End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +3696 -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_96_lr4e5
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# global_batchsize_96_lr4e5
|
| 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_96_lr4e5
|
|
|
|
| 16 |
|
| 17 |
# global_batchsize_96_lr4e5
|
| 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 bespokelabs/Bespoke-Stratos-17k dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.994263862332696,
|
| 3 |
+
"total_flos": 5.620362022127534e+17,
|
| 4 |
+
"train_loss": 0.4276364711452261,
|
| 5 |
+
"train_runtime": 8560.5176,
|
| 6 |
+
"train_samples_per_second": 5.856,
|
| 7 |
+
"train_steps_per_second": 0.061
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.994263862332696,
|
| 3 |
+
"total_flos": 5.620362022127534e+17,
|
| 4 |
+
"train_loss": 0.4276364711452261,
|
| 5 |
+
"train_runtime": 8560.5176,
|
| 6 |
+
"train_samples_per_second": 5.856,
|
| 7 |
+
"train_steps_per_second": 0.061
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3696 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.994263862332696,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 522,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0057361376673040155,
|
| 13 |
+
"grad_norm": 5.963601353196484,
|
| 14 |
+
"learning_rate": 7.547169811320755e-07,
|
| 15 |
+
"loss": 0.8872,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.011472275334608031,
|
| 20 |
+
"grad_norm": 6.333467701978284,
|
| 21 |
+
"learning_rate": 1.509433962264151e-06,
|
| 22 |
+
"loss": 0.9165,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.017208413001912046,
|
| 27 |
+
"grad_norm": 6.231014140658969,
|
| 28 |
+
"learning_rate": 2.2641509433962266e-06,
|
| 29 |
+
"loss": 0.9408,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.022944550669216062,
|
| 34 |
+
"grad_norm": 5.646301524394669,
|
| 35 |
+
"learning_rate": 3.018867924528302e-06,
|
| 36 |
+
"loss": 0.8925,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.028680688336520075,
|
| 41 |
+
"grad_norm": 4.6749029765975045,
|
| 42 |
+
"learning_rate": 3.7735849056603777e-06,
|
| 43 |
+
"loss": 0.8569,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03441682600382409,
|
| 48 |
+
"grad_norm": 4.477470504435412,
|
| 49 |
+
"learning_rate": 4.528301886792453e-06,
|
| 50 |
+
"loss": 0.8331,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.040152963671128104,
|
| 55 |
+
"grad_norm": 2.469128428269406,
|
| 56 |
+
"learning_rate": 5.283018867924529e-06,
|
| 57 |
+
"loss": 0.8192,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.045889101338432124,
|
| 62 |
+
"grad_norm": 3.1842562805095596,
|
| 63 |
+
"learning_rate": 6.037735849056604e-06,
|
| 64 |
+
"loss": 0.7936,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.05162523900573614,
|
| 69 |
+
"grad_norm": 4.1014744450012195,
|
| 70 |
+
"learning_rate": 6.792452830188679e-06,
|
| 71 |
+
"loss": 0.7749,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.05736137667304015,
|
| 76 |
+
"grad_norm": 4.176176317229083,
|
| 77 |
+
"learning_rate": 7.5471698113207555e-06,
|
| 78 |
+
"loss": 0.8084,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.06309751434034416,
|
| 83 |
+
"grad_norm": 3.5718306849844206,
|
| 84 |
+
"learning_rate": 8.301886792452832e-06,
|
| 85 |
+
"loss": 0.7579,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.06883365200764818,
|
| 90 |
+
"grad_norm": 2.9545908685425166,
|
| 91 |
+
"learning_rate": 9.056603773584907e-06,
|
| 92 |
+
"loss": 0.6838,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0745697896749522,
|
| 97 |
+
"grad_norm": 2.484202012476629,
|
| 98 |
+
"learning_rate": 9.811320754716981e-06,
|
| 99 |
+
"loss": 0.7421,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.08030592734225621,
|
| 104 |
+
"grad_norm": 1.6256320736281968,
|
| 105 |
+
"learning_rate": 1.0566037735849058e-05,
|
| 106 |
+
"loss": 0.6922,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.08604206500956023,
|
| 111 |
+
"grad_norm": 1.8910779905338204,
|
| 112 |
+
"learning_rate": 1.1320754716981132e-05,
|
| 113 |
+
"loss": 0.695,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.09177820267686425,
|
| 118 |
+
"grad_norm": 2.1618666538191085,
|
| 119 |
+
"learning_rate": 1.2075471698113209e-05,
|
| 120 |
+
"loss": 0.6969,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09751434034416825,
|
| 125 |
+
"grad_norm": 1.6536038409758815,
|
| 126 |
+
"learning_rate": 1.2830188679245283e-05,
|
| 127 |
+
"loss": 0.6608,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.10325047801147227,
|
| 132 |
+
"grad_norm": 1.1899674167485872,
|
| 133 |
+
"learning_rate": 1.3584905660377358e-05,
|
| 134 |
+
"loss": 0.6611,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1089866156787763,
|
| 139 |
+
"grad_norm": 1.3839358683063427,
|
| 140 |
+
"learning_rate": 1.4339622641509435e-05,
|
| 141 |
+
"loss": 0.5937,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.1147227533460803,
|
| 146 |
+
"grad_norm": 1.2164557799105977,
|
| 147 |
+
"learning_rate": 1.5094339622641511e-05,
|
| 148 |
+
"loss": 0.6311,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.12045889101338432,
|
| 153 |
+
"grad_norm": 0.9617228211418869,
|
| 154 |
+
"learning_rate": 1.5849056603773586e-05,
|
| 155 |
+
"loss": 0.613,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.12619502868068833,
|
| 160 |
+
"grad_norm": 0.9112538434649583,
|
| 161 |
+
"learning_rate": 1.6603773584905664e-05,
|
| 162 |
+
"loss": 0.6066,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.13193116634799235,
|
| 167 |
+
"grad_norm": 0.9079396604897542,
|
| 168 |
+
"learning_rate": 1.735849056603774e-05,
|
| 169 |
+
"loss": 0.5748,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.13766730401529637,
|
| 174 |
+
"grad_norm": 1.0350466631308726,
|
| 175 |
+
"learning_rate": 1.8113207547169813e-05,
|
| 176 |
+
"loss": 0.6075,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.14340344168260039,
|
| 181 |
+
"grad_norm": 0.7428776620391337,
|
| 182 |
+
"learning_rate": 1.8867924528301888e-05,
|
| 183 |
+
"loss": 0.5943,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.1491395793499044,
|
| 188 |
+
"grad_norm": 0.8363548105185957,
|
| 189 |
+
"learning_rate": 1.9622641509433963e-05,
|
| 190 |
+
"loss": 0.5737,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.15487571701720843,
|
| 195 |
+
"grad_norm": 1.110084813808486,
|
| 196 |
+
"learning_rate": 2.037735849056604e-05,
|
| 197 |
+
"loss": 0.6161,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.16061185468451242,
|
| 202 |
+
"grad_norm": 0.6819468789186882,
|
| 203 |
+
"learning_rate": 2.1132075471698115e-05,
|
| 204 |
+
"loss": 0.594,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.16634799235181644,
|
| 209 |
+
"grad_norm": 1.0895642393194147,
|
| 210 |
+
"learning_rate": 2.188679245283019e-05,
|
| 211 |
+
"loss": 0.5809,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.17208413001912046,
|
| 216 |
+
"grad_norm": 0.9651676521976803,
|
| 217 |
+
"learning_rate": 2.2641509433962265e-05,
|
| 218 |
+
"loss": 0.5813,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.17782026768642448,
|
| 223 |
+
"grad_norm": 0.8124804726360065,
|
| 224 |
+
"learning_rate": 2.339622641509434e-05,
|
| 225 |
+
"loss": 0.5523,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1835564053537285,
|
| 230 |
+
"grad_norm": 0.851159676858117,
|
| 231 |
+
"learning_rate": 2.4150943396226418e-05,
|
| 232 |
+
"loss": 0.5376,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.18929254302103252,
|
| 237 |
+
"grad_norm": 0.8124902743389897,
|
| 238 |
+
"learning_rate": 2.4905660377358492e-05,
|
| 239 |
+
"loss": 0.5652,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.1950286806883365,
|
| 244 |
+
"grad_norm": 0.8368258661976667,
|
| 245 |
+
"learning_rate": 2.5660377358490567e-05,
|
| 246 |
+
"loss": 0.5927,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.20076481835564053,
|
| 251 |
+
"grad_norm": 0.653616572010454,
|
| 252 |
+
"learning_rate": 2.641509433962264e-05,
|
| 253 |
+
"loss": 0.5668,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.20650095602294455,
|
| 258 |
+
"grad_norm": 0.7162845997163322,
|
| 259 |
+
"learning_rate": 2.7169811320754716e-05,
|
| 260 |
+
"loss": 0.5569,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.21223709369024857,
|
| 265 |
+
"grad_norm": 0.689294680809673,
|
| 266 |
+
"learning_rate": 2.7924528301886794e-05,
|
| 267 |
+
"loss": 0.5566,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.2179732313575526,
|
| 272 |
+
"grad_norm": 0.872345722524905,
|
| 273 |
+
"learning_rate": 2.867924528301887e-05,
|
| 274 |
+
"loss": 0.5757,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2237093690248566,
|
| 279 |
+
"grad_norm": 0.8894547605087567,
|
| 280 |
+
"learning_rate": 2.9433962264150944e-05,
|
| 281 |
+
"loss": 0.5794,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.2294455066921606,
|
| 286 |
+
"grad_norm": 0.6582795524486181,
|
| 287 |
+
"learning_rate": 3.0188679245283022e-05,
|
| 288 |
+
"loss": 0.5319,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.23518164435946462,
|
| 293 |
+
"grad_norm": 2.7193829449558033,
|
| 294 |
+
"learning_rate": 3.09433962264151e-05,
|
| 295 |
+
"loss": 0.587,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.24091778202676864,
|
| 300 |
+
"grad_norm": 0.9717090471397071,
|
| 301 |
+
"learning_rate": 3.169811320754717e-05,
|
| 302 |
+
"loss": 0.5268,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.24665391969407266,
|
| 307 |
+
"grad_norm": 0.9224645496458574,
|
| 308 |
+
"learning_rate": 3.245283018867925e-05,
|
| 309 |
+
"loss": 0.5802,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.25239005736137665,
|
| 314 |
+
"grad_norm": 0.8938202665523605,
|
| 315 |
+
"learning_rate": 3.320754716981133e-05,
|
| 316 |
+
"loss": 0.5766,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.25812619502868067,
|
| 321 |
+
"grad_norm": 0.9583812403407647,
|
| 322 |
+
"learning_rate": 3.39622641509434e-05,
|
| 323 |
+
"loss": 0.561,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.2638623326959847,
|
| 328 |
+
"grad_norm": 1.228357544928824,
|
| 329 |
+
"learning_rate": 3.471698113207548e-05,
|
| 330 |
+
"loss": 0.5193,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2695984703632887,
|
| 335 |
+
"grad_norm": 1.1698249381113741,
|
| 336 |
+
"learning_rate": 3.547169811320755e-05,
|
| 337 |
+
"loss": 0.5639,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.27533460803059273,
|
| 342 |
+
"grad_norm": 0.8489845786136891,
|
| 343 |
+
"learning_rate": 3.6226415094339626e-05,
|
| 344 |
+
"loss": 0.549,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.28107074569789675,
|
| 349 |
+
"grad_norm": 1.57687219740748,
|
| 350 |
+
"learning_rate": 3.6981132075471704e-05,
|
| 351 |
+
"loss": 0.5742,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.28680688336520077,
|
| 356 |
+
"grad_norm": 0.8718037736589133,
|
| 357 |
+
"learning_rate": 3.7735849056603776e-05,
|
| 358 |
+
"loss": 0.5326,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2925430210325048,
|
| 363 |
+
"grad_norm": 1.2871827675643652,
|
| 364 |
+
"learning_rate": 3.8490566037735854e-05,
|
| 365 |
+
"loss": 0.5245,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.2982791586998088,
|
| 370 |
+
"grad_norm": 1.0013962294494378,
|
| 371 |
+
"learning_rate": 3.9245283018867925e-05,
|
| 372 |
+
"loss": 0.5621,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.30401529636711283,
|
| 377 |
+
"grad_norm": 1.1733505550953005,
|
| 378 |
+
"learning_rate": 4e-05,
|
| 379 |
+
"loss": 0.5527,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.30975143403441685,
|
| 384 |
+
"grad_norm": 0.8228183926039204,
|
| 385 |
+
"learning_rate": 3.999955130375398e-05,
|
| 386 |
+
"loss": 0.5207,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.3154875717017208,
|
| 391 |
+
"grad_norm": 0.9720081493962336,
|
| 392 |
+
"learning_rate": 3.999820523514873e-05,
|
| 393 |
+
"loss": 0.5388,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.32122370936902483,
|
| 398 |
+
"grad_norm": 0.8768396168768982,
|
| 399 |
+
"learning_rate": 3.9995961854581855e-05,
|
| 400 |
+
"loss": 0.5443,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.32695984703632885,
|
| 405 |
+
"grad_norm": 0.9885103652652149,
|
| 406 |
+
"learning_rate": 3.999282126271299e-05,
|
| 407 |
+
"loss": 0.5475,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3326959847036329,
|
| 412 |
+
"grad_norm": 0.7263822248844192,
|
| 413 |
+
"learning_rate": 3.998878360045933e-05,
|
| 414 |
+
"loss": 0.5471,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.3384321223709369,
|
| 419 |
+
"grad_norm": 0.7898997625317963,
|
| 420 |
+
"learning_rate": 3.998384904898926e-05,
|
| 421 |
+
"loss": 0.532,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.3441682600382409,
|
| 426 |
+
"grad_norm": 0.7388781217225304,
|
| 427 |
+
"learning_rate": 3.997801782971423e-05,
|
| 428 |
+
"loss": 0.5196,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.34990439770554493,
|
| 433 |
+
"grad_norm": 0.7257057362841633,
|
| 434 |
+
"learning_rate": 3.997129020427888e-05,
|
| 435 |
+
"loss": 0.5485,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.35564053537284895,
|
| 440 |
+
"grad_norm": 0.6438468755093205,
|
| 441 |
+
"learning_rate": 3.996366647454924e-05,
|
| 442 |
+
"loss": 0.5466,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.361376673040153,
|
| 447 |
+
"grad_norm": 0.6663878490068373,
|
| 448 |
+
"learning_rate": 3.9955146982599194e-05,
|
| 449 |
+
"loss": 0.5468,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.367112810707457,
|
| 454 |
+
"grad_norm": 0.6745599593845647,
|
| 455 |
+
"learning_rate": 3.9945732110695145e-05,
|
| 456 |
+
"loss": 0.525,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.372848948374761,
|
| 461 |
+
"grad_norm": 0.7081809867814687,
|
| 462 |
+
"learning_rate": 3.993542228127886e-05,
|
| 463 |
+
"loss": 0.5382,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.37858508604206503,
|
| 468 |
+
