End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1974 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: global_batchsize_512_lradjusted2
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# global_batchsize_512_lradjusted2
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: global_batchsize_512_lradjusted2
|
|
|
|
| 16 |
|
| 17 |
# global_batchsize_512_lradjusted2
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the open-thoughts/OpenThoughts-114k dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9878213802435725,
|
| 3 |
+
"total_flos": 6.629121904995205e+18,
|
| 4 |
+
"train_loss": 0.4911867194417594,
|
| 5 |
+
"train_runtime": 27032.019,
|
| 6 |
+
"train_samples_per_second": 5.248,
|
| 7 |
+
"train_steps_per_second": 0.01
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9878213802435725,
|
| 3 |
+
"total_flos": 6.629121904995205e+18,
|
| 4 |
+
"train_loss": 0.4911867194417594,
|
| 5 |
+
"train_runtime": 27032.019,
|
| 6 |
+
"train_samples_per_second": 5.248,
|
| 7 |
+
"train_steps_per_second": 0.01
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1974 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9878213802435725,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 276,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.010825439783491205,
|
| 13 |
+
"grad_norm": 5.807920175447218,
|
| 14 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 15 |
+
"loss": 0.8567,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02165087956698241,
|
| 20 |
+
"grad_norm": 5.811623230162752,
|
| 21 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 22 |
+
"loss": 0.8604,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03247631935047361,
|
| 27 |
+
"grad_norm": 4.253584558151055,
|
| 28 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 29 |
+
"loss": 0.8173,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04330175913396482,
|
| 34 |
+
"grad_norm": 4.494099066603187,
|
| 35 |
+
"learning_rate": 2.2857142857142858e-05,
|
| 36 |
+
"loss": 0.8299,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05412719891745602,
|
| 41 |
+
"grad_norm": 4.509661541720279,
|
| 42 |
+
"learning_rate": 2.8571428571428574e-05,
|
| 43 |
+
"loss": 0.7651,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06495263870094722,
|
| 48 |
+
"grad_norm": 3.951348852730613,
|
| 49 |
+
"learning_rate": 3.4285714285714284e-05,
|
| 50 |
+
"loss": 0.7664,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07577807848443843,
|
| 55 |
+
"grad_norm": 2.62641811103538,
|
| 56 |
+
"learning_rate": 4e-05,
|
| 57 |
+
"loss": 0.7174,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08660351826792964,
|
| 62 |
+
"grad_norm": 2.5211356734881742,
|
| 63 |
+
"learning_rate": 4.5714285714285716e-05,
|
| 64 |
+
"loss": 0.7056,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09742895805142084,
|
| 69 |
+
"grad_norm": 2.2539730546361585,
|
| 70 |
+
"learning_rate": 5.1428571428571436e-05,
|
| 71 |
+
"loss": 0.6663,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.10825439783491204,
|
| 76 |
+
"grad_norm": 2.856988089650331,
|
| 77 |
+
"learning_rate": 5.714285714285715e-05,
|
| 78 |
+
"loss": 0.6637,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.11907983761840325,
|
| 83 |
+
"grad_norm": 1.8247182509862854,
|
| 84 |
+
"learning_rate": 6.285714285714286e-05,
|
| 85 |
+
"loss": 0.6377,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.12990527740189445,
|
| 90 |
+
"grad_norm": 2.5491735246742953,
|
| 91 |
+
"learning_rate": 6.857142857142857e-05,
|
| 92 |
+
"loss": 0.6408,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.14073071718538566,
|
| 97 |
+
"grad_norm": 2.464416812125527,
|
| 98 |
+
"learning_rate": 7.42857142857143e-05,
|
| 99 |
+
"loss": 0.6248,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.15155615696887687,
|
| 104 |
+
"grad_norm": 1.8774381374385238,
|
| 105 |
+
"learning_rate": 8e-05,
|
| 106 |
+
"loss": 0.632,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.16238159675236807,
|
| 111 |
+
"grad_norm": 2.186597255470316,
|
| 112 |
+
"learning_rate": 8.571428571428571e-05,
|
| 113 |
+
"loss": 0.6201,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.17320703653585928,
|
| 118 |
+
"grad_norm": 2.367228905837931,
|
| 119 |
+
"learning_rate": 9.142857142857143e-05,
|
| 120 |
+
"loss": 0.6084,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.18403247631935046,
|
| 125 |
+
"grad_norm": 1.961289391436032,
|
| 126 |
+
"learning_rate": 9.714285714285714e-05,
|
| 127 |
+
"loss": 0.5974,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.19485791610284167,
|
| 132 |
+
"grad_norm": 1.6062347832492823,
|
| 133 |
+
"learning_rate": 0.00010285714285714287,
|
| 134 |
+
"loss": 0.5851,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.20568335588633288,
|
| 139 |
+
"grad_norm": 2.5785754238732115,
|
| 140 |
+
"learning_rate": 0.00010857142857142859,
|
| 141 |
+
"loss": 0.5899,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2165087956698241,
|
| 146 |
+
"grad_norm": 2.4973397443279985,
|
| 147 |
+
"learning_rate": 0.0001142857142857143,
|
| 148 |
+
"loss": 0.59,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2273342354533153,
|
| 153 |
+
"grad_norm": 1.7261400197953252,
|
| 154 |
+
"learning_rate": 0.00012000000000000002,
|
| 155 |
+
"loss": 0.5817,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2381596752368065,
|
| 160 |
+
"grad_norm": 2.8676046622672464,
|
| 161 |
+
"learning_rate": 0.00012571428571428572,
|
| 162 |
+
"loss": 0.5856,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2489851150202977,
|
| 167 |
+
"grad_norm": 1.1982706010037665,
|
| 168 |
+
"learning_rate": 0.00013142857142857143,
|
| 169 |
+
"loss": 0.5718,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2598105548037889,
|
| 174 |
+
"grad_norm": 2.6334206150571764,
|
| 175 |
+
"learning_rate": 0.00013714285714285713,
|
| 176 |
+
"loss": 0.6143,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2706359945872801,
|
| 181 |
+
"grad_norm": 4.1727861440371905,
|
| 182 |
+
"learning_rate": 0.00014285714285714287,
|
| 183 |
+
"loss": 0.5957,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2814614343707713,
|
| 188 |
+
"grad_norm": 1.726889837548816,
|
| 189 |
+
"learning_rate": 0.0001485714285714286,
|
| 190 |
+
"loss": 0.5778,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2922868741542625,
|
| 195 |
+
"grad_norm": 1.9491289608648266,
|
| 196 |
+
"learning_rate": 0.0001542857142857143,
|
| 197 |
+
"loss": 0.5872,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.30311231393775373,
|
| 202 |
+
"grad_norm": 2.3922212205589464,
|
| 203 |
+
"learning_rate": 0.00016,
|
| 204 |
+
"loss": 0.5856,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.31393775372124494,
|
| 209 |
+
"grad_norm": 1.7812309864931277,
|
| 210 |
+
"learning_rate": 0.0001599935812484263,
|
| 211 |
+
"loss": 0.5814,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.32476319350473615,
|
| 216 |
+
"grad_norm": 1.4649634825431583,
|
| 217 |
+
"learning_rate": 0.00015997432602371444,
|
| 218 |
+
"loss": 0.5663,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.33558863328822736,
