End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +3318 -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: 10k_globalbatchsize64_lr4e5_epochs3
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# 10k_globalbatchsize64_lr4e5_epochs3
|
| 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: 10k_globalbatchsize64_lr4e5_epochs3
|
|
|
|
| 16 |
|
| 17 |
# 10k_globalbatchsize64_lr4e5_epochs3
|
| 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 mlfoundations-dev/openthoughts_10000 dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9904153354632586,
|
| 3 |
+
"total_flos": 3.310734730054861e+17,
|
| 4 |
+
"train_loss": 0.41292818673910237,
|
| 5 |
+
"train_runtime": 10004.6891,
|
| 6 |
+
"train_samples_per_second": 2.998,
|
| 7 |
+
"train_steps_per_second": 0.047
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9904153354632586,
|
| 3 |
+
"total_flos": 3.310734730054861e+17,
|
| 4 |
+
"train_loss": 0.41292818673910237,
|
| 5 |
+
"train_runtime": 10004.6891,
|
| 6 |
+
"train_samples_per_second": 2.998,
|
| 7 |
+
"train_steps_per_second": 0.047
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3318 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9904153354632586,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 468,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.006389776357827476,
|
| 13 |
+
"grad_norm": 5.9393923041460335,
|
| 14 |
+
"learning_rate": 8.510638297872341e-07,
|
| 15 |
+
"loss": 0.8883,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.012779552715654952,
|
| 20 |
+
"grad_norm": 5.645614037221844,
|
| 21 |
+
"learning_rate": 1.7021276595744682e-06,
|
| 22 |
+
"loss": 0.8365,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.019169329073482427,
|
| 27 |
+
"grad_norm": 6.260474581584071,
|
| 28 |
+
"learning_rate": 2.553191489361702e-06,
|
| 29 |
+
"loss": 0.8853,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.025559105431309903,
|
| 34 |
+
"grad_norm": 5.551335163218543,
|
| 35 |
+
"learning_rate": 3.4042553191489363e-06,
|
| 36 |
+
"loss": 0.8686,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03194888178913738,
|
| 41 |
+
"grad_norm": 4.506734407013277,
|
| 42 |
+
"learning_rate": 4.255319148936171e-06,
|
| 43 |
+
"loss": 0.792,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.038338658146964855,
|
| 48 |
+
"grad_norm": 2.7013711545792316,
|
| 49 |
+
"learning_rate": 5.106382978723404e-06,
|
| 50 |
+
"loss": 0.7978,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04472843450479233,
|
| 55 |
+
"grad_norm": 2.231426309167533,
|
| 56 |
+
"learning_rate": 5.957446808510638e-06,
|
| 57 |
+
"loss": 0.7656,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.051118210862619806,
|
| 62 |
+
"grad_norm": 3.786605436059839,
|
| 63 |
+
"learning_rate": 6.808510638297873e-06,
|
| 64 |
+
"loss": 0.7476,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.05750798722044728,
|
| 69 |
+
"grad_norm": 3.9559474965927994,
|
| 70 |
+
"learning_rate": 7.659574468085107e-06,
|
| 71 |
+
"loss": 0.751,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.06389776357827476,
|
| 76 |
+
"grad_norm": 4.3050608871997476,
|
| 77 |
+
"learning_rate": 8.510638297872341e-06,
|
| 78 |
+
"loss": 0.7376,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.07028753993610223,
|
| 83 |
+
"grad_norm": 3.844203590596342,
|
| 84 |
+
"learning_rate": 9.361702127659576e-06,
|
| 85 |
+
"loss": 0.6577,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.07667731629392971,
|
| 90 |
+
"grad_norm": 3.7090602450962535,
|
| 91 |
+
"learning_rate": 1.0212765957446808e-05,
|
| 92 |
+
"loss": 0.7587,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08306709265175719,
|
| 97 |
+
"grad_norm": 2.6605932751385915,
|
| 98 |
+
"learning_rate": 1.1063829787234044e-05,
|
| 99 |
+
"loss": 0.7102,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.08945686900958466,
|
| 104 |
+
"grad_norm": 1.841280162949687,
|
| 105 |
+
"learning_rate": 1.1914893617021277e-05,
|
| 106 |
+
"loss": 0.6686,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.09584664536741214,
|
| 111 |
+
"grad_norm": 2.4654109468445635,
|
| 112 |
+
"learning_rate": 1.2765957446808513e-05,
|
| 113 |
+
"loss": 0.6976,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.10223642172523961,
|
| 118 |
+
"grad_norm": 2.2718952209600842,
|
| 119 |
+
"learning_rate": 1.3617021276595745e-05,
|
| 120 |
+
"loss": 0.66,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.10862619808306709,
|
| 125 |
+
"grad_norm": 1.336892858370965,
|
| 126 |
+
"learning_rate": 1.4468085106382981e-05,
|
| 127 |
+
"loss": 0.6222,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.11501597444089456,
|
| 132 |
+
"grad_norm": 1.3994667991152954,
|
| 133 |
+
"learning_rate": 1.5319148936170214e-05,
|
| 134 |
+
"loss": 0.616,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.12140575079872204,
|
| 139 |
+
"grad_norm": 1.3560171283396125,
|
| 140 |
+
"learning_rate": 1.6170212765957446e-05,
|
| 141 |
+
"loss": 0.6394,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.12779552715654952,
|
| 146 |
+
"grad_norm": 1.1983042661201426,
|
| 147 |
+
"learning_rate": 1.7021276595744682e-05,
|
| 148 |
+
"loss": 0.5704,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.134185303514377,
|
| 153 |
+
"grad_norm": 0.9862694631668227,
|
| 154 |
+
"learning_rate": 1.7872340425531915e-05,
|
| 155 |
+
"loss": 0.592,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.14057507987220447,
|
| 160 |
+
"grad_norm": 1.1717058829411315,
|
| 161 |
+
"learning_rate": 1.872340425531915e-05,
|
| 162 |
+
"loss": 0.6111,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.14696485623003194,
|
| 167 |
+
"grad_norm": 1.052734463937942,
|
| 168 |
+
"learning_rate": 1.9574468085106384e-05,
|
| 169 |
+
"loss": 0.6105,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.15335463258785942,
|
| 174 |
+
"grad_norm": 0.9393704655813953,
|
| 175 |
+
"learning_rate": 2.0425531914893616e-05,
|
| 176 |
+
"loss": 0.6196,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1597444089456869,
|
| 181 |
+
"grad_norm": 1.064356434143729,
|
| 182 |
+
"learning_rate": 2.1276595744680852e-05,
|
| 183 |
+
"loss": 0.6022,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.16613418530351437,
|
| 188 |
+
"grad_norm": 0.8527356341897169,
|
| 189 |
+
"learning_rate": 2.2127659574468088e-05,
|
| 190 |
+
"loss": 0.6149,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.17252396166134185,
|
| 195 |
+
"grad_norm": 0.8856534958761616,
|
| 196 |
+
"learning_rate": 2.2978723404255324e-05,
|
| 197 |
+
"loss": 0.57,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.17891373801916932,
|
| 202 |
+
"grad_norm": 0.7965378935060776,
|
| 203 |
+
"learning_rate": 2.3829787234042553e-05,
|
| 204 |
+
"loss": 0.5663,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1853035143769968,
|
| 209 |
+
"grad_norm": 0.930055407459929,
|
| 210 |
+
"learning_rate": 2.468085106382979e-05,
|
| 211 |
+
"loss": 0.5675,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.19169329073482427,
|
| 216 |
+
"grad_norm": 0.9473480680946368,
|
| 217 |
+
"learning_rate": 2.5531914893617025e-05,
|
| 218 |
+
"loss": 0.5647,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.19808306709265175,
|
| 223 |
+
"grad_norm": 0.9035770727022399,
|
| 224 |
+
"learning_rate": 2.6382978723404255e-05,
|
| 225 |
+
"loss": 0.5571,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.20447284345047922,
|
| 230 |
+
"grad_norm": 0.9629442234127248,
|
| 231 |
+
"learning_rate": 2.723404255319149e-05,
|
| 232 |
+
"loss": 0.5675,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.2108626198083067,
|
| 237 |
+
"grad_norm": 0.8898757055373155,
|
| 238 |
+
"learning_rate": 2.8085106382978727e-05,
|
| 239 |
+
"loss": 0.5684,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.21725239616613418,
|
| 244 |
+
"grad_norm": 0.8818620757382937,
|
| 245 |
+
"learning_rate": 2.8936170212765963e-05,
|
| 246 |
+
"loss": 0.5394,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.22364217252396165,
|
| 251 |
+
"grad_norm": 1.2556928806711947,
|
| 252 |
+
"learning_rate": 2.9787234042553192e-05,
|
| 253 |
+
"loss": 0.5912,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.23003194888178913,
|
| 258 |
+
"grad_norm": 0.8995453098056544,
|
| 259 |
+
"learning_rate": 3.063829787234043e-05,
|
| 260 |
+
"loss": 0.5284,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2364217252396166,
|
| 265 |
+
"grad_norm": 1.1694120920465332,
|
| 266 |
+
"learning_rate": 3.1489361702127664e-05,
|
| 267 |
+
"loss": 0.5448,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.24281150159744408,
|
| 272 |
+
"grad_norm": 0.8640750703168888,
|
| 273 |
+
"learning_rate": 3.234042553191489e-05,
|
| 274 |
+
"loss": 0.5427,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.24920127795527156,
|
| 279 |
+
"grad_norm": 0.9511230435963061,
|
| 280 |
+
"learning_rate": 3.319148936170213e-05,
|
| 281 |
+
"loss": 0.5242,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.25559105431309903,
|
| 286 |
+
"grad_norm": 0.9815409113958286,
|
| 287 |
+
"learning_rate": 3.4042553191489365e-05,
|
| 288 |
+
"loss": 0.5327,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.26198083067092653,
|
| 293 |
+
"grad_norm": 0.9294918620323822,
|
| 294 |
+
"learning_rate": 3.48936170212766e-05,
|
| 295 |
+
"loss": 0.55,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.268370607028754,
|
| 300 |
+
"grad_norm": 1.2780033880918986,
|
| 301 |
+
"learning_rate": 3.574468085106383e-05,
|
| 302 |
+
"loss": 0.5057,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.2747603833865815,
|
| 307 |
+
"grad_norm": 0.970896465496613,
|
| 308 |
+
"learning_rate": 3.6595744680851066e-05,
|
| 309 |
+
"loss": 0.563,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.28115015974440893,
|
| 314 |
+
"grad_norm": 1.1743520181962854,
|
| 315 |
+
"learning_rate": 3.74468085106383e-05,
|
| 316 |
+
"loss": 0.5716,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.28753993610223644,
|
| 321 |
+
"grad_norm": 0.9440517537009965,
|
| 322 |
+
"learning_rate": 3.829787234042554e-05,
|
| 323 |
+
"loss": 0.5202,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.2939297124600639,
|
| 328 |
+
"grad_norm": 1.244837667755633,
|
| 329 |
+
"learning_rate": 3.914893617021277e-05,
|
| 330 |
+
"loss": 0.5333,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3003194888178914,
|
| 335 |
+
"grad_norm": 1.0156465350553556,
|
| 336 |
+
"learning_rate": 4e-05,
|
| 337 |
+
"loss": 0.5569,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.30670926517571884,
|
| 342 |
+
"grad_norm": 1.0875814805232027,
|
| 343 |
+
"learning_rate": 3.999944315600779e-05,
|
| 344 |
+
"loss": 0.5412,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.31309904153354634,
|
| 349 |
+
"grad_norm": 0.9841398658147307,
|
| 350 |
+
"learning_rate": 3.9997772655038674e-05,
|
| 351 |
+
"loss": 0.5493,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.3194888178913738,
|
| 356 |
+
"grad_norm": 1.041702971561358,
|
| 357 |
+
"learning_rate": 3.99949885901135e-05,
|
| 358 |
+
"loss": 0.5464,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.3258785942492013,
|
| 363 |
+
"grad_norm": 1.1971478020256678,
|
| 364 |
+
"learning_rate": 3.999109111626125e-05,
|
| 365 |
+
"loss": 0.5488,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.33226837060702874,
|
| 370 |
+
"grad_norm": 0.7937301188136895,
|
| 371 |
+
"learning_rate": 3.998608045051041e-05,
|
| 372 |
+
"loss": 0.5406,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.33865814696485624,
|
| 377 |
+
"grad_norm": 1.0893696428115565,
|
| 378 |
+
"learning_rate": 3.99799568718769e-05,
|
| 379 |
+
"loss": 0.5057,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.3450479233226837,
|
| 384 |
+
"grad_norm": 1.0041397722351062,
|
| 385 |
+
"learning_rate": 3.9972720721348503e-05,
|
| 386 |
+
"loss": 0.5568,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.3514376996805112,
|
| 391 |
+
"grad_norm": 1.1730368348535483,
|
| 392 |
+
"learning_rate": 3.996437240186593e-05,
|
| 393 |
+
"loss": 0.5376,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.35782747603833864,
|
| 398 |
+
"grad_norm": 1.0260574947019203,
|
| 399 |
+
"learning_rate": 3.995491237830033e-05,
|
| 400 |
+
"loss": 0.5845,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.36421725239616615,
|
| 405 |
+
"grad_norm": 0.9477092619910678,
|
| 406 |
+
"learning_rate": 3.994434117742743e-05,
|
| 407 |
+
"loss": 0.5861,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3706070287539936,
