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 +1092 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: obscura-blitz-v0.0.4-qwen-3
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# obscura-blitz-v0.0.4-qwen-3
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.0464
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: obscura-blitz-v0.0.4-qwen-3
|
|
|
|
| 16 |
|
| 17 |
# obscura-blitz-v0.0.4-qwen-3
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) on the obscura_finetune_train dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.0464
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.04641611501574516,
|
| 4 |
+
"eval_runtime": 48.5515,
|
| 5 |
+
"eval_samples_per_second": 4.119,
|
| 6 |
+
"eval_steps_per_second": 4.119,
|
| 7 |
+
"total_flos": 8.093314295223091e+16,
|
| 8 |
+
"train_loss": 0.09125252608899717,
|
| 9 |
+
"train_runtime": 5067.962,
|
| 10 |
+
"train_samples_per_second": 1.065,
|
| 11 |
+
"train_steps_per_second": 0.266
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.04641611501574516,
|
| 4 |
+
"eval_runtime": 48.5515,
|
| 5 |
+
"eval_samples_per_second": 4.119,
|
| 6 |
+
"eval_steps_per_second": 4.119
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 8.093314295223091e+16,
|
| 4 |
+
"train_loss": 0.09125252608899717,
|
| 5 |
+
"train_runtime": 5067.962,
|
| 6 |
+
"train_samples_per_second": 1.065,
|
| 7 |
+
"train_steps_per_second": 0.266
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1092 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 1350,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.022234574763757644,
|
| 14 |
+
"grad_norm": 13.383837699890137,
|
| 15 |
+
"learning_rate": 6.666666666666667e-06,
|
| 16 |
+
"loss": 1.1717,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.04446914952751529,
|
| 21 |
+
"grad_norm": 8.375042915344238,
|
| 22 |
+
"learning_rate": 1.4074074074074075e-05,
|
| 23 |
+
"loss": 0.687,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06670372429127293,
|
| 28 |
+
"grad_norm": 1.584594964981079,
|
| 29 |
+
"learning_rate": 2.148148148148148e-05,
|
| 30 |
+
"loss": 0.3803,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08893829905503058,
|
| 35 |
+
"grad_norm": 0.9581405520439148,
|
| 36 |
+
"learning_rate": 2.8888888888888888e-05,
|
| 37 |
+
"loss": 0.1693,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11117287381878821,
|
| 42 |
+
"grad_norm": 0.6701180338859558,
|
| 43 |
+
"learning_rate": 3.62962962962963e-05,
|
| 44 |
+
"loss": 0.3744,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.13340744858254586,
|
| 49 |
+
"grad_norm": 0.6323037147521973,
|
| 50 |
+
"learning_rate": 4.3703703703703705e-05,
|
| 51 |
+
"loss": 0.1978,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1556420233463035,
|
| 56 |
+
"grad_norm": 0.796017050743103,
|
| 57 |
+
"learning_rate": 5.111111111111111e-05,
|
| 58 |
+
"loss": 0.2044,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.17787659811006115,
|
| 63 |
+
"grad_norm": 0.6810458898544312,
|
| 64 |
+
"learning_rate": 5.851851851851852e-05,
|
| 65 |
+
"loss": 0.1671,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2001111728738188,
|
| 70 |
+
"grad_norm": 0.7922764420509338,
|
| 71 |
+
"learning_rate": 6.592592592592593e-05,
|
| 72 |
+
"loss": 0.2068,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.22234574763757642,
|
| 77 |
+
"grad_norm": 0.8138841986656189,
|
| 78 |
+
"learning_rate": 7.333333333333333e-05,
|
| 79 |
+
"loss": 0.1194,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.22234574763757642,
|
| 84 |
+
"eval_loss": 0.10435345023870468,
|
| 85 |
+
"eval_runtime": 48.2401,
|
| 86 |
+
"eval_samples_per_second": 4.146,
|
| 87 |
+
"eval_steps_per_second": 4.146,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.24458032240133407,
|
| 92 |
+
"grad_norm": 0.6520943641662598,
|
| 93 |
+
"learning_rate": 8.074074074074075e-05,
|
| 94 |
+
"loss": 0.1525,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.2668148971650917,
|
| 99 |
+
"grad_norm": 1.0254029035568237,
|
| 100 |
+
"learning_rate": 8.814814814814815e-05,
|
| 101 |
+
"loss": 0.1429,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.28904947192884933,
|
| 106 |
+
"grad_norm": 0.40128573775291443,
|
| 107 |
+
"learning_rate": 9.555555555555557e-05,
|
| 108 |
+
"loss": 0.1224,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.311284046692607,
|
| 113 |
+
"grad_norm": 0.544367253780365,
|
| 114 |
+