"grad_norm": 0.7366611396520816,
|
| 469 |
+
"learning_rate": 3.992421795694853e-05,
|
| 470 |
+
"loss": 0.5431,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.384321223709369,
|
| 475 |
+
"grad_norm": 0.7027778770800306,
|
| 476 |
+
"learning_rate": 3.9912119640437965e-05,
|
| 477 |
+
"loss": 0.5154,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.390057361376673,
|
| 482 |
+
"grad_norm": 0.6666822720365386,
|
| 483 |
+
"learning_rate": 3.989912787459409e-05,
|
| 484 |
+
"loss": 0.527,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.39579349904397704,
|
| 489 |
+
"grad_norm": 0.5660749653496684,
|
| 490 |
+
"learning_rate": 3.9885243242352565e-05,
|
| 491 |
+
"loss": 0.5351,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.40152963671128106,
|
| 496 |
+
"grad_norm": 0.5576960477632893,
|
| 497 |
+
"learning_rate": 3.987046636671162e-05,
|
| 498 |
+
"loss": 0.4824,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.4072657743785851,
|
| 503 |
+
"grad_norm": 0.658340932840387,
|
| 504 |
+
"learning_rate": 3.9854797910704124e-05,
|
| 505 |
+
"loss": 0.5364,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.4130019120458891,
|
| 510 |
+
"grad_norm": 0.6117526542482664,
|
| 511 |
+
"learning_rate": 3.9838238577367816e-05,
|
| 512 |
+
"loss": 0.5014,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.4187380497131931,
|
| 517 |
+
"grad_norm": 0.5936168327692725,
|
| 518 |
+
"learning_rate": 3.982078910971376e-05,
|
| 519 |
+
"loss": 0.5349,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.42447418738049714,
|
| 524 |
+
"grad_norm": 0.687524043308455,
|
| 525 |
+
"learning_rate": 3.980245029069302e-05,
|
| 526 |
+
"loss": 0.5334,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.43021032504780116,
|
| 531 |
+
"grad_norm": 0.6835492486583609,
|
| 532 |
+
"learning_rate": 3.978322294316153e-05,
|
| 533 |
+
"loss": 0.5509,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4359464627151052,
|
| 538 |
+
"grad_norm": 0.5286499638619044,
|
| 539 |
+
"learning_rate": 3.976310792984315e-05,
|
| 540 |
+
"loss": 0.5323,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.4416826003824092,
|
| 545 |
+
"grad_norm": 0.6642388755587706,
|
| 546 |
+
"learning_rate": 3.974210615329098e-05,
|
| 547 |
+
"loss": 0.5451,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.4474187380497132,
|
| 552 |
+
"grad_norm": 0.4999354398609915,
|
| 553 |
+
"learning_rate": 3.9720218555846834e-05,
|
| 554 |
+
"loss": 0.5339,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.45315487571701724,
|
| 559 |
+
"grad_norm": 0.642751208835366,
|
| 560 |
+
"learning_rate": 3.9697446119599015e-05,
|
| 561 |
+
"loss": 0.544,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.4588910133843212,
|
| 566 |
+
"grad_norm": 0.719086166881077,
|
| 567 |
+
"learning_rate": 3.967378986633818e-05,
|
| 568 |
+
"loss": 0.5256,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.4646271510516252,
|
| 573 |
+
"grad_norm": 0.6270310635224952,
|
| 574 |
+
"learning_rate": 3.964925085751152e-05,
|
| 575 |
+
"loss": 0.53,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.47036328871892924,
|
| 580 |
+
"grad_norm": 0.6955843238682398,
|
| 581 |
+
"learning_rate": 3.9623830194175175e-05,
|
| 582 |
+
"loss": 0.552,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.47609942638623326,
|
| 587 |
+
"grad_norm": 0.6300967187312061,
|
| 588 |
+
"learning_rate": 3.9597529016944746e-05,
|
| 589 |
+
"loss": 0.5265,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.4818355640535373,
|
| 594 |
+
"grad_norm": 0.6927514450309129,
|
| 595 |
+
"learning_rate": 3.9570348505944185e-05,
|
| 596 |
+
"loss": 0.5389,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.4875717017208413,
|
| 601 |
+
"grad_norm": 0.6581382765482165,
|
| 602 |
+
"learning_rate": 3.9542289880752827e-05,
|
| 603 |
+
"loss": 0.5258,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.4933078393881453,
|
| 608 |
+
"grad_norm": 0.6347863955072047,
|
| 609 |
+
"learning_rate": 3.951335440035063e-05,
|
| 610 |
+
"loss": 0.5295,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.49904397705544934,
|
| 615 |
+
"grad_norm": 0.7550386421946482,
|
| 616 |
+
"learning_rate": 3.948354336306176e-05,
|
| 617 |
+
"loss": 0.5516,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.5047801147227533,
|
| 622 |
+
"grad_norm": 0.5280267134452366,
|
| 623 |
+
"learning_rate": 3.945285810649626e-05,
|
| 624 |
+
"loss": 0.5315,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5105162523900574,
|
| 629 |
+
"grad_norm": 0.649947445862538,
|
| 630 |
+
"learning_rate": 3.942130000749008e-05,
|
| 631 |
+
"loss": 0.5415,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.5162523900573613,
|
| 636 |
+
"grad_norm": 0.5480518529513726,
|
| 637 |
+
"learning_rate": 3.938887048204326e-05,
|
| 638 |
+
"loss": 0.5465,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5219885277246654,
|
| 643 |
+
"grad_norm": 0.5610828231392423,
|
| 644 |
+
"learning_rate": 3.935557098525644e-05,
|
| 645 |
+
"loss": 0.5005,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.5277246653919694,
|
| 650 |
+
"grad_norm": 0.5706185940759887,
|
| 651 |
+
"learning_rate": 3.9321403011265546e-05,
|
| 652 |
+
"loss": 0.5189,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.5334608030592735,
|
| 657 |
+
"grad_norm": 0.5626627671265411,
|
| 658 |
+
"learning_rate": 3.9286368093174745e-05,
|
| 659 |
+
"loss": 0.5277,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.5391969407265774,
|
| 664 |
+
"grad_norm": 0.6290463734820702,
|
| 665 |
+
"learning_rate": 3.925046780298764e-05,
|
| 666 |
+
"loss": 0.5237,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5449330783938815,
|
| 671 |
+
"grad_norm": 0.5701628353252369,
|
| 672 |
+
"learning_rate": 3.921370375153681e-05,
|
| 673 |
+
"loss": 0.5348,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.5506692160611855,
|
| 678 |
+
"grad_norm": 0.6186142129858236,
|
| 679 |
+
"learning_rate": 3.917607758841141e-05,
|
| 680 |
+
"loss": 0.5349,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.5564053537284895,
|
| 685 |
+
"grad_norm": 0.4973723214529781,
|
| 686 |
+
"learning_rate": 3.913759100188327e-05,
|
| 687 |
+
"loss": 0.5061,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.5621414913957935,
|
| 692 |
+
"grad_norm": 0.682743340827704,
|
| 693 |
+
"learning_rate": 3.9098245718831076e-05,
|
| 694 |
+
"loss": 0.5615,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.5678776290630975,
|
| 699 |
+
"grad_norm": 0.6357989822661191,
|
| 700 |
+
"learning_rate": 3.905804350466291e-05,
|
| 701 |
+
"loss": 0.5243,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.5736137667304015,
|
| 706 |
+
"grad_norm": 0.5449769248133205,
|
| 707 |
+
"learning_rate": 3.901698616323703e-05,
|
| 708 |
+
"loss": 0.5155,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.5793499043977055,
|
| 713 |
+
"grad_norm": 0.6266775770075623,
|
| 714 |
+
"learning_rate": 3.897507553678093e-05,
|
| 715 |
+
"loss": 0.5451,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.5850860420650096,
|
| 720 |
+
"grad_norm": 0.7475144523577113,
|
| 721 |
+
"learning_rate": 3.893231350580869e-05,
|
| 722 |
+
"loss": 0.5383,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.5908221797323135,
|
| 727 |
+
"grad_norm": 0.5434812815586433,
|
| 728 |
+
"learning_rate": 3.888870198903658e-05,
|
| 729 |
+
"loss": 0.5316,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.5965583173996176,
|
| 734 |
+
"grad_norm": 0.6008597770179454,
|
| 735 |
+
"learning_rate": 3.8844242943297e-05,
|
| 736 |
+
"loss": 0.523,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.6022944550669216,
|
| 741 |
+
"grad_norm": 0.6384325056734049,
|
| 742 |
+
"learning_rate": 3.879893836345062e-05,
|
| 743 |
+
"loss": 0.5153,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.6080305927342257,
|
| 748 |
+
"grad_norm": 0.5480218749548357,
|
| 749 |
+
"learning_rate": 3.875279028229695e-05,
|
| 750 |
+
"loss": 0.5432,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.6137667304015296,
|
| 755 |
+
"grad_norm": 0.6160281910387104,
|
| 756 |
+
"learning_rate": 3.870580077048307e-05,
|
| 757 |
+
"loss": 0.5296,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.6195028680688337,
|
| 762 |
+
"grad_norm": 0.6894563819781858,
|
| 763 |
+
"learning_rate": 3.865797193641072e-05,
|
| 764 |
+
"loss": 0.5355,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.6252390057361377,
|
| 769 |
+
"grad_norm": 0.4774944165107399,
|
| 770 |
+
"learning_rate": 3.8609305926141735e-05,
|
| 771 |
+
"loss": 0.4964,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.6309751434034416,
|
| 776 |
+
"grad_norm": 0.7099537904032711,
|
| 777 |
+
"learning_rate": 3.855980492330173e-05,
|
| 778 |
+
"loss": 0.5399,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.6367112810707457,
|
| 783 |
+
"grad_norm": 0.6001030131052923,
|
| 784 |
+
"learning_rate": 3.850947114898212e-05,
|
| 785 |
+
"loss": 0.54,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.6424474187380497,
|
| 790 |
+
"grad_norm": 0.6169400599723738,
|
| 791 |
+
"learning_rate": 3.8458306861640465e-05,
|
| 792 |
+
"loss": 0.5478,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6481835564053537,
|
| 797 |
+
"grad_norm": 0.6331995497335126,
|
| 798 |
+
"learning_rate": 3.840631435699912e-05,
|
| 799 |
+
"loss": 0.5089,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.6539196940726577,
|
| 804 |
+
"grad_norm": 0.6758544384585873,
|
| 805 |
+
"learning_rate": 3.835349596794226e-05,
|
| 806 |
+
"loss": 0.524,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.6596558317399618,
|
| 811 |
+
"grad_norm": 0.6066427921666631,
|
| 812 |
+
"learning_rate": 3.829985406441118e-05,
|
| 813 |
+
"loss": 0.5371,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.6653919694072657,
|
| 818 |
+
"grad_norm": 0.6205375496679291,
|
| 819 |
+
"learning_rate": 3.8245391053297936e-05,
|
| 820 |
+
"loss": 0.4979,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.6711281070745698,
|
| 825 |
+
"grad_norm": 0.5806033479161776,
|
| 826 |
+
"learning_rate": 3.8190109378337413e-05,
|
| 827 |
+
"loss": 0.5239,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.6768642447418738,
|
| 832 |
+
"grad_norm": 0.6460511560696024,
|
| 833 |
+
"learning_rate": 3.813401151999759e-05,
|
| 834 |
+
"loss": 0.5475,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.6826003824091779,
|
| 839 |
+
"grad_norm": 0.5453484149762959,
|
| 840 |
+
"learning_rate": 3.807709999536834e-05,
|
| 841 |
+
"loss": 0.5395,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.6883365200764818,
|
| 846 |
+
"grad_norm": 0.5318167624766734,
|
| 847 |
+
"learning_rate": 3.801937735804838e-05,
|
| 848 |
+
"loss": 0.5087,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.6940726577437859,
|
| 853 |
+
"grad_norm": 0.8271638416761657,
|
| 854 |
+
"learning_rate": 3.7960846198030804e-05,
|
| 855 |
+
"loss": 0.5453,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.6998087954110899,
|
| 860 |
+
"grad_norm": 0.6479532137119753,
|
| 861 |
+
"learning_rate": 3.790150914158677e-05,
|
| 862 |
+
"loss": 0.5043,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.7055449330783938,
|
| 867 |
+
"grad_norm": 0.7435964195190743,
|
| 868 |
+
"learning_rate": 3.784136885114773e-05,
|
| 869 |
+
"loss": 0.5129,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.7112810707456979,
|
| 874 |
+
"grad_norm": 0.8946003605016197,
|
| 875 |
+
"learning_rate": 3.7780428025185954e-05,
|
| 876 |
+
"loss": 0.5533,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.7170172084130019,
|
| 881 |
+
"grad_norm": 0.6464116296407747,
|
| 882 |
+
"learning_rate": 3.77186893980934e-05,
|
| 883 |
+
"loss": 0.5421,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.722753346080306,
|
| 888 |
+
"grad_norm": 0.7126674023402929,
|
| 889 |
+
"learning_rate": 3.765615574005911e-05,
|
| 890 |
+
"loss": 0.5139,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.7284894837476099,
|
| 895 |
+
"grad_norm": 0.8135984381109922,
|
| 896 |
+
"learning_rate": 3.7592829856944835e-05,
|
| 897 |
+
"loss": 0.511,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.734225621414914,
|
| 902 |
+
"grad_norm": 0.7828468225319082,
|
| 903 |
+
"learning_rate": 3.752871459015918e-05,
|
| 904 |
+
"loss": 0.5286,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.739961759082218,
|
| 909 |
+
"grad_norm": 0.642287015277123,
|
| 910 |
+
"learning_rate": 3.74638128165301e-05,
|
| 911 |
+
"loss": 0.5329,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.745697896749522,
|
| 916 |
+
"grad_norm": 0.5442493722807862,
|
| 917 |
+
"learning_rate": 3.739812744817581e-05,
|
| 918 |
+
"loss": 0.5362,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.751434034416826,
|
| 923 |
+
"grad_norm": 0.5568845351714643,
|
| 924 |
+
"learning_rate": 3.733166143237413e-05,
|
| 925 |
+
"loss": 0.5035,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.7571701720841301,
|
| 930 |
+
"grad_norm": 0.49191832987393536,
|
| 931 |
+
"learning_rate": 3.7264417751430244e-05,
|
| 932 |
+
"loss": 0.5085,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.762906309751434,
|
| 937 |
+
"grad_norm": 0.6805242608433807,
|
| 938 |
+
"learning_rate": 3.7196399422542866e-05,
|
| 939 |
+
"loss": 0.5065,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.768642447418738,
|
| 944 |
+
"grad_norm": 0.5897633089426585,
|
| 945 |
+
"learning_rate": 3.712760949766888e-05,
|
| 946 |
+
"loss": 0.5038,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.7743785850860421,
|
| 951 |
+
"grad_norm": 0.6094976285430489,
|
| 952 |
+
"learning_rate": 3.70580510633864e-05,
|
| 953 |
+
"loss": 0.5008,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.780114722753346,
|
| 958 |
+
"grad_norm": 0.5467744310721907,
|
| 959 |
+
"learning_rate": 3.6987727240756246e-05,
|
| 960 |
+
"loss": 0.5142,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.7858508604206501,
|
| 965 |
+
"grad_norm": 0.5880627703365717,
|
| 966 |
+
"learning_rate": 3.691664118518195e-05,
|
| 967 |