|
| 412 |
+
"grad_norm": 1.020580513302534,
|
| 413 |
+
"learning_rate": 3.9932659387898195e-05,
|
| 414 |
+
"loss": 0.4967,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.3769968051118211,
|
| 419 |
+
"grad_norm": 1.117231150698062,
|
| 420 |
+
"learning_rate": 3.991986766020607e-05,
|
| 421 |
+
"loss": 0.5163,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.38338658146964855,
|
| 426 |
+
"grad_norm": 0.9136891394466323,
|
| 427 |
+
"learning_rate": 3.9905966706650715e-05,
|
| 428 |
+
"loss": 0.5236,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.38977635782747605,
|
| 433 |
+
"grad_norm": 0.9610320358708975,
|
| 434 |
+
"learning_rate": 3.9890957301298385e-05,
|
| 435 |
+
"loss": 0.5442,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.3961661341853035,
|
| 440 |
+
"grad_norm": 0.9525076230315872,
|
| 441 |
+
"learning_rate": 3.9874840279938794e-05,
|
| 442 |
+
"loss": 0.5481,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.402555910543131,
|
| 447 |
+
"grad_norm": 0.9886639116884637,
|
| 448 |
+
"learning_rate": 3.9857616540038595e-05,
|
| 449 |
+
"loss": 0.587,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.40894568690095845,
|
| 454 |
+
"grad_norm": 0.8789895879873663,
|
| 455 |
+
"learning_rate": 3.9839287040691396e-05,
|
| 456 |
+
"loss": 0.5405,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.41533546325878595,
|
| 461 |
+
"grad_norm": 1.2919381394585123,
|
| 462 |
+
"learning_rate": 3.981985280256436e-05,
|
| 463 |
+
"loss": 0.5661,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.4217252396166134,
|
| 468 |
+
"grad_norm": 0.8458840142981038,
|
| 469 |
+
"learning_rate": 3.979931490784136e-05,
|
| 470 |
+
"loss": 0.5376,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.4281150159744409,
|
| 475 |
+
"grad_norm": 0.7123621144432971,
|
| 476 |
+
"learning_rate": 3.977767450016272e-05,
|
| 477 |
+
"loss": 0.5501,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.43450479233226835,
|
| 482 |
+
"grad_norm": 0.9335736753943794,
|
| 483 |
+
"learning_rate": 3.9754932784561545e-05,
|
| 484 |
+
"loss": 0.5495,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.44089456869009586,
|
| 489 |
+
"grad_norm": 0.7759436980865956,
|
| 490 |
+
"learning_rate": 3.973109102739661e-05,
|
| 491 |
+
"loss": 0.5468,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.4472843450479233,
|
| 496 |
+
"grad_norm": 0.9317387591226213,
|
| 497 |
+
"learning_rate": 3.9706150556281827e-05,
|
| 498 |
+
"loss": 0.5578,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.4536741214057508,
|
| 503 |
+
"grad_norm": 1.125415618543546,
|
| 504 |
+
"learning_rate": 3.968011276001236e-05,
|
| 505 |
+
"loss": 0.5769,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.46006389776357826,
|
| 510 |
+
"grad_norm": 1.0297816336058314,
|
| 511 |
+
"learning_rate": 3.9652979088487246e-05,
|
| 512 |
+
"loss": 0.5545,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.46645367412140576,
|
| 517 |
+
"grad_norm": 0.977116035792409,
|
| 518 |
+
"learning_rate": 3.962475105262868e-05,
|
| 519 |
+
"loss": 0.5443,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.4728434504792332,
|
| 524 |
+
"grad_norm": 0.9591838077463976,
|
| 525 |
+
"learning_rate": 3.9595430224297874e-05,
|
| 526 |
+
"loss": 0.5597,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.4792332268370607,
|
| 531 |
+
"grad_norm": 1.062273213479338,
|
| 532 |
+
"learning_rate": 3.9565018236207545e-05,
|
| 533 |
+
"loss": 0.5364,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.48562300319488816,
|
| 538 |
+
"grad_norm": 1.3459560450980237,
|
| 539 |
+
"learning_rate": 3.953351678183099e-05,
|
| 540 |
+
"loss": 0.5507,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.49201277955271566,
|
| 545 |
+
"grad_norm": 0.9913845916559971,
|
| 546 |
+
"learning_rate": 3.9500927615307745e-05,
|
| 547 |
+
"loss": 0.5244,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.4984025559105431,
|
| 552 |
+
"grad_norm": 1.4251625906436933,
|
| 553 |
+
"learning_rate": 3.9467252551346e-05,
|
| 554 |
+
"loss": 0.5594,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.5047923322683706,
|
| 559 |
+
"grad_norm": 1.0112792856876618,
|
| 560 |
+
"learning_rate": 3.943249346512143e-05,
|
| 561 |
+
"loss": 0.4883,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.5111821086261981,
|
| 566 |
+
"grad_norm": 1.0989399875889763,
|
| 567 |
+
"learning_rate": 3.939665229217289e-05,
|
| 568 |
+
"loss": 0.5144,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.5175718849840255,
|
| 573 |
+
"grad_norm": 1.0239637264891768,
|
| 574 |
+
"learning_rate": 3.935973102829456e-05,
|
| 575 |
+
"loss": 0.5527,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.5239616613418531,
|
| 580 |
+
"grad_norm": 1.0068238967871816,
|
| 581 |
+
"learning_rate": 3.9321731729424826e-05,
|
| 582 |
+
"loss": 0.5672,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.5303514376996805,
|
| 587 |
+
"grad_norm": 0.9875459555325186,
|
| 588 |
+
"learning_rate": 3.928265651153183e-05,
|
| 589 |
+
"loss": 0.529,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.536741214057508,
|
| 594 |
+
"grad_norm": 1.0535928381866786,
|
| 595 |
+
"learning_rate": 3.92425075504956e-05,
|
| 596 |
+
"loss": 0.5037,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.5431309904153354,
|
| 601 |
+
"grad_norm": 0.8056689145152576,
|
| 602 |
+
"learning_rate": 3.9201287081986905e-05,
|
| 603 |
+
"loss": 0.5561,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.549520766773163,
|
| 608 |
+
"grad_norm": 0.9754123651205087,
|
| 609 |
+
"learning_rate": 3.915899740134277e-05,
|
| 610 |
+
"loss": 0.533,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.5559105431309904,
|
| 615 |
+
"grad_norm": 1.15840636473317,
|
| 616 |
+
"learning_rate": 3.9115640863438666e-05,
|
| 617 |
+
"loss": 0.5493,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.5623003194888179,
|
| 622 |
+
"grad_norm": 0.8988153421079207,
|
| 623 |
+
"learning_rate": 3.907121988255735e-05,
|
| 624 |
+
"loss": 0.5196,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5686900958466453,
|
| 629 |
+
"grad_norm": 1.1383255251414823,
|
| 630 |
+
"learning_rate": 3.9025736932254463e-05,
|
| 631 |
+
"loss": 0.527,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.5750798722044729,
|
| 636 |
+
"grad_norm": 1.1283342937219425,
|
| 637 |
+
"learning_rate": 3.8979194545220754e-05,
|
| 638 |
+
"loss": 0.5295,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5814696485623003,
|
| 643 |
+
"grad_norm": 0.9227752366498948,
|
| 644 |
+
"learning_rate": 3.893159531314109e-05,
|
| 645 |
+
"loss": 0.5306,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.5878594249201278,
|
| 650 |
+
"grad_norm": 1.0643565858340844,
|
| 651 |
+
"learning_rate": 3.888294188655012e-05,
|
| 652 |
+
"loss": 0.5093,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.5942492012779552,
|
| 657 |
+
"grad_norm": 0.7000539222261911,
|
| 658 |
+
"learning_rate": 3.8833236974684666e-05,
|
| 659 |
+
"loss": 0.4991,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.6006389776357828,
|
| 664 |
+
"grad_norm": 1.1723297653142641,
|
| 665 |
+
"learning_rate": 3.8782483345332876e-05,
|
| 666 |
+
"loss": 0.5068,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.6070287539936102,
|
| 671 |
+
"grad_norm": 0.7821654004337761,
|
| 672 |
+
"learning_rate": 3.873068382468012e-05,
|
| 673 |
+
"loss": 0.4921,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6134185303514377,
|
| 678 |
+
"grad_norm": 0.9387810448789369,
|
| 679 |
+
"learning_rate": 3.8677841297151595e-05,
|
| 680 |
+
"loss": 0.5062,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.6198083067092651,
|
| 685 |
+
"grad_norm": 1.0554276403586835,
|
| 686 |
+
"learning_rate": 3.862395870525167e-05,
|
| 687 |
+
"loss": 0.5563,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.6261980830670927,
|
| 692 |
+
"grad_norm": 0.7778950998937124,
|
| 693 |
+
"learning_rate": 3.856903904940014e-05,
|
| 694 |
+
"loss": 0.5336,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.6325878594249201,
|
| 699 |
+
"grad_norm": 0.9707505249343071,
|
| 700 |
+
"learning_rate": 3.851308538776501e-05,
|
| 701 |
+
"loss": 0.5042,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.6389776357827476,
|
| 706 |
+
"grad_norm": 0.9480577698679056,
|
| 707 |
+
"learning_rate": 3.845610083609234e-05,
|
| 708 |
+
"loss": 0.5125,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.645367412140575,
|
| 713 |
+
"grad_norm": 1.000490021841588,
|
| 714 |
+
"learning_rate": 3.839808856753264e-05,
|
| 715 |
+
"loss": 0.5378,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.6517571884984026,
|
| 720 |
+
"grad_norm": 1.150496995903701,
|
| 721 |
+
"learning_rate": 3.833905181246424e-05,
|
| 722 |
+
"loss": 0.5201,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.65814696485623,
|
| 727 |
+
"grad_norm": 1.119406744384519,
|
| 728 |
+
"learning_rate": 3.827899385831337e-05,
|
| 729 |
+
"loss": 0.5219,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.6645367412140575,
|
| 734 |
+
"grad_norm": 1.0112237142528195,
|
| 735 |
+
"learning_rate": 3.821791804937114e-05,
|
| 736 |
+
"loss": 0.5298,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.670926517571885,
|
| 741 |
+
"grad_norm": 0.7034761817860105,
|
| 742 |
+
"learning_rate": 3.815582778660726e-05,
|
| 743 |
+
"loss": 0.5192,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.6773162939297125,
|
| 748 |
+
"grad_norm": 1.0053867926801359,
|
| 749 |
+
"learning_rate": 3.809272652748072e-05,
|
| 750 |
+
"loss": 0.5276,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.6837060702875399,
|
| 755 |
+
"grad_norm": 0.7482460221471098,
|
| 756 |
+
"learning_rate": 3.8028617785747224e-05,
|
| 757 |
+
"loss": 0.5608,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.6900958466453674,
|
| 762 |
+
"grad_norm": 0.9865927820444385,
|
| 763 |
+
"learning_rate": 3.7963505131263534e-05,
|
| 764 |
+
"loss": 0.4968,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.6964856230031949,
|
| 769 |
+
"grad_norm": 1.038453462373431,
|
| 770 |
+
"learning_rate": 3.789739218978871e-05,
|
| 771 |
+
"loss": 0.5693,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.7028753993610224,
|
| 776 |
+
"grad_norm": 0.6920319585898572,
|
| 777 |
+
"learning_rate": 3.783028264278217e-05,
|
| 778 |
+
"loss": 0.5372,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.7092651757188498,
|
| 783 |
+
"grad_norm": 1.0352100256938261,
|
| 784 |
+
"learning_rate": 3.7762180227198707e-05,
|
| 785 |
+
"loss": 0.5277,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.7156549520766773,
|
| 790 |
+
"grad_norm": 0.64046404209257,
|
| 791 |
+
"learning_rate": 3.7693088735280435e-05,
|
| 792 |
+
"loss": 0.4962,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.7220447284345048,
|
| 797 |
+
"grad_norm": 1.0958799819009744,
|
| 798 |
+
"learning_rate": 3.762301201434558e-05,
|
| 799 |
+
"loss": 0.5407,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.7284345047923323,
|
| 804 |
+
"grad_norm": 0.7248797975531077,
|
| 805 |
+
"learning_rate": 3.755195396657423e-05,
|
| 806 |
+
"loss": 0.5282,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.7348242811501597,
|
| 811 |
+
"grad_norm": 1.051488291269328,
|
| 812 |
+
"learning_rate": 3.74799185487911e-05,
|
| 813 |
+
"loss": 0.5331,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.7412140575079872,
|
| 818 |
+
"grad_norm": 1.080506027543262,
|
| 819 |
+
"learning_rate": 3.7406909772245136e-05,
|
| 820 |
+
"loss": 0.5433,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.7476038338658147,
|
| 825 |
+
"grad_norm": 0.8852634100172303,
|
| 826 |
+
"learning_rate": 3.73329317023862e-05,
|
| 827 |
+
"loss": 0.5128,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.7539936102236422,
|
| 832 |
+
"grad_norm": 1.1931790977018395,
|
| 833 |
+
"learning_rate": 3.725798845863868e-05,
|
| 834 |
+
"loss": 0.5067,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.7603833865814696,
|
| 839 |
+
"grad_norm": 0.9230539545451707,
|
| 840 |
+
"learning_rate": 3.718208421417208e-05,
|
| 841 |
+
"loss": 0.518,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.7667731629392971,
|
| 846 |
+
"grad_norm": 0.9288097411893196,
|
| 847 |
+
"learning_rate": 3.710522319566864e-05,
|
| 848 |
+
"loss": 0.5025,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.7731629392971247,
|
| 853 |
+
"grad_norm": 0.8269049032128745,
|
| 854 |
+
"learning_rate": 3.7027409683087994e-05,
|