|
| 223 |
+
"grad_norm": 4.015544716712766,
|
| 224 |
+
"learning_rate": 0.00015994223741572707,
|
| 225 |
+
"loss": 0.5853,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.34641407307171856,
|
| 230 |
+
"grad_norm": 11.281220320234869,
|
| 231 |
+
"learning_rate": 0.00015989732057368423,
|
| 232 |
+
"loss": 0.6967,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.3572395128552097,
|
| 237 |
+
"grad_norm": 7690.086558155647,
|
| 238 |
+
"learning_rate": 0.00015983958270533721,
|
| 239 |
+
"loss": 4.6049,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.3680649526387009,
|
| 244 |
+
"grad_norm": 112.72682447862128,
|
| 245 |
+
"learning_rate": 0.0001597690330758118,
|
| 246 |
+
"loss": 2.8115,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.37889039242219213,
|
| 251 |
+
"grad_norm": 4.025212340328087,
|
| 252 |
+
"learning_rate": 0.0001596856830061217,
|
| 253 |
+
"loss": 0.7115,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.38971583220568334,
|
| 258 |
+
"grad_norm": 2.4843639071881074,
|
| 259 |
+
"learning_rate": 0.0001595895458713516,
|
| 260 |
+
"loss": 0.6295,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.40054127198917455,
|
| 265 |
+
"grad_norm": 1.7939204684367258,
|
| 266 |
+
"learning_rate": 0.00015948063709851125,
|
| 267 |
+
"loss": 0.6154,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.41136671177266576,
|
| 272 |
+
"grad_norm": 2.459210039805435,
|
| 273 |
+
"learning_rate": 0.00015935897416405944,
|
| 274 |
+
"loss": 0.6166,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.42219215155615697,
|
| 279 |
+
"grad_norm": 1.11090456282376,
|
| 280 |
+
"learning_rate": 0.00015922457659110005,
|
| 281 |
+
"loss": 0.6007,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4330175913396482,
|
| 286 |
+
"grad_norm": 84.92016735622583,
|
| 287 |
+
"learning_rate": 0.00015907746594624893,
|
| 288 |
+
"loss": 0.767,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.4438430311231394,
|
| 293 |
+
"grad_norm": 8.660965154683476,
|
| 294 |
+
"learning_rate": 0.0001589176658361731,
|
| 295 |
+
"loss": 0.8712,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.4546684709066306,
|
| 300 |
+
"grad_norm": 3.4936052679031158,
|
| 301 |
+
"learning_rate": 0.00015874520190380274,
|
| 302 |
+
"loss": 0.7434,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.4654939106901218,
|
| 307 |
+
"grad_norm": 1.7045480694962383,
|
| 308 |
+
"learning_rate": 0.00015856010182421635,
|
| 309 |
+
"loss": 0.6308,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.476319350473613,
|
| 314 |
+
"grad_norm": 14.30049648802306,
|
| 315 |
+
"learning_rate": 0.00015836239530019958,
|
| 316 |
+
"loss": 0.6371,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.4871447902571042,
|
| 321 |
+
"grad_norm": 4.053341450365789,
|
| 322 |
+
"learning_rate": 0.00015815211405747896,
|
| 323 |
+
"loss": 0.6844,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.4979702300405954,
|
| 328 |
+
"grad_norm": 1.7771803961776749,
|
| 329 |
+
"learning_rate": 0.00015792929183963098,
|
| 330 |
+
"loss": 0.6299,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5087956698240866,
|
| 335 |
+
"grad_norm": 1.8665193904465571,
|
| 336 |
+
"learning_rate": 0.00015769396440266714,
|
| 337 |
+
"loss": 0.6056,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5196211096075778,
|
| 342 |
+
"grad_norm": 1.9789963866244402,
|
| 343 |
+
"learning_rate": 0.00015744616950929635,
|
| 344 |
+
"loss": 0.6017,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.530446549391069,
|
| 349 |
+
"grad_norm": 2.0461657503603115,
|
| 350 |
+
"learning_rate": 0.00015718594692286516,
|
| 351 |
+
"loss": 0.5884,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5412719891745602,
|
| 356 |
+
"grad_norm": 1.216761740673657,
|
| 357 |
+
"learning_rate": 0.000156913338400977,
|
| 358 |
+
"loss": 0.5744,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.5520974289580515,
|
| 363 |
+
"grad_norm": 2.0980055824287938,
|
| 364 |
+
"learning_rate": 0.0001566283876887913,
|
| 365 |
+
"loss": 0.5937,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5629228687415426,
|
| 370 |
+
"grad_norm": 1.168756354199333,
|
| 371 |
+
"learning_rate": 0.00015633114051200392,
|
| 372 |
+
"loss": 0.5665,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5737483085250338,
|
| 377 |
+
"grad_norm": 1.486001286642052,
|
| 378 |
+
"learning_rate": 0.0001560216445695094,
|
| 379 |
+
"loss": 0.561,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.584573748308525,
|
| 384 |
+
"grad_norm": 1.385583557087864,
|
| 385 |
+
"learning_rate": 0.00015569994952574698,
|
| 386 |
+
"loss": 0.5679,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.5953991880920162,
|
| 391 |
+
"grad_norm": 1.1211177929259362,
|
| 392 |
+
"learning_rate": 0.0001553661070027308,
|
| 393 |
+
"loss": 0.5481,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6062246278755075,
|
| 398 |
+
"grad_norm": 1.338185754695372,
|
| 399 |
+
"learning_rate": 0.00015502017057176644,
|
| 400 |
+
"loss": 0.551,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6170500676589986,
|
| 405 |
+
"grad_norm": 0.9631327673448306,
|
| 406 |
+
"learning_rate": 0.00015466219574485415,
|
| 407 |
+
"loss": 0.5439,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.6278755074424899,
|
| 412 |
+
"grad_norm": 1.296708217652255,
|
| 413 |
+
"learning_rate": 0.000154292239965781,
|
| 414 |
+
"loss": 0.5444,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.638700947225981,
|
| 419 |
+
"grad_norm": 1.01308925336574,
|
| 420 |
+
"learning_rate": 0.00015391036260090294,
|
| 421 |
+
"loss": 0.529,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6495263870094723,
|
| 426 |
+
"grad_norm": 1.1113699538858748,
|
| 427 |
+
"learning_rate": 0.00015351662492961847,
|
| 428 |
+
"loss": 0.5353,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6603518267929634,
|
| 433 |
+
"grad_norm": 1.229664456155683,
|
| 434 |
+
"learning_rate": 0.00015311109013453495,
|
| 435 |
+
"loss": 0.5391,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.6711772665764547,
|
| 440 |
+
"grad_norm": 0.7696540318430937,
|
| 441 |
+
"learning_rate": 0.00015269382329133,
|
| 442 |
+
"loss": 0.5236,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.6820027063599459,
|
| 447 |
+
"grad_norm": 1.0452145349007034,
|
| 448 |
+
"learning_rate": 0.0001522648913583088,
|
| 449 |
+
"loss": 0.5333,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6928281461434371,
|
| 454 |
+
"grad_norm": 1.0076590725145298,
|
| 455 |
+
"learning_rate": 0.00015182436316565936,
|
| 456 |
+
"loss": 0.5239,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7036535859269283,
|
| 461 |
+
"grad_norm": 1.2124343568222422,
|
| 462 |
+
"learning_rate": 0.00015137230940440738,
|
| 463 |
+
"loss": 0.5236,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.7144790257104194,
|
| 468 |
+
"grad_norm": 1.2765073901945772,
|
| 469 |
+
"learning_rate": 0.00015090880261507268,
|
| 470 |
+
"loss": 0.5307,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.7253044654939107,
|
| 475 |
+
"grad_norm": 0.627724711812233,
|
| 476 |