"learning_rate": 9.999732574196451e-05,
|
| 115 |
+
"loss": 0.122,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.33351862145636463,
|
| 120 |
+
"grad_norm": 0.5095152258872986,
|
| 121 |
+
"learning_rate": 9.996724362426075e-05,
|
| 122 |
+
"loss": 0.1241,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.3557531962201223,
|
| 127 |
+
"grad_norm": 0.6605976819992065,
|
| 128 |
+
"learning_rate": 9.990375674425109e-05,
|
| 129 |
+
"loss": 0.0931,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.3779877709838799,
|
| 134 |
+
"grad_norm": 0.6440847516059875,
|
| 135 |
+
"learning_rate": 9.980690754502393e-05,
|
| 136 |
+
"loss": 0.1106,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.4002223457476376,
|
| 141 |
+
"grad_norm": 0.41629621386528015,
|
| 142 |
+
"learning_rate": 9.96767607734863e-05,
|
| 143 |
+
"loss": 0.0995,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.4224569205113952,
|
| 148 |
+
"grad_norm": 0.4533500075340271,
|
| 149 |
+
"learning_rate": 9.951340343707852e-05,
|
| 150 |
+
"loss": 0.1155,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.44469149527515284,
|
| 155 |
+
"grad_norm": 0.33990752696990967,
|
| 156 |
+
"learning_rate": 9.931694474560686e-05,
|
| 157 |
+
"loss": 0.1023,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.44469149527515284,
|
| 162 |
+
"eval_loss": 0.08741892129182816,
|
| 163 |
+
"eval_runtime": 48.1931,
|
| 164 |
+
"eval_samples_per_second": 4.15,
|
| 165 |
+
"eval_steps_per_second": 4.15,
|
| 166 |
+
"step": 200
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.4669260700389105,
|
| 170 |
+
"grad_norm": 0.5338679552078247,
|
| 171 |
+
"learning_rate": 9.908751603823301e-05,
|
| 172 |
+
"loss": 0.1177,
|
| 173 |
+
"step": 210
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.48916064480266813,
|
| 177 |
+
"grad_norm": 0.817176342010498,
|
| 178 |
+
"learning_rate": 9.882527069566965e-05,
|
| 179 |
+
"loss": 0.0899,
|
| 180 |
+
"step": 220
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.5113952195664258,
|
| 184 |
+
"grad_norm": 0.28271085023880005,
|
| 185 |
+
"learning_rate": 9.853038403764021e-05,
|
| 186 |
+
"loss": 0.1285,
|
| 187 |
+
"step": 230
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.5336297943301834,
|
| 191 |
+
"grad_norm": 0.4720575511455536,
|
| 192 |
+
"learning_rate": 9.820305320567192e-05,
|
| 193 |
+
"loss": 0.116,
|
| 194 |
+
"step": 240
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.5558643690939411,
|
| 198 |
+
"grad_norm": 0.2770315706729889,
|
| 199 |
+
"learning_rate": 9.784349703130007e-05,
|
| 200 |
+
"loss": 0.1355,
|
| 201 |
+
"step": 250
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.5780989438576987,
|
| 205 |
+
"grad_norm": 0.45048788189888,
|
| 206 |
+
"learning_rate": 9.745195588977192e-05,
|
| 207 |
+
"loss": 0.1187,
|
| 208 |
+
"step": 260
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.6003335186214563,
|
| 212 |
+
"grad_norm": 0.3435899317264557,
|
| 213 |
+
"learning_rate": 9.702869153934782e-05,
|
| 214 |
+
"loss": 0.1505,
|
| 215 |
+
"step": 270
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.622568093385214,
|
| 219 |
+
"grad_norm": 0.47825339436531067,
|
| 220 |
+
"learning_rate": 9.657398694630712e-05,
|
| 221 |
+
"loss": 0.113,
|
| 222 |
+
"step": 280
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.6448026681489717,
|
| 226 |
+
"grad_norm": 0.19181689620018005,
|
| 227 |
+
"learning_rate": 9.608814609577585e-05,
|
| 228 |
+
"loss": 0.0761,
|
| 229 |
+
"step": 290
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.6670372429127293,
|
| 233 |
+
"grad_norm": 0.2734505832195282,
|
| 234 |
+
"learning_rate": 9.557149378850254e-05,
|
| 235 |
+
"loss": 0.0873,
|
| 236 |
+
"step": 300
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.6670372429127293,
|
| 240 |
+
"eval_loss": 0.07399436831474304,
|
| 241 |
+
"eval_runtime": 48.0939,
|
| 242 |
+
"eval_samples_per_second": 4.159,
|
| 243 |
+
"eval_steps_per_second": 4.159,
|
| 244 |
+
"step": 300
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.6892718176764869,
|
| 248 |
+
"grad_norm": 0.438323050737381,
|
| 249 |
+
"learning_rate": 9.502437542371812e-05,
|
| 250 |
+
"loss": 0.105,
|
| 251 |
+
"step": 310
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.7115063924402446,
|
| 255 |
+
"grad_norm": 0.694514274597168,
|
| 256 |
+
"learning_rate": 9.444715676822501e-05,
|
| 257 |
+
"loss": 0.1134,
|
| 258 |
+
"step": 320