| 855 |
+
"loss": 0.509,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.7795527156549521,
|
| 860 |
+
"grad_norm": 1.063330879029129,
|
| 861 |
+
"learning_rate": 3.694864800942886e-05,
|
| 862 |
+
"loss": 0.5577,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.7859424920127795,
|
| 867 |
+
"grad_norm": 0.7741080297489087,
|
| 868 |
+
"learning_rate": 3.686894256048771e-05,
|
| 869 |
+
"loss": 0.5132,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.792332268370607,
|
| 874 |
+
"grad_norm": 0.9963198870882927,
|
| 875 |
+
"learning_rate": 3.678829777461457e-05,
|
| 876 |
+
"loss": 0.5456,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.7987220447284346,
|
| 881 |
+
"grad_norm": 0.9303282772631454,
|
| 882 |
+
"learning_rate": 3.670671814246591e-05,
|
| 883 |
+
"loss": 0.51,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.805111821086262,
|
| 888 |
+
"grad_norm": 0.8193974356952273,
|
| 889 |
+
"learning_rate": 3.662420820675453e-05,
|
| 890 |
+
"loss": 0.4998,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.8115015974440895,
|
| 895 |
+
"grad_norm": 0.8935114136883495,
|
| 896 |
+
"learning_rate": 3.654077256199662e-05,
|
| 897 |
+
"loss": 0.4945,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.8178913738019169,
|
| 902 |
+
"grad_norm": 0.8144910990007458,
|
| 903 |
+
"learning_rate": 3.645641585425594e-05,
|
| 904 |
+
"loss": 0.5031,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.8242811501597445,
|
| 909 |
+
"grad_norm": 0.8181401765209083,
|
| 910 |
+
"learning_rate": 3.6371142780885085e-05,
|
| 911 |
+
"loss": 0.4892,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.8306709265175719,
|
| 916 |
+
"grad_norm": 0.8625236903783421,
|
| 917 |
+
"learning_rate": 3.628495809026391e-05,
|
| 918 |
+
"loss": 0.526,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.8370607028753994,
|
| 923 |
+
"grad_norm": 0.807030171859448,
|
| 924 |
+
"learning_rate": 3.619786658153514e-05,
|
| 925 |
+
"loss": 0.5289,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.8434504792332268,
|
| 930 |
+
"grad_norm": 0.8764232140015433,
|
| 931 |
+
"learning_rate": 3.6109873104337096e-05,
|
| 932 |
+
"loss": 0.5394,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.8498402555910544,
|
| 937 |
+
"grad_norm": 0.6976250810888259,
|
| 938 |
+
"learning_rate": 3.602098255853372e-05,
|
| 939 |
+
"loss": 0.4852,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.8562300319488818,
|
| 944 |
+
"grad_norm": 0.721487679418641,
|
| 945 |
+
"learning_rate": 3.593119989394163e-05,
|
| 946 |
+
"loss": 0.4989,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.8626198083067093,
|
| 951 |
+
"grad_norm": 0.8535899066215291,
|
| 952 |
+
"learning_rate": 3.584053011005457e-05,
|
| 953 |
+
"loss": 0.5261,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.8690095846645367,
|
| 958 |
+
"grad_norm": 0.8308742651526032,
|
| 959 |
+
"learning_rate": 3.574897825576499e-05,
|
| 960 |
+
"loss": 0.5336,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.8753993610223643,
|
| 965 |
+
"grad_norm": 1.04154322336692,
|
| 966 |
+
"learning_rate": 3.565654942908289e-05,
|
| 967 |
+
"loss": 0.5291,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.8817891373801917,
|
| 972 |
+
"grad_norm": 0.7174442743523838,
|
| 973 |
+
"learning_rate": 3.556324877685195e-05,
|
| 974 |
+
"loss": 0.5135,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.8881789137380192,
|
| 979 |
+
"grad_norm": 1.0786600177139642,
|
| 980 |
+
"learning_rate": 3.546908149446294e-05,
|
| 981 |
+
"loss": 0.4844,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.8945686900958466,
|
| 986 |
+
"grad_norm": 0.9288876630518276,
|
| 987 |
+
"learning_rate": 3.53740528255644e-05,
|
| 988 |
+
"loss": 0.5467,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.9009584664536742,
|
| 993 |
+
"grad_norm": 0.7709318953465457,
|
| 994 |
+
"learning_rate": 3.527816806177068e-05,
|
| 995 |
+
"loss": 0.5182,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.9073482428115016,
|
| 1000 |
+
"grad_norm": 0.8923057265426987,
|
| 1001 |
+
"learning_rate": 3.518143254236724e-05,
|
| 1002 |
+
"loss": 0.5033,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.9137380191693291,
|
| 1007 |
+
"grad_norm": 0.6637070684857435,
|
| 1008 |
+
"learning_rate": 3.508385165401336e-05,
|
| 1009 |
+
"loss": 0.5127,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.9201277955271565,
|
| 1014 |
+
"grad_norm": 0.9230168482815491,
|
| 1015 |
+
"learning_rate": 3.4985430830442175e-05,
|
| 1016 |
+
"loss": 0.516,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.9265175718849841,
|
| 1021 |
+
"grad_norm": 0.8941920473315101,
|
| 1022 |
+
"learning_rate": 3.4886175552158135e-05,
|
| 1023 |
+
"loss": 0.4947,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.9329073482428115,
|
| 1028 |
+
"grad_norm": 0.8990821129059456,
|
| 1029 |
+
"learning_rate": 3.478609134613176e-05,
|
| 1030 |
+
"loss": 0.5022,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.939297124600639,
|
| 1035 |
+
"grad_norm": 0.8662214281666614,
|
| 1036 |
+
"learning_rate": 3.4685183785491956e-05,
|
| 1037 |
+
"loss": 0.5149,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.9456869009584664,
|
| 1042 |
+
"grad_norm": 0.761583043458421,
|
| 1043 |
+
"learning_rate": 3.45834584892156e-05,
|
| 1044 |
+
"loss": 0.5484,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.952076677316294,
|
| 1049 |
+
"grad_norm": 0.9833756730405143,
|
| 1050 |
+
"learning_rate": 3.448092112181469e-05,
|
| 1051 |
+
"loss": 0.5113,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.9584664536741214,
|
| 1056 |
+
"grad_norm": 0.6553490250245431,
|
| 1057 |
+
"learning_rate": 3.4377577393020955e-05,
|
| 1058 |
+
"loss": 0.5057,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.9648562300319489,
|
| 1063 |
+
"grad_norm": 0.9077550016293252,
|
| 1064 |
+
"learning_rate": 3.427343305746783e-05,
|
| 1065 |
+
"loss": 0.4993,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.9712460063897763,
|
| 1070 |
+
"grad_norm": 0.7171270449880269,
|
| 1071 |
+
"learning_rate": 3.416849391437007e-05,
|
| 1072 |
+
"loss": 0.4784,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.9776357827476039,
|
| 1077 |
+
"grad_norm": 0.9933525489448933,
|
| 1078 |
+
"learning_rate": 3.406276580720082e-05,
|
| 1079 |
+
"loss": 0.4958,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.9840255591054313,
|
| 1084 |
+
"grad_norm": 0.7952422694005465,
|
| 1085 |
+
"learning_rate": 3.3956254623366206e-05,
|
| 1086 |
+
"loss": 0.5126,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.9904153354632588,
|
| 1091 |
+
"grad_norm": 0.7573030595910021,
|
| 1092 |
+
"learning_rate": 3.384896629387751e-05,
|
| 1093 |
+
"loss": 0.4954,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.9968051118210862,
|
| 1098 |
+
"grad_norm": 0.6608346407299301,
|
| 1099 |
+
"learning_rate": 3.374090679302091e-05,
|
| 1100 |
+
"loss": 0.5326,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.0031948881789137,
|
| 1105 |
+
"grad_norm": 1.221115547246655,
|
| 1106 |
+
"learning_rate": 3.363208213802478e-05,
|
| 1107 |
+
"loss": 0.7746,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.0095846645367412,
|
| 1112 |
+
"grad_norm": 0.755241193707458,
|
| 1113 |
+
"learning_rate": 3.352249838872466e-05,
|
| 1114 |
+
"loss": 0.4163,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.0159744408945688,
|
| 1119 |
+
"grad_norm": 0.5770894202417984,
|
| 1120 |
+
"learning_rate": 3.3412161647225795e-05,
|
| 1121 |
+
"loss": 0.3854,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.0223642172523961,
|
| 1126 |
+
"grad_norm": 0.6479907351500458,
|
| 1127 |
+
"learning_rate": 3.330107805756334e-05,
|
| 1128 |
+
"loss": 0.3674,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.0287539936102237,
|
| 1133 |
+
"grad_norm": 0.8588766728374346,
|
| 1134 |
+
"learning_rate": 3.318925380536026e-05,
|
| 1135 |
+
"loss": 0.4473,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.035143769968051,
|
| 1140 |
+
"grad_norm": 0.6190221770598182,
|
| 1141 |
+
"learning_rate": 3.307669511748285e-05,
|
| 1142 |
+
"loss": 0.3834,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.0415335463258786,
|
| 1147 |
+
"grad_norm": 0.9380647190076025,
|
| 1148 |
+
"learning_rate": 3.2963408261694026e-05,
|
| 1149 |
+
"loss": 0.4215,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.0479233226837061,
|
| 1154 |
+
"grad_norm": 0.8105378167398238,
|
| 1155 |
+
"learning_rate": 3.284939954630428e-05,
|
| 1156 |
+
"loss": 0.4247,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.0543130990415335,
|
| 1161 |
+
"grad_norm": 0.7819386983119491,
|
| 1162 |
+
"learning_rate": 3.2734675319820446e-05,
|
| 1163 |
+
"loss": 0.4013,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.060702875399361,
|
| 1168 |
+
"grad_norm": 1.1818150256172972,
|
| 1169 |
+
"learning_rate": 3.261924197059215e-05,
|
| 1170 |
+
"loss": 0.4592,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.0670926517571886,
|
| 1175 |
+
"grad_norm": 0.7222613902999555,
|
| 1176 |
+
"learning_rate": 3.25031059264561e-05,
|
| 1177 |
+
"loss": 0.3779,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.073482428115016,
|
| 1182 |
+
"grad_norm": 0.695599012715811,
|
| 1183 |
+
"learning_rate": 3.2386273654378134e-05,
|
| 1184 |
+
"loss": 0.3354,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.0798722044728435,
|
| 1189 |
+
"grad_norm": 0.6636714986165804,
|
| 1190 |
+
"learning_rate": 3.226875166009313e-05,
|
| 1191 |
+
"loss": 0.3658,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.0862619808306708,
|
| 1196 |
+
"grad_norm": 0.9119019299436991,
|
| 1197 |
+
"learning_rate": 3.215054648774274e-05,
|
| 1198 |
+
"loss": 0.4916,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.0926517571884984,
|
| 1203 |
+
"grad_norm": 0.6438001573913675,
|
| 1204 |
+
"learning_rate": 3.2031664719510967e-05,
|
| 1205 |
+
"loss": 0.3829,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.099041533546326,
|
| 1210 |
+
"grad_norm": 0.892962035381319,
|
| 1211 |
+
"learning_rate": 3.1912112975257664e-05,
|
| 1212 |
+
"loss": 0.4622,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.1054313099041533,
|
| 1217 |
+
"grad_norm": 0.7025792696391929,
|
| 1218 |
+
"learning_rate": 3.1791897912149874e-05,
|
| 1219 |
+
"loss": 0.3948,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.1118210862619808,
|
| 1224 |
+
"grad_norm": 0.659137823569491,
|
| 1225 |
+
"learning_rate": 3.167102622429117e-05,
|
| 1226 |
+
"loss": 0.364,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.1182108626198084,
|
| 1231 |
+
"grad_norm": 0.7388120415365451,
|
| 1232 |
+
"learning_rate": 3.1549504642348856e-05,
|
| 1233 |
+
"loss": 0.3855,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.1246006389776357,
|
| 1238 |
+
"grad_norm": 0.6711108216098111,
|
| 1239 |
+
"learning_rate": 3.142733993317924e-05,
|
| 1240 |
+
"loss": 0.3966,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.1309904153354633,
|
| 1245 |
+
"grad_norm": 0.6360807358108843,
|
| 1246 |
+
"learning_rate": 3.130453889945075e-05,
|
| 1247 |
+
"loss": 0.4024,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.1373801916932909,
|
| 1252 |
+
"grad_norm": 0.6324189051210329,
|
| 1253 |
+
"learning_rate": 3.118110837926517e-05,
|
| 1254 |
+
"loss": 0.3553,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.1437699680511182,
|
| 1259 |
+
"grad_norm": 0.7964831390454978,
|
| 1260 |
+
"learning_rate": 3.105705524577686e-05,
|
| 1261 |
+
"loss": 0.4578,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.1501597444089458,
|
| 1266 |
+
"grad_norm": 0.6710667005919045,
|
| 1267 |
+
"learning_rate": 3.093238640681003e-05,
|
| 1268 |
+
"loss": 0.3781,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.156549520766773,
|
| 1273 |
+
"grad_norm": 0.6387506156404197,
|
| 1274 |
+
"learning_rate": 3.080710880447408e-05,
|
| 1275 |
+
"loss": 0.3887,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.1629392971246006,
|
| 1280 |
+
"grad_norm": 0.7478222110923342,
|
| 1281 |
+
"learning_rate": 3.068122941477704e-05,
|
| 1282 |
+
"loss": 0.4388,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.1693290734824282,
|
| 1287 |
+
"grad_norm": 0.6263047219752043,
|
| 1288 |
+
"learning_rate": 3.05547552472371e-05,
|
| 1289 |
+
"loss": 0.3889,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.1757188498402555,
|
| 1294 |
+
"grad_norm": 0.8473527998575385,
|
| 1295 |
+
"learning_rate": 3.0427693344492278e-05,
|
| 1296 |
+