+
"learning_rate": 0.0001504339171760286,
|
| 477 |
+
"loss": 0.5162,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.7361299052774019,
|
| 482 |
+
"grad_norm": 0.648664232932664,
|
| 483 |
+
"learning_rate": 0.00014994772929156658,
|
| 484 |
+
"loss": 0.525,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.7469553450608931,
|
| 489 |
+
"grad_norm": 0.853676037408326,
|
| 490 |
+
"learning_rate": 0.00014945031697966788,
|
| 491 |
+
"loss": 0.5147,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7577807848443843,
|
| 496 |
+
"grad_norm": 0.7593724841438597,
|
| 497 |
+
"learning_rate": 0.00014894176005948397,
|
| 498 |
+
"loss": 0.4967,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.7686062246278755,
|
| 503 |
+
"grad_norm": 0.5321774839143892,
|
| 504 |
+
"learning_rate": 0.00014842214013852817,
|
| 505 |
+
"loss": 0.4977,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.7794316644113667,
|
| 510 |
+
"grad_norm": 0.6449157547696196,
|
| 511 |
+
"learning_rate": 0.00014789154059958009,
|
| 512 |
+
"loss": 0.51,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.790257104194858,
|
| 517 |
+
"grad_norm": 0.527820608461116,
|
| 518 |
+
"learning_rate": 0.00014735004658730536,
|
| 519 |
+
"loss": 0.5134,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8010825439783491,
|
| 524 |
+
"grad_norm": 0.7495799991859693,
|
| 525 |
+
"learning_rate": 0.0001467977449945926,
|
| 526 |
+
"loss": 0.5122,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.8119079837618404,
|
| 531 |
+
"grad_norm": 1.038331830644402,
|
| 532 |
+
"learning_rate": 0.00014623472444860974,
|
| 533 |
+
"loss": 0.5134,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.8227334235453315,
|
| 538 |
+
"grad_norm": 1.4042907578050945,
|
| 539 |
+
"learning_rate": 0.00014566107529658212,
|
| 540 |
+
"loss": 0.5083,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.8335588633288228,
|
| 545 |
+
"grad_norm": 0.7986676831500767,
|
| 546 |
+
"learning_rate": 0.00014507688959129473,
|
| 547 |
+
"loss": 0.4975,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8443843031123139,
|
| 552 |
+
"grad_norm": 1.0273680785889077,
|
| 553 |
+
"learning_rate": 0.00014448226107632042,
|
| 554 |
+
"loss": 0.5049,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.8552097428958051,
|
| 559 |
+
"grad_norm": 1.064561031536024,
|
| 560 |
+
"learning_rate": 0.0001438772851709771,
|
| 561 |
+
"loss": 0.5053,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8660351826792964,
|
| 566 |
+
"grad_norm": 1.0710244196033907,
|
| 567 |
+
"learning_rate": 0.00014326205895501588,
|
| 568 |
+
"loss": 0.4977,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.8768606224627875,
|
| 573 |
+
"grad_norm": 0.8475945967427466,
|
| 574 |
+
"learning_rate": 0.00014263668115304285,
|
| 575 |
+
"loss": 0.5053,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.8876860622462788,
|
| 580 |
+
"grad_norm": 0.6798466426655683,
|
| 581 |
+
"learning_rate": 0.0001420012521186767,
|
| 582 |
+
"loss": 0.4898,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.8985115020297699,
|
| 587 |
+
"grad_norm": 0.720780663324741,
|
| 588 |
+
"learning_rate": 0.00014135587381844535,
|
| 589 |
+
"loss": 0.4932,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.9093369418132612,
|
| 594 |
+
"grad_norm": 0.6169019560016734,
|
| 595 |
+
"learning_rate": 0.0001407006498154233,
|
| 596 |
+
"loss": 0.4916,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9201623815967523,
|
| 601 |
+
"grad_norm": 0.48074951462504467,
|
| 602 |
+
"learning_rate": 0.00014003568525261303,
|
| 603 |
+
"loss": 0.4864,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.9309878213802436,
|
| 608 |
+
"grad_norm": 0.5675353244905835,
|
| 609 |
+
"learning_rate": 0.00013936108683607287,
|
| 610 |
+
"loss": 0.4902,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.9418132611637348,
|
| 615 |
+
"grad_norm": 0.5142478444309492,
|
| 616 |
+
"learning_rate": 0.0001386769628177941,
|
| 617 |
+
"loss": 0.4839,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.952638700947226,
|
| 622 |
+
"grad_norm": 0.4166415283022488,
|
| 623 |
+
"learning_rate": 0.0001379834229783296,
|
| 624 |
+
"loss": 0.4701,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.9634641407307172,
|
| 629 |
+
"grad_norm": 0.49915561344121656,
|
| 630 |
+
"learning_rate": 0.00013728057860917784,
|
| 631 |
+
"loss": 0.4842,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9742895805142084,
|
| 636 |
+
"grad_norm": 0.6649725562299833,
|
| 637 |
+
"learning_rate": 0.00013656854249492382,
|
| 638 |
+
"loss": 0.4837,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.9851150202976996,
|
| 643 |
+
"grad_norm": 1.1671140064989096,
|
| 644 |
+
"learning_rate": 0.00013584742889514073,
|
| 645 |
+
"loss": 0.486,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.9959404600811907,
|
| 650 |
+
"grad_norm": 1.368072672593922,
|
| 651 |
+
"learning_rate": 0.00013511735352605495,
|
| 652 |
+
"loss": 0.4884,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.006765899864682,
|
| 657 |
+
"grad_norm": 1.0201145301236891,
|
| 658 |
+
"learning_rate": 0.00013437843354197705,
|
| 659 |
+
"loss": 0.7512,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.0175913396481733,
|
| 664 |
+
"grad_norm": 1.8000094250512286,
|
| 665 |
+
"learning_rate": 0.0001336307875165023,
|
| 666 |
+
"loss": 0.4768,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.0284167794316643,
|
| 671 |
+
"grad_norm": 0.5472576337231695,
|
| 672 |
+
"learning_rate": 0.00013287453542348328,
|
| 673 |
+
"loss": 0.4613,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.0392422192151556,
|
| 678 |
+
"grad_norm": 1.1828047434659983,
|
| 679 |
+
"learning_rate": 0.0001321097986177778,
|
| 680 |
+
"loss": 0.4647,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.0500676589986468,
|
| 685 |
+
"grad_norm": 0.9813473966873533,
|
| 686 |
+
"learning_rate": 0.0001313366998157752,
|
| 687 |
+
"loss": 0.4528,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.060893098782138,
|
| 692 |
+
"grad_norm": 0.7578769026059632,
|
| 693 |
+
"learning_rate": 0.00013055536307570432,
|
| 694 |
+
"loss": 0.4603,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.0717185385656292,
|
| 699 |
+
"grad_norm": 0.5725242057599156,
|
| 700 |
+
"learning_rate": 0.0001297659137777259,
|
| 701 |
+
"loss": 0.4527,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.0825439783491204,
|
| 706 |
+
"grad_norm": 0.575770129842184,
|
| 707 |
+
"learning_rate": 0.00012896847860381305,
|
| 708 |
+
"loss": 0.4501,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.0933694181326117,
|
| 713 |
+
"grad_norm": 0.6026831960506396,
|
| 714 |
+
"learning_rate": 0.00012816318551742264,
|
| 715 |
+
"loss": 0.448,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.104194857916103,
|
| 720 |
+
"grad_norm": 0.4305530355604545,
|
| 721 |
+
"learning_rate": 0.0001273501637429614,
|
| 722 |
+
"loss": 0.4462,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.115020297699594,
|
| 727 |
+
"grad_norm": 0.4454666291048703,
|
| 728 |
+
"learning_rate": 0.0001265295437450491,
|
| 729 |
