 736 |
+
"eval_loss": 0.366115003824234,
|
| 737 |
+
"eval_runtime": 111.9956,
|
| 738 |
+
"eval_samples_per_second": 36.126,
|
| 739 |
+
"eval_steps_per_second": 2.259,
|
| 740 |
+
"step": 850
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.5553313423197999,
|
| 744 |
+
"grad_norm": 2.574977762111032,
|
| 745 |
+
"learning_rate": 4.904156848253184e-06,
|
| 746 |
+
"loss": 0.415,
|
| 747 |
+
"step": 860
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.5617886835095649,
|
| 751 |
+
"grad_norm": 2.918973319415968,
|
| 752 |
+
"learning_rate": 4.791447941592896e-06,
|
| 753 |
+
"loss": 0.4238,
|
| 754 |
+
"step": 870
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.56824602469933,
|
| 758 |
+
"grad_norm": 2.6402399209732863,
|
| 759 |
+
"learning_rate": 4.678845105180886e-06,
|
| 760 |
+
"loss": 0.4075,
|
| 761 |
+
"step": 880
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.5747033658890952,
|
| 765 |
+
"grad_norm": 2.513263276275295,
|
| 766 |
+
"learning_rate": 4.566405609182247e-06,
|
| 767 |
+
"loss": 0.4042,
|
| 768 |
+
"step": 890
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.5811607070788603,
|
| 772 |
+
"grad_norm": 2.407452866472799,
|
| 773 |
+
"learning_rate": 4.454186640686607e-06,
|
| 774 |
+
"loss": 0.4379,
|
| 775 |
+
"step": 900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.5811607070788603,
|
| 779 |
+
"eval_loss": 0.3636697232723236,
|
| 780 |
+
"eval_runtime": 111.939,
|
| 781 |
+
"eval_samples_per_second": 36.145,
|
| 782 |
+
"eval_steps_per_second": 2.26,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.5876180482686254,
|
| 787 |
+
"grad_norm": 2.813924190060926,
|
| 788 |
+
"learning_rate": 4.3422452746226e-06,
|
| 789 |
+
"loss": 0.4009,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.5940753894583906,
|
| 794 |
+
"grad_norm": 2.7536071015362262,
|
| 795 |
+
"learning_rate": 4.230638444729368e-06,
|
| 796 |
+
"loss": 0.4368,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.6005327306481556,
|
| 801 |
+
"grad_norm": 2.7536457081859362,
|
| 802 |
+
"learning_rate": 4.1194229145998795e-06,
|
| 803 |
+
"loss": 0.4047,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.6069900718379208,
|
| 808 |
+
"grad_norm": 2.5417632926155065,
|
| 809 |
+
"learning_rate": 4.008655248810787e-06,
|
| 810 |
+
"loss": 0.3952,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.6134474130276858,
|
| 815 |
+
"grad_norm": 2.539496645334203,
|
| 816 |
+
"learning_rate": 3.898391784153494e-06,
|
| 817 |
+
"loss": 0.4075,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.6134474130276858,
|
| 822 |
+
"eval_loss": 0.3558257520198822,
|
| 823 |
+
"eval_runtime": 111.9665,
|
| 824 |
+
"eval_samples_per_second": 36.136,
|
| 825 |
+
"eval_steps_per_second": 2.26,
|
| 826 |
+
"step": 950
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.619904754217451,
|
| 830 |
+
"grad_norm": 2.6691260702161093,
|
| 831 |
+
"learning_rate": 3.788688600981085e-06,
|
| 832 |
+
"loss": 0.405,
|
| 833 |
+
"step": 960
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.6263620954072161,
|
| 837 |
+
"grad_norm": 2.551402138928399,
|
| 838 |
+
"learning_rate": 3.679601494685679e-06,
|
| 839 |
+
"loss": 0.417,
|
| 840 |
+
"step": 970
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.6328194365969811,
|
| 844 |
+
