MHGanainy/gpt2-xl-lora-multi
Browse files- README.md +2 -0
- all_results.json +11 -6
- eval_results.json +6 -6
- train_results.json +8 -0
- trainer_state.json +3444 -0
README.md
CHANGED
|
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# gpt2-xl-lora-multi
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on the None dataset.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 15 |
# gpt2-xl-lora-multi
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.1721
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
CHANGED
|
@@ -1,8 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second": 0.
|
| 7 |
-
"perplexity":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.172133445739746,
|
| 4 |
+
"eval_runtime": 24239.0476,
|
| 5 |
+
"eval_samples_per_second": 4.285,
|
| 6 |
+
"eval_steps_per_second": 0.268,
|
| 7 |
+
"perplexity": 8.776989310759461,
|
| 8 |
+
"total_flos": 7.322050088623145e+18,
|
| 9 |
+
"train_loss": 2.3946414439395287,
|
| 10 |
+
"train_runtime": 14836.2948,
|
| 11 |
+
"train_samples_per_second": 52.513,
|
| 12 |
+
"train_steps_per_second": 3.282
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second": 0.
|
| 7 |
-
"perplexity":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.172133445739746,
|
| 4 |
+
"eval_runtime": 24239.0476,
|
| 5 |
+
"eval_samples_per_second": 4.285,
|
| 6 |
+
"eval_steps_per_second": 0.268,
|
| 7 |
+
"perplexity": 8.776989310759461
|
| 8 |
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 7.322050088623145e+18,
|
| 4 |
+
"train_loss": 2.3946414439395287,
|
| 5 |
+
"train_runtime": 14836.2948,
|
| 6 |
+
"train_samples_per_second": 52.513,
|
| 7 |
+
"train_steps_per_second": 3.282
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3444 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 48694,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0020536411056803713,
|
| 13 |
+
"grad_norm": 0.2409495860338211,
|
| 14 |
+
"learning_rate": 5.134260923140114e-08,
|
| 15 |
+
"loss": 2.927,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.004107282211360743,
|
| 20 |
+
"grad_norm": 0.19202615320682526,
|
| 21 |
+
"learning_rate": 1.0114494018586026e-07,
|
| 22 |
+
"loss": 2.9275,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.006160923317041114,
|
| 27 |
+
"grad_norm": 0.2235158383846283,
|
| 28 |
+
"learning_rate": 1.5197412332494739e-07,
|
| 29 |
+
"loss": 2.9242,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.008214564422721485,
|
| 34 |
+
"grad_norm": 0.2802189886569977,
|
| 35 |
+
"learning_rate": 2.0331673255634853e-07,
|
| 36 |
+
"loss": 2.9256,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.010268205528401856,
|
| 41 |
+
"grad_norm": 0.32697775959968567,
|
| 42 |
+
"learning_rate": 2.5465934178774966e-07,
|
| 43 |
+
"loss": 2.9051,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.012321846634082229,
|
| 48 |
+
"grad_norm": 0.22724781930446625,
|
| 49 |
+
"learning_rate": 3.0600195101915083e-07,
|
| 50 |
+
"loss": 2.9075,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0143754877397626,
|
| 55 |
+
"grad_norm": 0.18593861162662506,
|
| 56 |
+
"learning_rate": 3.5734456025055194e-07,
|
| 57 |
+
"loss": 2.8701,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.01642912884544297,
|
| 62 |
+
"grad_norm": 0.3414272665977478,
|
| 63 |
+
"learning_rate": 4.086871694819531e-07,
|
| 64 |
+
"loss": 2.8703,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.018482769951123343,
|
| 69 |
+
"grad_norm": 0.28912848234176636,
|
| 70 |
+
"learning_rate": 4.6002977871335427e-07,
|
| 71 |
+