"loss": 0.4279,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.182108626198083,
|
| 1301 |
+
"grad_norm": 0.5095696451206226,
|
| 1302 |
+
"learning_rate": 3.0300050781908305e-05,
|
| 1303 |
+
"loss": 0.3517,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.1884984025559104,
|
| 1308 |
+
"grad_norm": 0.7415470456207829,
|
| 1309 |
+
"learning_rate": 3.0171834667184597e-05,
|
| 1310 |
+
"loss": 0.3922,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.194888178913738,
|
| 1315 |
+
"grad_norm": 0.8177392758602474,
|
| 1316 |
+
"learning_rate": 3.0043052139958465e-05,
|
| 1317 |
+
"loss": 0.4332,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.2012779552715656,
|
| 1322 |
+
"grad_norm": 0.5193140042572805,
|
| 1323 |
+
"learning_rate": 2.9913710371407574e-05,
|
| 1324 |
+
"loss": 0.3973,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.207667731629393,
|
| 1329 |
+
"grad_norm": 0.8215524197527592,
|
| 1330 |
+
"learning_rate": 2.97838165638506e-05,
|
| 1331 |
+
"loss": 0.3988,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.2140575079872205,
|
| 1336 |
+
"grad_norm": 0.6518458707691871,
|
| 1337 |
+
"learning_rate": 2.965337795034617e-05,
|
| 1338 |
+
"loss": 0.4124,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.220447284345048,
|
| 1343 |
+
"grad_norm": 0.7141025249008749,
|
| 1344 |
+
"learning_rate": 2.9522401794290127e-05,
|
| 1345 |
+
"loss": 0.478,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.2268370607028753,
|
| 1350 |
+
"grad_norm": 0.6807610256712961,
|
| 1351 |
+
"learning_rate": 2.9390895389011024e-05,
|
| 1352 |
+
"loss": 0.3373,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.233226837060703,
|
| 1357 |
+
"grad_norm": 0.6877212054512275,
|
| 1358 |
+
"learning_rate": 2.9258866057364028e-05,
|
| 1359 |
+
"loss": 0.481,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.2396166134185305,
|
| 1364 |
+
"grad_norm": 0.6607586787800477,
|
| 1365 |
+
"learning_rate": 2.912632115132316e-05,
|
| 1366 |
+
"loss": 0.3599,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.2460063897763578,
|
| 1371 |
+
"grad_norm": 0.6239197081486476,
|
| 1372 |
+
"learning_rate": 2.8993268051571877e-05,
|
| 1373 |
+
"loss": 0.4054,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.2523961661341854,
|
| 1378 |
+
"grad_norm": 0.6374267993723667,
|
| 1379 |
+
"learning_rate": 2.885971416709211e-05,
|
| 1380 |
+
"loss": 0.4582,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.2587859424920127,
|
| 1385 |
+
"grad_norm": 0.6083181799353529,
|
| 1386 |
+
"learning_rate": 2.8725666934751678e-05,
|
| 1387 |
+
"loss": 0.3904,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.2651757188498403,
|
| 1392 |
+
"grad_norm": 0.567022003437379,
|
| 1393 |
+
"learning_rate": 2.859113381889018e-05,
|
| 1394 |
+
"loss": 0.3776,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.2715654952076676,
|
| 1399 |
+
"grad_norm": 0.5883698301032603,
|
| 1400 |
+
"learning_rate": 2.8456122310903342e-05,
|
| 1401 |
+
"loss": 0.3869,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.2779552715654952,
|
| 1406 |
+
"grad_norm": 0.6219746159300882,
|
| 1407 |
+
"learning_rate": 2.8320639928825885e-05,
|
| 1408 |
+
"loss": 0.4434,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.2843450479233227,
|
| 1413 |
+
"grad_norm": 0.5913066862304653,
|
| 1414 |
+
"learning_rate": 2.818469421691285e-05,
|
| 1415 |
+
"loss": 0.4034,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.29073482428115,
|
| 1420 |
+
"grad_norm": 0.7406263370585998,
|
| 1421 |
+
"learning_rate": 2.804829274521954e-05,
|
| 1422 |
+
"loss": 0.4592,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.2971246006389776,
|
| 1427 |
+
"grad_norm": 0.6535050713890558,
|
| 1428 |
+
"learning_rate": 2.7911443109179958e-05,
|
| 1429 |
+
"loss": 0.4018,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.3035143769968052,
|
| 1434 |
+
"grad_norm": 0.6660994073473191,
|
| 1435 |
+
"learning_rate": 2.777415292918386e-05,
|
| 1436 |
+
"loss": 0.3987,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.3099041533546325,
|
| 1441 |
+
"grad_norm": 0.5770049980372955,
|
| 1442 |
+
"learning_rate": 2.7636429850152452e-05,
|
| 1443 |
+
"loss": 0.3931,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.31629392971246,
|
| 1448 |
+
"grad_norm": 0.7664470442831808,
|
| 1449 |
+
"learning_rate": 2.7498281541112645e-05,
|
| 1450 |
+
"loss": 0.406,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.3226837060702876,
|
| 1455 |
+
"grad_norm": 0.5845799672630331,
|
| 1456 |
+
"learning_rate": 2.735971569477002e-05,
|
| 1457 |
+
"loss": 0.3969,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.329073482428115,
|
| 1462 |
+
"grad_norm": 0.7256834317235751,
|
| 1463 |
+
"learning_rate": 2.72207400270805e-05,
|
| 1464 |
+
"loss": 0.4243,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.3354632587859425,
|
| 1469 |
+
"grad_norm": 0.5160971519592359,
|
| 1470 |
+
"learning_rate": 2.7081362276820634e-05,
|
| 1471 |
+
"loss": 0.3745,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.34185303514377,
|
| 1476 |
+
"grad_norm": 0.8175757140515724,
|
| 1477 |
+
"learning_rate": 2.6941590205156715e-05,
|
| 1478 |
+
"loss": 0.4768,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.3482428115015974,
|
| 1483 |
+
"grad_norm": 0.47324065852496966,
|
| 1484 |
+
"learning_rate": 2.6801431595212585e-05,
|
| 1485 |
+
"loss": 0.3741,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.354632587859425,
|
| 1490 |
+
"grad_norm": 0.6620362519919619,
|
| 1491 |
+
"learning_rate": 2.666089425163623e-05,
|
| 1492 |
+
"loss": 0.4173,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.3610223642172525,
|
| 1497 |
+
"grad_norm": 0.5902652547868394,
|
| 1498 |
+
"learning_rate": 2.6519986000165197e-05,
|
| 1499 |
+
"loss": 0.3851,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.3674121405750799,
|
| 1504 |
+
"grad_norm": 0.5996280221322619,
|
| 1505 |
+
"learning_rate": 2.637871468719081e-05,
|
| 1506 |
+
"loss": 0.3976,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.3738019169329074,
|
| 1511 |
+
"grad_norm": 0.5952050484113727,
|
| 1512 |
+
"learning_rate": 2.623708817932127e-05,
|
| 1513 |
+
"loss": 0.3557,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.3801916932907348,
|
| 1518 |
+
"grad_norm": 0.5629505435064166,
|
| 1519 |
+
"learning_rate": 2.6095114362943567e-05,
|
| 1520 |
+
"loss": 0.3675,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.3865814696485623,
|
| 1525 |
+
"grad_norm": 0.7284878464385949,
|
| 1526 |
+
"learning_rate": 2.5952801143784377e-05,
|
| 1527 |
+
"loss": 0.4192,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.3929712460063897,
|
| 1532 |
+
"grad_norm": 0.5611770400782802,
|
| 1533 |
+
"learning_rate": 2.5810156446469815e-05,
|
| 1534 |
+
"loss": 0.3929,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.3993610223642172,
|
| 1539 |
+
"grad_norm": 0.7474665760149969,
|
| 1540 |
+
"learning_rate": 2.5667188214084156e-05,
|
| 1541 |
+
"loss": 0.4085,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.4057507987220448,
|
| 1546 |
+
"grad_norm": 0.6711723162682844,
|
| 1547 |
+
"learning_rate": 2.5523904407727518e-05,
|
| 1548 |
+
"loss": 0.4069,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.4121405750798721,
|
| 1553 |
+
"grad_norm": 0.6895348539751915,
|
| 1554 |
+
"learning_rate": 2.5380313006072576e-05,
|
| 1555 |
+
"loss": 0.3844,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.4185303514376997,
|
| 1560 |
+
"grad_norm": 0.6675508521520543,
|
| 1561 |
+
"learning_rate": 2.523642200492027e-05,
|
| 1562 |
+
"loss": 0.4525,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.4249201277955272,
|
| 1567 |
+
"grad_norm": 0.6837935351740067,
|
| 1568 |
+
"learning_rate": 2.5092239416754545e-05,
|
| 1569 |
+
"loss": 0.3858,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.4313099041533546,
|
| 1574 |
+
"grad_norm": 0.7055234490813711,
|
| 1575 |
+
"learning_rate": 2.4947773270296218e-05,
|
| 1576 |
+
"loss": 0.4076,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.4376996805111821,
|
| 1581 |
+
"grad_norm": 0.642041869833729,
|
| 1582 |
+
"learning_rate": 2.4803031610055847e-05,
|
| 1583 |
+
"loss": 0.4116,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.4440894568690097,
|
| 1588 |
+
"grad_norm": 0.5973792017921002,
|
| 1589 |
+
"learning_rate": 2.465802249588583e-05,
|
| 1590 |
+
"loss": 0.3701,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.450479233226837,
|
| 1595 |
+
"grad_norm": 0.6561472014273614,
|
| 1596 |
+
"learning_rate": 2.451275400253157e-05,
|
| 1597 |
+
"loss": 0.3497,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 1.4568690095846646,
|
| 1602 |
+
"grad_norm": 0.7636693842376161,
|
| 1603 |
+
"learning_rate": 2.436723421918185e-05,
|
| 1604 |
+
"loss": 0.4835,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.4632587859424921,
|
| 1609 |
+
"grad_norm": 0.78261861893272,
|
| 1610 |
+
"learning_rate": 2.4221471249018368e-05,
|
| 1611 |
+
"loss": 0.373,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 1.4696485623003195,
|
| 1616 |
+
"grad_norm": 0.7179566840944903,
|
| 1617 |
+
"learning_rate": 2.4075473208764558e-05,
|
| 1618 |
+
"loss": 0.3923,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.476038338658147,
|
| 1623 |
+
"grad_norm": 0.5427966480029829,
|
| 1624 |
+
"learning_rate": 2.392924822823357e-05,
|
| 1625 |
+
"loss": 0.3575,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.4824281150159744,
|
| 1630 |
+
"grad_norm": 0.8958851181734642,
|
| 1631 |
+
"learning_rate": 2.378280444987561e-05,
|
| 1632 |
+
"loss": 0.4385,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.488817891373802,
|
| 1637 |
+
"grad_norm": 0.5170480560665358,
|
| 1638 |
+
"learning_rate": 2.3636150028324486e-05,
|
| 1639 |
+
"loss": 0.3372,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.4952076677316293,
|
| 1644 |
+
"grad_norm": 0.7554046281590651,
|
| 1645 |
+
"learning_rate": 2.3489293129943555e-05,
|
| 1646 |
+
"loss": 0.4001,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.5015974440894568,
|
| 1651 |
+
"grad_norm": 0.7092746883912118,
|
| 1652 |
+
"learning_rate": 2.334224193237097e-05,
|
| 1653 |
+
"loss": 0.4067,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.5079872204472844,
|
| 1658 |
+
"grad_norm": 0.7165299708968617,
|
| 1659 |
+
"learning_rate": 2.319500462406434e-05,
|
| 1660 |
+
"loss": 0.3842,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.5143769968051117,
|
| 1665 |
+
"grad_norm": 0.6445134623150068,
|
| 1666 |
+
"learning_rate": 2.3047589403844702e-05,
|
| 1667 |
+
"loss": 0.4108,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.5207667731629393,
|
| 1672 |
+
"grad_norm": 0.4954710255941146,
|
| 1673 |
+
"learning_rate": 2.290000448044004e-05,
|
| 1674 |
+
"loss": 0.3344,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.5271565495207668,
|
| 1679 |
+
"grad_norm": 0.6207344756135259,
|
| 1680 |
+
"learning_rate": 2.2752258072028145e-05,
|
| 1681 |
+
"loss": 0.4079,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.5335463258785942,
|
| 1686 |
+
"grad_norm": 0.4812466788237613,
|
| 1687 |
+
"learning_rate": 2.260435840577901e-05,
|
| 1688 |
+
"loss": 0.3711,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.5399361022364217,
|
| 1693 |
+
"grad_norm": 0.7722622559224537,
|
| 1694 |
+
"learning_rate": 2.245631371739669e-05,
|
| 1695 |
+
"loss": 0.4798,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.5463258785942493,
|
| 1700 |
+
"grad_norm": 0.514025904239645,
|
| 1701 |
+
"learning_rate": 2.2308132250660717e-05,
|
| 1702 |
+
"loss": 0.3586,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.5527156549520766,
|
| 1707 |
+
"grad_norm": 0.6211683701769444,
|
| 1708 |
+
"learning_rate": 2.215982225696704e-05,
|
| 1709 |
+
"loss": 0.341,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.5591054313099042,
|
| 1714 |
+
"grad_norm": 0.5633667247279115,
|
| 1715 |
+
"learning_rate": 2.201139199486856e-05,
|
| 1716 |
+
"loss": 0.3927,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.5654952076677318,
|
| 1721 |
+
"grad_norm": 0.5601679935599658,
|
| 1722 |
+
"learning_rate": 2.186284972961525e-05,
|
| 1723 |
+
"loss": 0.4049,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.571884984025559,
|
| 1728 |
+
"grad_norm": 0.5442755218693436,
|
| 1729 |
+
"learning_rate": 2.1714203732693905e-05,
|
| 1730 |
+
"loss": 0.3493,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.5782747603833864,
|
| 1735 |
+
"grad_norm": 0.7005155470203877,