"grad_norm": 2.5606407585370152,
|
| 845 |
+
"learning_rate": 3.571185947320712e-06,
|
| 846 |
+
"loss": 0.4077,
|
| 847 |
+
"step": 980
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.6392767777867463,
|
| 851 |
+
"grad_norm": 2.6994790732851612,
|
| 852 |
+
"learning_rate": 3.4634970993825854e-06,
|
| 853 |
+
"loss": 0.3983,
|
| 854 |
+
"step": 990
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.6457341189765115,
|
| 858 |
+
"grad_norm": 2.731049592606316,
|
| 859 |
+
"learning_rate": 3.356589721766034e-06,
|
| 860 |
+
"loss": 0.4121,
|
| 861 |
+
"step": 1000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.6457341189765115,
|
| 865 |
+
"eval_loss": 0.35134828090667725,
|
| 866 |
+
"eval_runtime": 111.9125,
|
| 867 |
+
"eval_samples_per_second": 36.153,
|
| 868 |
+
"eval_steps_per_second": 2.261,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.6521914601662765,
|
| 873 |
+
"grad_norm": 2.979542200795537,
|
| 874 |
+
"learning_rate": 3.250518187907469e-06,
|
| 875 |
+
"loss": 0.3869,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.6586488013560416,
|
| 880 |
+
"grad_norm": 2.675413679581036,
|
| 881 |
+
"learning_rate": 3.1453364461304795e-06,
|
| 882 |
+
"loss": 0.3753,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.6651061425458068,
|
| 887 |
+
"grad_norm": 2.6493675186157404,
|
| 888 |
+
"learning_rate": 3.0410979922075344e-06,
|
| 889 |
+
"loss": 0.3915,
|
| 890 |
+
"step": 1030
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.6715634837355718,
|
| 894 |
+
"grad_norm": 2.469295262531258,
|
| 895 |
+
"learning_rate": 2.9378558421518645e-06,
|
| 896 |
+
"loss": 0.4089,
|
| 897 |
+
"step": 1040
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.678020824925337,
|
| 901 |
+
"grad_norm": 2.5114917155985728,
|
| 902 |
+
"learning_rate": 2.835662505253344e-06,
|
| 903 |
+
"loss": 0.4112,
|
| 904 |
+
"step": 1050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.678020824925337,
|
| 908 |
+
"eval_loss": 0.34539544582366943,
|
| 909 |
+
"eval_runtime": 111.9229,
|
| 910 |
+
"eval_samples_per_second": 36.15,
|
| 911 |
+
"eval_steps_per_second": 2.26,
|
| 912 |
+
"step": 1050
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.6844781661151021,
|
| 916 |
+
"grad_norm": 2.685555421636365,
|
| 917 |
+
"learning_rate": 2.7345699573721014e-06,
|
| 918 |
+
"loss": 0.3993,
|
| 919 |
+
"step": 1060
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.6909355073048672,
|
| 923 |
+
"grad_norm": 2.654393738157245,
|
| 924 |
+
"learning_rate": 2.634629614503428e-06,
|
| 925 |
+
"loss": 0.388,
|
| 926 |
+
"step": 1070
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.6973928484946323,
|
| 930 |
+
"grad_norm": 2.617694622896868,
|
| 931 |
+
"learning_rate": 2.5358923066274354e-06,
|
| 932 |
+
"loss": 0.3992,
|
| 933 |
+
"step": 1080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7038501896843975,
|
| 937 |
+
"grad_norm": 2.31267040049805,
|
| 938 |
+
"learning_rate": 2.4384082518567643e-06,
|
| 939 |
+
"loss": 0.3801,
|
| 940 |
+
"step": 1090
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.7103075308741625,
|
| 944 |
+
"grad_norm": 2.569343236018448,
|
| 945 |
+
"learning_rate": 2.3422270308954936e-06,
|
| 946 |
+
"loss": 0.4041,
|
| 947 |
+
"step": 1100
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.7103075308741625,
|