"loss": 2.8889,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.020536411056803712,
|
| 76 |
+
"grad_norm": 0.3757544457912445,
|
| 77 |
+
"learning_rate": 5.113723879447554e-07,
|
| 78 |
+
"loss": 2.8398,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.022590052162484085,
|
| 83 |
+
"grad_norm": 0.25070273876190186,
|
| 84 |
+
"learning_rate": 5.627149971761565e-07,
|
| 85 |
+
"loss": 2.8267,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.024643693268164457,
|
| 90 |
+
"grad_norm": 0.2661902606487274,
|
| 91 |
+
"learning_rate": 6.140576064075577e-07,
|
| 92 |
+
"loss": 2.808,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.026697334373844826,
|
| 97 |
+
"grad_norm": 0.2517978847026825,
|
| 98 |
+
"learning_rate": 6.654002156389588e-07,
|
| 99 |
+
"loss": 2.7978,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0287509754795252,
|
| 104 |
+
"grad_norm": 0.2020702064037323,
|
| 105 |
+
"learning_rate": 7.167428248703599e-07,
|
| 106 |
+
"loss": 2.79,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.030804616585205568,
|
| 111 |
+
"grad_norm": 0.24845516681671143,
|
| 112 |
+
"learning_rate": 7.680854341017612e-07,
|
| 113 |
+
"loss": 2.7695,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.03285825769088594,
|
| 118 |
+
"grad_norm": 0.2540706992149353,
|
| 119 |
+
"learning_rate": 8.194280433331622e-07,
|
| 120 |
+
"loss": 2.7671,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.03491189879656631,
|
| 125 |
+
"grad_norm": 0.24213051795959473,
|
| 126 |
+
"learning_rate": 8.707706525645635e-07,
|
| 127 |
+
"loss": 2.7319,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.036965539902246686,
|
| 132 |
+
"grad_norm": 0.2081119567155838,
|
| 133 |
+
"learning_rate": 9.221132617959646e-07,
|
| 134 |
+
"loss": 2.7264,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.039019181007927055,
|
| 139 |
+
"grad_norm": 0.19368572533130646,
|
| 140 |
+
"learning_rate": 9.734558710273657e-07,
|
| 141 |
+
"loss": 2.6948,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.041072822113607424,
|
| 146 |
+
"grad_norm": 0.23247301578521729,
|
| 147 |
+
"learning_rate": 1.0247984802587668e-06,
|
| 148 |
+
"loss": 2.6832,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.0431264632192878,
|
| 153 |
+
"grad_norm": 0.2121610939502716,
|
| 154 |
+
"learning_rate": 1.076141089490168e-06,
|
| 155 |
+
"loss": 2.6615,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.04518010432496817,
|
| 160 |
+
"grad_norm": 0.261663019657135,
|
| 161 |
+
"learning_rate": 1.1274836987215691e-06,
|
| 162 |
+
"loss": 2.655,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.04723374543064854,
|
| 167 |
+
"grad_norm": 0.21610794961452484,
|
| 168 |
+
"learning_rate": 1.1788263079529702e-06,
|
| 169 |
+
"loss": 2.6542,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.049287386536328914,
|
| 174 |
+
"grad_norm": 0.2257019430398941,
|
| 175 |
+
"learning_rate": 1.2301689171843714e-06,
|
| 176 |
+
"loss": 2.6342,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.05134102764200928,
|
| 181 |
+
"grad_norm": 0.3119538128376007,
|
| 182 |
+
"learning_rate": 1.2815115264157727e-06,
|
| 183 |
+
"loss": 2.6302,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.05339466874768965,
|
| 188 |
+
"grad_norm": 0.2009056657552719,
|
| 189 |
+
"learning_rate": 1.3328541356471736e-06,
|
| 190 |
+
"loss": 2.6279,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.05544830985337002,
|
| 195 |
+
"grad_norm": 0.23007695376873016,
|
| 196 |
+
"learning_rate": 1.3841967448785748e-06,
|
| 197 |
+