+
"loss": 0.4511,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.1258457374830853,
|
| 734 |
+
"grad_norm": 0.4678487064825796,
|
| 735 |
+
"learning_rate": 0.0001257014572075834,
|
| 736 |
+
"loss": 0.4411,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.1366711772665765,
|
| 741 |
+
"grad_norm": 0.37950754053596286,
|
| 742 |
+
"learning_rate": 0.00012486603701260837,
|
| 743 |
+
"loss": 0.4434,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.1474966170500678,
|
| 748 |
+
"grad_norm": 0.43449589812234013,
|
| 749 |
+
"learning_rate": 0.0001240234172189913,
|
| 750 |
+
"loss": 0.4477,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.1583220568335588,
|
| 755 |
+
"grad_norm": 0.43939536219651565,
|
| 756 |
+
"learning_rate": 0.0001231737330409104,
|
| 757 |
+
"loss": 0.4431,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.16914749661705,
|
| 762 |
+
"grad_norm": 0.3882093042316694,
|
| 763 |
+
"learning_rate": 0.000122317120826157,
|
| 764 |
+
"loss": 0.4364,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.1799729364005414,
|
| 769 |
+
"grad_norm": 0.4351026316208757,
|
| 770 |
+
"learning_rate": 0.00012145371803425616,
|
| 771 |
+
"loss": 0.4431,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.1907983761840324,
|
| 776 |
+
"grad_norm": 0.5501651171341266,
|
| 777 |
+
"learning_rate": 0.0001205836632144086,
|
| 778 |
+
"loss": 0.447,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.2016238159675237,
|
| 783 |
+
"grad_norm": 0.4174336327490401,
|
| 784 |
+
"learning_rate": 0.00011970709598325793,
|
| 785 |
+
"loss": 0.4452,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.212449255751015,
|
| 790 |
+
"grad_norm": 0.29631678479891477,
|
| 791 |
+
"learning_rate": 0.0001188241570024865,
|
| 792 |
+
"loss": 0.4398,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.2232746955345062,
|
| 797 |
+
"grad_norm": 0.339334632156724,
|
| 798 |
+
"learning_rate": 0.00011793498795624362,
|
| 799 |
+
"loss": 0.4349,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.2341001353179972,
|
| 804 |
+
"grad_norm": 0.30928533747901593,
|
| 805 |
+
"learning_rate": 0.00011703973152840967,
|
| 806 |
+
"loss": 0.4421,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.2449255751014885,
|
| 811 |
+
"grad_norm": 0.39017965923706066,
|
| 812 |
+
"learning_rate": 0.00011613853137969977,
|
| 813 |
+
"loss": 0.4501,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.2557510148849798,
|
| 818 |
+
"grad_norm": 0.6145727467731127,
|
| 819 |
+
"learning_rate": 0.00011523153212461075,
|
| 820 |
+
"loss": 0.4406,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.266576454668471,
|
| 825 |
+
"grad_norm": 1.0187083339327228,
|
| 826 |
+
"learning_rate": 0.00011431887930821501,
|
| 827 |
+
"loss": 0.4402,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.277401894451962,
|
| 832 |
+
"grad_norm": 1.2911461014630221,
|
| 833 |
+
"learning_rate": 0.00011340071938280507,
|
| 834 |
+
"loss": 0.4424,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.2882273342354533,
|
| 839 |
+
"grad_norm": 0.35131816146651274,
|
| 840 |
+
"learning_rate": 0.00011247719968439257,
|
| 841 |
+
"loss": 0.4418,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.2990527740189446,
|
| 846 |
+
"grad_norm": 0.7870620433304094,
|
| 847 |
+
"learning_rate": 0.00011154846840906549,
|
| 848 |
+
"loss": 0.4359,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.3098782138024356,
|
| 853 |
+
"grad_norm": 1.168118392838753,
|
| 854 |
+
"learning_rate": 0.00011061467458920719,
|
| 855 |
+
"loss": 0.4439,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.320703653585927,
|
| 860 |
+
"grad_norm": 0.46362753411050434,
|
| 861 |
+
"learning_rate": 0.00010967596806958144,
|
| 862 |
+
"loss": 0.4355,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.3315290933694182,
|
| 867 |
+
"grad_norm": 0.631341811837205,
|
| 868 |
+
"learning_rate": 0.00010873249948328698,
|
| 869 |
+
"loss": 0.4417,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.3423545331529092,
|
| 874 |
+
"grad_norm": 0.8838449406798384,
|
| 875 |
+
"learning_rate": 0.00010778442022758562,
|
| 876 |
+
"loss": 0.439,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.3531799729364005,
|
| 881 |
+
"grad_norm": 0.44202149476361463,
|
| 882 |
+
"learning_rate": 0.00010683188243960779,
|
| 883 |
+
"loss": 0.436,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.3640054127198917,
|
| 888 |
+
"grad_norm": 0.5464115885263443,
|
| 889 |
+
"learning_rate": 0.00010587503897193905,
|
| 890 |
+
"loss": 0.4365,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.374830852503383,
|
| 895 |
+
"grad_norm": 0.7244992161712334,
|
| 896 |
+
"learning_rate": 0.00010491404336809233,
|
| 897 |
+
"loss": 0.4292,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.3856562922868743,
|
| 902 |
+
"grad_norm": 0.3629285827544841,
|
| 903 |
+
"learning_rate": 0.00010394904983786867,
|
| 904 |
+
"loss": 0.4298,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.3964817320703653,
|
| 909 |
+
"grad_norm": 0.5706457571028368,
|
| 910 |
+
"learning_rate": 0.0001029802132326116,
|
| 911 |
+
"loss": 0.4306,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.4073071718538566,
|
| 916 |
+
"grad_norm": 0.5219581868931918,
|
| 917 |
+
"learning_rate": 0.00010200768902035825,
|
| 918 |
+
"loss": 0.4345,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.4181326116373478,
|
| 923 |
+
"grad_norm": 0.3128700720370998,
|
| 924 |
+
"learning_rate": 0.00010103163326089159,
|
| 925 |
+
"loss": 0.4352,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.4289580514208389,
|
| 930 |
+
"grad_norm": 0.5860532868715919,
|
| 931 |
+
"learning_rate": 0.00010005220258069766,
|
| 932 |
+
"loss": 0.4379,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.4397834912043301,
|
| 937 |
+
"grad_norm": 0.299205037891474,
|
| 938 |
+
"learning_rate": 9.906955414783193e-05,
|
| 939 |
+
"loss": 0.4286,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.4506089309878214,
|
| 944 |
+
"grad_norm": 0.47146400660400606,
|
| 945 |
+
"learning_rate": 9.80838456466988e-05,
|
| 946 |
+
"loss": 0.4324,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.4614343707713127,
|
| 951 |
+
"grad_norm": 0.5772068931303819,
|
| 952 |
+
"learning_rate": 9.709523525274806e-05,
|
| 953 |
+
"loss": 0.4326,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.472259810554804,
|
| 958 |
+
"grad_norm": 0.3805133128090234,
|
| 959 |
+
"learning_rate": 9.610388160709281e-05,
|
| 960 |
+
"loss": 0.4309,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.483085250338295,
|
| 965 |
+
"grad_norm": 0.4271236662578828,
|
| 966 |
+
"learning_rate": 9.510994379105235e-05,
|
| 967 |
+
"loss": 0.428,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.4939106901217862,
|
| 972 |
+
"grad_norm": 0.3913062302891241,
|
| 973 |
+
"learning_rate": 9.41135813006247e-05,
|
| 974 |
+
"loss": 0.4336,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.5047361299052775,
|
| 979 |
+
"grad_norm": 0.4959549867268792,
|
| 980 |
+
"learning_rate": 9.311495402089241e-05,
|
| 981 |
+