| 951 |
+
"eval_loss": 0.3457443118095398,
|
| 952 |
+
"eval_runtime": 111.8667,
|
| 953 |
+
"eval_samples_per_second": 36.168,
|
| 954 |
+
"eval_steps_per_second": 2.262,
|
| 955 |
+
"step": 1100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.7167648720639277,
|
| 959 |
+
"grad_norm": 2.460336553937589,
|
| 960 |
+
"learning_rate": 2.2473975618222304e-06,
|
| 961 |
+
"loss": 0.3909,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.7232222132536928,
|
| 966 |
+
"grad_norm": 2.5304504216094523,
|
| 967 |
+
"learning_rate": 2.1539680752102217e-06,
|
| 968 |
+
"loss": 0.3952,
|
| 969 |
+
"step": 1120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.7296795544434579,
|
| 973 |
+
"grad_norm": 2.4097797244963077,
|
| 974 |
+
"learning_rate": 2.0619860895971266e-06,
|
| 975 |
+
"loss": 0.3736,
|
| 976 |
+
"step": 1130
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.736136895633223,
|
| 980 |
+
"grad_norm": 2.77218237063129,
|
| 981 |
+
"learning_rate": 1.9714983873169376e-06,
|
| 982 |
+
"loss": 0.4042,
|
| 983 |
+
"step": 1140
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.7425942368229881,
|
| 987 |
+
"grad_norm": 2.3331103182547976,
|
| 988 |
+
"learning_rate": 1.8825509907063328e-06,
|
| 989 |
+
"loss": 0.3852,
|
| 990 |
+
"step": 1150
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.7425942368229881,
|
| 994 |
+
"eval_loss": 0.33838221430778503,
|
| 995 |
+
"eval_runtime": 111.9392,
|
| 996 |
+
"eval_samples_per_second": 36.145,
|
| 997 |
+
"eval_steps_per_second": 2.26,
|
| 998 |
+
"step": 1150
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.7490515780127532,
|
| 1002 |
+
"grad_norm": 3.014561790563234,
|
| 1003 |
+
"learning_rate": 1.7951891386975684e-06,
|
| 1004 |
+
"loss": 0.3756,
|
| 1005 |
+
"step": 1160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.7555089192025184,
|
| 1009 |
+
"grad_norm": 2.4960607171337297,
|
| 1010 |
+
"learning_rate": 1.7094572638098122e-06,
|
| 1011 |
+
"loss": 0.3561,
|
| 1012 |
+
"step": 1170
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.7619662603922834,
|
| 1016 |
+
"grad_norm": 2.3869622987622527,
|
| 1017 |
+
"learning_rate": 1.6253989695506207e-06,
|
| 1018 |
+
"loss": 0.3755,
|
| 1019 |
+
"step": 1180
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.7684236015820486,
|
| 1023 |
+
"grad_norm": 2.431698639338266,
|
| 1024 |
+
"learning_rate": 1.5430570082390545e-06,
|
| 1025 |
+
"loss": 0.3709,
|
| 1026 |
+
"step": 1190
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.7748809427718137,
|
| 1030 |
+
"grad_norm": 2.6565827092298284,
|
| 1031 |
+
"learning_rate": 1.462473259261713e-06,
|
| 1032 |
+
"loss": 0.3656,
|
| 1033 |
+
"step": 1200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.7748809427718137,
|
| 1037 |
+
"eval_loss": 0.33403000235557556,
|
| 1038 |
+
"eval_runtime": 111.9782,
|
| 1039 |
+
"eval_samples_per_second": 36.132,
|
| 1040 |
+
"eval_steps_per_second": 2.259,
|
| 1041 |
+
"step": 1200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.7813382839615788,
|
| 1045 |
+
"grad_norm": 2.678574249364229,
|
| 1046 |
+
"learning_rate": 1.3836887077727424e-06,
|
| 1047 |
+
"loss": 0.3842,
|
| 1048 |
+
"step": 1210
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.7877956251513439,
|
| 1052 |
+
"grad_norm": 2.7547839619954213,
|
| 1053 |
+