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.7337409672040022,
|
| 262 |
+
"grad_norm": 0.5426012277603149,
|
| 263 |
+
"learning_rate": 9.384022371187003e-05,
|
| 264 |
+
"loss": 0.1102,
|
| 265 |
+
"step": 330
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.7559755419677598,
|
| 269 |
+
"grad_norm": 0.38747844099998474,
|
| 270 |
+
"learning_rate": 9.320398200956403e-05,
|
| 271 |
+
"loss": 0.0883,
|
| 272 |
+
"step": 340
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.7782101167315175,
|
| 276 |
+
"grad_norm": 0.33049455285072327,
|
| 277 |
+
"learning_rate": 9.253885701002134e-05,
|
| 278 |
+
"loss": 0.1114,
|
| 279 |
+
"step": 350
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.8004446914952752,
|
| 283 |
+
"grad_norm": 0.2674323320388794,
|
| 284 |
+
"learning_rate": 9.184529337140002e-05,
|
| 285 |
+
"loss": 0.0803,
|
| 286 |
+
"step": 360
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.8226792662590328,
|
| 290 |
+
"grad_norm": 0.31980791687965393,
|
| 291 |
+
"learning_rate": 9.112375476403312e-05,
|
| 292 |
+
"loss": 0.1024,
|
| 293 |
+
"step": 370
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.8449138410227904,
|
| 297 |
+
"grad_norm": 0.15382544696331024,
|
| 298 |
+
"learning_rate": 9.037472356044962e-05,
|
| 299 |
+
"loss": 0.0588,
|
| 300 |
+
"step": 380
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.8671484157865481,
|
| 304 |
+
"grad_norm": 0.23380494117736816,
|
| 305 |
+
"learning_rate": 8.959870051289241e-05,
|
| 306 |
+
"loss": 0.0549,
|
| 307 |
+
"step": 390
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.8893829905503057,
|
| 311 |
+
"grad_norm": 0.2885076105594635,
|
| 312 |
+
"learning_rate": 8.879620441854872e-05,
|
| 313 |
+
"loss": 0.1051,
|
| 314 |
+
"step": 400
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.8893829905503057,
|
| 318 |
+
"eval_loss": 0.06723224371671677,
|
| 319 |
+
"eval_runtime": 48.2096,
|
| 320 |
+
"eval_samples_per_second": 4.149,
|
| 321 |
+
"eval_steps_per_second": 4.149,
|
| 322 |
+
"step": 400
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.9116175653140633,
|
| 326 |
+
"grad_norm": 0.3105609714984894,
|
| 327 |
+
"learning_rate": 8.796777177271708e-05,
|
| 328 |
+
"loss": 0.0823,
|
| 329 |
+
"step": 410
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.933852140077821,
|
| 333 |
+
"grad_norm": 0.4871651828289032,
|
| 334 |
+
"learning_rate": 8.711395641014228e-05,
|
| 335 |
+
"loss": 0.095,
|
| 336 |
+
"step": 420
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.9560867148415787,
|
| 340 |
+
"grad_norm": 0.34139370918273926,
|
| 341 |
+
"learning_rate": 8.623532913475847e-05,
|
| 342 |
+
"loss": 0.0742,
|
| 343 |
+
"step": 430
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.9783212896053363,
|
| 347 |
+
"grad_norm": 0.1284688413143158,
|
| 348 |
+
"learning_rate": 8.533247733808776e-05,
|
| 349 |
+
"loss": 0.074,
|
| 350 |
+
"step": 440
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.0,
|
| 354 |
+
"grad_norm": 0.15243172645568848,
|
| 355 |
+
"learning_rate": 8.440600460654958e-05,
|
| 356 |
+
"loss": 0.1033,
|
| 357 |
+
"step": 450
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.0222345747637576,
|
| 361 |
+
"grad_norm": 0.29170939326286316,
|
| 362 |
+
"learning_rate": 8.345653031794292e-05,
|
| 363 |
+
"loss": 0.0786,
|
| 364 |
+
"step": 460
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.0444691495275154,
|
| 368 |
+
"grad_norm": 0.1913299411535263,
|
| 369 |
+
"learning_rate": 8.248468922737188e-05,
|
| 370 |
+
"loss": 0.0568,
|
| 371 |
+
"step": 470
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.066703724291273,
|
| 375 |
+
"grad_norm": 0.38078683614730835,
|
| 376 |
+
"learning_rate": 8.149113104289063e-05,
|
| 377 |
+
"loss": 0.0809,
|
| 378 |
+
"step": 480
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.0889382990550305,
|
| 382 |
+
"grad_norm": 0.38182222843170166,
|
| 383 |
+
"learning_rate": 8.047651999115217e-05,
|
| 384 |
+
"loss": 0.0758,
|
| 385 |
+
"step": 490
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 1.1111728738187883,
|
| 389 |
+
"grad_norm": 0.13781729340553284,
|
| 390 |
+
"learning_rate": 7.944153437335057e-05,
|
| 391 |
+
"loss": 0.0636,
|
| 392 |
+
"step": 500
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.1111728738187883,
|
| 396 |
+
"eval_loss": 0.06643614917993546,
|
| 397 |
+
"eval_runtime": 48.2161,
|
| 398 |
+
"eval_samples_per_second": 4.148,
|
| 399 |
+
"eval_steps_per_second": 4.148,