|
| 1736 |
+
"learning_rate": 2.1565462281367572e-05,
|
| 1737 |
+
"loss": 0.446,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.5846645367412142,
|
| 1742 |
+
"grad_norm": 0.5005677905989587,
|
| 1743 |
+
"learning_rate": 2.141663365821459e-05,
|
| 1744 |
+
"loss": 0.3761,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.5910543130990416,
|
| 1749 |
+
"grad_norm": 0.598933880956211,
|
| 1750 |
+
"learning_rate": 2.1267726150667426e-05,
|
| 1751 |
+
"loss": 0.4227,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.5974440894568689,
|
| 1756 |
+
"grad_norm": 0.5823697199633178,
|
| 1757 |
+
"learning_rate": 2.1118748050551194e-05,
|
| 1758 |
+
"loss": 0.4185,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.6038338658146964,
|
| 1763 |
+
"grad_norm": 0.4661817463909431,
|
| 1764 |
+
"learning_rate": 2.0969707653621884e-05,
|
| 1765 |
+
"loss": 0.335,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.610223642172524,
|
| 1770 |
+
"grad_norm": 0.534066282750192,
|
| 1771 |
+
"learning_rate": 2.0820613259104462e-05,
|
| 1772 |
+
"loss": 0.4249,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.6166134185303513,
|
| 1777 |
+
"grad_norm": 0.5288717205900548,
|
| 1778 |
+
"learning_rate": 2.0671473169230715e-05,
|
| 1779 |
+
"loss": 0.4078,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.623003194888179,
|
| 1784 |
+
"grad_norm": 0.5850676124543679,
|
| 1785 |
+
"learning_rate": 2.0522295688776945e-05,
|
| 1786 |
+
"loss": 0.3872,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.6293929712460065,
|
| 1791 |
+
"grad_norm": 0.46385901267321095,
|
| 1792 |
+
"learning_rate": 2.037308912460153e-05,
|
| 1793 |
+
"loss": 0.3415,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.6357827476038338,
|
| 1798 |
+
"grad_norm": 0.6386876033156802,
|
| 1799 |
+
"learning_rate": 2.022386178518236e-05,
|
| 1800 |
+
"loss": 0.417,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.6421725239616614,
|
| 1805 |
+
"grad_norm": 0.4805587222138907,
|
| 1806 |
+
"learning_rate": 2.0074621980154167e-05,
|
| 1807 |
+
"loss": 0.3882,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.648562300319489,
|
| 1812 |
+
"grad_norm": 0.5746353853534201,
|
| 1813 |
+
"learning_rate": 1.9925378019845837e-05,
|
| 1814 |
+
"loss": 0.4104,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.6549520766773163,
|
| 1819 |
+
"grad_norm": 0.501859313648766,
|
| 1820 |
+
"learning_rate": 1.9776138214817648e-05,
|
| 1821 |
+
"loss": 0.3774,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.6613418530351438,
|
| 1826 |
+
"grad_norm": 0.5820108106526879,
|
| 1827 |
+
"learning_rate": 1.9626910875398475e-05,
|
| 1828 |
+
"loss": 0.3576,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.6677316293929714,
|
| 1833 |
+
"grad_norm": 0.5511522872814458,
|
| 1834 |
+
"learning_rate": 1.9477704311223062e-05,
|
| 1835 |
+
"loss": 0.4259,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.6741214057507987,
|
| 1840 |
+
"grad_norm": 0.5192707555977589,
|
| 1841 |
+
"learning_rate": 1.932852683076929e-05,
|
| 1842 |
+
"loss": 0.4159,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.680511182108626,
|
| 1847 |
+
"grad_norm": 0.5414396653048178,
|
| 1848 |
+
"learning_rate": 1.9179386740895538e-05,
|
| 1849 |
+
"loss": 0.3925,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.6869009584664538,
|
| 1854 |
+
"grad_norm": 0.5148601689863671,
|
| 1855 |
+
"learning_rate": 1.9030292346378116e-05,
|
| 1856 |
+
"loss": 0.3598,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.6932907348242812,
|
| 1861 |
+
"grad_norm": 0.5119362335475469,
|
| 1862 |
+
"learning_rate": 1.8881251949448817e-05,
|
| 1863 |
+
"loss": 0.4128,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 1.6996805111821085,
|
| 1868 |
+
"grad_norm": 0.5906313617691342,
|
| 1869 |
+
"learning_rate": 1.8732273849332577e-05,
|
| 1870 |
+
"loss": 0.3892,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.706070287539936,
|
| 1875 |
+
"grad_norm": 0.5726182137360729,
|
| 1876 |
+
"learning_rate": 1.8583366341785424e-05,
|
| 1877 |
+
"loss": 0.4135,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 1.7124600638977636,
|
| 1882 |
+
"grad_norm": 0.47501236190964014,
|
| 1883 |
+
"learning_rate": 1.8434537718632438e-05,
|
| 1884 |
+
"loss": 0.3966,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.718849840255591,
|
| 1889 |
+
"grad_norm": 0.5163914225737597,
|
| 1890 |
+
"learning_rate": 1.8285796267306098e-05,
|
| 1891 |
+
"loss": 0.3321,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.7252396166134185,
|
| 1896 |
+
"grad_norm": 0.5440727291416668,
|
| 1897 |
+
"learning_rate": 1.8137150270384755e-05,
|
| 1898 |
+
"loss": 0.4162,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.731629392971246,
|
| 1903 |
+
"grad_norm": 0.4932582814102065,
|
| 1904 |
+
"learning_rate": 1.7988608005131445e-05,
|
| 1905 |
+
"loss": 0.4086,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.7380191693290734,
|
| 1910 |
+
"grad_norm": 0.533011592071942,
|
| 1911 |
+
"learning_rate": 1.7840177743032964e-05,
|
| 1912 |
+
"loss": 0.414,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.744408945686901,
|
| 1917 |
+
"grad_norm": 0.49102076107513076,
|
| 1918 |
+
"learning_rate": 1.769186774933929e-05,
|
| 1919 |
+
"loss": 0.4176,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 1.7507987220447285,
|
| 1924 |
+
"grad_norm": 0.5771966331162738,
|
| 1925 |
+
"learning_rate": 1.7543686282603318e-05,
|
| 1926 |
+
"loss": 0.4432,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.7571884984025559,
|
| 1931 |
+
"grad_norm": 0.5461736300422602,
|
| 1932 |
+
"learning_rate": 1.7395641594220998e-05,
|
| 1933 |
+
"loss": 0.3829,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.7635782747603834,
|
| 1938 |
+
"grad_norm": 0.6577548367990437,
|
| 1939 |
+
"learning_rate": 1.724774192797186e-05,
|
| 1940 |
+
"loss": 0.382,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.769968051118211,
|
| 1945 |
+
"grad_norm": 0.43878563775490903,
|
| 1946 |
+
"learning_rate": 1.7099995519559963e-05,
|
| 1947 |
+
"loss": 0.3575,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 1.7763578274760383,
|
| 1952 |
+
"grad_norm": 0.5120401210743035,
|
| 1953 |
+
"learning_rate": 1.69524105961553e-05,
|
| 1954 |
+
"loss": 0.4286,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.7827476038338657,
|
| 1959 |
+
"grad_norm": 0.5653816201782214,
|
| 1960 |
+
"learning_rate": 1.6804995375935674e-05,
|
| 1961 |
+
"loss": 0.3742,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.7891373801916934,
|
| 1966 |
+
"grad_norm": 0.5726713802278968,
|
| 1967 |
+
"learning_rate": 1.665775806762903e-05,
|
| 1968 |
+
"loss": 0.3685,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.7955271565495208,
|
| 1973 |
+
"grad_norm": 0.5229354326981167,
|
| 1974 |
+
"learning_rate": 1.6510706870056455e-05,
|
| 1975 |
+
"loss": 0.408,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 1.8019169329073481,
|
| 1980 |
+
"grad_norm": 0.4954167189576208,
|
| 1981 |
+
"learning_rate": 1.6363849971675524e-05,
|
| 1982 |
+
"loss": 0.3659,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.8083067092651757,
|
| 1987 |
+
"grad_norm": 0.5076708644451216,
|
| 1988 |
+
"learning_rate": 1.6217195550124397e-05,
|
| 1989 |
+
"loss": 0.3686,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 1.8146964856230032,
|
| 1994 |
+
"grad_norm": 0.5824051094209408,
|
| 1995 |
+
"learning_rate": 1.6070751771766434e-05,
|
| 1996 |
+
"loss": 0.4467,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.8210862619808306,
|
| 2001 |
+
"grad_norm": 0.5285624925239529,
|
| 2002 |
+
"learning_rate": 1.592452679123545e-05,
|
| 2003 |
+
"loss": 0.3776,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 1.8274760383386581,
|
| 2008 |
+
"grad_norm": 0.5376124276180292,
|
| 2009 |
+
"learning_rate": 1.577852875098164e-05,
|
| 2010 |
+
"loss": 0.4504,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.8338658146964857,
|
| 2015 |
+
"grad_norm": 0.5373102243429786,
|
| 2016 |
+
"learning_rate": 1.563276578081816e-05,
|
| 2017 |
+
"loss": 0.3501,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.840255591054313,
|
| 2022 |
+
"grad_norm": 0.5462928026195687,
|
| 2023 |
+
"learning_rate": 1.5487245997468434e-05,
|
| 2024 |
+
"loss": 0.4209,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.8466453674121406,
|
| 2029 |
+
"grad_norm": 0.4909580614215068,
|
| 2030 |
+
"learning_rate": 1.5341977504114176e-05,
|
| 2031 |
+
"loss": 0.3647,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 1.8530351437699681,
|
| 2036 |
+
"grad_norm": 0.5421878755182835,
|
| 2037 |
+
"learning_rate": 1.5196968389944153e-05,
|
| 2038 |
+
"loss": 0.4069,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.8594249201277955,
|
| 2043 |
+
"grad_norm": 0.5053862903315562,
|
| 2044 |
+
"learning_rate": 1.5052226729703782e-05,
|
| 2045 |
+
"loss": 0.3763,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 1.865814696485623,
|
| 2050 |
+
"grad_norm": 0.43565640748900136,
|
| 2051 |
+
"learning_rate": 1.4907760583245451e-05,
|
| 2052 |
+
"loss": 0.367,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.8722044728434506,
|
| 2057 |
+
"grad_norm": 0.6034830380300681,
|
| 2058 |
+
"learning_rate": 1.4763577995079738e-05,
|
| 2059 |
+
"loss": 0.3964,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 1.878594249201278,
|
| 2064 |
+
"grad_norm": 0.5420427837665357,
|
| 2065 |
+
"learning_rate": 1.461968699392743e-05,
|
| 2066 |
+
"loss": 0.3378,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.8849840255591053,
|
| 2071 |
+
"grad_norm": 0.5951922897755679,
|
| 2072 |
+
"learning_rate": 1.4476095592272494e-05,
|
| 2073 |
+
"loss": 0.4326,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.891373801916933,
|
| 2078 |
+
"grad_norm": 0.4840728145584482,
|
| 2079 |
+
"learning_rate": 1.4332811785915852e-05,
|
| 2080 |
+
"loss": 0.369,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.8977635782747604,
|
| 2085 |
+
"grad_norm": 0.5037450720887865,
|
| 2086 |
+
"learning_rate": 1.418984355353019e-05,
|
| 2087 |
+
"loss": 0.3897,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 1.9041533546325877,
|
| 2092 |
+
"grad_norm": 0.6081578605737592,
|
| 2093 |
+
"learning_rate": 1.404719885621563e-05,
|
| 2094 |
+
"loss": 0.4251,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.9105431309904153,
|
| 2099 |
+
"grad_norm": 0.46944637013816987,
|
| 2100 |
+
"learning_rate": 1.390488563705644e-05,
|
| 2101 |
+
"loss": 0.3646,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 1.9169329073482428,
|
| 2106 |
+
"grad_norm": 0.5228222176493802,
|
| 2107 |
+
"learning_rate": 1.3762911820678739e-05,
|
| 2108 |
+
"loss": 0.4235,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.9233226837060702,
|
| 2113 |
+
"grad_norm": 0.5899737215877533,
|
| 2114 |
+
"learning_rate": 1.3621285312809193e-05,
|
| 2115 |
+
"loss": 0.3794,
|
| 2116 |
+
"step": 301
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.9297124600638977,
|
| 2120 |
+
"grad_norm": 0.5572929497186375,
|
| 2121 |
+
"learning_rate": 1.3480013999834811e-05,
|
| 2122 |
+
"loss": 0.4011,
|
| 2123 |
+
"step": 302
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.9361022364217253,
|
| 2127 |
+
"grad_norm": 0.5632588672503747,
|
| 2128 |
+
"learning_rate": 1.3339105748363776e-05,
|
| 2129 |
+
"loss": 0.3981,
|
| 2130 |
+
"step": 303
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.9424920127795526,
|
| 2134 |
+
"grad_norm": 0.5276160699091037,
|
| 2135 |
+
"learning_rate": 1.3198568404787418e-05,
|
| 2136 |
+
"loss": 0.3767,
|
| 2137 |
+
"step": 304
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.9488817891373802,
|
| 2141 |
+
"grad_norm": 0.6024773811499252,
|
| 2142 |
+
"learning_rate": 1.3058409794843288e-05,
|
| 2143 |
+
"loss": 0.4415,
|
| 2144 |
+
"step": 305
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.9552715654952078,
|
| 2148 |
+
"grad_norm": 0.5259393060101312,
|
| 2149 |
+
"learning_rate": 1.2918637723179371e-05,
|
| 2150 |
+
"loss": 0.3879,
|
| 2151 |
+
"step": 306
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.961661341853035,
|
| 2155 |
+
"grad_norm": 0.5317965049616244,
|
| 2156 |
+
"learning_rate": 1.2779259972919512e-05,
|
| 2157 |
+
"loss": 0.4269,
|
| 2158 |
+
"step": 307
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 1.9680511182108626,
|
| 2162 |
+
"grad_norm": 0.45743435082366124,
|
| 2163 |
+
"learning_rate": 1.2640284305229989e-05,
|
| 2164 |
+
"loss": 0.3205,