"learning_rate": 1.3067434238486527e-06,
|
| 1054 |
+
"loss": 0.3773,
|
| 1055 |
+
"step": 1220
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.7942529663411091,
|
| 1059 |
+
"grad_norm": 2.7583655228352564,
|
| 1060 |
+
"learning_rate": 1.2316765421085513e-06,
|
| 1061 |
+
"loss": 0.3769,
|
| 1062 |
+
"step": 1230
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.8007103075308741,
|
| 1066 |
+
"grad_norm": 2.7630568820041668,
|
| 1067 |
+
"learning_rate": 1.1585262418101468e-06,
|
| 1068 |
+
"loss": 0.3586,
|
| 1069 |
+
"step": 1240
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.8071676487206393,
|
| 1073 |
+
"grad_norm": 2.6227879310348405,
|
| 1074 |
+
"learning_rate": 1.0873297274316568e-06,
|
| 1075 |
+
"loss": 0.384,
|
| 1076 |
+
"step": 1250
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.8071676487206393,
|
| 1080 |
+
"eval_loss": 0.3302658796310425,
|
| 1081 |
+
"eval_runtime": 111.9384,
|
| 1082 |
+
"eval_samples_per_second": 36.145,
|
| 1083 |
+
"eval_steps_per_second": 2.26,
|
| 1084 |
+
"step": 1250
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.8136249899104044,
|
| 1088 |
+
"grad_norm": 2.510577646614575,
|
| 1089 |
+
"learning_rate": 1.0181232097494904e-06,
|
| 1090 |
+
"loss": 0.3816,
|
| 1091 |
+
"step": 1260
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.8200823311001695,
|
| 1095 |
+
"grad_norm": 2.5172171373880627,
|
| 1096 |
+
"learning_rate": 9.509418874213316e-07,
|
| 1097 |
+
"loss": 0.3651,
|
| 1098 |
+
"step": 1270
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.8265396722899346,
|
| 1102 |
+
"grad_norm": 2.4416458810554853,
|
| 1103 |
+
"learning_rate": 8.858199290839859e-07,
|
| 1104 |
+
"loss": 0.3573,
|
| 1105 |
+
"step": 1280
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.8329970134796998,
|
| 1109 |
+
"grad_norm": 2.8967263378458457,
|
| 1110 |
+
"learning_rate": 8.22790455975106e-07,
|
| 1111 |
+
"loss": 0.383,
|
| 1112 |
+
"step": 1290
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.8394543546694648,
|
| 1116 |
+
"grad_norm": 2.525922134184123,
|
| 1117 |
+
"learning_rate": 7.61885525087619e-07,
|
| 1118 |
+
"loss": 0.3605,
|
| 1119 |
+
"step": 1300
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.8394543546694648,
|
| 1123 |
+
"eval_loss": 0.327566921710968,
|
| 1124 |
+
"eval_runtime": 111.9302,
|
| 1125 |
+
"eval_samples_per_second": 36.148,
|
| 1126 |
+
"eval_steps_per_second": 2.26,
|
| 1127 |
+
"step": 1300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.84591169585923,
|
| 1131 |
+
"grad_norm": 2.4695538863228497,
|
| 1132 |
+
"learning_rate": 7.031361128654402e-07,
|
| 1133 |
+
"loss": 0.3508,
|
| 1134 |
+
"step": 1310
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.852369037048995,
|
| 1138 |
+
"grad_norm": 2.6517631021997685,
|
| 1139 |
+
"learning_rate": 6.465720994487523e-07,
|
| 1140 |
+
"loss": 0.3806,
|
| 1141 |
+
"step": 1320
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.8588263782387602,
|
| 1145 |
+
"grad_norm": 2.7621954854306843,
|
| 1146 |
+
"learning_rate": 5.922222534768707e-07,
|
| 1147 |
+
"loss": 0.3838,
|
| 1148 |
+
"step": 1330
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.8652837194285253,
|
| 1152 |
+
"grad_norm": 2.5607471184144077,
|
| 1153 |
+
"learning_rate": 5.401142174564195e-07,
|
| 1154 |
+