"loss": 0.4324,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.5155615696887685,
|
| 986 |
+
"grad_norm": 0.47173284252778047,
|
| 987 |
+
"learning_rate": 9.211422220036615e-05,
|
| 988 |
+
"loss": 0.4322,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.5263870094722598,
|
| 993 |
+
"grad_norm": 0.4218219584473093,
|
| 994 |
+
"learning_rate": 9.111154642526954e-05,
|
| 995 |
+
"loss": 0.4285,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.537212449255751,
|
| 1000 |
+
"grad_norm": 0.4956469938375666,
|
| 1001 |
+
"learning_rate": 9.010708759377035e-05,
|
| 1002 |
+
"loss": 0.4289,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.548037889039242,
|
| 1007 |
+
"grad_norm": 0.4107706925787467,
|
| 1008 |
+
"learning_rate": 8.910100689016121e-05,
|
| 1009 |
+
"loss": 0.4352,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.5588633288227334,
|
| 1014 |
+
"grad_norm": 0.4458931818501929,
|
| 1015 |
+
"learning_rate": 8.809346575899459e-05,
|
| 1016 |
+
"loss": 0.4268,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.5696887686062246,
|
| 1021 |
+
"grad_norm": 0.4721100077989787,
|
| 1022 |
+
"learning_rate": 8.708462587917602e-05,
|
| 1023 |
+
"loss": 0.4245,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.5805142083897157,
|
| 1028 |
+
"grad_norm": 0.3742345022103872,
|
| 1029 |
+
"learning_rate": 8.607464913801971e-05,
|
| 1030 |
+
"loss": 0.4244,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.5913396481732072,
|
| 1035 |
+
"grad_norm": 0.33389508877981666,
|
| 1036 |
+
"learning_rate": 8.506369760527053e-05,
|
| 1037 |
+
"loss": 0.4216,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.6021650879566982,
|
| 1042 |
+
"grad_norm": 0.2725464341226312,
|
| 1043 |
+
"learning_rate": 8.405193350709702e-05,
|
| 1044 |
+
"loss": 0.4396,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.6129905277401895,
|
| 1049 |
+
"grad_norm": 0.2561974791876615,
|
| 1050 |
+
"learning_rate": 8.303951920005916e-05,
|
| 1051 |
+
"loss": 0.4226,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.6238159675236807,
|
| 1056 |
+
"grad_norm": 0.2312801621695805,
|
| 1057 |
+
"learning_rate": 8.202661714505503e-05,
|
| 1058 |
+
"loss": 0.4296,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.6346414073071718,
|
| 1063 |
+
"grad_norm": 0.2539035606451629,
|
| 1064 |
+
"learning_rate": 8.101338988125122e-05,
|
| 1065 |
+
"loss": 0.4297,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.645466847090663,
|
| 1070 |
+
"grad_norm": 0.2795943345506495,
|
| 1071 |
+
"learning_rate": 8e-05,
|
| 1072 |
+
"loss": 0.4232,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.6562922868741543,
|
| 1077 |
+
"grad_norm": 0.305802751614139,
|
| 1078 |
+
"learning_rate": 7.898661011874881e-05,
|
| 1079 |
+
"loss": 0.435,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.6671177266576453,
|
| 1084 |
+
"grad_norm": 0.29309245201661993,
|
| 1085 |
+
"learning_rate": 7.797338285494499e-05,
|
| 1086 |
+
"loss": 0.4276,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.6779431664411368,
|
| 1091 |
+
"grad_norm": 0.329501466273318,
|
| 1092 |
+
"learning_rate": 7.696048079994087e-05,
|
| 1093 |
+
"loss": 0.421,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.6887686062246279,
|
| 1098 |
+
"grad_norm": 0.3142714545795239,
|
| 1099 |
+
"learning_rate": 7.594806649290299e-05,
|
| 1100 |
+
"loss": 0.4295,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.699594046008119,
|
| 1105 |
+
"grad_norm": 0.33315198074843505,
|
| 1106 |
+
"learning_rate": 7.49363023947295e-05,
|
| 1107 |
+
"loss": 0.4155,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.7104194857916104,
|
| 1112 |
+
"grad_norm": 0.34360494433039884,
|
| 1113 |
+
"learning_rate": 7.392535086198032e-05,
|
| 1114 |
+
"loss": 0.4269,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.7212449255751014,
|
| 1119 |
+
"grad_norm": 0.28517772111690337,
|
| 1120 |
+
"learning_rate": 7.2915374120824e-05,
|
| 1121 |
+
"loss": 0.4337,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.7320703653585927,
|
| 1126 |
+
"grad_norm": 0.31951375045950287,
|
| 1127 |
+
"learning_rate": 7.190653424100544e-05,
|
| 1128 |
+
"loss": 0.4267,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.742895805142084,
|
| 1133 |
+
"grad_norm": 0.34023285855014257,
|
| 1134 |
+
"learning_rate": 7.089899310983883e-05,
|
| 1135 |
+
"loss": 0.4256,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.753721244925575,
|
| 1140 |
+
"grad_norm": 0.2949489362370772,
|
| 1141 |
+
"learning_rate": 6.989291240622969e-05,
|
| 1142 |
+
"loss": 0.4296,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.7645466847090663,
|
| 1147 |
+
"grad_norm": 0.26157765123078286,
|
| 1148 |
+
"learning_rate": 6.88884535747305e-05,
|
| 1149 |
+
"loss": 0.4234,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.7753721244925575,
|
| 1154 |
+
"grad_norm": 0.2795081501666077,
|
| 1155 |
+
"learning_rate": 6.78857777996339e-05,
|
| 1156 |
+
"loss": 0.4205,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.7861975642760486,
|
| 1161 |
+
"grad_norm": 0.19331675781027863,
|
| 1162 |
+
"learning_rate": 6.68850459791076e-05,
|
| 1163 |
+
"loss": 0.4275,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.79702300405954,
|
| 1168 |
+
"grad_norm": 0.21357341104162766,
|
| 1169 |
+
"learning_rate": 6.588641869937535e-05,
|
| 1170 |
+
"loss": 0.4203,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.8078484438430311,
|
| 1175 |
+
"grad_norm": 0.2167571809187653,
|
| 1176 |
+
"learning_rate": 6.489005620894769e-05,
|
| 1177 |
+
"loss": 0.4254,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.8186738836265224,
|
| 1182 |
+
"grad_norm": 0.24601105327924508,
|
| 1183 |
+
"learning_rate": 6.389611839290719e-05,
|
| 1184 |
+
"loss": 0.4223,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.8294993234100136,
|
| 1189 |
+
"grad_norm": 0.3019894658869235,
|
| 1190 |
+
"learning_rate": 6.290476474725193e-05,
|
| 1191 |
+
"loss": 0.4307,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.8403247631935047,
|
| 1196 |
+
"grad_norm": 0.2435718708672937,
|
| 1197 |
+
"learning_rate": 6.191615435330121e-05,
|
| 1198 |
+
"loss": 0.4213,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.851150202976996,
|
| 1203 |
+
"grad_norm": 0.17781892789685452,
|
| 1204 |
+
"learning_rate": 6.093044585216807e-05,
|
| 1205 |
+
"loss": 0.4177,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.8619756427604872,
|
| 1210 |
+
"grad_norm": 0.19371420909940787,
|
| 1211 |
+
"learning_rate": 5.994779741930236e-05,
|
| 1212 |
+
"loss": 0.4186,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.8728010825439783,
|
| 1217 |
+
"grad_norm": 0.20962600669395126,
|
| 1218 |
+
"learning_rate": 5.896836673910842e-05,
|
| 1219 |
+
"loss": 0.4126,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.8836265223274695,
|
| 1224 |
+
"grad_norm": 0.26385576587957305,
|
| 1225 |
+
"learning_rate": 5.799231097964176e-05,
|
| 1226 |
+
"loss": 0.4251,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.8944519621109608,
|
| 1231 |
+
"grad_norm": 0.186706517180332,
|
| 1232 |
+
"learning_rate": 5.7019786767388426e-05,
|
| 1233 |
+