+
"loss": 0.4994,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.7915869980879541,
|
| 972 |
+
"grad_norm": 0.5006717341236084,
|
| 973 |
+
"learning_rate": 3.6844796086268136e-05,
|
| 974 |
+
"loss": 0.5164,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.7973231357552581,
|
| 979 |
+
"grad_norm": 0.5642072424368477,
|
| 980 |
+
"learning_rate": 3.677219516767743e-05,
|
| 981 |
+
"loss": 0.5349,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.8030592734225621,
|
| 986 |
+
"grad_norm": 0.5741831253551103,
|
| 987 |
+
"learning_rate": 3.669884168698578e-05,
|
| 988 |
+
"loss": 0.559,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.8087954110898662,
|
| 993 |
+
"grad_norm": 0.5577991231255239,
|
| 994 |
+
"learning_rate": 3.6624738935536336e-05,
|
| 995 |
+
"loss": 0.5082,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.8145315487571702,
|
| 1000 |
+
"grad_norm": 0.6263509656905389,
|
| 1001 |
+
"learning_rate": 3.654989023829174e-05,
|
| 1002 |
+
"loss": 0.5401,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.8202676864244742,
|
| 1007 |
+
"grad_norm": 0.562818325762248,
|
| 1008 |
+
"learning_rate": 3.6474298953684945e-05,
|
| 1009 |
+
"loss": 0.5071,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.8260038240917782,
|
| 1014 |
+
"grad_norm": 0.5540399435211395,
|
| 1015 |
+
"learning_rate": 3.639796847346849e-05,
|
| 1016 |
+
"loss": 0.5343,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.8317399617590823,
|
| 1021 |
+
"grad_norm": 0.5580743271553504,
|
| 1022 |
+
"learning_rate": 3.6320902222562405e-05,
|
| 1023 |
+
"loss": 0.515,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.8374760994263862,
|
| 1028 |
+
"grad_norm": 0.5846568206692573,
|
| 1029 |
+
"learning_rate": 3.62431036589004e-05,
|
| 1030 |
+
"loss": 0.5235,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.8432122370936902,
|
| 1035 |
+
"grad_norm": 0.6959565954811155,
|
| 1036 |
+
"learning_rate": 3.616457627327484e-05,
|
| 1037 |
+
"loss": 0.5075,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.8489483747609943,
|
| 1042 |
+
"grad_norm": 0.565057362201928,
|
| 1043 |
+
"learning_rate": 3.6085323589180046e-05,
|
| 1044 |
+
"loss": 0.5092,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.8546845124282982,
|
| 1049 |
+
"grad_norm": 0.6281295561065597,
|
| 1050 |
+
"learning_rate": 3.600534916265419e-05,
|
| 1051 |
+
"loss": 0.4943,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.8604206500956023,
|
| 1056 |
+
"grad_norm": 0.6023614171022365,
|
| 1057 |
+
"learning_rate": 3.592465658211977e-05,
|
| 1058 |
+
"loss": 0.5133,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8661567877629063,
|
| 1063 |
+
"grad_norm": 0.6315201878036348,
|
| 1064 |
+
"learning_rate": 3.5843249468222585e-05,
|
| 1065 |
+
"loss": 0.5264,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.8718929254302104,
|
| 1070 |
+
"grad_norm": 0.6634687345841984,
|
| 1071 |
+
"learning_rate": 3.5761131473669285e-05,
|
| 1072 |
+
"loss": 0.4759,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.8776290630975143,
|
| 1077 |
+
"grad_norm": 0.6850113724699497,
|
| 1078 |
+
"learning_rate": 3.567830628306344e-05,
|
| 1079 |
+
"loss": 0.5335,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.8833652007648184,
|
| 1084 |
+
"grad_norm": 0.7083577814147579,
|
| 1085 |
+
"learning_rate": 3.5594777612740263e-05,
|
| 1086 |
+
"loss": 0.4993,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.8891013384321224,
|
| 1091 |
+
"grad_norm": 0.7378709536755256,
|
| 1092 |
+
"learning_rate": 3.551054921059985e-05,
|
| 1093 |
+
"loss": 0.5176,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.8948374760994264,
|
| 1098 |
+
"grad_norm": 0.7648244850245753,
|
| 1099 |
+
"learning_rate": 3.542562485593897e-05,
|
| 1100 |
+
"loss": 0.5238,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.9005736137667304,
|
| 1105 |
+
"grad_norm": 0.6956157652186921,
|
| 1106 |
+
"learning_rate": 3.5340008359281546e-05,
|
| 1107 |
+
"loss": 0.501,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.9063097514340345,
|
| 1112 |
+
"grad_norm": 0.7645790590701518,
|
| 1113 |
+
"learning_rate": 3.525370356220764e-05,
|
| 1114 |
+
"loss": 0.5345,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.9120458891013384,
|
| 1119 |
+
"grad_norm": 0.6517490678032604,
|
| 1120 |
+
"learning_rate": 3.5166714337181104e-05,
|
| 1121 |
+
"loss": 0.5018,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.9177820267686424,
|
| 1126 |
+
"grad_norm": 0.5764447491349046,
|
| 1127 |
+
"learning_rate": 3.50790445873758e-05,
|
| 1128 |
+
"loss": 0.5078,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.9235181644359465,
|
| 1133 |
+
"grad_norm": 0.6747308853100928,
|
| 1134 |
+
"learning_rate": 3.4990698246500484e-05,
|
| 1135 |
+
"loss": 0.5256,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.9292543021032504,
|
| 1140 |
+
"grad_norm": 0.47711018256334037,
|
| 1141 |
+
"learning_rate": 3.490167927862233e-05,
|
| 1142 |
+
"loss": 0.4722,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.9349904397705545,
|
| 1147 |
+
"grad_norm": 0.6778658770774263,
|
| 1148 |
+
"learning_rate": 3.481199167798899e-05,
|
| 1149 |
+
"loss": 0.5223,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.9407265774378585,
|
| 1154 |
+
"grad_norm": 0.4558533116863511,
|
| 1155 |
+
"learning_rate": 3.4721639468849436e-05,
|
| 1156 |
+
"loss": 0.5213,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.9464627151051626,
|
| 1161 |
+
"grad_norm": 0.6385762668945828,
|
| 1162 |
+
"learning_rate": 3.463062670527338e-05,
|
| 1163 |
+
"loss": 0.5273,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.9521988527724665,
|
| 1168 |
+
"grad_norm": 0.4616066439052544,
|
| 1169 |
+
"learning_rate": 3.4538957470969365e-05,
|
| 1170 |
+
"loss": 0.4904,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.9579349904397706,
|
| 1175 |
+
"grad_norm": 0.6031035010764613,
|
| 1176 |
+
"learning_rate": 3.444663587910151e-05,
|
| 1177 |
+
"loss": 0.4922,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.9636711281070746,
|
| 1182 |
+
"grad_norm": 0.4890495218308744,
|
| 1183 |
+
"learning_rate": 3.435366607210499e-05,
|
| 1184 |
+
"loss": 0.4877,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9694072657743786,
|
| 1189 |
+
"grad_norm": 0.6620804135308059,
|
| 1190 |
+
"learning_rate": 3.426005222150014e-05,
|
| 1191 |
+
"loss": 0.5106,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.9751434034416826,
|
| 1196 |
+
"grad_norm": 0.5095511322768239,
|
| 1197 |
+
"learning_rate": 3.41657985277053e-05,
|
| 1198 |
+
"loss": 0.5008,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.9808795411089866,
|
| 1203 |
+
"grad_norm": 0.6827188978217906,
|
| 1204 |
+
"learning_rate": 3.407090921984832e-05,
|
| 1205 |
+
"loss": 0.5477,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.9866156787762906,
|
| 1210 |
+
"grad_norm": 0.5541219385903691,
|
| 1211 |
+
"learning_rate": 3.397538855557684e-05,
|
| 1212 |
+
"loss": 0.5009,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.9923518164435946,
|
| 1217 |
+
"grad_norm": 0.6443008399746032,
|
| 1218 |
+
"learning_rate": 3.387924082086718e-05,
|
| 1219 |
+
"loss": 0.5332,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.9980879541108987,
|
| 1224 |
+
"grad_norm": 0.4936165614613112,
|
| 1225 |
+
"learning_rate": 3.378247032983213e-05,
|
| 1226 |
+
"loss": 0.522,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.0038240917782026,
|
| 1231 |
+
"grad_norm": 0.9746986187989416,
|
| 1232 |
+
"learning_rate": 3.368508142452728e-05,
|
| 1233 |
+
"loss": 0.7212,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.0095602294455066,
|
| 1238 |
+
"grad_norm": 0.6720620316515331,
|
| 1239 |
+
"learning_rate": 3.358707847475626e-05,
|
| 1240 |
+
"loss": 0.4198,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.0152963671128108,
|
| 1245 |
+
"grad_norm": 0.6268806895754554,
|
| 1246 |
+
"learning_rate": 3.348846587787462e-05,
|
| 1247 |
+
"loss": 0.461,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.0210325047801148,
|
| 1252 |
+
"grad_norm": 0.7216148037661133,
|
| 1253 |
+
"learning_rate": 3.3389248058592576e-05,
|
| 1254 |
+
"loss": 0.4066,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.0267686424474187,
|
| 1259 |
+
"grad_norm": 0.6818445339544676,
|
| 1260 |
+
"learning_rate": 3.328942946877644e-05,
|
| 1261 |
+
"loss": 0.3977,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.0325047801147227,
|
| 1266 |
+
"grad_norm": 0.6950993166160578,
|
| 1267 |
+
"learning_rate": 3.318901458724885e-05,
|
| 1268 |
+
"loss": 0.4345,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.0382409177820269,
|
| 1273 |
+
"grad_norm": 0.6428355368495283,
|
| 1274 |
+
"learning_rate": 3.308800791958785e-05,
|
| 1275 |
+
"loss": 0.3577,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.0439770554493308,
|
| 1280 |
+
"grad_norm": 0.5373947494002963,
|
| 1281 |
+
"learning_rate": 3.2986413997924706e-05,
|
| 1282 |
+
"loss": 0.4369,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.0497131931166348,
|
| 1287 |
+
"grad_norm": 0.6925796288170799,
|
| 1288 |
+
"learning_rate": 3.2884237380740545e-05,
|
| 1289 |
+
"loss": 0.4328,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.0554493307839388,
|
| 1294 |
+
"grad_norm": 0.5233829993400329,
|
| 1295 |
+
"learning_rate": 3.278148265266182e-05,
|
| 1296 |
+
"loss": 0.4174,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.0611854684512427,
|
| 1301 |
+
"grad_norm": 0.6185297505581466,
|
| 1302 |
+
"learning_rate": 3.267815442425459e-05,
|
| 1303 |
+
"loss": 0.3828,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.066921606118547,
|
| 1308 |
+
"grad_norm": 0.6274152460265636,
|
| 1309 |
+
"learning_rate": 3.25742573318177e-05,
|
| 1310 |
+
"loss": 0.4549,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.0726577437858509,
|
| 1315 |
+
"grad_norm": 0.6366347848494356,
|
| 1316 |
+
"learning_rate": 3.246979603717467e-05,
|
| 1317 |
+
"loss": 0.4203,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.0783938814531548,
|
| 1322 |
+
"grad_norm": 0.6227490389766099,
|
| 1323 |
+
"learning_rate": 3.236477522746459e-05,
|
| 1324 |
+
"loss": 0.4675,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0841300191204588,
|
| 1329 |
+
"grad_norm": 0.5094295149535436,
|
| 1330 |
+
"learning_rate": 3.2259199614931745e-05,
|
| 1331 |
+
"loss": 0.3542,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.089866156787763,
|
| 1336 |
+
"grad_norm": 0.7037793847977521,
|
| 1337 |
+
"learning_rate": 3.215307393671426e-05,
|
| 1338 |
+
"loss": 0.4785,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.095602294455067,
|
| 1343 |
+
"grad_norm": 0.5619740614381676,
|
| 1344 |
+
"learning_rate": 3.204640295463146e-05,
|
| 1345 |
+
"loss": 0.3886,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.101338432122371,
|
| 1350 |
+
"grad_norm": 0.519062950155675,
|
| 1351 |
+
"learning_rate": 3.193919145497028e-05,
|
| 1352 |
+
"loss": 0.3842,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.107074569789675,
|
| 1357 |
+
"grad_norm": 0.5853788545600012,
|
| 1358 |
+
"learning_rate": 3.1831444248270455e-05,
|
| 1359 |
+
"loss": 0.423,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.1128107074569789,
|
| 1364 |
+
"grad_norm": 0.4775535757004622,
|
| 1365 |
+
"learning_rate": 3.17231661691087e-05,
|
| 1366 |
+
"loss": 0.4239,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.118546845124283,
|
| 1371 |
+
"grad_norm": 0.5172569912420082,
|
| 1372 |
+
"learning_rate": 3.161436207588178e-05,
|
| 1373 |
+
"loss": 0.425,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.124282982791587,
|
| 1378 |
+
"grad_norm": 0.5147855471578512,
|
| 1379 |
+
"learning_rate": 3.1505036850588516e-05,
|
| 1380 |
+
"loss": 0.3557,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.130019120458891,
|
| 1385 |
+
"grad_norm": 0.5476099573273011,
|
| 1386 |
+
"learning_rate": 3.139519539861074e-05,
|
| 1387 |
+
"loss": 0.4791,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.135755258126195,
|
| 1392 |
+
"grad_norm": 0.5619357244873963,
|
| 1393 |
+
"learning_rate": 3.128484264849314e-05,
|
| 1394 |
+
"loss": 0.4214,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.1414913957934991,
|
| 1399 |
+
"grad_norm": 0.48517078514017925,
|
| 1400 |
+
"learning_rate": 3.1173983551722205e-05,
|
| 1401 |
+
"loss": 0.3698,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.147227533460803,
|
| 1406 |
+
"grad_norm": 0.6343332709061799,
|
| 1407 |
+
"learning_rate": 3.106262308250399e-05,
|
| 1408 |
+
"loss": 0.3882,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.152963671128107,
|
| 1413 |
+
"grad_norm": 0.4706809203743212,
|
| 1414 |
+
"learning_rate": 3.0950766237540946e-05,
|
| 1415 |
+
"loss": 0.3937,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.158699808795411,
|
| 1420 |
+
"grad_norm": 0.6399176928230911,
|
| 1421 |
+
"learning_rate": 3.083841803580771e-05,
|
| 1422 |
+
"loss": 0.4585,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.1644359464627152,
|
| 1427 |
+
"grad_norm": 0.4919902699693636,
|
| 1428 |
+
"learning_rate": 3.072558351832592e-05,
|
| 1429 |
+
"loss": 0.3764,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.1701720841300192,
|
| 1434 |
+
"grad_norm": 0.6185212786022399,
|
| 1435 |
+
"learning_rate": 3.0612267747938015e-05,
|
| 1436 |
+
"loss": 0.4736,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.1759082217973231,
|
| 1441 |
+
"grad_norm": 0.5805762135464895,
|
| 1442 |
+
"learning_rate": 3.0498475809080082e-05,
|
| 1443 |
+
"loss": 0.4208,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.181644359464627,
|
| 1448 |
+
"grad_norm": 0.5097240529240963,
|
| 1449 |
+
"learning_rate": 3.03842128075537e-05,
|
| 1450 |
+
"loss": 0.4024,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.1873804971319313,
|
| 1455 |
+
"grad_norm": 0.591913249803808,
|
| 1456 |
+
"learning_rate": 3.026948387029684e-05,
|
| 1457 |
+
"loss": 0.4055,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.1931166347992352,
|