"loss": 0.3627,
|
| 1155 |
+
"step": 1340
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.8717410606182904,
|
| 1159 |
+
"grad_norm": 2.595008916816477,
|
| 1160 |
+
"learning_rate": 4.902744937022658e-07,
|
| 1161 |
+
"loss": 0.3593,
|
| 1162 |
+
"step": 1350
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.8717410606182904,
|
| 1166 |
+
"eval_loss": 0.3246610164642334,
|
| 1167 |
+
"eval_runtime": 111.9365,
|
| 1168 |
+
"eval_samples_per_second": 36.145,
|
| 1169 |
+
"eval_steps_per_second": 2.26,
|
| 1170 |
+
"step": 1350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.8781984018080555,
|
| 1174 |
+
"grad_norm": 2.414235664744641,
|
| 1175 |
+
"learning_rate": 4.4272843085835515e-07,
|
| 1176 |
+
"loss": 0.3804,
|
| 1177 |
+
"step": 1360
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.8846557429978207,
|
| 1181 |
+
"grad_norm": 2.419217625399164,
|
| 1182 |
+
"learning_rate": 3.9750021100531e-07,
|
| 1183 |
+
"loss": 0.3764,
|
| 1184 |
+
"step": 1370
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.8911130841875857,
|
| 1188 |
+
"grad_norm": 2.6264090328200225,
|
| 1189 |
+
"learning_rate": 3.546128373613472e-07,
|
| 1190 |
+
"loss": 0.3743,
|
| 1191 |
+
"step": 1380
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.8975704253773509,
|
| 1195 |
+
"grad_norm": 2.707604001939969,
|
| 1196 |
+
"learning_rate": 3.1408812258276575e-07,
|
| 1197 |
+
"loss": 0.3566,
|
| 1198 |
+
"step": 1390
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 0.904027766567116,
|
| 1202 |
+
"grad_norm": 2.622265420891989,
|
| 1203 |
+
"learning_rate": 2.7594667766995933e-07,
|
| 1204 |
+
"loss": 0.3624,
|
| 1205 |
+
"step": 1400
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.904027766567116,
|
| 1209 |
+
"eval_loss": 0.323292076587677,
|
| 1210 |
+
"eval_runtime": 111.9791,
|
| 1211 |
+
"eval_samples_per_second": 36.132,
|
| 1212 |
+
"eval_steps_per_second": 2.259,
|
| 1213 |
+
"step": 1400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.9104851077568811,
|
| 1217 |
+
"grad_norm": 2.6447995971566876,
|
| 1218 |
+
"learning_rate": 2.402079014845943e-07,
|
| 1219 |
+
"loss": 0.3792,
|
| 1220 |
+
"step": 1410
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.9169424489466462,
|
| 1224 |
+
"grad_norm": 2.3016748893365193,
|
| 1225 |
+
"learning_rate": 2.068899708832911e-07,
|
| 1226 |
+
"loss": 0.3812,
|
| 1227 |
+
"step": 1420
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.9233997901364114,
|
| 1231 |
+
"grad_norm": 2.6336324469401697,
|
| 1232 |
+
"learning_rate": 1.7600983147280982e-07,
|
| 1233 |
+
"loss": 0.3579,
|
| 1234 |
+
"step": 1430
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.9298571313261764,
|
| 1238 |
+
"grad_norm": 2.559116903117589,
|
| 1239 |
+
"learning_rate": 1.475831889914642e-07,
|
| 1240 |
+
"loss": 0.3504,
|
| 1241 |
+
"step": 1440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.9363144725159416,
|
| 1245 |
+
"grad_norm": 2.440040379975165,
|
| 1246 |
+
"learning_rate": 1.2162450132113202e-07,
|
| 1247 |
+
"loss": 0.3734,
|
| 1248 |
+
"step": 1450
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.9363144725159416,
|
| 1252 |
+
"eval_loss": 0.3228907585144043,
|
| 1253 |
+
"eval_runtime": 111.9148,
|
| 1254 |
+
"eval_samples_per_second": 36.153,
|
| 1255 |
+
"eval_steps_per_second": 2.261,
|