|
| 2165 |
+
"step": 308
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 1.9744408945686902,
|
| 2169 |
+
"grad_norm": 0.5754797561825906,
|
| 2170 |
+
"learning_rate": 1.2501718458887369e-05,
|
| 2171 |
+
"loss": 0.395,
|
| 2172 |
+
"step": 309
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 1.9808306709265175,
|
| 2176 |
+
"grad_norm": 0.5096694579354405,
|
| 2177 |
+
"learning_rate": 1.2363570149847556e-05,
|
| 2178 |
+
"loss": 0.3931,
|
| 2179 |
+
"step": 310
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 1.9872204472843449,
|
| 2183 |
+
"grad_norm": 0.5649164808169996,
|
| 2184 |
+
"learning_rate": 1.2225847070816148e-05,
|
| 2185 |
+
"loss": 0.3755,
|
| 2186 |
+
"step": 311
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 1.9936102236421727,
|
| 2190 |
+
"grad_norm": 0.4969808916941929,
|
| 2191 |
+
"learning_rate": 1.208855689082005e-05,
|
| 2192 |
+
"loss": 0.4243,
|
| 2193 |
+
"step": 312
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 2.0,
|
| 2197 |
+
"grad_norm": 0.7954635925002451,
|
| 2198 |
+
"learning_rate": 1.1951707254780465e-05,
|
| 2199 |
+
"loss": 0.4858,
|
| 2200 |
+
"step": 313
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 2.0063897763578273,
|
| 2204 |
+
"grad_norm": 0.6662795810886528,
|
| 2205 |
+
"learning_rate": 1.1815305783087153e-05,
|
| 2206 |
+
"loss": 0.2806,
|
| 2207 |
+
"step": 314
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 2.012779552715655,
|
| 2211 |
+
"grad_norm": 0.5137310238156836,
|
| 2212 |
+
"learning_rate": 1.1679360071174121e-05,
|
| 2213 |
+
"loss": 0.295,
|
| 2214 |
+
"step": 315
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 2.0191693290734825,
|
| 2218 |
+
"grad_norm": 0.815847533118561,
|
| 2219 |
+
"learning_rate": 1.1543877689096661e-05,
|
| 2220 |
+
"loss": 0.2896,
|
| 2221 |
+
"step": 316
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 2.02555910543131,
|
| 2225 |
+
"grad_norm": 0.5069824950228584,
|
| 2226 |
+
"learning_rate": 1.1408866181109824e-05,
|
| 2227 |
+
"loss": 0.2837,
|
| 2228 |
+
"step": 317
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 2.0319488817891376,
|
| 2232 |
+
"grad_norm": 0.5850695127338842,
|
| 2233 |
+
"learning_rate": 1.1274333065248327e-05,
|
| 2234 |
+
"loss": 0.2856,
|
| 2235 |
+
"step": 318
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 2.038338658146965,
|
| 2239 |
+
"grad_norm": 0.5779513618203883,
|
| 2240 |
+
"learning_rate": 1.1140285832907888e-05,
|
| 2241 |
+
"loss": 0.2885,
|
| 2242 |
+
"step": 319
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 2.0447284345047922,
|
| 2246 |
+
"grad_norm": 0.5351383370576208,
|
| 2247 |
+
"learning_rate": 1.1006731948428118e-05,
|
| 2248 |
+
"loss": 0.3018,
|
| 2249 |
+
"step": 320
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 2.0511182108626196,
|
| 2253 |
+
"grad_norm": 0.4884202390865607,
|
| 2254 |
+
"learning_rate": 1.0873678848676852e-05,
|
| 2255 |
+
"loss": 0.2815,
|
| 2256 |
+
"step": 321
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 2.0575079872204474,
|
| 2260 |
+
"grad_norm": 0.5191469140904564,
|
| 2261 |
+
"learning_rate": 1.074113394263598e-05,
|
| 2262 |
+
"loss": 0.2685,
|
| 2263 |
+
"step": 322
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 2.0638977635782747,
|
| 2267 |
+
"grad_norm": 0.541141996904648,
|
| 2268 |
+
"learning_rate": 1.0609104610988986e-05,
|
| 2269 |
+
"loss": 0.2809,
|
| 2270 |
+
"step": 323
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 2.070287539936102,
|
| 2274 |
+
"grad_norm": 0.5063236911612786,
|
| 2275 |
+
"learning_rate": 1.0477598205709882e-05,
|
| 2276 |
+
"loss": 0.2979,
|
| 2277 |
+
"step": 324
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 2.07667731629393,
|
| 2281 |
+
"grad_norm": 0.48822674540291033,
|
| 2282 |
+
"learning_rate": 1.0346622049653832e-05,
|
| 2283 |
+
"loss": 0.2493,
|
| 2284 |
+
"step": 325
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 2.083067092651757,
|
| 2288 |
+
"grad_norm": 0.5172260293987238,
|
| 2289 |
+
"learning_rate": 1.0216183436149412e-05,
|
| 2290 |
+
"loss": 0.3062,
|
| 2291 |
+
"step": 326
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 2.0894568690095845,
|
| 2295 |
+
"grad_norm": 0.5077833533693695,
|
| 2296 |
+
"learning_rate": 1.0086289628592429e-05,
|
| 2297 |
+
"loss": 0.2817,
|
| 2298 |
+
"step": 327
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 2.0958466453674123,
|
| 2302 |
+
"grad_norm": 0.47094358503601513,
|
| 2303 |
+
"learning_rate": 9.956947860041535e-06,
|
| 2304 |
+
"loss": 0.2633,
|
| 2305 |
+
"step": 328
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 2.1022364217252396,
|
| 2309 |
+
"grad_norm": 0.4678422611989536,
|
| 2310 |
+
"learning_rate": 9.82816533281541e-06,
|
| 2311 |
+
"loss": 0.2519,
|
| 2312 |
+
"step": 329
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 2.108626198083067,
|
| 2316 |
+
"grad_norm": 0.4961545238058503,
|
| 2317 |
+
"learning_rate": 9.699949218091698e-06,
|
| 2318 |
+
"loss": 0.2806,
|
| 2319 |
+
"step": 330
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 2.1150159744408947,
|
| 2323 |
+
"grad_norm": 0.45400755049188124,
|
| 2324 |
+
"learning_rate": 9.57230665550773e-06,
|
| 2325 |
+
"loss": 0.2845,
|
| 2326 |
+
"step": 331
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 2.121405750798722,
|
| 2330 |
+
"grad_norm": 0.4087039835019054,
|
| 2331 |
+
"learning_rate": 9.44524475276291e-06,
|
| 2332 |
+
"loss": 0.2712,
|
| 2333 |
+
"step": 332
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 2.1277955271565494,
|
| 2337 |
+
"grad_norm": 0.45141929812295156,
|
| 2338 |
+
"learning_rate": 9.318770585222959e-06,
|
| 2339 |
+
"loss": 0.2751,
|
| 2340 |
+
"step": 333
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 2.134185303514377,
|
| 2344 |
+
"grad_norm": 0.4285243933890445,
|
| 2345 |
+
"learning_rate": 9.19289119552592e-06,
|
| 2346 |
+
"loss": 0.2715,
|
| 2347 |
+
"step": 334
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 2.1405750798722045,
|
| 2351 |
+
"grad_norm": 0.4298003352353432,
|
| 2352 |
+
"learning_rate": 9.067613593189978e-06,
|
| 2353 |
+
"loss": 0.2806,
|
| 2354 |
+
"step": 335
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 2.146964856230032,
|
| 2358 |
+
"grad_norm": 0.45672324827943345,
|
| 2359 |
+
"learning_rate": 8.942944754223148e-06,
|
| 2360 |
+
"loss": 0.2973,
|
| 2361 |
+
"step": 336
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 2.1533546325878596,
|
| 2365 |
+
"grad_norm": 0.4370811146410844,
|
| 2366 |
+
"learning_rate": 8.818891620734843e-06,
|
| 2367 |
+
"loss": 0.3125,
|
| 2368 |
+
"step": 337
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 2.159744408945687,
|
| 2372 |
+
"grad_norm": 0.43681333400547245,
|
| 2373 |
+
"learning_rate": 8.695461100549257e-06,
|
| 2374 |
+
"loss": 0.2928,
|
| 2375 |
+
"step": 338
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 2.1661341853035143,
|
| 2379 |
+
"grad_norm": 0.4180585221813101,
|
| 2380 |
+
"learning_rate": 8.572660066820768e-06,
|
| 2381 |
+
"loss": 0.2434,
|
| 2382 |
+
"step": 339
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 2.1725239616613417,
|
| 2386 |
+
"grad_norm": 0.42261573045223133,
|
| 2387 |
+
"learning_rate": 8.450495357651147e-06,
|
| 2388 |
+
"loss": 0.2675,
|
| 2389 |
+
"step": 340
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 2.1789137380191694,
|
| 2393 |
+
"grad_norm": 0.4068510209903175,
|
| 2394 |
+
"learning_rate": 8.328973775708848e-06,
|
| 2395 |
+
"loss": 0.2813,
|
| 2396 |
+
"step": 341
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 2.1853035143769968,
|
| 2400 |
+
"grad_norm": 0.388040708146111,
|
| 2401 |
+
"learning_rate": 8.208102087850136e-06,
|
| 2402 |
+
"loss": 0.2878,
|
| 2403 |
+
"step": 342
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 2.191693290734824,
|
| 2407 |
+
"grad_norm": 0.43053220862581665,
|
| 2408 |
+
"learning_rate": 8.087887024742343e-06,
|
| 2409 |
+
"loss": 0.2825,
|
| 2410 |
+
"step": 343
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 2.198083067092652,
|
| 2414 |
+
"grad_norm": 0.41793950177347855,
|
| 2415 |
+
"learning_rate": 7.968335280489037e-06,
|
| 2416 |
+
"loss": 0.2986,
|
| 2417 |
+
"step": 344
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 2.2044728434504792,
|
| 2421 |
+
"grad_norm": 0.40031758724937355,
|
| 2422 |
+
"learning_rate": 7.849453512257264e-06,
|
| 2423 |
+
"loss": 0.3,
|
| 2424 |
+
"step": 345
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 2.2108626198083066,
|
| 2428 |
+
"grad_norm": 0.38059364454447125,
|
| 2429 |
+
"learning_rate": 7.731248339906879e-06,
|
| 2430 |
+
"loss": 0.2727,
|
| 2431 |
+
"step": 346
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 2.2172523961661343,
|
| 2435 |
+
"grad_norm": 0.41990913510389755,
|
| 2436 |
+
"learning_rate": 7.613726345621873e-06,
|
| 2437 |
+
"loss": 0.3046,
|
| 2438 |
+
"step": 347
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 2.2236421725239617,
|
| 2442 |
+
"grad_norm": 0.43424406475522437,
|
| 2443 |
+
"learning_rate": 7.496894073543899e-06,
|
| 2444 |
+
"loss": 0.2936,
|
| 2445 |
+
"step": 348
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 2.230031948881789,
|
| 2449 |
+
"grad_norm": 0.3750088497925214,
|
| 2450 |
+
"learning_rate": 7.380758029407857e-06,
|
| 2451 |
+
"loss": 0.2664,
|
| 2452 |
+
"step": 349
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 2.236421725239617,
|
| 2456 |
+
"grad_norm": 0.418532871938177,
|
| 2457 |
+
"learning_rate": 7.2653246801795594e-06,
|
| 2458 |
+
"loss": 0.2891,
|
| 2459 |
+
"step": 350
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 2.242811501597444,
|
| 2463 |
+
"grad_norm": 0.4028035425262737,
|
| 2464 |
+
"learning_rate": 7.150600453695726e-06,
|
| 2465 |
+
"loss": 0.2734,
|
| 2466 |
+
"step": 351
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 2.2492012779552715,
|
| 2470 |
+
"grad_norm": 0.4466135219208513,
|
| 2471 |
+
"learning_rate": 7.036591738305989e-06,
|
| 2472 |
+
"loss": 0.2815,
|
| 2473 |
+
"step": 352
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 2.255591054313099,
|
| 2477 |
+
"grad_norm": 0.3867166130148223,
|
| 2478 |
+
"learning_rate": 6.923304882517159e-06,
|
| 2479 |
+
"loss": 0.296,
|
| 2480 |
+
"step": 353
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 2.2619808306709266,
|
| 2484 |
+
"grad_norm": 0.3917494183899583,
|
| 2485 |
+
"learning_rate": 6.81074619463975e-06,
|
| 2486 |
+
"loss": 0.2325,
|
| 2487 |
+
"step": 354
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 2.268370607028754,
|
| 2491 |
+
"grad_norm": 0.4190504448138774,
|
| 2492 |
+
"learning_rate": 6.698921942436665e-06,
|
| 2493 |
+
"loss": 0.2535,
|
| 2494 |
+
"step": 355
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 2.2747603833865817,
|
| 2498 |
+
"grad_norm": 0.41331962647091514,
|
| 2499 |
+
"learning_rate": 6.587838352774209e-06,
|
| 2500 |
+
"loss": 0.2587,
|
| 2501 |
+
"step": 356
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 2.281150159744409,
|
| 2505 |
+
"grad_norm": 0.41804090107839076,
|
| 2506 |
+
"learning_rate": 6.477501611275345e-06,
|
| 2507 |
+
"loss": 0.2758,
|
| 2508 |
+
"step": 357
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 2.2875399361022364,
|
| 2512 |
+
"grad_norm": 0.39910602146901847,
|
| 2513 |
+
"learning_rate": 6.367917861975224e-06,
|
| 2514 |
+
"loss": 0.2607,
|
| 2515 |
+
"step": 358
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 2.2939297124600637,
|
| 2519 |
+
"grad_norm": 0.36374725362936167,
|
| 2520 |
+
"learning_rate": 6.2590932069790965e-06,
|
| 2521 |
+
"loss": 0.2896,
|
| 2522 |
+
"step": 359
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 2.3003194888178915,
|
| 2526 |
+
"grad_norm": 0.3931796715710283,
|
| 2527 |
+
"learning_rate": 6.151033706122489e-06,
|
| 2528 |
+
"loss": 0.2562,
|
| 2529 |
+
"step": 360
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 2.306709265175719,
|
| 2533 |
+
"grad_norm": 0.39607678195113055,
|
| 2534 |
+
"learning_rate": 6.043745376633792e-06,
|
| 2535 |
+
"loss": 0.2575,
|
| 2536 |
+
"step": 361
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 2.313099041533546,
|
| 2540 |
+
"grad_norm": 0.370701894040692,
|
| 2541 |
+
"learning_rate": 5.937234192799184e-06,
|
| 2542 |
+
"loss": 0.2476,
|
| 2543 |
+
"step": 362
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 2.319488817891374,
|
| 2547 |
+
"grad_norm": 0.3922675962076736,
|
| 2548 |
+
"learning_rate": 5.831506085629937e-06,
|
| 2549 |
+
"loss": 0.2758,
|