| 1462 |
+
"grad_norm": 0.5073228529458789,
|
| 1463 |
+
"learning_rate": 3.0154294145153865e-05,
|
| 1464 |
+
"loss": 0.4051,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.1988527724665392,
|
| 1469 |
+
"grad_norm": 0.5492611084308193,
|
| 1470 |
+
"learning_rate": 3.003864880064449e-05,
|
| 1471 |
+
"loss": 0.41,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.2045889101338432,
|
| 1476 |
+
"grad_norm": 0.49487668182682537,
|
| 1477 |
+
"learning_rate": 2.9922553025731907e-05,
|
| 1478 |
+
"loss": 0.4053,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.2103250478011471,
|
| 1483 |
+
"grad_norm": 0.5668757218011339,
|
| 1484 |
+
"learning_rate": 2.9806012029589966e-05,
|
| 1485 |
+
"loss": 0.4272,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.2160611854684513,
|
| 1490 |
+
"grad_norm": 0.4975892481813516,
|
| 1491 |
+
"learning_rate": 2.9689031041369406e-05,
|
| 1492 |
+
"loss": 0.4182,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.2217973231357553,
|
| 1497 |
+
"grad_norm": 0.5294244433263008,
|
| 1498 |
+
"learning_rate": 2.9571615309963255e-05,
|
| 1499 |
+
"loss": 0.3871,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.2275334608030593,
|
| 1504 |
+
"grad_norm": 0.5243327767554817,
|
| 1505 |
+
"learning_rate": 2.9453770103771308e-05,
|
| 1506 |
+
"loss": 0.39,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.2332695984703632,
|
| 1511 |
+
"grad_norm": 0.48558339355845753,
|
| 1512 |
+
"learning_rate": 2.9335500710463725e-05,
|
| 1513 |
+
"loss": 0.435,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.2390057361376674,
|
| 1518 |
+
"grad_norm": 0.5519168520623398,
|
| 1519 |
+
"learning_rate": 2.9216812436743788e-05,
|
| 1520 |
+
"loss": 0.4313,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.2447418738049714,
|
| 1525 |
+
"grad_norm": 0.4381015639162095,
|
| 1526 |
+
"learning_rate": 2.9097710608109776e-05,
|
| 1527 |
+
"loss": 0.3601,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.2504780114722753,
|
| 1532 |
+
"grad_norm": 0.5354350555855661,
|
| 1533 |
+
"learning_rate": 2.8978200568616036e-05,
|
| 1534 |
+
"loss": 0.3711,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.2562141491395793,
|
| 1539 |
+
"grad_norm": 0.48392108469684075,
|
| 1540 |
+
"learning_rate": 2.885828768063317e-05,
|
| 1541 |
+
"loss": 0.4385,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.2619502868068833,
|
| 1546 |
+
"grad_norm": 0.5147905754022055,
|
| 1547 |
+
"learning_rate": 2.8737977324607466e-05,
|
| 1548 |
+
"loss": 0.4318,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.2676864244741874,
|
| 1553 |
+
"grad_norm": 0.45875460028412374,
|
| 1554 |
+
"learning_rate": 2.861727489881941e-05,
|
| 1555 |
+
"loss": 0.4165,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.2734225621414914,
|
| 1560 |
+
"grad_norm": 0.46767203325180406,
|
| 1561 |
+
"learning_rate": 2.8496185819141547e-05,
|
| 1562 |
+
"loss": 0.4346,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.2791586998087954,
|
| 1567 |
+
"grad_norm": 0.5325780804765026,
|
| 1568 |
+
"learning_rate": 2.837471551879543e-05,
|
| 1569 |
+
"loss": 0.4488,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.2848948374760996,
|
| 1574 |
+
"grad_norm": 0.45604591940023564,
|
| 1575 |
+
"learning_rate": 2.825286944810783e-05,
|
| 1576 |
+
"loss": 0.4172,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.2906309751434035,
|
| 1581 |
+
"grad_norm": 0.48182478279469737,
|
| 1582 |
+
"learning_rate": 2.8130653074266188e-05,
|
| 1583 |
+
"loss": 0.3899,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.2963671128107075,
|
| 1588 |
+
"grad_norm": 0.4285203303941567,
|
| 1589 |
+
"learning_rate": 2.8008071881073342e-05,
|
| 1590 |
+
"loss": 0.4119,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.3021032504780115,
|
| 1595 |
+
"grad_norm": 0.5203451219224136,
|
| 1596 |
+
"learning_rate": 2.78851313687014e-05,
|
| 1597 |
+
"loss": 0.4167,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 1.3078393881453154,
|
| 1602 |
+
"grad_norm": 0.44867616077783923,
|
| 1603 |
+
"learning_rate": 2.7761837053444994e-05,
|
| 1604 |
+
"loss": 0.4428,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.3135755258126194,
|
| 1609 |
+
"grad_norm": 0.5176774633567216,
|
| 1610 |
+
"learning_rate": 2.7638194467473776e-05,
|
| 1611 |
+
"loss": 0.4623,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 1.3193116634799236,
|
| 1616 |
+
"grad_norm": 0.41453804129004856,
|
| 1617 |
+
"learning_rate": 2.7514209158584164e-05,
|
| 1618 |
+
"loss": 0.3855,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.3250478011472275,
|
| 1623 |
+
"grad_norm": 0.44139671451368523,
|
| 1624 |
+
"learning_rate": 2.7389886689950428e-05,
|
| 1625 |
+
"loss": 0.3704,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.3307839388145315,
|
| 1630 |
+
"grad_norm": 0.5091495369537983,
|
| 1631 |
+
"learning_rate": 2.7265232639875043e-05,
|
| 1632 |
+
"loss": 0.4346,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.3365200764818357,
|
| 1637 |
+
"grad_norm": 0.4627275608117313,
|
| 1638 |
+
"learning_rate": 2.7140252601538466e-05,
|
| 1639 |
+
"loss": 0.4339,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.3422562141491396,
|
| 1644 |
+
"grad_norm": 0.48547168450981104,
|
| 1645 |
+
"learning_rate": 2.7014952182748083e-05,
|
| 1646 |
+
"loss": 0.4307,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.3479923518164436,
|
| 1651 |
+
"grad_norm": 0.47854324223280925,
|
| 1652 |
+
"learning_rate": 2.688933700568666e-05,
|
| 1653 |
+
"loss": 0.4091,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.3537284894837476,
|
| 1658 |
+
"grad_norm": 0.4845854941728673,
|
| 1659 |
+
"learning_rate": 2.676341270666003e-05,
|
| 1660 |
+
"loss": 0.4544,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.3594646271510515,
|
| 1665 |
+
"grad_norm": 0.45196894051562736,
|
| 1666 |
+
"learning_rate": 2.663718493584422e-05,
|
| 1667 |
+
"loss": 0.3461,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.3652007648183555,
|
| 1672 |
+
"grad_norm": 0.543415301575274,
|
| 1673 |
+
"learning_rate": 2.6510659357031917e-05,
|
| 1674 |
+
"loss": 0.4336,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.3709369024856597,
|
| 1679 |
+
"grad_norm": 0.4471607463074475,
|
| 1680 |
+
"learning_rate": 2.6383841647378356e-05,
|
| 1681 |
+
"loss": 0.38,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.3766730401529637,
|
| 1686 |
+
"grad_norm": 0.6022022438673463,
|
| 1687 |
+
"learning_rate": 2.6256737497146544e-05,
|
| 1688 |
+
"loss": 0.4709,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.3824091778202676,
|
| 1693 |
+
"grad_norm": 0.44800638598268433,
|
| 1694 |
+
"learning_rate": 2.6129352609452003e-05,
|
| 1695 |
+
"loss": 0.4105,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.3881453154875718,
|
| 1700 |
+
"grad_norm": 0.4385968231933793,
|
| 1701 |
+
"learning_rate": 2.600169270000682e-05,
|
| 1702 |
+
"loss": 0.3782,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.3938814531548758,
|
| 1707 |
+
"grad_norm": 0.48914377606117937,
|
| 1708 |
+
"learning_rate": 2.5873763496863203e-05,
|
| 1709 |
+
"loss": 0.3954,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.3996175908221797,
|
| 1714 |
+
"grad_norm": 0.5851945762803631,
|
| 1715 |
+
"learning_rate": 2.574557074015648e-05,
|
| 1716 |
+
"loss": 0.458,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.4053537284894837,
|
| 1721 |
+
"grad_norm": 0.46457478071444297,
|
| 1722 |
+
"learning_rate": 2.561712018184752e-05,
|
| 1723 |
+
"loss": 0.438,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.4110898661567877,
|
| 1728 |
+
"grad_norm": 0.5204965149805247,
|
| 1729 |
+
"learning_rate": 2.5488417585464648e-05,
|
| 1730 |
+
"loss": 0.4171,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.4168260038240919,
|
| 1735 |
+
"grad_norm": 0.47781885084741565,
|
| 1736 |
+
"learning_rate": 2.535946872584506e-05,
|
| 1737 |
+
"loss": 0.4265,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.4225621414913958,
|
| 1742 |
+
"grad_norm": 0.5009930687067327,
|
| 1743 |
+
"learning_rate": 2.523027938887567e-05,
|
| 1744 |
+
"loss": 0.39,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.4282982791586998,
|
| 1749 |
+
"grad_norm": 0.5407445516705907,
|
| 1750 |
+
"learning_rate": 2.5100855371233533e-05,
|
| 1751 |
+
"loss": 0.4255,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.4340344168260037,
|
| 1756 |
+
"grad_norm": 0.4288547555150977,
|
| 1757 |
+
"learning_rate": 2.4971202480125737e-05,
|
| 1758 |
+
"loss": 0.3925,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.439770554493308,
|
| 1763 |
+
"grad_norm": 0.4567682163636214,
|
| 1764 |
+
"learning_rate": 2.4841326533028838e-05,
|
| 1765 |
+
"loss": 0.4283,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.445506692160612,
|
| 1770 |
+
"grad_norm": 0.47732054782696987,
|
| 1771 |
+
"learning_rate": 2.4711233357427817e-05,
|
| 1772 |
+
"loss": 0.429,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.4512428298279159,
|
| 1777 |
+
"grad_norm": 0.3827981714632121,
|
| 1778 |
+
"learning_rate": 2.458092879055464e-05,
|
| 1779 |
+
"loss": 0.3684,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.4569789674952198,
|
| 1784 |
+
"grad_norm": 0.4566303964863475,
|
| 1785 |
+
"learning_rate": 2.445041867912629e-05,
|
| 1786 |
+
"loss": 0.4141,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.4627151051625238,
|
| 1791 |
+
"grad_norm": 0.41932149526107115,
|
| 1792 |
+
"learning_rate": 2.431970887908249e-05,
|
| 1793 |
+
"loss": 0.428,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.468451242829828,
|
| 1798 |
+
"grad_norm": 0.4777606018140004,
|
| 1799 |
+
"learning_rate": 2.4188805255322895e-05,
|
| 1800 |
+
"loss": 0.422,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.474187380497132,
|
| 1805 |
+
"grad_norm": 0.4146884687116362,
|
| 1806 |
+
"learning_rate": 2.405771368144395e-05,
|
| 1807 |
+
"loss": 0.4407,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.479923518164436,
|
| 1812 |
+
"grad_norm": 0.43435634926442834,
|
| 1813 |
+
"learning_rate": 2.3926440039475382e-05,
|
| 1814 |
+
"loss": 0.4004,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.48565965583174,
|
| 1819 |
+
"grad_norm": 0.4184729261005328,
|
| 1820 |
+
"learning_rate": 2.3794990219616217e-05,
|
| 1821 |
+
"loss": 0.433,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.491395793499044,
|
| 1826 |
+
"grad_norm": 0.4475976249485021,
|
| 1827 |
+
"learning_rate": 2.3663370119970527e-05,
|
| 1828 |
+
"loss": 0.4281,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.497131931166348,
|
| 1833 |
+
"grad_norm": 0.4366125484429576,
|
| 1834 |
+
"learning_rate": 2.353158564628277e-05,
|
| 1835 |
+
"loss": 0.3873,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.502868068833652,
|
| 1840 |
+
"grad_norm": 0.4323743190887814,
|
| 1841 |
+
"learning_rate": 2.339964271167282e-05,
|
| 1842 |
+
"loss": 0.3906,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.508604206500956,
|
| 1847 |
+
"grad_norm": 0.4349582181643138,
|
| 1848 |
+
"learning_rate": 2.3267547236370604e-05,
|
| 1849 |
+
"loss": 0.4153,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.51434034416826,
|
| 1854 |
+
"grad_norm": 0.4300055874488965,
|
| 1855 |
+
"learning_rate": 2.3135305147450525e-05,
|
| 1856 |
+
"loss": 0.4243,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.520076481835564,
|
| 1861 |
+
"grad_norm": 0.41191944546871323,
|
| 1862 |
+
"learning_rate": 2.3002922378565468e-05,
|
| 1863 |
+
"loss": 0.379,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 1.525812619502868,
|
| 1868 |
+
"grad_norm": 0.4205849071289299,
|
| 1869 |
+
"learning_rate": 2.2870404869680573e-05,
|
| 1870 |
+
"loss": 0.3992,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.5315487571701722,
|
| 1875 |
+
"grad_norm": 0.4167651488072966,
|
| 1876 |
+
"learning_rate": 2.273775856680672e-05,
|
| 1877 |
+
"loss": 0.4029,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 1.5372848948374762,
|
| 1882 |
+
"grad_norm": 0.39362974229347514,
|
| 1883 |
+
"learning_rate": 2.2604989421733718e-05,
|
| 1884 |
+
"loss": 0.3964,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.5430210325047802,
|
| 1889 |
+
"grad_norm": 0.4554936101687405,
|
| 1890 |
+
"learning_rate": 2.2472103391763268e-05,
|
| 1891 |
+
"loss": 0.4573,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.5487571701720841,
|
| 1896 |
+
"grad_norm": 0.4225697521408909,
|
| 1897 |
+
"learning_rate": 2.2339106439441656e-05,
|
| 1898 |
+
"loss": 0.4331,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.554493307839388,
|
| 1903 |
+
"grad_norm": 0.3839293540385542,
|
| 1904 |
+
"learning_rate": 2.2206004532292192e-05,
|
| 1905 |
+
"loss": 0.4301,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.560229445506692,
|
| 1910 |
+
"grad_norm": 0.39780099781282624,
|
| 1911 |
+
"learning_rate": 2.20728036425475e-05,
|
| 1912 |
+
"loss": 0.4029,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.565965583173996,
|
| 1917 |
+
"grad_norm": 0.39896699881977027,
|
| 1918 |
+
"learning_rate": 2.1939509746881486e-05,
|
| 1919 |
+
"loss": 0.4204,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 1.5717017208413002,
|
| 1924 |
+
"grad_norm": 0.4011711852263823,
|
| 1925 |
+
"learning_rate": 2.1806128826141223e-05,
|
| 1926 |
+
"loss": 0.4556,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.5774378585086042,
|
| 1931 |
+
"grad_norm": 0.3780449285964431,
|
| 1932 |
+
"learning_rate": 2.1672666865078544e-05,
|
| 1933 |
+
"loss": 0.3854,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.5831739961759084,
|
| 1938 |
+
"grad_norm": 0.3815103294469426,
|
| 1939 |
+
"learning_rate": 2.153912985208154e-05,
|
| 1940 |
+
"loss": 0.4304,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.5889101338432123,
|
| 1945 |
+
"grad_norm": 0.39420124826230263,
|
| 1946 |
+
"learning_rate": 2.140552377890586e-05,
|
| 1947 |
+
"loss": 0.413,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 1.5946462715105163,
|
| 1952 |
+