|
| 400 |
+
"step": 500
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.1334074485825458,
|
| 404 |
+
"grad_norm": 0.06484173983335495,
|
| 405 |
+
"learning_rate": 7.838686611175421e-05,
|
| 406 |
+
"loss": 0.068,
|
| 407 |
+
"step": 510
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.1556420233463034,
|
| 411 |
+
"grad_norm": 0.34467655420303345,
|
| 412 |
+
"learning_rate": 7.73132202871327e-05,
|
| 413 |
+
"loss": 0.0778,
|
| 414 |
+
"step": 520
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.1778765981100612,
|
| 418 |
+
"grad_norm": 0.35296931862831116,
|
| 419 |
+
"learning_rate": 7.6221314667387e-05,
|
| 420 |
+
"loss": 0.0796,
|
| 421 |
+
"step": 530
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.2001111728738187,
|
| 425 |
+
"grad_norm": 0.09108947217464447,
|
| 426 |
+
"learning_rate": 7.511187922769768e-05,
|
| 427 |
+
"loss": 0.0643,
|
| 428 |
+
"step": 540
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.2223457476375765,
|
| 432 |
+
"grad_norm": 0.3470743000507355,
|
| 433 |
+
"learning_rate": 7.398565566251232e-05,
|
| 434 |
+
"loss": 0.0716,
|
| 435 |
+
"step": 550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.244580322401334,
|
| 439 |
+
"grad_norm": 0.23976042866706848,
|
| 440 |
+
"learning_rate": 7.284339688969809e-05,
|
| 441 |
+
"loss": 0.051,
|
| 442 |
+
"step": 560
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.2668148971650917,
|
| 446 |
+
"grad_norm": 0.36250776052474976,
|
| 447 |
+
"learning_rate": 7.168586654719117e-05,
|
| 448 |
+
"loss": 0.0608,
|
| 449 |
+
"step": 570
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.2890494719288492,
|
| 453 |
+
"grad_norm": 0.31230035424232483,
|
| 454 |
+
"learning_rate": 7.051383848247942e-05,
|
| 455 |
+
"loss": 0.0565,
|
| 456 |
+
"step": 580
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.311284046692607,
|
| 460 |
+
"grad_norm": 0.22365595400333405,
|
| 461 |
+
"learning_rate": 6.932809623525957e-05,
|
| 462 |
+
"loss": 0.0735,
|
| 463 |
+
"step": 590
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 1.3335186214563646,
|
| 467 |
+
"grad_norm": 0.26981058716773987,
|
| 468 |
+
"learning_rate": 6.812943251361505e-05,
|
| 469 |
+
"loss": 0.072,
|
| 470 |
+
"step": 600
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.3335186214563646,
|
| 474 |
+
"eval_loss": 0.06549877673387527,
|
| 475 |
+
"eval_runtime": 48.2581,
|
| 476 |
+
"eval_samples_per_second": 4.144,
|
| 477 |
+
"eval_steps_per_second": 4.144,
|
| 478 |
+
"step": 600
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.3557531962201224,
|
| 482 |
+
"grad_norm": 0.3754810690879822,
|
| 483 |
+
"learning_rate": 6.691864866406407e-05,
|
| 484 |
+
"loss": 0.0678,
|
| 485 |
+
"step": 610
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.37798777098388,
|
| 489 |
+
"grad_norm": 0.31102293729782104,
|
| 490 |
+
"learning_rate": 6.569655413583306e-05,
|
| 491 |
+
"loss": 0.0946,
|
| 492 |
+
"step": 620
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.4002223457476375,
|
| 496 |
+
"grad_norm": 0.2776915729045868,
|
| 497 |
+
"learning_rate": 6.446396593971294e-05,
|
| 498 |
+
"loss": 0.0649,
|
| 499 |
+
"step": 630
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.4224569205113953,
|
| 503 |
+
"grad_norm": 0.5137710571289062,
|
| 504 |
+
"learning_rate": 6.322170810186012e-05,
|
| 505 |
+
"loss": 0.0718,
|
| 506 |
+
"step": 640
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.4446914952751528,
|
| 510 |
+
"grad_norm": 0.255832314491272,
|
| 511 |
+
"learning_rate": 6.197061111290779e-05,
|
| 512 |
+
"loss": 0.0705,
|
| 513 |
+
"step": 650
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.4669260700389106,
|
| 517 |
+
"grad_norm": 0.19154119491577148,
|
| 518 |
+
"learning_rate": 6.07115113727553e-05,
|
| 519 |
+
"loss": 0.0682,
|
| 520 |
+
"step": 660
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.4891606448026682,
|
| 524 |
+
"grad_norm": 0.2686958909034729,
|
| 525 |
+
"learning_rate": 5.9445250631407024e-05,
|
| 526 |
+
"loss": 0.081,
|
| 527 |
+
"step": 670
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.5113952195664258,
|
| 531 |
+
"grad_norm": 0.31166499853134155,
|
| 532 |
+
"learning_rate": 5.817267542623451e-05,
|
| 533 |
+
"loss": 0.0574,
|
| 534 |
+
"step": 680
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.5336297943301833,
|
| 538 |
+
"grad_norm": 0.22264094650745392,
|
| 539 |
+
"learning_rate": 5.689463651603818e-05,