"loss": 2.6305,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.0575019509590504,
|
| 202 |
+
"grad_norm": 0.21969914436340332,
|
| 203 |
+
"learning_rate": 1.435539354109976e-06,
|
| 204 |
+
"loss": 2.6316,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.05955559206473077,
|
| 209 |
+
"grad_norm": 0.3167186677455902,
|
| 210 |
+
"learning_rate": 1.4868819633413772e-06,
|
| 211 |
+
"loss": 2.6103,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.061609233170411136,
|
| 216 |
+
"grad_norm": 0.2724080979824066,
|
| 217 |
+
"learning_rate": 1.5382245725727782e-06,
|
| 218 |
+
"loss": 2.6127,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.0636628742760915,
|
| 223 |
+
"grad_norm": 0.2623263895511627,
|
| 224 |
+
"learning_rate": 1.5895671818041795e-06,
|
| 225 |
+
"loss": 2.6131,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.06571651538177188,
|
| 230 |
+
"grad_norm": 0.22106924653053284,
|
| 231 |
+
"learning_rate": 1.6409097910355805e-06,
|
| 232 |
+
"loss": 2.6123,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.06777015648745226,
|
| 237 |
+
"grad_norm": 0.23635180294513702,
|
| 238 |
+
"learning_rate": 1.6922524002669818e-06,
|
| 239 |
+
"loss": 2.6071,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.06982379759313262,
|
| 244 |
+
"grad_norm": 0.3364904224872589,
|
| 245 |
+
"learning_rate": 1.7435950094983829e-06,
|
| 246 |
+
"loss": 2.6102,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.071877438698813,
|
| 251 |
+
"grad_norm": 0.3253539800643921,
|
| 252 |
+
"learning_rate": 1.794937618729784e-06,
|
| 253 |
+
"loss": 2.6042,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.07393107980449337,
|
| 258 |
+
"grad_norm": 0.2709799110889435,
|
| 259 |
+
"learning_rate": 1.8462802279611852e-06,
|
| 260 |
+
"loss": 2.609,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.07598472091017373,
|
| 265 |
+
"grad_norm": 0.31026512384414673,
|
| 266 |
+
"learning_rate": 1.8976228371925863e-06,
|
| 267 |
+
"loss": 2.5833,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.07803836201585411,
|
| 272 |
+
"grad_norm": 0.2669944167137146,
|
| 273 |
+
"learning_rate": 1.9489654464239875e-06,
|
| 274 |
+
"loss": 2.5922,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.08009200312153449,
|
| 279 |
+
"grad_norm": 0.2561105787754059,
|
| 280 |
+
"learning_rate": 2.0003080556553886e-06,
|
| 281 |
+
"loss": 2.6047,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.08214564422721485,
|
| 286 |
+
"grad_norm": 0.22908590734004974,
|
| 287 |
+
"learning_rate": 2.0516506648867897e-06,
|
| 288 |
+
"loss": 2.5738,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.08419928533289522,
|
| 293 |
+
"grad_norm": 0.23380373418331146,
|
| 294 |
+
"learning_rate": 2.1029932741181907e-06,
|
| 295 |
+
"loss": 2.5787,
|
| 296 |
+
"step": 4100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.0862529264385756,
|
| 300 |
+
"grad_norm": 0.22019442915916443,
|
| 301 |
+
"learning_rate": 2.1543358833495918e-06,
|
| 302 |
+
"loss": 2.5815,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.08830656754425596,
|
| 307 |
+
"grad_norm": 0.23664426803588867,
|
| 308 |
+
"learning_rate": 2.2056784925809933e-06,
|
| 309 |
+
"loss": 2.5621,
|
| 310 |
+
"step": 4300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.09036020864993634,
|
| 314 |
+
"grad_norm": 0.25547099113464355,
|
| 315 |
+
"learning_rate": 2.2570211018123943e-06,
|
| 316 |
+
"loss": 2.5697,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.09241384975561671,
|
| 321 |
+
"grad_norm": 0.2742305099964142,
|
| 322 |
+