"grad_norm": 0.37547444058482843,
|
| 1953 |
+
"learning_rate": 2.1271854640405856e-05,
|
| 1954 |
+
"loss": 0.4033,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.6003824091778203,
|
| 1959 |
+
"grad_norm": 0.3676214604101024,
|
| 1960 |
+
"learning_rate": 2.1138128434265583e-05,
|
| 1961 |
+
"loss": 0.3809,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.6061185468451242,
|
| 1966 |
+
"grad_norm": 0.402628978813413,
|
| 1967 |
+
"learning_rate": 2.1004351160729714e-05,
|
| 1968 |
+
"loss": 0.4356,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.6118546845124282,
|
| 1973 |
+
"grad_norm": 0.4259466481121817,
|
| 1974 |
+
"learning_rate": 2.0870528822334296e-05,
|
| 1975 |
+
"loss": 0.4071,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 1.6175908221797322,
|
| 1980 |
+
"grad_norm": 0.3980303656074581,
|
| 1981 |
+
"learning_rate": 2.073666742363742e-05,
|
| 1982 |
+
"loss": 0.4566,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.6233269598470363,
|
| 1987 |
+
"grad_norm": 0.3793866215066068,
|
| 1988 |
+
"learning_rate": 2.0602772970949777e-05,
|
| 1989 |
+
"loss": 0.4084,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 1.6290630975143403,
|
| 1994 |
+
"grad_norm": 0.4043370635632085,
|
| 1995 |
+
"learning_rate": 2.0468851472065213e-05,
|
| 1996 |
+
"loss": 0.4276,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.6347992351816445,
|
| 2001 |
+
"grad_norm": 0.4295543543276556,
|
| 2002 |
+
"learning_rate": 2.03349089359911e-05,
|
| 2003 |
+
"loss": 0.3797,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 1.6405353728489485,
|
| 2008 |
+
"grad_norm": 0.4415259564693047,
|
| 2009 |
+
"learning_rate": 2.020095137267876e-05,
|
| 2010 |
+
"loss": 0.4344,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.6462715105162524,
|
| 2015 |
+
"grad_norm": 0.3894742791133544,
|
| 2016 |
+
"learning_rate": 2.0066984792753757e-05,
|
| 2017 |
+
"loss": 0.4187,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.6520076481835564,
|
| 2022 |
+
"grad_norm": 0.4128327836910975,
|
| 2023 |
+
"learning_rate": 1.993301520724625e-05,
|
| 2024 |
+
"loss": 0.4036,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.6577437858508604,
|
| 2029 |
+
"grad_norm": 0.35013244959729184,
|
| 2030 |
+
"learning_rate": 1.9799048627321247e-05,
|
| 2031 |
+
"loss": 0.4141,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 1.6634799235181643,
|
| 2036 |
+
"grad_norm": 0.3924223109946273,
|
| 2037 |
+
"learning_rate": 1.966509106400891e-05,
|
| 2038 |
+
"loss": 0.4098,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.6692160611854685,
|
| 2043 |
+
"grad_norm": 0.375681252496487,
|
| 2044 |
+
"learning_rate": 1.9531148527934794e-05,
|
| 2045 |
+
"loss": 0.372,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 1.6749521988527725,
|
| 2050 |
+
"grad_norm": 0.3583704837247699,
|
| 2051 |
+
"learning_rate": 1.9397227029050233e-05,
|
| 2052 |
+
"loss": 0.3977,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.6806883365200764,
|
| 2057 |
+
"grad_norm": 0.4225858356870719,
|
| 2058 |
+
"learning_rate": 1.9263332576362586e-05,
|
| 2059 |
+
"loss": 0.4654,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 1.6864244741873806,
|
| 2064 |
+
"grad_norm": 0.43936703075105055,
|
| 2065 |
+
"learning_rate": 1.9129471177665714e-05,
|
| 2066 |
+
"loss": 0.5054,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.6921606118546846,
|
| 2071 |
+
"grad_norm": 0.36215467983870736,
|
| 2072 |
+
"learning_rate": 1.899564883927029e-05,
|
| 2073 |
+
"loss": 0.3574,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.6978967495219885,
|
| 2078 |
+
"grad_norm": 0.3732898278812787,
|
| 2079 |
+
"learning_rate": 1.8861871565734427e-05,
|
| 2080 |
+
"loss": 0.408,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.7036328871892925,
|
| 2085 |
+
"grad_norm": 0.4033046527093117,
|
| 2086 |
+
"learning_rate": 1.8728145359594147e-05,
|
| 2087 |
+
"loss": 0.414,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 1.7093690248565965,
|
| 2092 |
+
"grad_norm": 0.48233034016482407,
|
| 2093 |
+
"learning_rate": 1.859447622109415e-05,
|
| 2094 |
+
"loss": 0.4452,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.7151051625239004,
|
| 2099 |
+
"grad_norm": 0.35022422393865005,
|
| 2100 |
+
"learning_rate": 1.8460870147918464e-05,
|
| 2101 |
+
"loss": 0.4098,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 1.7208413001912046,
|
| 2106 |
+
"grad_norm": 0.3503756135613716,
|
| 2107 |
+
"learning_rate": 1.832733313492147e-05,
|
| 2108 |
+
"loss": 0.3665,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.7265774378585086,
|
| 2113 |
+
"grad_norm": 0.453240573589918,
|
| 2114 |
+
"learning_rate": 1.8193871173858784e-05,
|
| 2115 |
+
"loss": 0.4017,
|
| 2116 |
+
"step": 301
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.7323135755258128,
|
| 2120 |
+
"grad_norm": 0.4106965211287676,
|
| 2121 |
+
"learning_rate": 1.8060490253118524e-05,
|
| 2122 |
+
"loss": 0.457,
|
| 2123 |
+
"step": 302
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.7380497131931167,
|
| 2127 |
+
"grad_norm": 0.3580924920858784,
|
| 2128 |
+
"learning_rate": 1.7927196357452507e-05,
|
| 2129 |
+
"loss": 0.3524,
|
| 2130 |
+
"step": 303
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.7437858508604207,
|
| 2134 |
+
"grad_norm": 0.40465378202399943,
|
| 2135 |
+
"learning_rate": 1.7793995467707808e-05,
|
| 2136 |
+
"loss": 0.4125,
|
| 2137 |
+
"step": 304
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.7495219885277247,
|
| 2141 |
+
"grad_norm": 0.42671419730243126,
|
| 2142 |
+
"learning_rate": 1.766089356055835e-05,
|
| 2143 |
+
"loss": 0.4564,
|
| 2144 |
+
"step": 305
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.7552581261950286,
|
| 2148 |
+
"grad_norm": 0.392872725834381,
|
| 2149 |
+
"learning_rate": 1.7527896608236735e-05,
|
| 2150 |
+
"loss": 0.3906,
|
| 2151 |
+
"step": 306
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.7609942638623326,
|
| 2155 |
+
"grad_norm": 0.37117518719191533,
|
| 2156 |
+
"learning_rate": 1.7395010578266292e-05,
|
| 2157 |
+
"loss": 0.4225,
|
| 2158 |
+
"step": 307
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 1.7667304015296366,
|
| 2162 |
+
"grad_norm": 0.36968574125016307,
|
| 2163 |
+
"learning_rate": 1.7262241433193284e-05,
|
| 2164 |
+
"loss": 0.3477,
|
| 2165 |
+
"step": 308
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 1.7724665391969407,
|
| 2169 |
+
"grad_norm": 0.38953378877838585,
|
| 2170 |
+
"learning_rate": 1.712959513031943e-05,
|
| 2171 |
+
"loss": 0.3823,
|
| 2172 |
+
"step": 309
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 1.7782026768642447,
|
| 2176 |
+
"grad_norm": 0.36085297573229624,
|
| 2177 |
+
"learning_rate": 1.6997077621434535e-05,
|
| 2178 |
+
"loss": 0.4066,
|
| 2179 |
+
"step": 310
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 1.783938814531549,
|
| 2183 |
+
"grad_norm": 0.4252176810480222,
|
| 2184 |
+
"learning_rate": 1.6864694852549478e-05,
|
| 2185 |
+
"loss": 0.4268,
|
| 2186 |
+
"step": 311
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 1.7896749521988529,
|
| 2190 |
+
"grad_norm": 0.4412549537519878,
|
| 2191 |
+
"learning_rate": 1.6732452763629396e-05,
|
| 2192 |
+
"loss": 0.4326,
|
| 2193 |
+
"step": 312
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 1.7954110898661568,
|
| 2197 |
+
"grad_norm": 0.3812059474272243,
|
| 2198 |
+
"learning_rate": 1.6600357288327186e-05,
|
| 2199 |
+
"loss": 0.379,
|
| 2200 |
+
"step": 313
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 1.8011472275334608,
|
| 2204 |
+
"grad_norm": 0.47503505255362904,
|
| 2205 |
+
"learning_rate": 1.646841435371723e-05,
|
| 2206 |
+
"loss": 0.432,
|
| 2207 |
+
"step": 314
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 1.8068833652007648,
|
| 2211 |
+
"grad_norm": 0.41481678543056555,
|
| 2212 |
+
"learning_rate": 1.6336629880029483e-05,
|
| 2213 |
+
"loss": 0.4023,
|
| 2214 |
+
"step": 315
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 1.8126195028680687,
|
| 2218 |
+
"grad_norm": 0.4124532353847639,
|
| 2219 |
+
"learning_rate": 1.6205009780383783e-05,
|
| 2220 |
+
"loss": 0.4308,
|
| 2221 |
+
"step": 316
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 1.8183556405353727,
|
| 2225 |
+
"grad_norm": 0.38098821964138535,
|
| 2226 |
+
"learning_rate": 1.6073559960524624e-05,
|
| 2227 |
+
"loss": 0.3976,
|
| 2228 |
+
"step": 317
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 1.8240917782026769,
|
| 2232 |
+
"grad_norm": 0.3811565535669034,
|
| 2233 |
+
"learning_rate": 1.594228631855605e-05,
|
| 2234 |
+
"loss": 0.3835,
|
| 2235 |
+
"step": 318
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 1.8298279158699808,
|
| 2239 |
+
"grad_norm": 0.36589564234813393,
|
| 2240 |
+
"learning_rate": 1.5811194744677116e-05,
|
| 2241 |
+
"loss": 0.4129,
|
| 2242 |
+
"step": 319
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 1.835564053537285,
|
| 2246 |
+
"grad_norm": 0.3653636034932473,
|
| 2247 |
+
"learning_rate": 1.5680291120917512e-05,
|
| 2248 |
+
"loss": 0.36,
|
| 2249 |
+
"step": 320
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 1.841300191204589,
|
| 2253 |
+
"grad_norm": 0.40122714496956696,
|
| 2254 |
+
"learning_rate": 1.5549581320873715e-05,
|
| 2255 |
+
"loss": 0.3892,
|
| 2256 |
+
"step": 321
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 1.847036328871893,
|
| 2260 |
+
"grad_norm": 0.38832451390149825,
|
| 2261 |
+
"learning_rate": 1.541907120944537e-05,
|
| 2262 |
+
"loss": 0.3865,
|
| 2263 |
+
"step": 322
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 1.852772466539197,
|
| 2267 |
+
"grad_norm": 0.437571883751778,
|
| 2268 |
+
"learning_rate": 1.528876664257219e-05,
|
| 2269 |
+
"loss": 0.4356,
|
| 2270 |
+
"step": 323
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 1.8585086042065009,
|
| 2274 |
+
"grad_norm": 0.36968778383694306,
|
| 2275 |
+
"learning_rate": 1.5158673466971168e-05,
|
| 2276 |
+
"loss": 0.4257,
|
| 2277 |
+
"step": 324
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 1.8642447418738048,
|
| 2281 |
+
"grad_norm": 0.35073154051519584,
|
| 2282 |
+
"learning_rate": 1.502879751987427e-05,
|
| 2283 |
+
"loss": 0.3947,
|
| 2284 |
+
"step": 325
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 1.869980879541109,
|
| 2288 |
+
"grad_norm": 0.3805701203026406,
|
| 2289 |
+
"learning_rate": 1.4899144628766473e-05,
|
| 2290 |
+
"loss": 0.4197,
|
| 2291 |
+
"step": 326
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 1.875717017208413,
|
| 2295 |
+
"grad_norm": 0.36051788842397653,
|
| 2296 |
+
"learning_rate": 1.4769720611124342e-05,
|
| 2297 |
+
"loss": 0.3862,
|
| 2298 |
+
"step": 327
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 1.8814531548757172,
|
| 2302 |
+
"grad_norm": 0.390822308734316,
|
| 2303 |
+
"learning_rate": 1.4640531274154946e-05,
|
| 2304 |
+
"loss": 0.4547,
|
| 2305 |
+
"step": 328
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 1.8871892925430211,
|
| 2309 |
+
"grad_norm": 0.35188013033472365,
|
| 2310 |
+
"learning_rate": 1.4511582414535359e-05,
|
| 2311 |
+
"loss": 0.372,
|
| 2312 |
+
"step": 329
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 1.892925430210325,
|
| 2316 |
+
"grad_norm": 0.3492988111143338,
|
| 2317 |
+
"learning_rate": 1.4382879818152486e-05,
|
| 2318 |
+
"loss": 0.391,
|
| 2319 |
+
"step": 330
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 1.898661567877629,
|
| 2323 |
+
"grad_norm": 0.3506998309752745,
|
| 2324 |
+
"learning_rate": 1.425442925984353e-05,
|
| 2325 |
+
"loss": 0.3807,
|
| 2326 |
+
"step": 331
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 1.904397705544933,
|
| 2330 |
+
"grad_norm": 0.4030721263174961,
|
| 2331 |
+
"learning_rate": 1.41262365031368e-05,
|
| 2332 |
+
"loss": 0.376,
|
| 2333 |
+
"step": 332
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 1.910133843212237,
|
| 2337 |
+
"grad_norm": 0.3504037718749043,
|
| 2338 |
+
"learning_rate": 1.399830729999319e-05,
|
| 2339 |
+
"loss": 0.3761,
|
| 2340 |
+
"step": 333
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 1.915869980879541,
|
| 2344 |
+
"grad_norm": 0.3571642792832744,
|
| 2345 |
+
"learning_rate": 1.3870647390548004e-05,
|
| 2346 |
+
"loss": 0.3989,
|
| 2347 |
+
"step": 334
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 1.9216061185468452,
|
| 2351 |
+
"grad_norm": 0.3995469257986992,
|
| 2352 |
+
"learning_rate": 1.3743262502853458e-05,
|
| 2353 |
+
"loss": 0.4614,
|
| 2354 |
+
"step": 335
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 1.9273422562141491,
|
| 2358 |
+
"grad_norm": 0.3374515530857516,
|
| 2359 |
+
"learning_rate": 1.3616158352621653e-05,
|
| 2360 |
+
"loss": 0.3545,
|
| 2361 |
+
"step": 336
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 1.9330783938814533,
|
| 2365 |
+
"grad_norm": 0.3785045797006251,
|
| 2366 |
+
"learning_rate": 1.3489340642968088e-05,
|
| 2367 |
+
"loss": 0.3725,
|
| 2368 |
+
"step": 337
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 1.9388145315487573,
|
| 2372 |
+
"grad_norm": 0.3651730179303691,
|
| 2373 |
+
"learning_rate": 1.336281506415579e-05,
|
| 2374 |
+
"loss": 0.4091,
|
| 2375 |
+
"step": 338
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 1.9445506692160612,
|
| 2379 |
+
"grad_norm": 0.35782792229426036,
|
| 2380 |
+
"learning_rate": 1.3236587293339974e-05,
|
| 2381 |
+
"loss": 0.4097,
|
| 2382 |
+
"step": 339
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 1.9502868068833652,
|
| 2386 |
+
"grad_norm": 0.3715183571626738,
|
| 2387 |
+
"learning_rate": 1.3110662994313343e-05,
|
| 2388 |
+
"loss": 0.4238,
|
| 2389 |
+
"step": 340
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 1.9560229445506692,
|
| 2393 |
+
"grad_norm": 0.3754585864645323,
|
| 2394 |
+
"learning_rate": 1.2985047817251916e-05,
|
| 2395 |
+
"loss": 0.4284,
|
| 2396 |
+
"step": 341
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 1.9617590822179731,
|
| 2400 |
+
"grad_norm": 0.37208739976821165,
|
| 2401 |
+
"learning_rate": 1.2859747398461542e-05,