|
| 540 |
+
"loss": 0.0513,
|
| 541 |
+
"step": 690
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.555864369093941,
|
| 545 |
+
"grad_norm": 0.23241780698299408,
|
| 546 |
+
"learning_rate": 5.561198831228675e-05,
|
| 547 |
+
"loss": 0.0807,
|
| 548 |
+
"step": 700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.555864369093941,
|
| 552 |
+
"eval_loss": 0.05730433017015457,
|
| 553 |
+
"eval_runtime": 48.1316,
|
| 554 |
+
"eval_samples_per_second": 4.155,
|
| 555 |
+
"eval_steps_per_second": 4.155,
|
| 556 |
+
"step": 700
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.5780989438576987,
|
| 560 |
+
"grad_norm": 0.36841678619384766,
|
| 561 |
+
"learning_rate": 5.432558830791479e-05,
|
| 562 |
+
"loss": 0.0601,
|
| 563 |
+
"step": 710
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.6003335186214565,
|
| 567 |
+
"grad_norm": 0.20728759467601776,
|
| 568 |
+
"learning_rate": 5.3036296504060235e-05,
|
| 569 |
+
"loss": 0.0841,
|
| 570 |
+
"step": 720
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.622568093385214,
|
| 574 |
+
"grad_norm": 0.10159023851156235,
|
| 575 |
+
"learning_rate": 5.174497483512506e-05,
|
| 576 |
+
"loss": 0.042,
|
| 577 |
+
"step": 730
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.6448026681489716,
|
| 581 |
+
"grad_norm": 0.31575503945350647,
|
| 582 |
+
"learning_rate": 5.045248659254344e-05,
|
| 583 |
+
"loss": 0.0829,
|
| 584 |
+
"step": 740
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.6670372429127291,
|
| 588 |
+
"grad_norm": 0.1763896644115448,
|
| 589 |
+
"learning_rate": 4.915969584764282e-05,
|
| 590 |
+
"loss": 0.0893,
|
| 591 |
+
"step": 750
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.689271817676487,
|
| 595 |
+
"grad_norm": 0.3741007447242737,
|
| 596 |
+
"learning_rate": 4.7867466873983464e-05,
|
| 597 |
+
"loss": 0.0694,
|
| 598 |
+
"step": 760
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.7115063924402447,
|
| 602 |
+
"grad_norm": 0.28057777881622314,
|
| 603 |
+
"learning_rate": 4.657666356956296e-05,
|
| 604 |
+
"loss": 0.0499,
|
| 605 |
+
"step": 770
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.7337409672040023,
|
| 609 |
+
"grad_norm": 0.23745323717594147,
|
| 610 |
+
"learning_rate": 4.528814887927157e-05,
|
| 611 |
+
"loss": 0.063,
|
| 612 |
+
"step": 780
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.7559755419677598,
|
| 616 |
+
"grad_norm": 0.22828607261180878,
|
| 617 |
+
"learning_rate": 4.400278421798501e-05,
|
| 618 |
+
"loss": 0.0623,
|
| 619 |
+
"step": 790
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.7782101167315174,
|
| 623 |
+
"grad_norm": 0.35160404443740845,
|
| 624 |
+
"learning_rate": 4.272142889468002e-05,
|
| 625 |
+
"loss": 0.0536,
|
| 626 |
+
"step": 800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.7782101167315174,
|
| 630 |
+
"eval_loss": 0.05802774429321289,
|
| 631 |
+
"eval_runtime": 48.2104,
|
| 632 |
+
"eval_samples_per_second": 4.148,
|
| 633 |
+
"eval_steps_per_second": 4.148,
|
| 634 |
+
"step": 800
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.8004446914952752,
|
| 638 |
+
"grad_norm": 0.30460554361343384,
|
| 639 |
+
"learning_rate": 4.144493953795759e-05,
|
| 640 |
+
"loss": 0.074,
|
| 641 |
+
"step": 810
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.8226792662590328,
|
| 645 |
+
"grad_norm": 0.1435527503490448,
|
| 646 |
+
"learning_rate": 4.017416952335849e-05,
|
| 647 |
+
"loss": 0.0576,
|
| 648 |
+
"step": 820
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.8449138410227905,
|
| 652 |
+
"grad_norm": 0.13923799991607666,
|
| 653 |
+
"learning_rate": 3.890996840285328e-05,
|
| 654 |
+
"loss": 0.0441,
|
| 655 |
+
"step": 830
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.867148415786548,
|
| 659 |
+
"grad_norm": 0.2655491232872009,
|
| 660 |
+
"learning_rate": 3.765318133688853e-05,
|
| 661 |
+
"loss": 0.0779,
|
| 662 |
+
"step": 840
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 1.8893829905503057,
|
| 666 |
+
"grad_norm": 0.2776850759983063,
|
| 667 |
+
"learning_rate": 3.640464852936909e-05,
|
| 668 |
+
"loss": 0.0552,
|
| 669 |
+
"step": 850
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.9116175653140632,
|
| 673 |
+
"grad_norm": 0.10389228910207748,
|
| 674 |
+
"learning_rate": 3.5165204665953875e-05,
|
| 675 |
+
"loss": 0.0545,
|
| 676 |
+
"step": 860
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.933852140077821,