| 1256 |
+
"step": 1450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.9427718137057067,
|
| 1260 |
+
"grad_norm": 2.444760573532335,
|
| 1261 |
+
"learning_rate": 9.814697113392835e-08,
|
| 1262 |
+
"loss": 0.3687,
|
| 1263 |
+
"step": 1460
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.9492291548954718,
|
| 1267 |
+
"grad_norm": 2.5518514323077888,
|
| 1268 |
+
"learning_rate": 7.716253917728622e-08,
|
| 1269 |
+
"loss": 0.3485,
|
| 1270 |
+
"step": 1470
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.9556864960852369,
|
| 1274 |
+
"grad_norm": 2.3430257341500043,
|
| 1275 |
+
"learning_rate": 5.8681878200850805e-08,
|
| 1276 |
+
"loss": 0.3713,
|
| 1277 |
+
"step": 1480
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.962143837275002,
|
| 1281 |
+
"grad_norm": 2.517063988800139,
|
| 1282 |
+
"learning_rate": 4.27143875282876e-08,
|
| 1283 |
+
"loss": 0.3499,
|
| 1284 |
+
"step": 1490
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.9686011784647671,
|
| 1288 |
+
"grad_norm": 2.4117594779372586,
|
| 1289 |
+
"learning_rate": 2.9268188276757035e-08,
|
| 1290 |
+
"loss": 0.3609,
|
| 1291 |
+
"step": 1500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.9686011784647671,
|
| 1295 |
+
"eval_loss": 0.3223486840724945,
|
| 1296 |
+
"eval_runtime": 111.972,
|
| 1297 |
+
"eval_samples_per_second": 36.134,
|
| 1298 |
+
"eval_steps_per_second": 2.259,
|
| 1299 |
+
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.9750585196545323,
|
| 1303 |
+
"grad_norm": 2.2584672304426157,
|
| 1304 |
+
"learning_rate": 1.8350119226483442e-08,
|
| 1305 |
+
"loss": 0.3609,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.9815158608442973,
|
| 1310 |
+
"grad_norm": 2.4425634500856472,
|
| 1311 |
+
"learning_rate": 9.965733342532925e-09,
|
| 1312 |
+
"loss": 0.4155,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.9879732020340625,
|
| 1317 |
+
"grad_norm": 2.3744660767238868,
|
| 1318 |
+
"learning_rate": 4.119294950558072e-09,
|
| 1319 |
+
"loss": 0.3591,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 0.9944305432238276,
|
| 1324 |
+
"grad_norm": 2.4281464000637336,
|
| 1325 |
+
"learning_rate": 8.137775679456505e-10,
|
| 1326 |
+
"loss": 0.3655,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.9995964161756397,
|
| 1331 |
+
"step": 1548,
|
| 1332 |
+
"total_flos": 836493551075328.0,
|
| 1333 |
+
"train_loss": 0.4527231248466235,
|
| 1334 |
+
"train_runtime": 23130.6046,
|
| 1335 |
+
"train_samples_per_second": 8.569,
|
| 1336 |
+
"train_steps_per_second": 0.067
|
| 1337 |
+
}
|
| 1338 |
+
],
|
| 1339 |
+
"logging_steps": 10,
|
| 1340 |
+
"max_steps": 1548,
|
| 1341 |
+
"num_input_tokens_seen": 0,
|
| 1342 |
+
"num_train_epochs": 1,
|
| 1343 |
+
"save_steps": 500,
|
| 1344 |
+
"stateful_callbacks": {
|
| 1345 |
+
"TrainerControl": {
|
| 1346 |
+
"args": {
|
| 1347 |
+
"should_epoch_stop": false,
|
| 1348 |
+
"should_evaluate": false,
|
| 1349 |
+
"should_log": false,
|
| 1350 |
+
"should_save": true,
|
| 1351 |
+
"should_training_stop": true
|
| 1352 |
+
},
|
| 1353 |
+
"attributes": {}
|
| 1354 |
+
}
|
| 1355 |
+
},
|
| 1356 |
+
"total_flos": 836493551075328.0,
|
| 1357 |
+
"train_batch_size": 1,
|
| 1358 |
+
"trial_name": null,
|
| 1359 |
+
"trial_params": null
|
| 1360 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|