|
| 2402 |
+
"loss": 0.4178,
|
| 2403 |
+
"step": 342
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 1.967495219885277,
|
| 2407 |
+
"grad_norm": 0.3608587542718569,
|
| 2408 |
+
"learning_rate": 1.2734767360124955e-05,
|
| 2409 |
+
"loss": 0.3667,
|
| 2410 |
+
"step": 343
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 1.9732313575525813,
|
| 2414 |
+
"grad_norm": 0.37784527768886184,
|
| 2415 |
+
"learning_rate": 1.261011331004958e-05,
|
| 2416 |
+
"loss": 0.3512,
|
| 2417 |
+
"step": 344
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 1.9789674952198852,
|
| 2421 |
+
"grad_norm": 0.37238567685296753,
|
| 2422 |
+
"learning_rate": 1.2485790841415834e-05,
|
| 2423 |
+
"loss": 0.4461,
|
| 2424 |
+
"step": 345
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 1.9847036328871894,
|
| 2428 |
+
"grad_norm": 0.3926981132666437,
|
| 2429 |
+
"learning_rate": 1.2361805532526225e-05,
|
| 2430 |
+
"loss": 0.4303,
|
| 2431 |
+
"step": 346
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 1.9904397705544934,
|
| 2435 |
+
"grad_norm": 0.386796605292204,
|
| 2436 |
+
"learning_rate": 1.2238162946555004e-05,
|
| 2437 |
+
"loss": 0.4182,
|
| 2438 |
+
"step": 347
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 1.9961759082217974,
|
| 2442 |
+
"grad_norm": 0.32573202133902224,
|
| 2443 |
+
"learning_rate": 1.2114868631298608e-05,
|
| 2444 |
+
"loss": 0.3843,
|
| 2445 |
+
"step": 348
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 2.0019120458891013,
|
| 2449 |
+
"grad_norm": 0.856534667430809,
|
| 2450 |
+
"learning_rate": 1.1991928118926661e-05,
|
| 2451 |
+
"loss": 0.5702,
|
| 2452 |
+
"step": 349
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 2.0076481835564053,
|
| 2456 |
+
"grad_norm": 0.4595192074096811,
|
| 2457 |
+
"learning_rate": 1.1869346925733813e-05,
|
| 2458 |
+
"loss": 0.3478,
|
| 2459 |
+
"step": 350
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 2.0133843212237093,
|
| 2463 |
+
"grad_norm": 0.8854412030509314,
|
| 2464 |
+
"learning_rate": 1.1747130551892176e-05,
|
| 2465 |
+
"loss": 0.3504,
|
| 2466 |
+
"step": 351
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 2.019120458891013,
|
| 2470 |
+
"grad_norm": 0.5095848588351017,
|
| 2471 |
+
"learning_rate": 1.1625284481204577e-05,
|
| 2472 |
+
"loss": 0.3247,
|
| 2473 |
+
"step": 352
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 2.024856596558317,
|
| 2477 |
+
"grad_norm": 0.45215495379418424,
|
| 2478 |
+
"learning_rate": 1.1503814180858451e-05,
|
| 2479 |
+
"loss": 0.3293,
|
| 2480 |
+
"step": 353
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 2.0305927342256216,
|
| 2484 |
+
"grad_norm": 0.4983547198588867,
|
| 2485 |
+
"learning_rate": 1.1382725101180593e-05,
|
| 2486 |
+
"loss": 0.3068,
|
| 2487 |
+
"step": 354
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 2.0363288718929256,
|
| 2491 |
+
"grad_norm": 0.4664207227186065,
|
| 2492 |
+
"learning_rate": 1.1262022675392544e-05,
|
| 2493 |
+
"loss": 0.3031,
|
| 2494 |
+
"step": 355
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 2.0420650095602295,
|
| 2498 |
+
"grad_norm": 0.4171482692909067,
|
| 2499 |
+
"learning_rate": 1.1141712319366835e-05,
|
| 2500 |
+
"loss": 0.3104,
|
| 2501 |
+
"step": 356
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 2.0478011472275335,
|
| 2505 |
+
"grad_norm": 0.48388082613280514,
|
| 2506 |
+
"learning_rate": 1.1021799431383969e-05,
|
| 2507 |
+
"loss": 0.3355,
|
| 2508 |
+
"step": 357
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 2.0535372848948374,
|
| 2512 |
+
"grad_norm": 0.4405839370097391,
|
| 2513 |
+
"learning_rate": 1.0902289391890232e-05,
|
| 2514 |
+
"loss": 0.3181,
|
| 2515 |
+
"step": 358
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 2.0592734225621414,
|
| 2519 |
+
"grad_norm": 0.38572618966224764,
|
| 2520 |
+
"learning_rate": 1.0783187563256218e-05,
|
| 2521 |
+
"loss": 0.255,
|
| 2522 |
+
"step": 359
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 2.0650095602294454,
|
| 2526 |
+
"grad_norm": 0.4124079647312535,
|
| 2527 |
+
"learning_rate": 1.0664499289536283e-05,
|
| 2528 |
+
"loss": 0.3179,
|
| 2529 |
+
"step": 360
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 2.0707456978967493,
|
| 2533 |
+
"grad_norm": 0.36220901351046625,
|
| 2534 |
+
"learning_rate": 1.0546229896228692e-05,
|
| 2535 |
+
"loss": 0.2607,
|
| 2536 |
+
"step": 361
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 2.0764818355640537,
|
| 2540 |
+
"grad_norm": 0.4049509171035621,
|
| 2541 |
+
"learning_rate": 1.0428384690036749e-05,
|
| 2542 |
+
"loss": 0.2878,
|
| 2543 |
+
"step": 362
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 2.0822179732313577,
|
| 2547 |
+
"grad_norm": 0.48057213951850675,
|
| 2548 |
+
"learning_rate": 1.0310968958630601e-05,
|
| 2549 |
+
"loss": 0.3607,
|
| 2550 |
+
"step": 363
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 2.0879541108986617,
|
| 2554 |
+
"grad_norm": 0.33983057117406296,
|
| 2555 |
+
"learning_rate": 1.0193987970410046e-05,
|
| 2556 |
+
"loss": 0.2914,
|
| 2557 |
+
"step": 364
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 2.0936902485659656,
|
| 2561 |
+
"grad_norm": 0.4031998241867442,
|
| 2562 |
+
"learning_rate": 1.0077446974268098e-05,
|
| 2563 |
+
"loss": 0.3372,
|
| 2564 |
+
"step": 365
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 2.0994263862332696,
|
| 2568 |
+
"grad_norm": 0.3811905438226048,
|
| 2569 |
+
"learning_rate": 9.961351199355513e-06,
|
| 2570 |
+
"loss": 0.311,
|
| 2571 |
+
"step": 366
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 2.1051625239005736,
|
| 2575 |
+
"grad_norm": 0.38408888784962325,
|
| 2576 |
+
"learning_rate": 9.84570585484614e-06,
|
| 2577 |
+
"loss": 0.3563,
|
| 2578 |
+
"step": 367
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 2.1108986615678775,
|
| 2582 |
+
"grad_norm": 0.33981693233156296,
|
| 2583 |
+
"learning_rate": 9.730516129703158e-06,
|
| 2584 |
+
"loss": 0.2871,
|
| 2585 |
+
"step": 368
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 2.1166347992351815,
|
| 2589 |
+
"grad_norm": 0.3518672236516868,
|
| 2590 |
+
"learning_rate": 9.615787192446304e-06,
|
| 2591 |
+
"loss": 0.3125,
|
| 2592 |
+
"step": 369
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 2.1223709369024855,
|
| 2596 |
+
"grad_norm": 0.3802739825741615,
|
| 2597 |
+
"learning_rate": 9.50152419091992e-06,
|
| 2598 |
+
"loss": 0.3254,
|
| 2599 |
+
"step": 370
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 2.12810707456979,
|
| 2603 |
+
"grad_norm": 0.3350283722430752,
|
| 2604 |
+
"learning_rate": 9.38773225206199e-06,
|
| 2605 |
+
"loss": 0.2669,
|
| 2606 |
+
"step": 371
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 2.133843212237094,
|
| 2610 |
+
"grad_norm": 0.37579814126338135,
|
| 2611 |
+
"learning_rate": 9.274416481674084e-06,
|
| 2612 |
+
"loss": 0.334,
|
| 2613 |
+
"step": 372
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 2.139579349904398,
|
| 2617 |
+
"grad_norm": 0.32704016552087445,
|
| 2618 |
+
"learning_rate": 9.161581964192298e-06,
|
| 2619 |
+
"loss": 0.2568,
|
| 2620 |
+
"step": 373
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 2.1453154875717018,
|
| 2624 |
+
"grad_norm": 0.414672276708601,
|
| 2625 |
+
"learning_rate": 9.049233762459057e-06,
|
| 2626 |
+
"loss": 0.4001,
|
| 2627 |
+
"step": 374
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 2.1510516252390057,
|
| 2631 |
+
"grad_norm": 0.3112648437196225,
|
| 2632 |
+
"learning_rate": 8.937376917496012e-06,
|
| 2633 |
+
"loss": 0.2447,
|
| 2634 |
+
"step": 375
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 2.1567877629063097,
|
| 2638 |
+
"grad_norm": 0.3535914113780811,
|
| 2639 |
+
"learning_rate": 8.826016448277795e-06,
|
| 2640 |
+
"loss": 0.3157,
|
| 2641 |
+
"step": 376
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 2.1625239005736137,
|
| 2645 |
+
"grad_norm": 0.3434081422193142,
|
| 2646 |
+
"learning_rate": 8.715157351506864e-06,
|
| 2647 |
+
"loss": 0.2992,
|
| 2648 |
+
"step": 377
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 2.1682600382409176,
|
| 2652 |
+
"grad_norm": 0.3422884659233757,
|
| 2653 |
+
"learning_rate": 8.604804601389271e-06,
|
| 2654 |
+
"loss": 0.3132,
|
| 2655 |
+
"step": 378
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 2.173996175908222,
|
| 2659 |
+
"grad_norm": 0.3430270987205145,
|
| 2660 |
+
"learning_rate": 8.494963149411489e-06,
|
| 2661 |
+
"loss": 0.2712,
|
| 2662 |
+
"step": 379
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 2.179732313575526,
|
| 2666 |
+
"grad_norm": 0.36832674053444375,
|
| 2667 |
+
"learning_rate": 8.385637924118224e-06,
|
| 2668 |
+
"loss": 0.2803,
|
| 2669 |
+
"step": 380
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 2.18546845124283,
|
| 2673 |
+
"grad_norm": 0.338652106601731,
|
| 2674 |
+
"learning_rate": 8.276833830891312e-06,
|
| 2675 |
+
"loss": 0.2937,
|
| 2676 |
+
"step": 381
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 2.191204588910134,
|
| 2680 |
+
"grad_norm": 0.347795356928778,
|
| 2681 |
+
"learning_rate": 8.168555751729552e-06,
|
| 2682 |
+
"loss": 0.3159,
|
| 2683 |
+
"step": 382
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 2.196940726577438,
|
| 2687 |
+
"grad_norm": 0.37649404917042467,
|
| 2688 |
+
"learning_rate": 8.060808545029727e-06,
|
| 2689 |
+
"loss": 0.3159,
|
| 2690 |
+
"step": 383
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 2.202676864244742,
|
| 2694 |
+
"grad_norm": 0.4275027691702314,
|
| 2695 |
+
"learning_rate": 7.95359704536854e-06,
|
| 2696 |
+
"loss": 0.3051,
|
| 2697 |
+
"step": 384
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 2.208413001912046,
|
| 2701 |
+
"grad_norm": 0.36709280229253105,
|
| 2702 |
+
"learning_rate": 7.846926063285745e-06,
|
| 2703 |
+
"loss": 0.3082,
|
| 2704 |
+
"step": 385
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 2.21414913957935,
|
| 2708 |
+
"grad_norm": 0.3197758439418705,
|
| 2709 |
+
"learning_rate": 7.740800385068256e-06,
|
| 2710 |
+
"loss": 0.3044,
|
| 2711 |
+
"step": 386
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 2.2198852772466537,
|
| 2715 |
+
"grad_norm": 0.36467098789844404,
|
| 2716 |
+
"learning_rate": 7.63522477253542e-06,
|
| 2717 |
+
"loss": 0.3192,
|
| 2718 |
+
"step": 387
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 2.2256214149139577,
|
| 2722 |
+
"grad_norm": 0.3792955542610236,
|
| 2723 |
+
"learning_rate": 7.530203962825331e-06,
|
| 2724 |
+
"loss": 0.3374,
|
| 2725 |
+
"step": 388
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 2.231357552581262,
|
| 2729 |
+
"grad_norm": 0.33901384143705177,
|
| 2730 |
+
"learning_rate": 7.425742668182308e-06,
|
| 2731 |
+
"loss": 0.3056,
|
| 2732 |
+
"step": 389
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 2.237093690248566,
|
| 2736 |
+
"grad_norm": 0.33544808925545067,
|
| 2737 |
+
"learning_rate": 7.3218455757454125e-06,
|
| 2738 |
+
"loss": 0.2674,
|
| 2739 |
+
"step": 390
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 2.24282982791587,
|
| 2743 |
+
"grad_norm": 0.32597707317340413,
|
| 2744 |
+
"learning_rate": 7.218517347338194e-06,
|
| 2745 |
+
"loss": 0.2843,
|
| 2746 |
+
"step": 391
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 2.248565965583174,
|
| 2750 |
+
"grad_norm": 0.3555015121926318,
|
| 2751 |
+
"learning_rate": 7.115762619259459e-06,
|
| 2752 |
+
"loss": 0.3234,
|
| 2753 |
+
"step": 392
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 2.254302103250478,
|
| 2757 |
+
"grad_norm": 0.3593977217633907,
|
| 2758 |
+
"learning_rate": 7.013586002075297e-06,
|
| 2759 |
+
"loss": 0.3573,
|
| 2760 |
+
"step": 393
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 2.260038240917782,
|
| 2764 |
+
"grad_norm": 0.326928535932432,
|
| 2765 |
+
"learning_rate": 6.911992080412153e-06,
|
| 2766 |
+
"loss": 0.3053,
|
| 2767 |
+
"step": 394
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 2.265774378585086,
|
| 2771 |
+
"grad_norm": 0.3661810608640239,
|
| 2772 |
+
"learning_rate": 6.810985412751159e-06,
|
| 2773 |
+
"loss": 0.3411,
|
| 2774 |
+
"step": 395
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 2.27151051625239,
|
| 2778 |
+
"grad_norm": 0.33182512098109557,
|
| 2779 |
+
"learning_rate": 6.710570531223568e-06,
|
| 2780 |
+
"loss": 0.2988,
|
| 2781 |
+
"step": 396
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 2.2772466539196943,
|
| 2785 |
+
"grad_norm": 0.37198993314527246,
|
| 2786 |
+
"learning_rate": 6.610751941407423e-06,
|
| 2787 |
+
"loss": 0.2987,
|
| 2788 |
+
"step": 397
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 2.2829827915869982,
|
| 2792 |
+
"grad_norm": 0.3605089217084053,
|
| 2793 |
+
"learning_rate": 6.511534122125385e-06,
|
| 2794 |
+
"loss": 0.3126,
|
| 2795 |
+
"step": 398
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 2.288718929254302,
|
| 2799 |
+
"grad_norm": 0.35417912926194517,
|
| 2800 |
+
"learning_rate": 6.412921525243747e-06,
|
| 2801 |
+
"loss": 0.3179,
|
| 2802 |
+
"step": 399
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 2.294455066921606,
|
| 2806 |
+
"grad_norm": 0.34739676511363254,
|
| 2807 |
+
"learning_rate": 6.314918575472724e-06,
|
| 2808 |
+
"loss": 0.3213,
|
| 2809 |
+
"step": 400
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 2.30019120458891,
|
| 2813 |
+
"grad_norm": 0.34538986538232874,
|
| 2814 |
+
"learning_rate": 6.2175296701678765e-06,
|
| 2815 |
+
"loss": 0.3267,
|
| 2816 |
+
"step": 401
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 2.305927342256214,
|
| 2820 |
+
"grad_norm": 0.33419006023335046,
|
| 2821 |
+
"learning_rate": 6.120759179132825e-06,
|
| 2822 |
+
"loss": 0.3022,
|
| 2823 |
+
"step": 402
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 2.311663479923518,
|
| 2827 |
+
"grad_norm": 0.3490791821453638,
|
| 2828 |
+
"learning_rate": 6.024611444423167e-06,
|
| 2829 |
+
"loss": 0.3331,
|
| 2830 |
+
"step": 403
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 2.317399617590822,
|
| 2834 |
+