"loss": 0.4198,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.9052774018944518,
|
| 1238 |
+
"grad_norm": 0.20177197005120157,
|
| 1239 |
+
"learning_rate": 5.605095016213137e-05,
|
| 1240 |
+
"loss": 0.4142,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.9161028416779433,
|
| 1245 |
+
"grad_norm": 0.22218528258050108,
|
| 1246 |
+
"learning_rate": 5.50859566319077e-05,
|
| 1247 |
+
"loss": 0.4159,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.9269282814614344,
|
| 1252 |
+
"grad_norm": 0.25615151629013416,
|
| 1253 |
+
"learning_rate": 5.4124961028060956e-05,
|
| 1254 |
+
"loss": 0.4256,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.9377537212449256,
|
| 1259 |
+
"grad_norm": 0.23647599450178192,
|
| 1260 |
+
"learning_rate": 5.316811756039224e-05,
|
| 1261 |
+
"loss": 0.4194,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.9485791610284169,
|
| 1266 |
+
"grad_norm": 0.2353513525938554,
|
| 1267 |
+
"learning_rate": 5.221557977241439e-05,
|
| 1268 |
+
"loss": 0.4217,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.959404600811908,
|
| 1273 |
+
"grad_norm": 0.1652695325427714,
|
| 1274 |
+
"learning_rate": 5.126750051671304e-05,
|
| 1275 |
+
"loss": 0.4197,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.9702300405953992,
|
| 1280 |
+
"grad_norm": 0.23356895899115995,
|
| 1281 |
+
"learning_rate": 5.032403193041859e-05,
|
| 1282 |
+
"loss": 0.4159,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.9810554803788905,
|
| 1287 |
+
"grad_norm": 0.1988738455239412,
|
| 1288 |
+
"learning_rate": 4.9385325410792824e-05,
|
| 1289 |
+
"loss": 0.4247,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.9918809201623815,
|
| 1294 |
+
"grad_norm": 0.20607159435477782,
|
| 1295 |
+
"learning_rate": 4.8451531590934535e-05,
|
| 1296 |
+
"loss": 0.4254,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.002706359945873,
|
| 1301 |
+
"grad_norm": 0.33625717644811787,
|
| 1302 |
+
"learning_rate": 4.752280031560744e-05,
|
| 1303 |
+
"loss": 0.6634,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.013531799729364,
|
| 1308 |
+
"grad_norm": 0.3504909382927573,
|
| 1309 |
+
"learning_rate": 4.659928061719497e-05,
|
| 1310 |
+
"loss": 0.3805,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.024357239512855,
|
| 1315 |
+
"grad_norm": 0.2417890196803602,
|
| 1316 |
+
"learning_rate": 4.5681120691785035e-05,
|
| 1317 |
+
"loss": 0.3785,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.0351826792963466,
|
| 1322 |
+
"grad_norm": 0.3195492118572409,
|
| 1323 |
+
"learning_rate": 4.476846787538925e-05,
|
| 1324 |
+
"loss": 0.3796,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.0460081190798376,
|
| 1329 |
+
"grad_norm": 0.28392833843993076,
|
| 1330 |
+
"learning_rate": 4.386146862030023e-05,
|
| 1331 |
+
"loss": 0.3727,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.0568335588633286,
|
| 1336 |
+
"grad_norm": 0.253698837225003,
|
| 1337 |
+
"learning_rate": 4.2960268471590345e-05,
|
| 1338 |
+
"loss": 0.3774,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.06765899864682,
|
| 1343 |
+
"grad_norm": 0.2795134398632703,
|
| 1344 |
+
"learning_rate": 4.20650120437564e-05,
|
| 1345 |
+
"loss": 0.383,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.078484438430311,
|
| 1350 |
+
"grad_norm": 0.23404884349599717,
|
| 1351 |
+
"learning_rate": 4.1175842997513535e-05,
|
| 1352 |
+
"loss": 0.3862,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.089309878213802,
|
| 1357 |
+
"grad_norm": 0.2623191416209601,
|
| 1358 |
+
"learning_rate": 4.02929040167421e-05,
|
| 1359 |
+
"loss": 0.3784,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.1001353179972937,
|
| 1364 |
+
"grad_norm": 0.22037288605612937,
|
| 1365 |
+
"learning_rate": 3.9416336785591436e-05,
|
| 1366 |
+
"loss": 0.3705,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.1109607577807847,
|
| 1371 |
+
"grad_norm": 0.21836908464552335,
|
| 1372 |
+
"learning_rate": 3.854628196574387e-05,
|
| 1373 |
+
"loss": 0.3805,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.121786197564276,
|
| 1378 |
+
"grad_norm": 0.2557311206491114,
|
| 1379 |
+
"learning_rate": 3.768287917384303e-05,
|
| 1380 |
+
"loss": 0.378,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.1326116373477673,
|
| 1385 |
+
"grad_norm": 0.18179411448982316,
|
| 1386 |
+
"learning_rate": 3.682626695908964e-05,
|
| 1387 |
+
"loss": 0.3729,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.1434370771312583,
|
| 1392 |
+
"grad_norm": 0.2687321585152136,
|
| 1393 |
+
"learning_rate": 3.5976582781008695e-05,
|
| 1394 |
+
"loss": 0.3726,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.15426251691475,
|
| 1399 |
+
"grad_norm": 0.16496012357687265,
|
| 1400 |
+
"learning_rate": 3.5133962987391655e-05,
|
| 1401 |
+
"loss": 0.3791,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.165087956698241,
|
| 1406 |
+
"grad_norm": 0.201693140671645,
|
| 1407 |
+
"learning_rate": 3.42985427924166e-05,
|
| 1408 |
+
"loss": 0.3815,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.175913396481732,
|
| 1413 |
+
"grad_norm": 0.18160977177829019,
|
| 1414 |
+
"learning_rate": 3.347045625495088e-05,
|
| 1415 |
+
"loss": 0.3753,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.1867388362652234,
|
| 1420 |
+
"grad_norm": 0.17670354726721407,
|
| 1421 |
+
"learning_rate": 3.264983625703861e-05,
|
| 1422 |
+
"loss": 0.3731,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.1975642760487144,
|
| 1427 |
+
"grad_norm": 0.18581677779566666,
|
| 1428 |
+
"learning_rate": 3.1836814482577355e-05,
|
| 1429 |
+
"loss": 0.3803,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 2.208389715832206,
|
| 1434 |
+
"grad_norm": 0.17123638159588167,
|
| 1435 |
+
"learning_rate": 3.103152139618697e-05,
|
| 1436 |
+
"loss": 0.3779,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.219215155615697,
|
| 1441 |
+
"grad_norm": 0.20118541787477454,
|
| 1442 |
+
"learning_rate": 3.02340862222741e-05,
|
| 1443 |
+
"loss": 0.3764,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 2.230040595399188,
|
| 1448 |
+
"grad_norm": 0.1623232875171876,
|
| 1449 |
+
"learning_rate": 2.944463692429569e-05,
|
| 1450 |
+
"loss": 0.3772,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 2.2408660351826795,
|
| 1455 |
+
"grad_norm": 0.20276172261445644,
|
| 1456 |
+
"learning_rate": 2.866330018422481e-05,
|
| 1457 |
+
"loss": 0.3808,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.2516914749661705,
|
| 1462 |
+
"grad_norm": 0.16912420408288342,
|
| 1463 |
+
"learning_rate": 2.789020138222224e-05,
|
| 1464 |
+
"loss": 0.3714,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.2625169147496615,
|
| 1469 |
+
"grad_norm": 0.15940767575093126,
|
| 1470 |
+
"learning_rate": 2.7125464576516754e-05,
|
| 1471 |
+
"loss": 0.3762,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.273342354533153,
|
| 1476 |
+
"grad_norm": 0.15384987091038757,
|
| 1477 |
+
"learning_rate": 2.6369212483497714e-05,
|
| 1478 |
+
"loss": 0.372,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.284167794316644,
|
| 1483 |
+
"grad_norm": 0.13258610865988332,
|