"learning_rate": 2.3083637110437954e-06,
|
| 323 |
+
"loss": 2.5514,
|
| 324 |
+
"step": 4500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.09446749086129708,
|
| 328 |
+
"grad_norm": 0.2590065002441406,
|
| 329 |
+
"learning_rate": 2.3597063202751964e-06,
|
| 330 |
+
"loss": 2.5522,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.09652113196697745,
|
| 335 |
+
"grad_norm": 0.3027460277080536,
|
| 336 |
+
"learning_rate": 2.411048929506598e-06,
|
| 337 |
+
"loss": 2.5566,
|
| 338 |
+
"step": 4700
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.09857477307265783,
|
| 342 |
+
"grad_norm": 0.3074556887149811,
|
| 343 |
+
"learning_rate": 2.4623915387379986e-06,
|
| 344 |
+
"loss": 2.5465,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.10062841417833819,
|
| 349 |
+
"grad_norm": 0.2754651606082916,
|
| 350 |
+
"learning_rate": 2.5137341479694e-06,
|
| 351 |
+
"loss": 2.5428,
|
| 352 |
+
"step": 4900
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.10268205528401857,
|
| 356 |
+
"grad_norm": 0.32703617215156555,
|
| 357 |
+
"learning_rate": 2.565076757200801e-06,
|
| 358 |
+
"loss": 2.554,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.10473569638969894,
|
| 363 |
+
"grad_norm": 0.24852938950061798,
|
| 364 |
+
"learning_rate": 2.6164193664322026e-06,
|
| 365 |
+
"loss": 2.5499,
|
| 366 |
+
"step": 5100
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.1067893374953793,
|
| 370 |
+
"grad_norm": 0.3230968117713928,
|
| 371 |
+
"learning_rate": 2.6677619756636036e-06,
|
| 372 |
+
"loss": 2.5316,
|
| 373 |
+
"step": 5200
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.10884297860105968,
|
| 377 |
+
"grad_norm": 0.2494313269853592,
|
| 378 |
+
"learning_rate": 2.7191045848950047e-06,
|
| 379 |
+
"loss": 2.5242,
|
| 380 |
+
"step": 5300
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.11089661970674004,
|
| 384 |
+
"grad_norm": 0.27314093708992004,
|
| 385 |
+
"learning_rate": 2.7704471941264053e-06,
|
| 386 |
+
"loss": 2.5281,
|
| 387 |
+
"step": 5400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.11295026081242042,
|
| 391 |
+
"grad_norm": 0.26759541034698486,
|
| 392 |
+
"learning_rate": 2.821789803357807e-06,
|
| 393 |
+
"loss": 2.5274,
|
| 394 |
+
"step": 5500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1150039019181008,
|
| 398 |
+
"grad_norm": 0.2792930006980896,
|
| 399 |
+
"learning_rate": 2.873132412589208e-06,
|
| 400 |
+
"loss": 2.5301,
|
| 401 |
+
"step": 5600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.11705754302378116,
|
| 405 |
+
"grad_norm": 0.2926984429359436,
|
| 406 |
+
"learning_rate": 2.9244750218206094e-06,
|
| 407 |
+
"loss": 2.5329,
|
| 408 |
+
"step": 5700
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.11911118412946153,
|
| 412 |
+
"grad_norm": 0.25933071970939636,
|
| 413 |
+
"learning_rate": 2.9758176310520104e-06,
|
| 414 |
+
"loss": 2.522,
|
| 415 |
+
"step": 5800
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.12116482523514191,
|
| 419 |
+
"grad_norm": 0.37489551305770874,
|
| 420 |
+
"learning_rate": 3.0271602402834115e-06,
|
| 421 |
+
"loss": 2.5345,
|
| 422 |
+
"step": 5900
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.12321846634082227,
|
| 426 |
+
"grad_norm": 0.280924916267395,
|
| 427 |
+
"learning_rate": 3.078502849514813e-06,
|
| 428 |
+
"loss": 2.523,
|
| 429 |
+
"step": 6000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.12527210744650266,
|
| 433 |
+
"grad_norm": 0.27692222595214844,
|
| 434 |
+
"learning_rate": 3.1298454587462136e-06,
|
| 435 |
+
"loss": 2.5212,
|
| 436 |