| 2550 |
+
"step": 363
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 2.3258785942492013,
|
| 2554 |
+
"grad_norm": 0.39508969009396355,
|
| 2555 |
+
"learning_rate": 5.7265669425321765e-06,
|
| 2556 |
+
"loss": 0.2572,
|
| 2557 |
+
"step": 364
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 2.3322683706070286,
|
| 2561 |
+
"grad_norm": 0.4127067246019672,
|
| 2562 |
+
"learning_rate": 5.622422606979055e-06,
|
| 2563 |
+
"loss": 0.2507,
|
| 2564 |
+
"step": 365
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 2.3386581469648564,
|
| 2568 |
+
"grad_norm": 0.40000330806363765,
|
| 2569 |
+
"learning_rate": 5.519078878185311e-06,
|
| 2570 |
+
"loss": 0.2973,
|
| 2571 |
+
"step": 366
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 2.3450479233226837,
|
| 2575 |
+
"grad_norm": 0.3982421880351729,
|
| 2576 |
+
"learning_rate": 5.416541510784414e-06,
|
| 2577 |
+
"loss": 0.2778,
|
| 2578 |
+
"step": 367
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 2.351437699680511,
|
| 2582 |
+
"grad_norm": 0.37370414007694336,
|
| 2583 |
+
"learning_rate": 5.314816214508054e-06,
|
| 2584 |
+
"loss": 0.2815,
|
| 2585 |
+
"step": 368
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 2.357827476038339,
|
| 2589 |
+
"grad_norm": 0.4150724253275529,
|
| 2590 |
+
"learning_rate": 5.21390865386824e-06,
|
| 2591 |
+
"loss": 0.2968,
|
| 2592 |
+
"step": 369
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 2.364217252396166,
|
| 2596 |
+
"grad_norm": 0.3761463056883756,
|
| 2597 |
+
"learning_rate": 5.113824447841873e-06,
|
| 2598 |
+
"loss": 0.2363,
|
| 2599 |
+
"step": 370
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 2.3706070287539935,
|
| 2603 |
+
"grad_norm": 0.35871951677398056,
|
| 2604 |
+
"learning_rate": 5.014569169557826e-06,
|
| 2605 |
+
"loss": 0.2612,
|
| 2606 |
+
"step": 371
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 2.376996805111821,
|
| 2610 |
+
"grad_norm": 0.3892389571463014,
|
| 2611 |
+
"learning_rate": 4.916148345986649e-06,
|
| 2612 |
+
"loss": 0.2759,
|
| 2613 |
+
"step": 372
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 2.3833865814696487,
|
| 2617 |
+
"grad_norm": 0.37772421711614007,
|
| 2618 |
+
"learning_rate": 4.8185674576327615e-06,
|
| 2619 |
+
"loss": 0.2608,
|
| 2620 |
+
"step": 373
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 2.389776357827476,
|
| 2624 |
+
"grad_norm": 0.382653409586813,
|
| 2625 |
+
"learning_rate": 4.721831938229315e-06,
|
| 2626 |
+
"loss": 0.3155,
|
| 2627 |
+
"step": 374
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 2.3961661341853033,
|
| 2631 |
+
"grad_norm": 0.39130961949763166,
|
| 2632 |
+
"learning_rate": 4.625947174435596e-06,
|
| 2633 |
+
"loss": 0.292,
|
| 2634 |
+
"step": 375
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 2.402555910543131,
|
| 2638 |
+
"grad_norm": 0.3689264594938094,
|
| 2639 |
+
"learning_rate": 4.530918505537061e-06,
|
| 2640 |
+
"loss": 0.2778,
|
| 2641 |
+
"step": 376
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 2.4089456869009584,
|
| 2645 |
+
"grad_norm": 0.3583777664156191,
|
| 2646 |
+
"learning_rate": 4.436751223148055e-06,
|
| 2647 |
+
"loss": 0.2793,
|
| 2648 |
+
"step": 377
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 2.415335463258786,
|
| 2652 |
+
"grad_norm": 0.3792734486077673,
|
| 2653 |
+
"learning_rate": 4.343450570917118e-06,
|
| 2654 |
+
"loss": 0.2987,
|
| 2655 |
+
"step": 378
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 2.4217252396166136,
|
| 2659 |
+
"grad_norm": 0.3559642646144205,
|
| 2660 |
+
"learning_rate": 4.251021744235013e-06,
|
| 2661 |
+
"loss": 0.2782,
|
| 2662 |
+
"step": 379
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 2.428115015974441,
|
| 2666 |
+
"grad_norm": 0.4010256232612567,
|
| 2667 |
+
"learning_rate": 4.159469889945434e-06,
|
| 2668 |
+
"loss": 0.2529,
|
| 2669 |
+
"step": 380
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 2.4345047923322682,
|
| 2673 |
+
"grad_norm": 0.3765358138333099,
|
| 2674 |
+
"learning_rate": 4.068800106058375e-06,
|
| 2675 |
+
"loss": 0.279,
|
| 2676 |
+
"step": 381
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 2.440894568690096,
|
| 2680 |
+
"grad_norm": 0.3685887074154549,
|
| 2681 |
+
"learning_rate": 3.9790174414662844e-06,
|
| 2682 |
+
"loss": 0.2705,
|
| 2683 |
+
"step": 382
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 2.4472843450479234,
|
| 2687 |
+
"grad_norm": 0.3728894980841834,
|
| 2688 |
+
"learning_rate": 3.890126895662904e-06,
|
| 2689 |
+
"loss": 0.2583,
|
| 2690 |
+
"step": 383
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 2.4536741214057507,
|
| 2694 |
+
"grad_norm": 0.36277573516201544,
|
| 2695 |
+
"learning_rate": 3.8021334184648685e-06,
|
| 2696 |
+
"loss": 0.2807,
|
| 2697 |
+
"step": 384
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 2.460063897763578,
|
| 2701 |
+
"grad_norm": 0.35706119183313567,
|
| 2702 |
+
"learning_rate": 3.7150419097360944e-06,
|
| 2703 |
+
"loss": 0.2898,
|
| 2704 |
+
"step": 385
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 2.466453674121406,
|
| 2708 |
+
"grad_norm": 0.38011267281397304,
|
| 2709 |
+
"learning_rate": 3.628857219114916e-06,
|
| 2710 |
+
"loss": 0.2553,
|
| 2711 |
+
"step": 386
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 2.472843450479233,
|
| 2715 |
+
"grad_norm": 0.3863113162029853,
|
| 2716 |
+
"learning_rate": 3.543584145744057e-06,
|
| 2717 |
+
"loss": 0.2534,
|
| 2718 |
+
"step": 387
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 2.479233226837061,
|
| 2722 |
+
"grad_norm": 0.439587610934195,
|
| 2723 |
+
"learning_rate": 3.459227438003383e-06,
|
| 2724 |
+
"loss": 0.2975,
|
| 2725 |
+
"step": 388
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 2.4856230031948883,
|
| 2729 |
+
"grad_norm": 0.3793664447722741,
|
| 2730 |
+
"learning_rate": 3.3757917932454732e-06,
|
| 2731 |
+
"loss": 0.2902,
|
| 2732 |
+
"step": 389
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 2.4920127795527156,
|
| 2736 |
+
"grad_norm": 0.406296707834338,
|
| 2737 |
+
"learning_rate": 3.293281857534094e-06,
|
| 2738 |
+
"loss": 0.2969,
|
| 2739 |
+
"step": 390
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 2.498402555910543,
|
| 2743 |
+
"grad_norm": 0.37691162956880797,
|
| 2744 |
+
"learning_rate": 3.2117022253854356e-06,
|
| 2745 |
+
"loss": 0.2889,
|
| 2746 |
+
"step": 391
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 2.5047923322683707,
|
| 2750 |
+
"grad_norm": 0.35367935501619513,
|
| 2751 |
+
"learning_rate": 3.1310574395122994e-06,
|
| 2752 |
+
"loss": 0.2516,
|
| 2753 |
+
"step": 392
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 2.511182108626198,
|
| 2757 |
+
"grad_norm": 0.3525236924672651,
|
| 2758 |
+
"learning_rate": 3.0513519905711474e-06,
|
| 2759 |
+
"loss": 0.2781,
|
| 2760 |
+
"step": 393
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 2.5175718849840254,
|
| 2764 |
+
"grad_norm": 0.3564008946825266,
|
| 2765 |
+
"learning_rate": 2.9725903169120073e-06,
|
| 2766 |
+
"loss": 0.2698,
|
| 2767 |
+
"step": 394
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 2.523961661341853,
|
| 2771 |
+
"grad_norm": 0.3718042292779991,
|
| 2772 |
+
"learning_rate": 2.894776804331372e-06,
|
| 2773 |
+
"loss": 0.2557,
|
| 2774 |
+
"step": 395
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 2.5303514376996805,
|
| 2778 |
+
"grad_norm": 0.3716672854028638,
|
| 2779 |
+
"learning_rate": 2.817915785827927e-06,
|
| 2780 |
+
"loss": 0.2579,
|
| 2781 |
+
"step": 396
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 2.536741214057508,
|
| 2785 |
+
"grad_norm": 0.353812866963394,
|
| 2786 |
+
"learning_rate": 2.742011541361318e-06,
|
| 2787 |
+
"loss": 0.2715,
|
| 2788 |
+
"step": 397
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 2.543130990415335,
|
| 2792 |
+
"grad_norm": 0.3844045853121929,
|
| 2793 |
+
"learning_rate": 2.6670682976137994e-06,
|
| 2794 |
+
"loss": 0.3141,
|
| 2795 |
+
"step": 398
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 2.549520766773163,
|
| 2799 |
+
"grad_norm": 0.37146608361893524,
|
| 2800 |
+
"learning_rate": 2.5930902277548686e-06,
|
| 2801 |
+
"loss": 0.2504,
|
| 2802 |
+
"step": 399
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 2.5559105431309903,
|
| 2806 |
+
"grad_norm": 0.35978150748451004,
|
| 2807 |
+
"learning_rate": 2.5200814512089088e-06,
|
| 2808 |
+
"loss": 0.2868,
|
| 2809 |
+
"step": 400
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 2.562300319488818,
|
| 2813 |
+
"grad_norm": 0.3498821367555298,
|
| 2814 |
+
"learning_rate": 2.4480460334257727e-06,
|
| 2815 |
+
"loss": 0.2778,
|
| 2816 |
+
"step": 401
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 2.5686900958466454,
|
| 2820 |
+
"grad_norm": 0.3590299815828268,
|
| 2821 |
+
"learning_rate": 2.376987985654422e-06,
|
| 2822 |
+
"loss": 0.2466,
|
| 2823 |
+
"step": 402
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 2.5750798722044728,
|
| 2827 |
+
"grad_norm": 0.3560328836577989,
|
| 2828 |
+
"learning_rate": 2.3069112647195647e-06,
|
| 2829 |
+
"loss": 0.229,
|
| 2830 |
+
"step": 403
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 2.5814696485623,
|
| 2834 |
+
"grad_norm": 0.37314736778508073,
|
| 2835 |
+
"learning_rate": 2.2378197728012975e-06,
|
| 2836 |
+
"loss": 0.2704,
|
| 2837 |
+
"step": 404
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 2.587859424920128,
|
| 2841 |
+
"grad_norm": 0.3763392516149028,
|
| 2842 |
+
"learning_rate": 2.169717357217844e-06,
|
| 2843 |
+
"loss": 0.259,
|
| 2844 |
+
"step": 405
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 2.594249201277955,
|
| 2848 |
+
"grad_norm": 0.3399458492987759,
|
| 2849 |
+
"learning_rate": 2.1026078102113014e-06,
|
| 2850 |
+
"loss": 0.2684,
|
| 2851 |
+
"step": 406
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 2.600638977635783,
|
| 2855 |
+
"grad_norm": 0.3578314862739145,
|
| 2856 |
+
"learning_rate": 2.0364948687364692e-06,
|
| 2857 |
+
"loss": 0.2664,
|
| 2858 |
+
"step": 407
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 2.6070287539936103,
|
| 2862 |
+
"grad_norm": 0.39093714164893223,
|
| 2863 |
+
"learning_rate": 1.971382214252784e-06,
|
| 2864 |
+
"loss": 0.3064,
|
| 2865 |
+
"step": 408
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 2.6134185303514377,
|
| 2869 |
+
"grad_norm": 0.35226742624856194,
|
| 2870 |
+
"learning_rate": 1.9072734725192844e-06,
|
| 2871 |
+
"loss": 0.3043,
|
| 2872 |
+
"step": 409
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 2.619808306709265,
|
| 2876 |
+
"grad_norm": 0.34363517197221133,
|
| 2877 |
+
"learning_rate": 1.844172213392743e-06,
|
| 2878 |
+
"loss": 0.2771,
|
| 2879 |
+
"step": 410
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 2.626198083067093,
|
| 2883 |
+
"grad_norm": 0.35717003311156614,
|
| 2884 |
+
"learning_rate": 1.7820819506288688e-06,
|
| 2885 |
+
"loss": 0.2916,
|
| 2886 |
+
"step": 411
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 2.63258785942492,
|
| 2890 |
+
"grad_norm": 0.3397444551813988,
|
| 2891 |
+
"learning_rate": 1.7210061416866297e-06,
|
| 2892 |
+
"loss": 0.2802,
|
| 2893 |
+
"step": 412
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 2.6389776357827475,
|
| 2897 |
+
"grad_norm": 0.3374288264378377,
|
| 2898 |
+
"learning_rate": 1.660948187535767e-06,
|
| 2899 |
+
"loss": 0.2996,
|
| 2900 |
+
"step": 413
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 2.6453674121405752,
|
| 2904 |
+
"grad_norm": 0.348235164857282,
|
| 2905 |
+
"learning_rate": 1.6019114324673647e-06,
|
| 2906 |
+
"loss": 0.2643,
|
| 2907 |
+
"step": 414
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 2.6517571884984026,
|
| 2911 |
+
"grad_norm": 0.3728291742720239,
|
| 2912 |
+
"learning_rate": 1.543899163907665e-06,
|
| 2913 |
+
"loss": 0.2875,
|
| 2914 |
+
"step": 415
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 2.65814696485623,
|
| 2918 |
+
"grad_norm": 0.33982563684444306,
|
| 2919 |
+
"learning_rate": 1.4869146122349932e-06,
|
| 2920 |
+
"loss": 0.2545,
|
| 2921 |
+
"step": 416
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 2.6645367412140573,
|
| 2925 |
+
"grad_norm": 0.34046077697953536,
|
| 2926 |
+
"learning_rate": 1.4309609505998689e-06,
|
| 2927 |
+
"loss": 0.2647,
|
| 2928 |
+
"step": 417
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 2.670926517571885,
|
| 2932 |
+
"grad_norm": 0.3459458344871144,
|
| 2933 |
+
"learning_rate": 1.3760412947483292e-06,
|
| 2934 |
+