|
| 680 |
+
"grad_norm": 0.17789633572101593,
|
| 681 |
+
"learning_rate": 3.393567835604063e-05,
|
| 682 |
+
"loss": 0.0647,
|
| 683 |
+
"step": 870
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.9560867148415788,
|
| 687 |
+
"grad_norm": 0.19800323247909546,
|
| 688 |
+
"learning_rate": 3.271689157881317e-05,
|
| 689 |
+
"loss": 0.0728,
|
| 690 |
+
"step": 880
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.9783212896053364,
|
| 694 |
+
"grad_norm": 0.33102431893348694,
|
| 695 |
+
"learning_rate": 3.150965913372095e-05,
|
| 696 |
+
"loss": 0.0566,
|
| 697 |
+
"step": 890
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.0,
|
| 701 |
+
"grad_norm": 0.31623104214668274,
|
| 702 |
+
"learning_rate": 3.031478809575852e-05,
|
| 703 |
+
"loss": 0.0453,
|
| 704 |
+
"step": 900
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.0,
|
| 708 |
+
"eval_loss": 0.0510103702545166,
|
| 709 |
+
"eval_runtime": 48.2625,
|
| 710 |
+
"eval_samples_per_second": 4.144,
|
| 711 |
+
"eval_steps_per_second": 4.144,
|
| 712 |
+
"step": 900
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.0222345747637576,
|
| 716 |
+
"grad_norm": 0.190277099609375,
|
| 717 |
+
"learning_rate": 2.9133077275909108e-05,
|
| 718 |
+
"loss": 0.0461,
|
| 719 |
+
"step": 910
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 2.044469149527515,
|
| 723 |
+
"grad_norm": 0.30117812752723694,
|
| 724 |
+
"learning_rate": 2.7965316687112976e-05,
|
| 725 |
+
"loss": 0.0457,
|
| 726 |
+
"step": 920
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 2.066703724291273,
|
| 730 |
+
"grad_norm": 0.22665348649024963,
|
| 731 |
+
"learning_rate": 2.6812287016117477e-05,
|
| 732 |
+
"loss": 0.0416,
|
| 733 |
+
"step": 930
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 2.0889382990550307,
|
| 737 |
+
"grad_norm": 0.26945072412490845,
|
| 738 |
+
"learning_rate": 2.5674759101562006e-05,
|
| 739 |
+
"loss": 0.0492,
|
| 740 |
+
"step": 940
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.1111728738187883,
|
| 744 |
+
"grad_norm": 0.20119303464889526,
|
| 745 |
+
"learning_rate": 2.455349341864685e-05,
|
| 746 |
+
"loss": 0.0506,
|
| 747 |
+
"step": 950
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.133407448582546,
|
| 751 |
+
"grad_norm": 0.16967110335826874,
|
| 752 |
+
"learning_rate": 2.344923957073021e-05,
|
| 753 |
+
"loss": 0.0438,
|
| 754 |
+
"step": 960
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 2.1556420233463034,
|
| 758 |
+
"grad_norm": 0.17140169441699982,
|
| 759 |
+
"learning_rate": 2.2362735788193367e-05,
|
| 760 |
+
"loss": 0.0337,
|
| 761 |
+
"step": 970
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.177876598110061,
|
| 765 |
+
"grad_norm": 0.22932595014572144,
|
| 766 |
+
"learning_rate": 2.129470843490932e-05,
|
| 767 |
+
"loss": 0.0539,
|
| 768 |
+
"step": 980
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 2.200111172873819,
|
| 772 |
+
"grad_norm": 0.24180778861045837,
|
| 773 |
+
"learning_rate": 2.024587152264428e-05,
|
| 774 |
+
"loss": 0.0317,
|
| 775 |
+
"step": 990
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.2223457476375765,
|
| 779 |
+
"grad_norm": 0.4643738865852356,
|
| 780 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 781 |
+
"loss": 0.0469,
|
| 782 |
+
"step": 1000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.2223457476375765,
|
| 786 |
+
"eval_loss": 0.048854030668735504,
|
| 787 |
+
"eval_runtime": 48.1955,
|
| 788 |
+
"eval_samples_per_second": 4.15,
|
| 789 |
+
"eval_steps_per_second": 4.15,
|
| 790 |
+
"step": 1000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 2.244580322401334,
|
| 794 |
+
"grad_norm": 0.266984224319458,
|
| 795 |
+
"learning_rate": 1.8208560452235625e-05,
|
| 796 |
+
"loss": 0.0614,
|
| 797 |
+
"step": 1010
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 2.2668148971650917,
|
| 801 |
+
"grad_norm": 0.24567271769046783,
|
| 802 |
+
"learning_rate": 1.7221448304223327e-05,
|
| 803 |
+
"loss": 0.0385,
|
| 804 |
+
"step": 1020
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 2.289049471928849,
|
| 808 |
+
"grad_norm": 0.15998658537864685,
|
| 809 |
+
"learning_rate": 1.6256249706943628e-05,
|
| 810 |
+
"loss": 0.0482,
|
| 811 |
+
"step": 1030
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 2.311284046692607,
|
| 815 |
+
"grad_norm": 0.2101755291223526,
|
| 816 |
+
"learning_rate": 1.5313609927723332e-05,
|
| 817 |
+
"loss": 0.0419,
|
| 818 |
+