| 1484 |
+
"learning_rate": 2.5621566458022972e-05,
|
| 1485 |
+
"loss": 0.3735,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.2949932341001356,
|
| 1490 |
+
"grad_norm": 0.15584495134484205,
|
| 1491 |
+
"learning_rate": 2.4882646473945072e-05,
|
| 1492 |
+
"loss": 0.3741,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.3058186738836266,
|
| 1497 |
+
"grad_norm": 0.13063314218715893,
|
| 1498 |
+
"learning_rate": 2.4152571104859284e-05,
|
| 1499 |
+
"loss": 0.3819,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.3166441136671176,
|
| 1504 |
+
"grad_norm": 0.15183169354187515,
|
| 1505 |
+
"learning_rate": 2.3431457505076205e-05,
|
| 1506 |
+
"loss": 0.3761,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.3274695534506087,
|
| 1511 |
+
"grad_norm": 0.15612284126375733,
|
| 1512 |
+
"learning_rate": 2.2719421390822173e-05,
|
| 1513 |
+
"loss": 0.3768,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.3382949932341,
|
| 1518 |
+
"grad_norm": 0.14653578705168283,
|
| 1519 |
+
"learning_rate": 2.201657702167042e-05,
|
| 1520 |
+
"loss": 0.3824,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.349120433017591,
|
| 1525 |
+
"grad_norm": 0.15086974405889184,
|
| 1526 |
+
"learning_rate": 2.1323037182205945e-05,
|
| 1527 |
+
"loss": 0.376,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.3599458728010827,
|
| 1532 |
+
"grad_norm": 0.1290378904007159,
|
| 1533 |
+
"learning_rate": 2.0638913163927156e-05,
|
| 1534 |
+
"loss": 0.3834,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.3707713125845737,
|
| 1539 |
+
"grad_norm": 0.13318235861496663,
|
| 1540 |
+
"learning_rate": 1.9964314747387005e-05,
|
| 1541 |
+
"loss": 0.3803,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.381596752368065,
|
| 1546 |
+
"grad_norm": 0.13330711346211635,
|
| 1547 |
+
"learning_rate": 1.9299350184576733e-05,
|
| 1548 |
+
"loss": 0.3691,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.3924221921515563,
|
| 1553 |
+
"grad_norm": 0.1279862282948995,
|
| 1554 |
+
"learning_rate": 1.8644126181554663e-05,
|
| 1555 |
+
"loss": 0.3757,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 2.4032476319350473,
|
| 1560 |
+
"grad_norm": 0.11677628138557435,
|
| 1561 |
+
"learning_rate": 1.79987478813233e-05,
|
| 1562 |
+
"loss": 0.3806,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.414073071718539,
|
| 1567 |
+
"grad_norm": 0.12619918683231618,
|
| 1568 |
+
"learning_rate": 1.7363318846957175e-05,
|
| 1569 |
+
"loss": 0.3803,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 2.42489851150203,
|
| 1574 |
+
"grad_norm": 0.1380173906206575,
|
| 1575 |
+
"learning_rate": 1.6737941044984127e-05,
|
| 1576 |
+
"loss": 0.3784,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 2.435723951285521,
|
| 1581 |
+
"grad_norm": 0.11282616881280712,
|
| 1582 |
+
"learning_rate": 1.612271482902292e-05,
|
| 1583 |
+
"loss": 0.3755,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.4465493910690124,
|
| 1588 |
+
"grad_norm": 0.13236199767020781,
|
| 1589 |
+
"learning_rate": 1.5517738923679616e-05,
|
| 1590 |
+
"loss": 0.379,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 2.4573748308525034,
|
| 1595 |
+
"grad_norm": 0.12480115347036357,
|
| 1596 |
+
"learning_rate": 1.492311040870531e-05,
|
| 1597 |
+
"loss": 0.3721,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 2.4682002706359945,
|
| 1602 |
+
"grad_norm": 0.11687086053065535,
|
| 1603 |
+
"learning_rate": 1.4338924703417916e-05,
|
| 1604 |
+
"loss": 0.3744,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 2.479025710419486,
|
| 1609 |
+
"grad_norm": 0.12453487485947455,
|
| 1610 |
+
"learning_rate": 1.3765275551390293e-05,
|
| 1611 |
+
"loss": 0.3718,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 2.489851150202977,
|
| 1616 |
+
"grad_norm": 0.12306865218763892,
|
| 1617 |
+
"learning_rate": 1.320225500540742e-05,
|
| 1618 |
+
"loss": 0.3724,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 2.500676589986468,
|
| 1623 |
+
"grad_norm": 0.10843672768522547,
|
| 1624 |
+
"learning_rate": 1.2649953412694634e-05,
|
| 1625 |
+
"loss": 0.3819,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 2.5115020297699595,
|
| 1630 |
+
"grad_norm": 0.11114457199744829,
|
| 1631 |
+
"learning_rate": 1.2108459400419919e-05,
|
| 1632 |
+
"loss": 0.3778,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 2.5223274695534506,
|
| 1637 |
+
"grad_norm": 0.1166727854863552,
|
| 1638 |
+
"learning_rate": 1.1577859861471833e-05,
|
| 1639 |
+
"loss": 0.3741,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.533152909336942,
|
| 1644 |
+
"grad_norm": 0.10791002146328788,
|
| 1645 |
+
"learning_rate": 1.1058239940516028e-05,
|
| 1646 |
+
"loss": 0.3773,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 2.543978349120433,
|
| 1651 |
+
"grad_norm": 0.10154469628935157,
|
| 1652 |
+
"learning_rate": 1.0549683020332125e-05,
|
| 1653 |
+
"loss": 0.3693,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 2.554803788903924,
|
| 1658 |
+
"grad_norm": 0.09966044957220346,
|
| 1659 |
+
"learning_rate": 1.0052270708433434e-05,
|
| 1660 |
+
"loss": 0.3696,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 2.565629228687415,
|
| 1665 |
+
"grad_norm": 0.09113621422642913,
|
| 1666 |
+
"learning_rate": 9.566082823971432e-06,
|
| 1667 |
+
"loss": 0.3759,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 2.5764546684709067,
|
| 1672 |
+
"grad_norm": 0.09597646217579717,
|
| 1673 |
+
"learning_rate": 9.09119738492735e-06,
|
| 1674 |
+
"loss": 0.375,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 2.5872801082543977,
|
| 1679 |
+
"grad_norm": 0.10190240288320754,
|
| 1680 |
+
"learning_rate": 8.627690595592653e-06,
|
| 1681 |
+
"loss": 0.3725,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 2.598105548037889,
|
| 1686 |
+
"grad_norm": 0.09510018971201405,
|
| 1687 |
+
"learning_rate": 8.175636834340674e-06,
|
| 1688 |
+
"loss": 0.3784,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.60893098782138,
|
| 1693 |
+
"grad_norm": 0.09762377519980237,
|
| 1694 |
+
"learning_rate": 7.735108641691202e-06,
|
| 1695 |
+
"loss": 0.3814,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.6197564276048713,
|
| 1700 |
+
"grad_norm": 0.09742308222941193,
|
| 1701 |
+
"learning_rate": 7.3061767086700075e-06,
|
| 1702 |
+
"loss": 0.381,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 2.6305818673883627,
|
| 1707 |
+
"grad_norm": 0.107032573161411,
|
| 1708 |
+
"learning_rate": 6.888909865465065e-06,
|
| 1709 |
+
"loss": 0.3724,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.641407307171854,
|
| 1714 |
+
"grad_norm": 0.10638149049322657,
|
| 1715 |
+
"learning_rate": 6.483375070381552e-06,
|
| 1716 |
+
"loss": 0.3715,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 2.6522327469553453,
|
| 1721 |
+
"grad_norm": 0.09269800135085551,
|
| 1722 |
+
"learning_rate": 6.0896373990970614e-06,
|
| 1723 |
+
"loss": 0.3721,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 2.6630581867388363,
|
| 1728 |
+
"grad_norm": 0.09447916428148233,
|
| 1729 |
+
"learning_rate": 5.707760034219032e-06,
|
| 1730 |
+