+
"step": 6100
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.127325748552183,
|
| 440 |
+
"grad_norm": 0.33660975098609924,
|
| 441 |
+
"learning_rate": 3.1811880679776147e-06,
|
| 442 |
+
"loss": 2.5335,
|
| 443 |
+
"step": 6200
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.1293793896578634,
|
| 447 |
+
"grad_norm": 0.2802388370037079,
|
| 448 |
+
"learning_rate": 3.2325306772090157e-06,
|
| 449 |
+
"loss": 2.5155,
|
| 450 |
+
"step": 6300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.13143303076354376,
|
| 454 |
+
"grad_norm": 0.2762887477874756,
|
| 455 |
+
"learning_rate": 3.283873286440417e-06,
|
| 456 |
+
"loss": 2.5186,
|
| 457 |
+
"step": 6400
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.13348667186922414,
|
| 461 |
+
"grad_norm": 0.30897897481918335,
|
| 462 |
+
"learning_rate": 3.3352158956718183e-06,
|
| 463 |
+
"loss": 2.5026,
|
| 464 |
+
"step": 6500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.13554031297490451,
|
| 468 |
+
"grad_norm": 0.2809106707572937,
|
| 469 |
+
"learning_rate": 3.3865585049032198e-06,
|
| 470 |
+
"loss": 2.5189,
|
| 471 |
+
"step": 6600
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.1375939540805849,
|
| 475 |
+
"grad_norm": 0.25316041707992554,
|
| 476 |
+
"learning_rate": 3.437901114134621e-06,
|
| 477 |
+
"loss": 2.5043,
|
| 478 |
+
"step": 6700
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.13964759518626524,
|
| 482 |
+
"grad_norm": 0.267139732837677,
|
| 483 |
+
"learning_rate": 3.489243723366022e-06,
|
| 484 |
+
"loss": 2.5158,
|
| 485 |
+
"step": 6800
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.14170123629194561,
|
| 489 |
+
"grad_norm": 0.29980820417404175,
|
| 490 |
+
"learning_rate": 3.5405863325974225e-06,
|
| 491 |
+
"loss": 2.5114,
|
| 492 |
+
"step": 6900
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.143754877397626,
|
| 496 |
+
"grad_norm": 0.2696675658226013,
|
| 497 |
+
"learning_rate": 3.591928941828824e-06,
|
| 498 |
+
"loss": 2.5209,
|
| 499 |
+
"step": 7000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.14580851850330637,
|
| 503 |
+
"grad_norm": 0.3216298520565033,
|
| 504 |
+
"learning_rate": 3.643271551060225e-06,
|
| 505 |
+
"loss": 2.5077,
|
| 506 |
+
"step": 7100
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.14786215960898674,
|
| 510 |
+
"grad_norm": 0.29979774355888367,
|
| 511 |
+
"learning_rate": 3.6946141602916265e-06,
|
| 512 |
+
"loss": 2.5017,
|
| 513 |
+
"step": 7200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.1499158007146671,
|
| 517 |
+
"grad_norm": 0.2669665813446045,
|
| 518 |
+
"learning_rate": 3.7459567695230276e-06,
|
| 519 |
+
"loss": 2.5057,
|
| 520 |
+
"step": 7300
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.15196944182034747,
|
| 524 |
+
"grad_norm": 0.37219077348709106,
|
| 525 |
+
"learning_rate": 3.7972993787544287e-06,
|
| 526 |
+
"loss": 2.5005,
|
| 527 |
+
"step": 7400
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.15402308292602784,
|
| 531 |
+
"grad_norm": 0.37116026878356934,
|
| 532 |
+
"learning_rate": 3.84864198798583e-06,
|
| 533 |
+
"loss": 2.4993,
|
| 534 |
+
"step": 7500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.15607672403170822,
|
| 538 |
+
"grad_norm": 0.31641533970832825,
|
| 539 |
+
"learning_rate": 3.899984597217231e-06,
|
| 540 |
+
"loss": 2.4803,
|
| 541 |
+
"step": 7600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.1581303651373886,
|
| 545 |
+
"grad_norm": 0.2628764510154724,
|
| 546 |
+
"learning_rate": 3.951327206448632e-06,
|
| 547 |
+
"loss": 2.4909,