"step": 1040
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.333518621456365,
|
| 822 |
+
"grad_norm": 0.10369472205638885,
|
| 823 |
+
"learning_rate": 1.4394159152569903e-05,
|
| 824 |
+
"loss": 0.0248,
|
| 825 |
+
"step": 1050
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.3557531962201224,
|
| 829 |
+
"grad_norm": 0.3291586637496948,
|
| 830 |
+
"learning_rate": 1.3498512064871271e-05,
|
| 831 |
+
"loss": 0.0611,
|
| 832 |
+
"step": 1060
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 2.37798777098388,
|
| 836 |
+
"grad_norm": 0.5122426748275757,
|
| 837 |
+
"learning_rate": 1.262726743445954e-05,
|
| 838 |
+
"loss": 0.0628,
|
| 839 |
+
"step": 1070
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 2.4002223457476375,
|
| 843 |
+
"grad_norm": 0.1757289469242096,
|
| 844 |
+
"learning_rate": 1.178100771731339e-05,
|
| 845 |
+
"loss": 0.0414,
|
| 846 |
+
"step": 1080
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 2.422456920511395,
|
| 850 |
+
"grad_norm": 0.3590919077396393,
|
| 851 |
+
"learning_rate": 1.096029866616704e-05,
|
| 852 |
+
"loss": 0.0349,
|
| 853 |
+
"step": 1090
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 2.444691495275153,
|
| 857 |
+
"grad_norm": 0.21179239451885223,
|
| 858 |
+
"learning_rate": 1.0165688952285651e-05,
|
| 859 |
+
"loss": 0.0318,
|
| 860 |
+
"step": 1100
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 2.444691495275153,
|
| 864 |
+
"eval_loss": 0.048208702355623245,
|
| 865 |
+
"eval_runtime": 48.1747,
|
| 866 |
+
"eval_samples_per_second": 4.152,
|
| 867 |
+
"eval_steps_per_second": 4.152,
|
| 868 |
+
"step": 1100
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.4669260700389106,
|
| 872 |
+
"grad_norm": 0.2429758608341217,
|
| 873 |
+
"learning_rate": 9.397709798660359e-06,
|
| 874 |
+
"loss": 0.0389,
|
| 875 |
+
"step": 1110
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 2.489160644802668,
|
| 879 |
+
"grad_norm": 0.3247833251953125,
|
| 880 |
+
"learning_rate": 8.656874624868134e-06,
|
| 881 |
+
"loss": 0.0474,
|
| 882 |
+
"step": 1120
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 2.5113952195664258,
|
| 886 |
+
"grad_norm": 0.20058025419712067,
|
| 887 |
+
"learning_rate": 7.943678703833657e-06,
|
| 888 |
+
"loss": 0.0446,
|
| 889 |
+
"step": 1130
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 2.5336297943301833,
|
| 893 |
+
"grad_norm": 0.22172123193740845,
|
| 894 |
+
"learning_rate": 7.258598830722946e-06,
|
| 895 |
+
"loss": 0.0429,
|
| 896 |
+
"step": 1140
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.555864369093941,
|
| 900 |
+
"grad_norm": 0.3664150834083557,
|
| 901 |
+
"learning_rate": 6.6020930041899635e-06,
|
| 902 |
+
"loss": 0.0487,
|
| 903 |
+
"step": 1150
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 2.5780989438576984,
|
| 907 |
+
"grad_norm": 0.13659419119358063,
|
| 908 |
+
"learning_rate": 5.974600120189289e-06,
|
| 909 |
+
"loss": 0.0438,
|
| 910 |
+
"step": 1160
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 2.6003335186214565,
|
| 914 |
+
"grad_norm": 0.18766269087791443,
|
| 915 |
+
"learning_rate": 5.376539678559567e-06,
|
| 916 |
+
"loss": 0.0385,
|
| 917 |
+
"step": 1170
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 2.622568093385214,
|
| 921 |
+
"grad_norm": 0.24047650396823883,
|
| 922 |
+
"learning_rate": 4.8083115025739756e-06,
|
| 923 |
+
"loss": 0.0413,
|
| 924 |
+
"step": 1180
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 2.6448026681489716,
|
| 928 |
+
"grad_norm": 0.10476374626159668,
|
| 929 |
+
"learning_rate": 4.270295471645064e-06,
|
| 930 |
+
"loss": 0.0426,
|
| 931 |
+
"step": 1190
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 2.667037242912729,
|
| 935 |
+
"grad_norm": 0.3628266155719757,
|
| 936 |
+
"learning_rate": 3.7628512673627215e-06,
|
| 937 |
+
"loss": 0.0527,
|
| 938 |
+
"step": 1200
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 2.667037242912729,
|
| 942 |
+
"eval_loss": 0.04677248001098633,
|
| 943 |
+
"eval_runtime": 48.3089,
|
| 944 |
+
"eval_samples_per_second": 4.14,
|
| 945 |
+
"eval_steps_per_second": 4.14,
|
| 946 |
+
"step": 1200
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.689271817676487,
|
| 950 |
+
"grad_norm": 0.2052982747554779,
|
| 951 |
+
"learning_rate": 3.286318133035132e-06,
|
| 952 |
+
"loss": 0.0394,
|
| 953 |
+
"step": 1210
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 2.7115063924402447,
|
| 957 |
+