"loss": 0.3737,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 2.6738836265223274,
|
| 1735 |
+
"grad_norm": 0.10758712743393119,
|
| 1736 |
+
"learning_rate": 5.337804255145873e-06,
|
| 1737 |
+
"loss": 0.3779,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 2.6847090663058184,
|
| 1742 |
+
"grad_norm": 0.11068434930689386,
|
| 1743 |
+
"learning_rate": 4.979829428233576e-06,
|
| 1744 |
+
"loss": 0.3751,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 2.69553450608931,
|
| 1749 |
+
"grad_norm": 0.10188815124559192,
|
| 1750 |
+
"learning_rate": 4.63389299726921e-06,
|
| 1751 |
+
"loss": 0.3696,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.706359945872801,
|
| 1756 |
+
"grad_norm": 0.0846895734709407,
|
| 1757 |
+
"learning_rate": 4.3000504742530505e-06,
|
| 1758 |
+
"loss": 0.3809,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 2.7171853856562924,
|
| 1763 |
+
"grad_norm": 0.09582049879963728,
|
| 1764 |
+
"learning_rate": 3.978355430490614e-06,
|
| 1765 |
+
"loss": 0.3765,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 2.7280108254397835,
|
| 1770 |
+
"grad_norm": 0.08128736985428159,
|
| 1771 |
+
"learning_rate": 3.668859487996095e-06,
|
| 1772 |
+
"loss": 0.3799,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 2.7388362652232745,
|
| 1777 |
+
"grad_norm": 0.09410442627327706,
|
| 1778 |
+
"learning_rate": 3.371612311208692e-06,
|
| 1779 |
+
"loss": 0.3787,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 2.749661705006766,
|
| 1784 |
+
"grad_norm": 0.08704554678240813,
|
| 1785 |
+
"learning_rate": 3.0866615990230085e-06,
|
| 1786 |
+
"loss": 0.3726,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 2.760487144790257,
|
| 1791 |
+
"grad_norm": 0.08454007173317693,
|
| 1792 |
+
"learning_rate": 2.814053077134835e-06,
|
| 1793 |
+
"loss": 0.3689,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 2.7713125845737485,
|
| 1798 |
+
"grad_norm": 0.0842299187052216,
|
| 1799 |
+
"learning_rate": 2.553830490703666e-06,
|
| 1800 |
+
"loss": 0.3677,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 2.7821380243572396,
|
| 1805 |
+
"grad_norm": 0.08055057722300664,
|
| 1806 |
+
"learning_rate": 2.306035597332885e-06,
|
| 1807 |
+
"loss": 0.3796,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 2.7929634641407306,
|
| 1812 |
+
"grad_norm": 0.07811234003228873,
|
| 1813 |
+
"learning_rate": 2.0707081603690458e-06,
|
| 1814 |
+
"loss": 0.3733,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 2.803788903924222,
|
| 1819 |
+
"grad_norm": 0.07814276948421515,
|
| 1820 |
+
"learning_rate": 1.8478859425210548e-06,
|
| 1821 |
+
"loss": 0.3724,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 2.814614343707713,
|
| 1826 |
+
"grad_norm": 0.07992325685583533,
|
| 1827 |
+
"learning_rate": 1.6376046998004413e-06,
|
| 1828 |
+
"loss": 0.3784,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 2.825439783491204,
|
| 1833 |
+
"grad_norm": 0.08281854715683096,
|
| 1834 |
+
"learning_rate": 1.4398981757836628e-06,
|
| 1835 |
+
"loss": 0.3675,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 2.8362652232746957,
|
| 1840 |
+
"grad_norm": 0.07865994423809364,
|
| 1841 |
+
"learning_rate": 1.2547980961972629e-06,
|
| 1842 |
+
"loss": 0.3722,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 2.8470906630581867,
|
| 1847 |
+
"grad_norm": 0.0785799626146214,
|
| 1848 |
+
"learning_rate": 1.0823341638269303e-06,
|
| 1849 |
+
"loss": 0.377,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.8579161028416777,
|
| 1854 |
+
"grad_norm": 0.08336944108556697,
|
| 1855 |
+
"learning_rate": 9.225340537510897e-07,
|
| 1856 |
+
"loss": 0.3724,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 2.8687415426251692,
|
| 1861 |
+
"grad_norm": 0.07735010497815362,
|
| 1862 |
+
"learning_rate": 7.754234088999379e-07,
|
| 1863 |
+
"loss": 0.3779,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.8795669824086603,
|
| 1868 |
+
"grad_norm": 0.07582962822504996,
|
| 1869 |
+
"learning_rate": 6.410258359405585e-07,
|
| 1870 |
+
"loss": 0.3749,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 2.8903924221921518,
|
| 1875 |
+
"grad_norm": 0.07634846186806633,
|
| 1876 |
+
"learning_rate": 5.19362901488778e-07,
|
| 1877 |
+
"loss": 0.3713,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 2.901217861975643,
|
| 1882 |
+
"grad_norm": 0.07627711053895611,
|
| 1883 |
+
"learning_rate": 4.1045412864838765e-07,
|
| 1884 |
+
"loss": 0.3722,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 2.912043301759134,
|
| 1889 |
+
"grad_norm": 0.07557853802708582,
|
| 1890 |
+
"learning_rate": 3.143169938783253e-07,
|
| 1891 |
+
"loss": 0.3744,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 2.9228687415426253,
|
| 1896 |
+
"grad_norm": 0.08096730663606065,
|
| 1897 |
+
"learning_rate": 2.3096692418820733e-07,
|
| 1898 |
+
"loss": 0.377,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 2.9336941813261164,
|
| 1903 |
+
"grad_norm": 0.0767483032746884,
|
| 1904 |
+
"learning_rate": 1.6041729466280686e-07,
|
| 1905 |
+
"loss": 0.3725,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 2.944519621109608,
|
| 1910 |
+
"grad_norm": 0.07637424113539698,
|
| 1911 |
+
"learning_rate": 1.0267942631577932e-07,
|
| 1912 |
+
"loss": 0.3786,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 2.955345060893099,
|
| 1917 |
+
"grad_norm": 0.07515546978566537,
|
| 1918 |
+
"learning_rate": 5.7762584272937903e-08,
|
| 1919 |
+
"loss": 0.3765,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.96617050067659,
|
| 1924 |
+
"grad_norm": 0.07848788057525896,
|
| 1925 |
+
"learning_rate": 2.5673976285558455e-08,
|
| 1926 |
+
"loss": 0.3746,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 2.976995940460081,
|
| 1931 |
+
"grad_norm": 0.07564833351349101,
|
| 1932 |
+
"learning_rate": 6.418751573713522e-09,
|
| 1933 |
+
"loss": 0.3818,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 2.9878213802435725,
|
| 1938 |
+
"grad_norm": 0.07278613437346892,
|
| 1939 |
+
"learning_rate": 0.0,
|
| 1940 |
+
"loss": 0.37,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 2.9878213802435725,
|
| 1945 |
+
"step": 276,
|
| 1946 |
+
"total_flos": 6.629121904995205e+18,
|
| 1947 |
+
"train_loss": 0.4911867194417594,
|
| 1948 |
+
"train_runtime": 27032.019,
|
| 1949 |
+
"train_samples_per_second": 5.248,
|
| 1950 |
+
"train_steps_per_second": 0.01
|
| 1951 |
+
}
|
| 1952 |
+
],
|
| 1953 |
+
"logging_steps": 1.0,
|
| 1954 |
+
"max_steps": 276,
|
| 1955 |
+
"num_input_tokens_seen": 0,
|
| 1956 |
+
"num_train_epochs": 3,
|
| 1957 |
+
"save_steps": 500,
|
| 1958 |
+
"stateful_callbacks": {
|
| 1959 |
+
"TrainerControl": {
|
| 1960 |
+
"args": {
|
| 1961 |
+
"should_epoch_stop": false,
|
| 1962 |
+
"should_evaluate": false,
|
| 1963 |
+
"should_log": false,
|
| 1964 |
+
"should_save": true,
|
| 1965 |
+
"should_training_stop": true
|
| 1966 |
+
},
|
| 1967 |
+
"attributes": {}
|
| 1968 |
+
}
|
| 1969 |
+
},
|
| 1970 |
+
"total_flos": 6.629121904995205e+18,
|
| 1971 |
+
"train_batch_size": 1,
|
| 1972 |
+
"trial_name": null,
|
| 1973 |
+
"trial_params": null
|
| 1974 |
+
}
|
training_loss.png
ADDED
|