|
| 548 |
+
"step": 7700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.16018400624306897,
|
| 552 |
+
"grad_norm": 0.3081704378128052,
|
| 553 |
+
"learning_rate": 4.002669815680033e-06,
|
| 554 |
+
"loss": 2.489,
|
| 555 |
+
"step": 7800
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.16223764734874932,
|
| 559 |
+
"grad_norm": 0.28597038984298706,
|
| 560 |
+
"learning_rate": 4.054012424911434e-06,
|
| 561 |
+
"loss": 2.4907,
|
| 562 |
+
"step": 7900
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.1642912884544297,
|
| 566 |
+
"grad_norm": 0.3018709421157837,
|
| 567 |
+
"learning_rate": 4.105355034142836e-06,
|
| 568 |
+
"loss": 2.4768,
|
| 569 |
+
"step": 8000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.16634492956011007,
|
| 573 |
+
"grad_norm": 0.3312239646911621,
|
| 574 |
+
"learning_rate": 4.1566976433742365e-06,
|
| 575 |
+
"loss": 2.4873,
|
| 576 |
+
"step": 8100
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.16839857066579045,
|
| 580 |
+
"grad_norm": 0.28529542684555054,
|
| 581 |
+
"learning_rate": 4.208040252605638e-06,
|
| 582 |
+
"loss": 2.4861,
|
| 583 |
+
"step": 8200
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.17045221177147082,
|
| 587 |
+
"grad_norm": 0.3306364417076111,
|
| 588 |
+
"learning_rate": 4.259382861837039e-06,
|
| 589 |
+
"loss": 2.4852,
|
| 590 |
+
"step": 8300
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.1725058528771512,
|
| 594 |
+
"grad_norm": 0.27952802181243896,
|
| 595 |
+
"learning_rate": 4.31072547106844e-06,
|
| 596 |
+
"loss": 2.4781,
|
| 597 |
+
"step": 8400
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.17455949398283155,
|
| 601 |
+
"grad_norm": 0.3546277582645416,
|
| 602 |
+
"learning_rate": 4.362068080299841e-06,
|
| 603 |
+
"loss": 2.4824,
|
| 604 |
+
"step": 8500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.17661313508851192,
|
| 608 |
+
"grad_norm": 0.320534348487854,
|
| 609 |
+
"learning_rate": 4.413410689531242e-06,
|
| 610 |
+
"loss": 2.4886,
|
| 611 |
+
"step": 8600
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.1786667761941923,
|
| 615 |
+
"grad_norm": 0.30237877368927,
|
| 616 |
+
"learning_rate": 4.464753298762644e-06,
|
| 617 |
+
"loss": 2.4719,
|
| 618 |
+
"step": 8700
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.18072041729987268,
|
| 622 |
+
"grad_norm": 0.34376901388168335,
|
| 623 |
+
"learning_rate": 4.516095907994044e-06,
|
| 624 |
+
"loss": 2.4817,
|
| 625 |
+
"step": 8800
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.18277405840555305,
|
| 629 |
+
"grad_norm": 0.3278101086616516,
|
| 630 |
+
"learning_rate": 4.567438517225446e-06,
|
| 631 |
+
"loss": 2.4641,
|
| 632 |
+
"step": 8900
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.18482769951123343,
|
| 636 |
+
"grad_norm": 0.304239422082901,
|
| 637 |
+
"learning_rate": 4.618781126456847e-06,
|
| 638 |
+
"loss": 2.4746,
|
| 639 |
+
"step": 9000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.18688134061691378,
|
| 643 |
+
"grad_norm": 0.3272424340248108,
|
| 644 |
+
"learning_rate": 4.670123735688248e-06,
|
| 645 |
+
"loss": 2.4767,
|
| 646 |
+
"step": 9100
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.18893498172259415,
|
| 650 |
+
"grad_norm": 0.35533037781715393,
|
| 651 |
+
"learning_rate": 4.721466344919649e-06,
|
| 652 |
+
"loss": 2.4776,
|
| 653 |
+
"step": 9200
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.19098862282827453,
|
| 657 |
+
"grad_norm": 0.37344789505004883,
|
| 658 |
+
"learning_rate": 4.77280895415105e-06,
|
| 659 |
+