"grad_norm": 0.14959484338760376,
|
| 958 |
+
"learning_rate": 2.8410146468933364e-06,
|
| 959 |
+
"loss": 0.0351,
|
| 960 |
+
"step": 1220
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 2.7337409672040023,
|
| 964 |
+
"grad_norm": 0.17867030203342438,
|
| 965 |
+
"learning_rate": 2.4272385091110516e-06,
|
| 966 |
+
"loss": 0.0465,
|
| 967 |
+
"step": 1230
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 2.75597554196776,
|
| 971 |
+
"grad_norm": 0.2831536531448364,
|
| 972 |
+
"learning_rate": 2.0452663427823093e-06,
|
| 973 |
+
"loss": 0.0487,
|
| 974 |
+
"step": 1240
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.7782101167315174,
|
| 978 |
+
"grad_norm": 0.16684742271900177,
|
| 979 |
+
"learning_rate": 1.6953535089896555e-06,
|
| 980 |
+
"loss": 0.0335,
|
| 981 |
+
"step": 1250
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 2.800444691495275,
|
| 985 |
+
"grad_norm": 0.12368661165237427,
|
| 986 |
+
"learning_rate": 1.3777339360867836e-06,
|
| 987 |
+
"loss": 0.0317,
|
| 988 |
+
"step": 1260
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 2.8226792662590325,
|
| 992 |
+
"grad_norm": 0.13758961856365204,
|
| 993 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 994 |
+
"loss": 0.0305,
|
| 995 |
+
"step": 1270
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 2.8449138410227905,
|
| 999 |
+
"grad_norm": 0.3133557438850403,
|
| 1000 |
+
"learning_rate": 8.402021988209218e-07,
|
| 1001 |
+
"loss": 0.0488,
|
| 1002 |
+
"step": 1280
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 2.867148415786548,
|
| 1006 |
+
"grad_norm": 0.13724081218242645,
|
| 1007 |
+
"learning_rate": 6.20649392281425e-07,
|
| 1008 |
+
"loss": 0.0406,
|
| 1009 |
+
"step": 1290
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 2.8893829905503057,
|
| 1013 |
+
"grad_norm": 0.286937952041626,
|
| 1014 |
+
"learning_rate": 4.341083220360864e-07,
|
| 1015 |
+
"loss": 0.049,
|
| 1016 |
+
"step": 1300
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 2.8893829905503057,
|
| 1020 |
+
"eval_loss": 0.0463690422475338,
|
| 1021 |
+
"eval_runtime": 48.3097,
|
| 1022 |
+
"eval_samples_per_second": 4.14,
|
| 1023 |
+
"eval_steps_per_second": 4.14,
|
| 1024 |
+
"step": 1300
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.9116175653140632,
|
| 1028 |
+
"grad_norm": 0.06224232539534569,
|
| 1029 |
+
"learning_rate": 2.807036969873722e-07,
|
| 1030 |
+
"loss": 0.0565,
|
| 1031 |
+
"step": 1310
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.9338521400778212,
|
| 1035 |
+
"grad_norm": 0.08071974664926529,
|
| 1036 |
+
"learning_rate": 1.6053807322333191e-07,
|
| 1037 |
+
"loss": 0.0369,
|
| 1038 |
+
"step": 1320
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.956086714841579,
|
| 1042 |
+
"grad_norm": 0.22806085646152496,
|
| 1043 |
+
"learning_rate": 7.369178545542088e-08,
|
| 1044 |
+
"loss": 0.0376,
|
| 1045 |
+
"step": 1330
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.9783212896053364,
|
| 1049 |
+
"grad_norm": 0.20774702727794647,
|
| 1050 |
+
"learning_rate": 2.022289331209959e-08,
|
| 1051 |
+
"loss": 0.0467,
|
| 1052 |
+
"step": 1340
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.0,
|
| 1056 |
+
"grad_norm": 0.19576112926006317,
|
| 1057 |
+
"learning_rate": 1.671425240434843e-10,
|
| 1058 |
+
"loss": 0.0531,
|
| 1059 |
+
"step": 1350
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 3.0,
|
| 1063 |
+
"step": 1350,
|
| 1064 |
+
"total_flos": 8.093314295223091e+16,
|
| 1065 |
+
"train_loss": 0.09125252608899717,
|
| 1066 |
+
"train_runtime": 5067.962,
|
| 1067 |
+
"train_samples_per_second": 1.065,
|
| 1068 |
+
"train_steps_per_second": 0.266
|
| 1069 |
+
}
|
| 1070 |
+
],
|
| 1071 |
+
"logging_steps": 10,
|
| 1072 |
+
"max_steps": 1350,
|
| 1073 |
+
"num_input_tokens_seen": 0,
|
| 1074 |
+
"num_train_epochs": 3,
|
| 1075 |
+
"save_steps": 500,
|
| 1076 |
+
"stateful_callbacks": {
|
| 1077 |
+
"TrainerControl": {
|
| 1078 |
+
"args": {
|
| 1079 |
+
"should_epoch_stop": false,
|
| 1080 |
+
"should_evaluate": false,
|
| 1081 |
+
"should_log": false,
|
| 1082 |
+
"should_save": true,
|
| 1083 |
+
"should_training_stop": true
|
| 1084 |
+
},
|
| 1085 |
+
"attributes": {}
|
| 1086 |
+
}
|
| 1087 |
+
},
|
| 1088 |
+
"total_flos": 8.093314295223091e+16,
|
| 1089 |
+
"train_batch_size": 1,
|
| 1090 |
+
"trial_name": null,
|
| 1091 |
+
"trial_params": null
|
| 1092 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|