"loss": 0.2972,
|
| 2935 |
+
"step": 418
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 2.6773162939297124,
|
| 2939 |
+
"grad_norm": 0.36579406936806147,
|
| 2940 |
+
"learning_rate": 1.322158702848415e-06,
|
| 2941 |
+
"loss": 0.2695,
|
| 2942 |
+
"step": 419
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 2.68370607028754,
|
| 2946 |
+
"grad_norm": 0.3707374256323378,
|
| 2947 |
+
"learning_rate": 1.269316175319879e-06,
|
| 2948 |
+
"loss": 0.2719,
|
| 2949 |
+
"step": 420
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 2.6900958466453675,
|
| 2953 |
+
"grad_norm": 0.3709423910066585,
|
| 2954 |
+
"learning_rate": 1.217516654667128e-06,
|
| 2955 |
+
"loss": 0.298,
|
| 2956 |
+
"step": 421
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 2.696485623003195,
|
| 2960 |
+
"grad_norm": 0.37469291952689926,
|
| 2961 |
+
"learning_rate": 1.1667630253153428e-06,
|
| 2962 |
+
"loss": 0.2612,
|
| 2963 |
+
"step": 422
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 2.702875399361022,
|
| 2967 |
+
"grad_norm": 0.347832218730705,
|
| 2968 |
+
"learning_rate": 1.1170581134498849e-06,
|
| 2969 |
+
"loss": 0.2918,
|
| 2970 |
+
"step": 423
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 2.70926517571885,
|
| 2974 |
+
"grad_norm": 0.36883525953686164,
|
| 2975 |
+
"learning_rate": 1.0684046868589103e-06,
|
| 2976 |
+
"loss": 0.2719,
|
| 2977 |
+
"step": 424
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 2.7156549520766773,
|
| 2981 |
+
"grad_norm": 0.34462150376832146,
|
| 2982 |
+
"learning_rate": 1.0208054547792478e-06,
|
| 2983 |
+
"loss": 0.2524,
|
| 2984 |
+
"step": 425
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 2.722044728434505,
|
| 2988 |
+
"grad_norm": 0.33935916043461156,
|
| 2989 |
+
"learning_rate": 9.742630677455422e-07,
|
| 2990 |
+
"loss": 0.2525,
|
| 2991 |
+
"step": 426
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 2.7284345047923324,
|
| 2995 |
+
"grad_norm": 0.35482552002227297,
|
| 2996 |
+
"learning_rate": 9.287801174426491e-07,
|
| 2997 |
+
"loss": 0.2701,
|
| 2998 |
+
"step": 427
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 2.7348242811501597,
|
| 3002 |
+
"grad_norm": 0.341771079482618,
|
| 3003 |
+
"learning_rate": 8.843591365613324e-07,
|
| 3004 |
+
"loss": 0.2759,
|
| 3005 |
+
"step": 428
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 2.741214057507987,
|
| 3009 |
+
"grad_norm": 0.3437210997091319,
|
| 3010 |
+
"learning_rate": 8.410025986572279e-07,
|
| 3011 |
+
"loss": 0.2507,
|
| 3012 |
+
"step": 429
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 2.747603833865815,
|
| 3016 |
+
"grad_norm": 0.35387497003554297,
|
| 3017 |
+
"learning_rate": 7.987129180130981e-07,
|
| 3018 |
+
"loss": 0.2934,
|
| 3019 |
+
"step": 430
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 2.753993610223642,
|
| 3023 |
+
"grad_norm": 0.3433319826548646,
|
| 3024 |
+
"learning_rate": 7.574924495044067e-07,
|
| 3025 |
+
"loss": 0.2816,
|
| 3026 |
+
"step": 431
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 2.7603833865814695,
|
| 3030 |
+
"grad_norm": 0.3445699585899121,
|
| 3031 |
+
"learning_rate": 7.17343488468174e-07,
|
| 3032 |
+
"loss": 0.2938,
|
| 3033 |
+
"step": 432
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 2.7667731629392973,
|
| 3037 |
+
"grad_norm": 0.36179132098384625,
|
| 3038 |
+
"learning_rate": 6.782682705751775e-07,
|
| 3039 |
+
"loss": 0.259,
|
| 3040 |
+
"step": 433
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 2.7731629392971247,
|
| 3044 |
+
"grad_norm": 0.35409736012157567,
|
| 3045 |
+
"learning_rate": 6.402689717054467e-07,
|
| 3046 |
+
"loss": 0.2694,
|
| 3047 |
+
"step": 434
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 2.779552715654952,
|
| 3051 |
+
"grad_norm": 0.3347120611379767,
|
| 3052 |
+
"learning_rate": 6.033477078271132e-07,
|
| 3053 |
+
"loss": 0.2791,
|
| 3054 |
+
"step": 435
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 2.7859424920127793,
|
| 3058 |
+
"grad_norm": 0.34362095896036443,
|
| 3059 |
+
"learning_rate": 5.675065348785724e-07,
|
| 3060 |
+
"loss": 0.3029,
|
| 3061 |
+
"step": 436
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 2.792332268370607,
|
| 3065 |
+
"grad_norm": 0.3623549484091769,
|
| 3066 |
+
"learning_rate": 5.327474486540097e-07,
|
| 3067 |
+
"loss": 0.2857,
|
| 3068 |
+
"step": 437
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 2.7987220447284344,
|
| 3072 |
+
"grad_norm": 0.3849385006693377,
|
| 3073 |
+
"learning_rate": 4.990723846922563e-07,
|
| 3074 |
+
"loss": 0.2437,
|
| 3075 |
+
"step": 438
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 2.8051118210862622,
|
| 3079 |
+
"grad_norm": 0.3456451470480186,
|
| 3080 |
+
"learning_rate": 4.664832181690204e-07,
|
| 3081 |
+
"loss": 0.2464,
|
| 3082 |
+
"step": 439
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 2.8115015974440896,
|
| 3086 |
+
"grad_norm": 0.3623322322297761,
|
| 3087 |
+
"learning_rate": 4.3498176379245696e-07,
|
| 3088 |
+
"loss": 0.266,
|
| 3089 |
+
"step": 440
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 2.817891373801917,
|
| 3093 |
+
"grad_norm": 0.33249253792620725,
|
| 3094 |
+
"learning_rate": 4.045697757021327e-07,
|
| 3095 |
+
"loss": 0.2745,
|
| 3096 |
+
"step": 441
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 2.8242811501597442,
|
| 3100 |
+
"grad_norm": 0.35011482248093373,
|
| 3101 |
+
"learning_rate": 3.7524894737133164e-07,
|
| 3102 |
+
"loss": 0.2849,
|
| 3103 |
+
"step": 442
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 2.830670926517572,
|
| 3107 |
+
"grad_norm": 0.35867683687456126,
|
| 3108 |
+
"learning_rate": 3.4702091151276094e-07,
|
| 3109 |
+
"loss": 0.309,
|
| 3110 |
+
"step": 443
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 2.8370607028753994,
|
| 3114 |
+
"grad_norm": 0.35152581911491154,
|
| 3115 |
+
"learning_rate": 3.1988723998764405e-07,
|
| 3116 |
+
"loss": 0.2618,
|
| 3117 |
+
"step": 444
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 2.8434504792332267,
|
| 3121 |
+
"grad_norm": 0.3729635038125147,
|
| 3122 |
+
"learning_rate": 2.938494437181727e-07,
|
| 3123 |
+
"loss": 0.2999,
|
| 3124 |
+
"step": 445
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 2.8498402555910545,
|
| 3128 |
+
"grad_norm": 0.33552722155677045,
|
| 3129 |
+
"learning_rate": 2.689089726033922e-07,
|
| 3130 |
+
"loss": 0.2825,
|
| 3131 |
+
"step": 446
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 2.856230031948882,
|
| 3135 |
+
"grad_norm": 0.3924095079184395,
|
| 3136 |
+
"learning_rate": 2.450672154384548e-07,
|
| 3137 |
+
"loss": 0.2687,
|
| 3138 |
+
"step": 447
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 2.862619808306709,
|
| 3142 |
+
"grad_norm": 0.5138097567383261,
|
| 3143 |
+
"learning_rate": 2.2232549983728146e-07,
|
| 3144 |
+
"loss": 0.3004,
|
| 3145 |
+
"step": 448
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 2.8690095846645365,
|
| 3149 |
+
"grad_norm": 0.3283039402589176,
|
| 3150 |
+
"learning_rate": 2.006850921586434e-07,
|
| 3151 |
+
"loss": 0.294,
|
| 3152 |
+
"step": 449
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 2.8753993610223643,
|
| 3156 |
+
"grad_norm": 0.37738305697605573,
|
| 3157 |
+
"learning_rate": 1.801471974356428e-07,
|
| 3158 |
+
"loss": 0.2692,
|
| 3159 |
+
"step": 450
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 2.8817891373801916,
|
| 3163 |
+
"grad_norm": 0.3418654851564619,
|
| 3164 |
+
"learning_rate": 1.607129593086043e-07,
|
| 3165 |
+
"loss": 0.3001,
|
| 3166 |
+
"step": 451
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 2.8881789137380194,
|
| 3170 |
+
"grad_norm": 0.3402266094342756,
|
| 3171 |
+
"learning_rate": 1.4238345996140824e-07,
|
| 3172 |
+
"loss": 0.2911,
|
| 3173 |
+
"step": 452
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 2.8945686900958467,
|
| 3177 |
+
"grad_norm": 0.31824348901824345,
|
| 3178 |
+
"learning_rate": 1.251597200612098e-07,
|
| 3179 |
+
"loss": 0.279,
|
| 3180 |
+
"step": 453
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 2.900958466453674,
|
| 3184 |
+
"grad_norm": 0.34531177153096265,
|
| 3185 |
+
"learning_rate": 1.0904269870161799e-07,
|
| 3186 |
+
"loss": 0.3028,
|
| 3187 |
+
"step": 454
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 2.9073482428115014,
|
| 3191 |
+
"grad_norm": 0.3568279096820218,
|
| 3192 |
+
"learning_rate": 9.40332933492849e-08,
|
| 3193 |
+
"loss": 0.2927,
|
| 3194 |
+
"step": 455
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 2.913738019169329,
|
| 3198 |
+
"grad_norm": 0.34527750344815883,
|
| 3199 |
+
"learning_rate": 8.013233979393242e-08,
|
| 3200 |
+
"loss": 0.2933,
|
| 3201 |
+
"step": 456
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 2.9201277955271565,
|
| 3205 |
+
"grad_norm": 0.3493059274199788,
|
| 3206 |
+
"learning_rate": 6.734061210180499e-08,
|
| 3207 |
+
"loss": 0.252,
|
| 3208 |
+
"step": 457
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 2.9265175718849843,
|
| 3212 |
+
"grad_norm": 0.370444099756165,
|
| 3213 |
+
"learning_rate": 5.565882257257515e-08,
|
| 3214 |
+
"loss": 0.2883,
|
| 3215 |
+
"step": 458
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 2.9329073482428116,
|
| 3219 |
+
"grad_norm": 0.3400590434922779,
|
| 3220 |
+
"learning_rate": 4.508762169967318e-08,
|
| 3221 |
+
"loss": 0.2418,
|
| 3222 |
+
"step": 459
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 2.939297124600639,
|
| 3226 |
+
"grad_norm": 0.3380417666194957,
|
| 3227 |
+
"learning_rate": 3.562759813407146e-08,
|
| 3228 |
+
"loss": 0.2928,
|
| 3229 |
+
"step": 460
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 2.9456869009584663,
|
| 3233 |
+
"grad_norm": 0.34811024230473875,
|
| 3234 |
+
"learning_rate": 2.7279278651497487e-08,
|
| 3235 |
+
"loss": 0.3067,
|
| 3236 |
+
"step": 461
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 2.952076677316294,
|
| 3240 |
+
"grad_norm": 0.37158100906796243,
|
| 3241 |
+
"learning_rate": 2.0043128123108378e-08,
|
| 3242 |
+
"loss": 0.2683,
|
| 3243 |
+
"step": 462
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 2.9584664536741214,
|
| 3247 |
+
"grad_norm": 0.3508788377065571,
|
| 3248 |
+
"learning_rate": 1.3919549489593841e-08,
|
| 3249 |
+
"loss": 0.2738,
|
| 3250 |
+
"step": 463
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 2.9648562300319488,
|
| 3254 |
+
"grad_norm": 0.34321071515720997,
|
| 3255 |
+
"learning_rate": 8.908883738754093e-09,
|
| 3256 |
+
"loss": 0.2583,
|
| 3257 |
+
"step": 464
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 2.9712460063897765,
|
| 3261 |
+
"grad_norm": 0.34013241840819486,
|
| 3262 |
+
"learning_rate": 5.011409886503949e-09,
|
| 3263 |
+
"loss": 0.2974,
|
| 3264 |
+
"step": 465
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 2.977635782747604,
|
| 3268 |
+
"grad_norm": 0.3266932550661067,
|
| 3269 |
+
"learning_rate": 2.2273449613274822e-09,
|
| 3270 |
+
"loss": 0.264,
|
| 3271 |
+
"step": 466
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 2.984025559105431,
|
| 3275 |
+
"grad_norm": 0.33590879102094134,
|
| 3276 |
+
"learning_rate": 5.568439922121194e-10,
|
| 3277 |
+
"loss": 0.2854,
|
| 3278 |
+
"step": 467
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 2.9904153354632586,
|
| 3282 |
+
"grad_norm": 0.36927881731237316,
|
| 3283 |
+
"learning_rate": 0.0,
|
| 3284 |
+
"loss": 0.2865,
|
| 3285 |
+
"step": 468
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 2.9904153354632586,
|
| 3289 |
+
"step": 468,
|
| 3290 |
+
"total_flos": 3.310734730054861e+17,
|
| 3291 |
+
"train_loss": 0.41292818673910237,
|
| 3292 |
+
"train_runtime": 10004.6891,
|
| 3293 |
+
"train_samples_per_second": 2.998,
|
| 3294 |
+
"train_steps_per_second": 0.047
|
| 3295 |
+
}
|
| 3296 |
+
],
|
| 3297 |
+
"logging_steps": 1.0,
|
| 3298 |
+
"max_steps": 468,
|
| 3299 |
+
"num_input_tokens_seen": 0,
|
| 3300 |
+
"num_train_epochs": 3,
|
| 3301 |
+
"save_steps": 500,
|
| 3302 |
+
"stateful_callbacks": {
|
| 3303 |
+
"TrainerControl": {
|
| 3304 |
+
"args": {
|
| 3305 |
+
"should_epoch_stop": false,
|
| 3306 |
+
"should_evaluate": false,
|
| 3307 |
+
"should_log": false,
|
| 3308 |
+
"should_save": true,
|
| 3309 |
+
"should_training_stop": true
|
| 3310 |
+
},
|
| 3311 |
+
"attributes": {}
|
| 3312 |
+
}
|
| 3313 |
+
},
|
| 3314 |
+
"total_flos": 3.310734730054861e+17,
|
| 3315 |
+
"train_batch_size": 1,
|
| 3316 |
+
"trial_name": null,
|
| 3317 |
+
"trial_params": null
|
| 3318 |
+
}
|
training_loss.png
ADDED
|