"grad_norm": 0.3423057899783048,
|
| 2835 |
+
"learning_rate": 5.929090780151683e-06,
|
| 2836 |
+
"loss": 0.3235,
|
| 2837 |
+
"step": 404
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 2.323135755258126,
|
| 2841 |
+
"grad_norm": 0.3160266995434583,
|
| 2842 |
+
"learning_rate": 5.8342014722947025e-06,
|
| 2843 |
+
"loss": 0.2911,
|
| 2844 |
+
"step": 405
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 2.3288718929254304,
|
| 2848 |
+
"grad_norm": 0.3271039700649619,
|
| 2849 |
+
"learning_rate": 5.739947778499866e-06,
|
| 2850 |
+
"loss": 0.2625,
|
| 2851 |
+
"step": 406
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 2.3346080305927344,
|
| 2855 |
+
"grad_norm": 0.357397125079873,
|
| 2856 |
+
"learning_rate": 5.6463339278950135e-06,
|
| 2857 |
+
"loss": 0.2686,
|
| 2858 |
+
"step": 407
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 2.3403441682600383,
|
| 2862 |
+
"grad_norm": 0.3626417105072833,
|
| 2863 |
+
"learning_rate": 5.553364120898495e-06,
|
| 2864 |
+
"loss": 0.3078,
|
| 2865 |
+
"step": 408
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 2.3460803059273423,
|
| 2869 |
+
"grad_norm": 0.330368230833986,
|
| 2870 |
+
"learning_rate": 5.461042529030643e-06,
|
| 2871 |
+
"loss": 0.2669,
|
| 2872 |
+
"step": 409
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 2.3518164435946463,
|
| 2876 |
+
"grad_norm": 0.35751740719995606,
|
| 2877 |
+
"learning_rate": 5.369373294726625e-06,
|
| 2878 |
+
"loss": 0.3035,
|
| 2879 |
+
"step": 410
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 2.35755258126195,
|
| 2883 |
+
"grad_norm": 0.35220579168854316,
|
| 2884 |
+
"learning_rate": 5.2783605311505705e-06,
|
| 2885 |
+
"loss": 0.2959,
|
| 2886 |
+
"step": 411
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 2.363288718929254,
|
| 2890 |
+
"grad_norm": 0.3719450476826788,
|
| 2891 |
+
"learning_rate": 5.188008322011022e-06,
|
| 2892 |
+
"loss": 0.3271,
|
| 2893 |
+
"step": 412
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 2.369024856596558,
|
| 2897 |
+
"grad_norm": 0.3413354729055759,
|
| 2898 |
+
"learning_rate": 5.098320721377677e-06,
|
| 2899 |
+
"loss": 0.2821,
|
| 2900 |
+
"step": 413
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 2.3747609942638626,
|
| 2904 |
+
"grad_norm": 0.31970016663963907,
|
| 2905 |
+
"learning_rate": 5.00930175349952e-06,
|
| 2906 |
+
"loss": 0.2978,
|
| 2907 |
+
"step": 414
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 2.3804971319311665,
|
| 2911 |
+
"grad_norm": 0.3405014390669701,
|
| 2912 |
+
"learning_rate": 4.920955412624206e-06,
|
| 2913 |
+
"loss": 0.3298,
|
| 2914 |
+
"step": 415
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 2.3862332695984705,
|
| 2918 |
+
"grad_norm": 0.32022737076210306,
|
| 2919 |
+
"learning_rate": 4.833285662818903e-06,
|
| 2920 |
+
"loss": 0.3205,
|
| 2921 |
+
"step": 416
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 2.3919694072657744,
|
| 2925 |
+
"grad_norm": 0.326492045130511,
|
| 2926 |
+
"learning_rate": 4.746296437792364e-06,
|
| 2927 |
+
"loss": 0.3073,
|
| 2928 |
+
"step": 417
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 2.3977055449330784,
|
| 2932 |
+
"grad_norm": 0.32202773276443253,
|
| 2933 |
+
"learning_rate": 4.65999164071846e-06,
|
| 2934 |
+
"loss": 0.3132,
|
| 2935 |
+
"step": 418
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 2.4034416826003824,
|
| 2939 |
+
"grad_norm": 0.30026610991923225,
|
| 2940 |
+
"learning_rate": 4.5743751440610315e-06,
|
| 2941 |
+
"loss": 0.2999,
|
| 2942 |
+
"step": 419
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 2.4091778202676863,
|
| 2946 |
+
"grad_norm": 0.3263265838303172,
|
| 2947 |
+
"learning_rate": 4.489450789400158e-06,
|
| 2948 |
+
"loss": 0.3396,
|
| 2949 |
+
"step": 420
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 2.4149139579349903,
|
| 2953 |
+
"grad_norm": 0.31887864810796523,
|
| 2954 |
+
"learning_rate": 4.405222387259737e-06,
|
| 2955 |
+
"loss": 0.2785,
|
| 2956 |
+
"step": 421
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 2.4206500956022943,
|
| 2960 |
+
"grad_norm": 0.33803434408500127,
|
| 2961 |
+
"learning_rate": 4.32169371693657e-06,
|
| 2962 |
+
"loss": 0.3396,
|
| 2963 |
+
"step": 422
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 2.4263862332695982,
|
| 2967 |
+
"grad_norm": 0.30385763232746726,
|
| 2968 |
+
"learning_rate": 4.238868526330722e-06,
|
| 2969 |
+
"loss": 0.2888,
|
| 2970 |
+
"step": 423
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 2.4321223709369026,
|
| 2974 |
+
"grad_norm": 0.32177073146894075,
|
| 2975 |
+
"learning_rate": 4.156750531777414e-06,
|
| 2976 |
+
"loss": 0.2814,
|
| 2977 |
+
"step": 424
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 2.4378585086042066,
|
| 2981 |
+
"grad_norm": 0.3331670974871312,
|
| 2982 |
+
"learning_rate": 4.075343417880233e-06,
|
| 2983 |
+
"loss": 0.3166,
|
| 2984 |
+
"step": 425
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 2.4435946462715106,
|
| 2988 |
+
"grad_norm": 0.34367786083186397,
|
| 2989 |
+
"learning_rate": 3.994650837345817e-06,
|
| 2990 |
+
"loss": 0.2981,
|
| 2991 |
+
"step": 426
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 2.4493307839388145,
|
| 2995 |
+
"grad_norm": 0.3379368579815228,
|
| 2996 |
+
"learning_rate": 3.914676410819957e-06,
|
| 2997 |
+
"loss": 0.3439,
|
| 2998 |
+
"step": 427
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 2.4550669216061185,
|
| 3002 |
+
"grad_norm": 0.32413796456612975,
|
| 3003 |
+
"learning_rate": 3.835423726725162e-06,
|
| 3004 |
+
"loss": 0.3026,
|
| 3005 |
+
"step": 428
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 2.4608030592734225,
|
| 3009 |
+
"grad_norm": 0.33686529783092345,
|
| 3010 |
+
"learning_rate": 3.7568963410996028e-06,
|
| 3011 |
+
"loss": 0.3366,
|
| 3012 |
+
"step": 429
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 2.4665391969407264,
|
| 3016 |
+
"grad_norm": 0.29819612441201854,
|
| 3017 |
+
"learning_rate": 3.6790977774376013e-06,
|
| 3018 |
+
"loss": 0.2838,
|
| 3019 |
+
"step": 430
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 2.472275334608031,
|
| 3023 |
+
"grad_norm": 0.33348914715995587,
|
| 3024 |
+
"learning_rate": 3.6020315265315087e-06,
|
| 3025 |
+
"loss": 0.3133,
|
| 3026 |
+
"step": 431
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 2.478011472275335,
|
| 3030 |
+
"grad_norm": 0.30518415557095047,
|
| 3031 |
+
"learning_rate": 3.5257010463150642e-06,
|
| 3032 |
+
"loss": 0.3132,
|
| 3033 |
+
"step": 432
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 2.4837476099426388,
|
| 3037 |
+
"grad_norm": 0.33485851224923785,
|
| 3038 |
+
"learning_rate": 3.4501097617082648e-06,
|
| 3039 |
+
"loss": 0.3567,
|
| 3040 |
+
"step": 433
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 2.4894837476099427,
|
| 3044 |
+
"grad_norm": 0.3176169459499719,
|
| 3045 |
+
"learning_rate": 3.375261064463666e-06,
|
| 3046 |
+
"loss": 0.3047,
|
| 3047 |
+
"step": 434
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 2.4952198852772467,
|
| 3051 |
+
"grad_norm": 0.35821675236801026,
|
| 3052 |
+
"learning_rate": 3.3011583130142277e-06,
|
| 3053 |
+
"loss": 0.3054,
|
| 3054 |
+
"step": 435
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 2.5009560229445507,
|
| 3058 |
+
"grad_norm": 0.31447192397671203,
|
| 3059 |
+
"learning_rate": 3.2278048323225764e-06,
|
| 3060 |
+
"loss": 0.3002,
|
| 3061 |
+
"step": 436
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 2.5066921606118546,
|
| 3065 |
+
"grad_norm": 0.29814490505492547,
|
| 3066 |
+
"learning_rate": 3.155203913731868e-06,
|
| 3067 |
+
"loss": 0.3145,
|
| 3068 |
+
"step": 437
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 2.5124282982791586,
|
| 3072 |
+
"grad_norm": 0.31338084805310423,
|
| 3073 |
+
"learning_rate": 3.0833588148180516e-06,
|
| 3074 |
+
"loss": 0.316,
|
| 3075 |
+
"step": 438
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 2.5181644359464626,
|
| 3079 |
+
"grad_norm": 0.33273295840043154,
|
| 3080 |
+
"learning_rate": 3.0122727592437574e-06,
|
| 3081 |
+
"loss": 0.3052,
|
| 3082 |
+
"step": 439
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 2.5239005736137665,
|
| 3086 |
+
"grad_norm": 0.3586562727340161,
|
| 3087 |
+
"learning_rate": 2.941948936613608e-06,
|
| 3088 |
+
"loss": 0.3584,
|
| 3089 |
+
"step": 440
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 2.5296367112810705,
|
| 3093 |
+
"grad_norm": 0.3149636280687063,
|
| 3094 |
+
"learning_rate": 2.8723905023311237e-06,
|
| 3095 |
+
"loss": 0.3323,
|
| 3096 |
+
"step": 441
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 2.535372848948375,
|
| 3100 |
+
"grad_norm": 0.29354487416787345,
|
| 3101 |
+
"learning_rate": 2.8036005774571373e-06,
|
| 3102 |
+
"loss": 0.27,
|
| 3103 |
+
"step": 442
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 2.541108986615679,
|
| 3107 |
+
"grad_norm": 0.32300649834326484,
|
| 3108 |
+
"learning_rate": 2.7355822485697615e-06,
|
| 3109 |
+
"loss": 0.2927,
|
| 3110 |
+
"step": 443
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 2.546845124282983,
|
| 3114 |
+
"grad_norm": 0.32585893999440413,
|
| 3115 |
+
"learning_rate": 2.668338567625872e-06,
|
| 3116 |
+
"loss": 0.2917,
|
| 3117 |
+
"step": 444
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 2.552581261950287,
|
| 3121 |
+
"grad_norm": 0.3206957295285485,
|
| 3122 |
+
"learning_rate": 2.601872551824196e-06,
|
| 3123 |
+
"loss": 0.3305,
|
| 3124 |
+
"step": 445
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 2.5583173996175907,
|
| 3128 |
+
"grad_norm": 0.31706654167791043,
|
| 3129 |
+
"learning_rate": 2.536187183469905e-06,
|
| 3130 |
+
"loss": 0.3036,
|
| 3131 |
+
"step": 446
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 2.5640535372848947,
|
| 3135 |
+
"grad_norm": 0.29637565255206266,
|
| 3136 |
+
"learning_rate": 2.4712854098408245e-06,
|
| 3137 |
+
"loss": 0.296,
|
| 3138 |
+
"step": 447
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 2.569789674952199,
|
| 3142 |
+
"grad_norm": 0.3242672724124806,
|
| 3143 |
+
"learning_rate": 2.407170143055173e-06,
|
| 3144 |
+
"loss": 0.3165,
|
| 3145 |
+
"step": 448
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 2.575525812619503,
|
| 3149 |
+
"grad_norm": 0.31283308105656626,
|
| 3150 |
+
"learning_rate": 2.3438442599408995e-06,
|
| 3151 |
+
"loss": 0.2685,
|
| 3152 |
+
"step": 449
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 2.581261950286807,
|
| 3156 |
+
"grad_norm": 0.31850570032908976,
|
| 3157 |
+
"learning_rate": 2.2813106019066055e-06,
|
| 3158 |
+
"loss": 0.2677,
|
| 3159 |
+
"step": 450
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 2.586998087954111,
|
| 3163 |
+
"grad_norm": 0.33792122182008616,
|
| 3164 |
+
"learning_rate": 2.219571974814059e-06,
|
| 3165 |
+
"loss": 0.3382,
|
| 3166 |
+
"step": 451
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 2.592734225621415,
|
| 3170 |
+
"grad_norm": 0.31634274129393675,
|
| 3171 |
+
"learning_rate": 2.1586311488522705e-06,
|
| 3172 |
+
"loss": 0.2952,
|
| 3173 |
+
"step": 452
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 2.598470363288719,
|
| 3177 |
+
"grad_norm": 0.3044886559468434,
|
| 3178 |
+
"learning_rate": 2.0984908584132356e-06,
|
| 3179 |
+
"loss": 0.322,
|
| 3180 |
+
"step": 453
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 2.604206500956023,
|
| 3184 |
+
"grad_norm": 0.3025610232808951,
|
| 3185 |
+
"learning_rate": 2.0391538019691983e-06,
|
| 3186 |
+
"loss": 0.2895,
|
| 3187 |
+
"step": 454
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 2.609942638623327,
|
| 3191 |
+
"grad_norm": 0.31674447409176193,
|
| 3192 |
+
"learning_rate": 1.9806226419516195e-06,
|
| 3193 |
+
"loss": 0.3372,
|
| 3194 |
+
"step": 455
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 2.615678776290631,
|
| 3198 |
+
"grad_norm": 0.3163602428641736,
|
| 3199 |
+
"learning_rate": 1.922900004631667e-06,
|
| 3200 |
+
"loss": 0.2956,
|
| 3201 |
+
"step": 456
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 2.621414913957935,
|
| 3205 |
+
"grad_norm": 0.29617871455956285,
|
| 3206 |
+
"learning_rate": 1.8659884800024119e-06,
|
| 3207 |
+
"loss": 0.281,
|
| 3208 |
+
"step": 457
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 2.6271510516252388,
|
| 3212 |
+
"grad_norm": 0.3054337634119753,
|
| 3213 |
+
"learning_rate": 1.8098906216625934e-06,
|
| 3214 |
+
"loss": 0.2779,
|
| 3215 |
+
"step": 458
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 2.632887189292543,
|
| 3219 |
+
"grad_norm": 0.3473718579857251,
|
| 3220 |
+
"learning_rate": 1.7546089467020677e-06,
|
| 3221 |
+
"loss": 0.3322,
|
| 3222 |
+
"step": 459
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 2.638623326959847,
|
| 3226 |
+
"grad_norm": 0.3369008816792107,
|
| 3227 |
+
"learning_rate": 1.700145935588826e-06,
|
| 3228 |
+
"loss": 0.333,
|
| 3229 |
+
"step": 460
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 2.644359464627151,
|
| 3233 |
+
"grad_norm": 0.3127691638231103,
|
| 3234 |
+
"learning_rate": 1.6465040320577408e-06,
|
| 3235 |
+
"loss": 0.3012,
|
| 3236 |
+
"step": 461
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 2.650095602294455,
|
| 3240 |
+
"grad_norm": 0.30464242733494856,
|
| 3241 |
+
"learning_rate": 1.593685643000884e-06,
|
| 3242 |
+
"loss": 0.2875,
|
| 3243 |
+
"step": 462
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 2.655831739961759,
|
| 3247 |
+
"grad_norm": 0.33106117803370116,
|
| 3248 |
+
"learning_rate": 1.5416931383595436e-06,
|
| 3249 |
+
"loss": 0.3258,
|
| 3250 |
+
"step": 463
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 2.661567877629063,
|
| 3254 |
+
"grad_norm": 0.3246679490688405,
|
| 3255 |
+
"learning_rate": 1.490528851017885e-06,
|
| 3256 |
+
"loss": 0.3027,
|
| 3257 |
+
"step": 464
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 2.667304015296367,
|
| 3261 |
+
"grad_norm": 0.30458861657265374,
|
| 3262 |
+
"learning_rate": 1.440195076698272e-06,
|
| 3263 |
+
"loss": 0.2916,
|
| 3264 |
+
"step": 465
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 2.6730401529636714,
|
| 3268 |
+
"grad_norm": 0.3186347058123626,
|
| 3269 |
+
"learning_rate": 1.3906940738582698e-06,
|
| 3270 |
+
"loss": 0.2863,
|
| 3271 |
+
"step": 466
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 2.6787762906309753,
|
| 3275 |
+
"grad_norm": 0.31369585810148204,
|
| 3276 |
+
"learning_rate": 1.3420280635892847e-06,
|
| 3277 |
+
"loss": 0.3104,
|
| 3278 |
+
"step": 467
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 2.6845124282982793,
|
| 3282 |
+
"grad_norm": 0.316446279408055,
|
| 3283 |
+
"learning_rate": 1.2941992295169369e-06,
|
| 3284 |
+
"loss": 0.3303,
|
| 3285 |
+
"step": 468
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 2.6902485659655833,
|
| 3289 |
+
"grad_norm": 0.32320749119463515,
|
| 3290 |
+
"learning_rate": 1.2472097177030485e-06,
|
| 3291 |
+
"loss": 0.2923,
|
| 3292 |
+
"step": 469
|
| 3293 |
+
},
|
| 3294 |
+
{
|
| 3295 |
+
"epoch": 2.6959847036328872,
|
| 3296 |
+
"grad_norm": 0.3397456933911356,
|
| 3297 |
+
"learning_rate": 1.2010616365493811e-06,
|
| 3298 |
+
"loss": 0.3006,
|
| 3299 |
+
"step": 470
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 2.701720841300191,
|
| 3303 |
+
"grad_norm": 0.3135400345614286,
|
| 3304 |
+
"learning_rate": 1.1557570567030108e-06,
|
| 3305 |
+
"loss": 0.2936,
|
| 3306 |
+
"step": 471
|
| 3307 |
+
},
|
| 3308 |
+
{
|
| 3309 |
+
"epoch": 2.707456978967495,
|
| 3310 |
+
"grad_norm": 0.3021698093355975,
|
| 3311 |
+
"learning_rate": 1.1112980109634263e-06,
|
| 3312 |
+
"loss": 0.3341,
|
| 3313 |
+
"step": 472
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 2.713193116634799,
|
| 3317 |
+
"grad_norm": 0.30592288821677366,
|
| 3318 |
+
"learning_rate": 1.067686494191318e-06,
|
| 3319 |
+
"loss": 0.318,
|
| 3320 |
+
"step": 473
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 2.718929254302103,
|
| 3324 |
+
"grad_norm": 0.3320062239605175,
|
| 3325 |
+
"learning_rate": 1.0249244632190769e-06,
|
| 3326 |
+
"loss": 0.3299,
|
| 3327 |
+
"step": 474
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 2.724665391969407,
|
| 3331 |
+
"grad_norm": 0.30860296916444196,
|
| 3332 |
+
"learning_rate": 9.83013836762976e-07,
|
| 3333 |
+
"loss": 0.2836,
|
| 3334 |
+
"step": 475
|
| 3335 |
+
},
|
| 3336 |
+
{
|
| 3337 |
+
"epoch": 2.730401529636711,
|
| 3338 |
+
"grad_norm": 0.3361749125512604,
|
| 3339 |
+
"learning_rate": 9.419564953370952e-07,
|
| 3340 |
+
"loss": 0.3298,
|
| 3341 |
+
"step": 476
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 2.7361376673040154,
|
| 3345 |
+
"grad_norm": 0.30689246179518487,
|
| 3346 |
+
"learning_rate": 9.017542811689272e-07,
|
| 3347 |
+
"loss": 0.3033,
|
| 3348 |
+
"step": 477
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"epoch": 2.7418738049713194,
|
| 3352 |
+
"grad_norm": 0.2838154253297985,
|
| 3353 |
+
"learning_rate": 8.624089981167349e-07,
|
| 3354 |
+
"loss": 0.2356,
|
| 3355 |
+
"step": 478
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 2.7476099426386233,
|
| 3359 |
+
"grad_norm": 0.31969377880658495,
|
| 3360 |
+
"learning_rate": 8.239224115885957e-07,
|
| 3361 |
+
"loss": 0.3049,
|
| 3362 |
+
"step": 479
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 2.7533460803059273,
|
| 3366 |
+
"grad_norm": 0.30060258657145644,
|
| 3367 |
+
"learning_rate": 7.862962484631986e-07,
|
| 3368 |
+
"loss": 0.3063,
|
| 3369 |
+
"step": 480
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 2.7590822179732313,
|
| 3373 |
+
"grad_norm": 0.3022284718933698,
|
| 3374 |
+
"learning_rate": 7.49532197012357e-07,
|
| 3375 |
+
"loss": 0.2886,
|
| 3376 |
+
"step": 481
|
| 3377 |
+
},
|
| 3378 |
+
{
|
| 3379 |
+
"epoch": 2.7648183556405352,
|
| 3380 |
+
"grad_norm": 0.31537349530205033,
|
| 3381 |
+
"learning_rate": 7.136319068252629e-07,
|
| 3382 |
+
"loss": 0.327,
|
| 3383 |
+
"step": 482
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 2.7705544933078396,
|
| 3387 |
+
"grad_norm": 0.3214439225809495,
|
| 3388 |
+
"learning_rate": 6.785969887344546e-07,
|
| 3389 |
+
"loss": 0.3239,
|
| 3390 |
+
"step": 483
|
| 3391 |
+
},
|
| 3392 |
+
{
|
| 3393 |
+
"epoch": 2.7762906309751436,
|
| 3394 |
+
"grad_norm": 0.30881041163907574,
|
| 3395 |
+
"learning_rate": 6.444290147435617e-07,
|
| 3396 |
+
"loss": 0.2923,
|
| 3397 |
+
"step": 484
|
| 3398 |
+
},
|
| 3399 |
+
{
|
| 3400 |
+
"epoch": 2.7820267686424476,
|
| 3401 |
+
"grad_norm": 0.2968321026529436,
|
| 3402 |
+
"learning_rate": 6.111295179567434e-07,
|
| 3403 |
+
"loss": 0.2962,
|
| 3404 |
+
"step": 485
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 2.7877629063097515,
|
| 3408 |
+
"grad_norm": 0.32452460610512424,
|
| 3409 |
+
"learning_rate": 5.786999925099257e-07,
|
| 3410 |
+
"loss": 0.3019,
|
| 3411 |
+
"step": 486
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 2.7934990439770555,
|
| 3415 |
+
"grad_norm": 0.28214977997629037,
|
| 3416 |
+
"learning_rate": 5.471418935037398e-07,
|
| 3417 |
+
"loss": 0.2949,
|
| 3418 |
+
"step": 487
|
| 3419 |
+
},
|
| 3420 |
+
{
|
| 3421 |
+
"epoch": 2.7992351816443595,
|
| 3422 |
+
"grad_norm": 0.30056333465804613,
|
| 3423 |
+
"learning_rate": 5.164566369382407e-07,
|
| 3424 |
+
"loss": 0.3396,
|
| 3425 |
+
"step": 488
|
| 3426 |
+
},
|
| 3427 |
+
{
|
| 3428 |
+
"epoch": 2.8049713193116634,
|
| 3429 |
+
"grad_norm": 0.3025564251244908,
|
| 3430 |
+
"learning_rate": 4.866455996493691e-07,
|
| 3431 |
+
"loss": 0.2909,
|
| 3432 |
+
"step": 489
|
| 3433 |
+
},
|
| 3434 |
+
{
|
| 3435 |
+
"epoch": 2.8107074569789674,
|
| 3436 |
+
"grad_norm": 0.30674628776531615,
|
| 3437 |
+
"learning_rate": 4.577101192471811e-07,
|
| 3438 |
+
"loss": 0.3128,
|
| 3439 |
+
"step": 490
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 2.8164435946462714,
|
| 3443 |
+
"grad_norm": 0.31971943977257217,
|
| 3444 |
+
"learning_rate": 4.296514940558161e-07,
|
| 3445 |
+
"loss": 0.3299,
|
| 3446 |
+
"step": 491
|
| 3447 |
+
},
|
| 3448 |
+
{
|
| 3449 |
+
"epoch": 2.8221797323135753,
|
| 3450 |
+
"grad_norm": 0.32117510140100713,
|
| 3451 |
+
"learning_rate": 4.0247098305525645e-07,
|
| 3452 |
+
"loss": 0.3237,
|
| 3453 |
+
"step": 492
|
| 3454 |
+
},
|
| 3455 |
+
{
|
| 3456 |
+
"epoch": 2.8279158699808793,
|
| 3457 |
+
"grad_norm": 0.30441550056900496,
|
| 3458 |
+
"learning_rate": 3.7616980582482866e-07,
|
| 3459 |
+
"loss": 0.3431,
|
| 3460 |
+
"step": 493
|
| 3461 |
+
},
|
| 3462 |
+
{
|
| 3463 |
+
"epoch": 2.8336520076481837,
|
| 3464 |
+
"grad_norm": 0.2937689706082808,
|
| 3465 |
+
"learning_rate": 3.507491424884779e-07,
|
| 3466 |
+
"loss": 0.279,
|
| 3467 |
+
"step": 494
|
| 3468 |
+
},
|
| 3469 |
+
{
|
| 3470 |
+
"epoch": 2.8393881453154877,
|
| 3471 |
+
"grad_norm": 0.3243702100672169,
|
| 3472 |
+
"learning_rate": 3.262101336618262e-07,
|
| 3473 |
+
"loss": 0.3258,
|
| 3474 |
+
"step": 495
|
| 3475 |
+
},
|
| 3476 |
+
{
|
| 3477 |
+
"epoch": 2.8451242829827916,
|
| 3478 |
+
"grad_norm": 0.29048595506865943,
|
| 3479 |
+
"learning_rate": 3.0255388040098864e-07,
|
| 3480 |
+
"loss": 0.3202,
|
| 3481 |
+
"step": 496
|
| 3482 |
+
},
|
| 3483 |
+
{
|
| 3484 |
+
"epoch": 2.8508604206500956,
|
| 3485 |
+
"grad_norm": 0.32709366282528524,
|
| 3486 |
+
"learning_rate": 2.7978144415316656e-07,
|
| 3487 |
+
"loss": 0.3105,
|
| 3488 |
+
"step": 497
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 2.8565965583173996,
|
| 3492 |
+
"grad_norm": 0.28160883870197856,
|
| 3493 |
+
"learning_rate": 2.5789384670902753e-07,
|
| 3494 |
+
"loss": 0.2349,
|
| 3495 |
+
"step": 498
|
| 3496 |
+
},
|
| 3497 |
+
{
|
| 3498 |
+
"epoch": 2.8623326959847035,
|
| 3499 |
+
"grad_norm": 0.32964689233644207,
|
| 3500 |
+
"learning_rate": 2.3689207015685334e-07,
|
| 3501 |
+
"loss": 0.3767,
|
| 3502 |
+
"step": 499
|
| 3503 |
+
},
|
| 3504 |
+
{
|
| 3505 |
+
"epoch": 2.8680688336520075,
|
| 3506 |
+
"grad_norm": 0.30156232678290884,
|
| 3507 |
+
"learning_rate": 2.1677705683847082e-07,
|
| 3508 |
+
"loss": 0.2827,
|
| 3509 |
+
"step": 500
|
| 3510 |
+
},
|
| 3511 |
+
{
|
| 3512 |
+
"epoch": 2.873804971319312,
|
| 3513 |
+
"grad_norm": 0.29788501422144353,
|
| 3514 |
+
"learning_rate": 1.9754970930698115e-07,
|
| 3515 |
+
"loss": 0.2988,
|
| 3516 |
+
"step": 501
|
| 3517 |
+
},
|
| 3518 |
+
{
|
| 3519 |
+
"epoch": 2.879541108986616,
|
| 3520 |
+
"grad_norm": 0.3025299588676407,
|
| 3521 |
+
"learning_rate": 1.792108902862455e-07,
|
| 3522 |
+
"loss": 0.2925,
|
| 3523 |
+
"step": 502
|
| 3524 |
+
},
|
| 3525 |
+
{
|
| 3526 |
+
"epoch": 2.88527724665392,
|
| 3527 |
+
"grad_norm": 0.3248363141852775,
|
| 3528 |
+
"learning_rate": 1.6176142263219173e-07,
|
| 3529 |
+
"loss": 0.3148,
|
| 3530 |
+
"step": 503
|
| 3531 |
+
},
|
| 3532 |
+
{
|
| 3533 |
+
"epoch": 2.891013384321224,
|
| 3534 |
+
"grad_norm": 0.3189914861271819,
|
| 3535 |
+
"learning_rate": 1.4520208929587942e-07,
|
| 3536 |
+
"loss": 0.2563,
|
| 3537 |
+
"step": 504
|
| 3538 |
+
},
|
| 3539 |
+
{
|
| 3540 |
+
"epoch": 2.8967495219885278,
|
| 3541 |
+
"grad_norm": 0.2861804455486256,
|
| 3542 |
+
"learning_rate": 1.2953363328838342e-07,
|
| 3543 |
+
"loss": 0.2708,
|
| 3544 |
+
"step": 505
|
| 3545 |
+
},
|
| 3546 |
+
{
|
| 3547 |
+
"epoch": 2.9024856596558317,
|
| 3548 |
+
"grad_norm": 0.3137865936214283,
|
| 3549 |
+
"learning_rate": 1.1475675764743843e-07,
|
| 3550 |
+
"loss": 0.3803,
|
| 3551 |
+
"step": 506
|
| 3552 |
+
},
|
| 3553 |
+
{
|
| 3554 |
+
"epoch": 2.9082217973231357,
|
| 3555 |
+
"grad_norm": 0.321251565354294,
|
| 3556 |
+
"learning_rate": 1.0087212540591307e-07,
|
| 3557 |
+
"loss": 0.3431,
|
| 3558 |
+
"step": 507
|
| 3559 |
+
},
|
| 3560 |
+
{
|
| 3561 |
+
"epoch": 2.9139579349904396,
|
| 3562 |
+
"grad_norm": 0.2951230413126827,
|
| 3563 |
+
"learning_rate": 8.78803595620381e-08,
|
| 3564 |
+
"loss": 0.27,
|
| 3565 |
+
"step": 508
|
| 3566 |
+
},
|
| 3567 |
+
{
|
| 3568 |
+
"epoch": 2.9196940726577436,
|
| 3569 |
+
"grad_norm": 0.3247014517591854,
|
| 3570 |
+
"learning_rate": 7.57820430514733e-08,
|
| 3571 |
+
"loss": 0.2853,
|
| 3572 |
+
"step": 509
|
| 3573 |
+
},
|
| 3574 |
+
{
|
| 3575 |
+
"epoch": 2.9254302103250476,
|
| 3576 |
+
"grad_norm": 0.3229719006514364,
|
| 3577 |
+
"learning_rate": 6.457771872113716e-08,
|
| 3578 |
+
"loss": 0.3274,
|
| 3579 |
+
"step": 510
|
| 3580 |
+
},
|
| 3581 |
+
{
|
| 3582 |
+
"epoch": 2.9311663479923515,
|
| 3583 |
+
"grad_norm": 0.30781258564862424,
|
| 3584 |
+
"learning_rate": 5.4267889304859824e-08,
|
| 3585 |
+
"loss": 0.2917,
|
| 3586 |
+
"step": 511
|
| 3587 |
+
},
|
| 3588 |
+
{
|
| 3589 |
+
"epoch": 2.936902485659656,
|
| 3590 |
+
"grad_norm": 0.3008043286280689,
|
| 3591 |
+
"learning_rate": 4.485301740080994e-08,
|
| 3592 |
+
"loss": 0.3029,
|
| 3593 |
+
"step": 512
|
| 3594 |
+
},
|
| 3595 |
+
{
|
| 3596 |
+
"epoch": 2.94263862332696,
|
| 3597 |
+
"grad_norm": 0.2969030376672524,
|
| 3598 |
+
"learning_rate": 3.633352545076241e-08,
|
| 3599 |
+
"loss": 0.2627,
|
| 3600 |
+
"step": 513
|
| 3601 |
+
},
|
| 3602 |
+
{
|
| 3603 |
+
"epoch": 2.948374760994264,
|
| 3604 |
+
"grad_norm": 0.2974333758480683,
|
| 3605 |
+
"learning_rate": 2.8709795721117984e-08,
|
| 3606 |
+
"loss": 0.3265,
|
| 3607 |
+
"step": 514
|
| 3608 |
+
},
|
| 3609 |
+
{
|
| 3610 |
+
"epoch": 2.954110898661568,
|
| 3611 |
+
"grad_norm": 0.3173221368962474,
|
| 3612 |
+
"learning_rate": 2.198217028577254e-08,
|
| 3613 |
+
"loss": 0.3039,
|
| 3614 |
+
"step": 515
|
| 3615 |
+
},
|
| 3616 |
+
{
|
| 3617 |
+
"epoch": 2.959847036328872,
|
| 3618 |
+
"grad_norm": 0.33002144156652646,
|
| 3619 |
+
"learning_rate": 1.6150951010747152e-08,
|
| 3620 |
+
"loss": 0.2785,
|
| 3621 |
+
"step": 516
|
| 3622 |
+
},
|
| 3623 |
+
{
|
| 3624 |
+
"epoch": 2.9655831739961758,
|
| 3625 |
+
"grad_norm": 0.30529921643631025,
|
| 3626 |
+
"learning_rate": 1.1216399540669998e-08,
|
| 3627 |
+
"loss": 0.2788,
|
| 3628 |
+
"step": 517
|
| 3629 |
+
},
|
| 3630 |
+
{
|
| 3631 |
+
"epoch": 2.97131931166348,
|
| 3632 |
+
"grad_norm": 0.31427963839680284,
|
| 3633 |
+
"learning_rate": 7.178737287005799e-09,
|
| 3634 |
+
"loss": 0.3469,
|
| 3635 |
+
"step": 518
|
| 3636 |
+
},
|
| 3637 |
+
{
|
| 3638 |
+
"epoch": 2.977055449330784,
|
| 3639 |
+
"grad_norm": 0.31476300056888123,
|
| 3640 |
+
"learning_rate": 4.038145418148176e-09,
|
| 3641 |
+
"loss": 0.2671,
|
| 3642 |
+
"step": 519
|
| 3643 |
+
},
|
| 3644 |
+
{
|
| 3645 |
+
"epoch": 2.982791586998088,
|
| 3646 |
+
"grad_norm": 0.3064284484610742,
|
| 3647 |
+
"learning_rate": 1.7947648512728343e-09,
|
| 3648 |
+
"loss": 0.32,
|
| 3649 |
+
"step": 520
|
| 3650 |
+
},
|
| 3651 |
+
{
|
| 3652 |
+
"epoch": 2.988527724665392,
|
| 3653 |
+
"grad_norm": 0.30798998882484835,
|
| 3654 |
+
"learning_rate": 4.486962460270583e-10,
|
| 3655 |
+
"loss": 0.3146,
|
| 3656 |
+
"step": 521
|
| 3657 |
+
},
|
| 3658 |
+
{
|
| 3659 |
+
"epoch": 2.994263862332696,
|
| 3660 |
+
"grad_norm": 0.28978511666305123,
|
| 3661 |
+
"learning_rate": 0.0,
|
| 3662 |
+
"loss": 0.2861,
|
| 3663 |
+
"step": 522
|
| 3664 |
+
},
|
| 3665 |
+
{
|
| 3666 |
+
"epoch": 2.994263862332696,
|
| 3667 |
+
"step": 522,
|
| 3668 |
+
"total_flos": 5.620362022127534e+17,
|
| 3669 |
+
"train_loss": 0.4276364711452261,
|
| 3670 |
+
"train_runtime": 8560.5176,
|
| 3671 |
+
"train_samples_per_second": 5.856,
|
| 3672 |
+
"train_steps_per_second": 0.061
|
| 3673 |
+
}
|
| 3674 |
+
],
|
| 3675 |
+
"logging_steps": 1.0,
|
| 3676 |
+
"max_steps": 522,
|
| 3677 |
+
"num_input_tokens_seen": 0,
|
| 3678 |
+
"num_train_epochs": 3,
|
| 3679 |
+
"save_steps": 500,
|
| 3680 |
+
"stateful_callbacks": {
|
| 3681 |
+
"TrainerControl": {
|
| 3682 |
+
"args": {
|
| 3683 |
+
"should_epoch_stop": false,
|
| 3684 |
+
"should_evaluate": false,
|
| 3685 |
+
"should_log": false,
|
| 3686 |
+
"should_save": true,
|
| 3687 |
+
"should_training_stop": true
|
| 3688 |
+
},
|
| 3689 |
+
"attributes": {}
|
| 3690 |
+
}
|
| 3691 |
+
},
|
| 3692 |
+
"total_flos": 5.620362022127534e+17,
|
| 3693 |
+
"train_batch_size": 1,
|
| 3694 |
+
"trial_name": null,
|
| 3695 |
+
"trial_params": null
|
| 3696 |
+
}
|
training_loss.png
ADDED
|