"loss": 2.4733,
|
| 660 |
+
"step": 9300
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.1930422639339549,
|
| 664 |
+
"grad_norm": 0.3110647201538086,
|
| 665 |
+
"learning_rate": 4.8241515633824515e-06,
|
| 666 |
+
"loss": 2.4734,
|
| 667 |
+
"step": 9400
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.19509590503963528,
|
| 671 |
+
"grad_norm": 0.3108662962913513,
|
| 672 |
+
"learning_rate": 4.875494172613853e-06,
|
| 673 |
+
"loss": 2.4717,
|
| 674 |
+
"step": 9500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.19714954614531566,
|
| 678 |
+
"grad_norm": 0.3166399300098419,
|
| 679 |
+
"learning_rate": 4.926836781845254e-06,
|
| 680 |
+
"loss": 2.4652,
|
| 681 |
+
"step": 9600
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.199203187250996,
|
| 685 |
+
"grad_norm": 0.3000437021255493,
|
| 686 |
+
"learning_rate": 4.978179391076655e-06,
|
| 687 |
+
"loss": 2.4568,
|
| 688 |
+
"step": 9700
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.20125682835667638,
|
| 692 |
+
"grad_norm": 0.34338313341140747,
|
| 693 |
+
"learning_rate": 5.029522000308056e-06,
|
| 694 |
+
"loss": 2.4721,
|
| 695 |
+
"step": 9800
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.20331046946235676,
|
| 699 |
+
"grad_norm": 0.36998987197875977,
|
| 700 |
+
"learning_rate": 5.080864609539457e-06,
|
| 701 |
+
"loss": 2.4715,
|
| 702 |
+
"step": 9900
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.20536411056803713,
|
| 706 |
+
"grad_norm": 0.4209326207637787,
|
| 707 |
+
"learning_rate": 5.132207218770858e-06,
|
| 708 |
+
"loss": 2.459,
|
| 709 |
+
"step": 10000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.2074177516737175,
|
| 713 |
+
"grad_norm": 0.31479907035827637,
|
| 714 |
+
"learning_rate": 5.18354982800226e-06,
|
| 715 |
+
"loss": 2.4609,
|
| 716 |
+
"step": 10100
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.20947139277939789,
|
| 720 |
+
"grad_norm": 0.32337868213653564,
|
| 721 |
+
"learning_rate": 5.234892437233661e-06,
|
| 722 |
+
"loss": 2.4636,
|
| 723 |
+
"step": 10200
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.21152503388507823,
|
| 727 |
+
"grad_norm": 0.3118475377559662,
|
| 728 |
+
"learning_rate": 5.2862350464650615e-06,
|
| 729 |
+
"loss": 2.459,
|
| 730 |
+
"step": 10300
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.2135786749907586,
|
| 734 |
+
"grad_norm": 0.35402822494506836,
|
| 735 |
+
"learning_rate": 5.337577655696463e-06,
|
| 736 |
+
"loss": 2.4502,
|
| 737 |
+
"step": 10400
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.215632316096439,
|
| 741 |
+
"grad_norm": 0.4079764187335968,
|
| 742 |
+
"learning_rate": 5.388920264927864e-06,
|
| 743 |
+
"loss": 2.4516,
|
| 744 |
+
"step": 10500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.21768595720211936,
|
| 748 |
+
"grad_norm": 0.3345820903778076,
|
| 749 |
+
"learning_rate": 5.440262874159266e-06,
|
| 750 |
+
"loss": 2.4714,
|
| 751 |
+
"step": 10600
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.21973959830779974,
|
| 755 |
+
"grad_norm": 0.34505167603492737,
|
| 756 |
+
"learning_rate": 5.491605483390667e-06,
|
| 757 |
+
"loss": 2.4683,
|
| 758 |
+
"step": 10700
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.2217932394134801,
|
| 762 |
+
"grad_norm": 0.37150588631629944,
|
| 763 |
+
"learning_rate": 5.542948092622068e-06,
|
| 764 |
+
"loss": 2.4577,
|
| 765 |
+
"step": 10800
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.22384688051916046,
|
| 769 |
+
"grad_norm": 0.40776118636131287,
|
| 770 |
+
"learning_rate": 5.594290701853469e-06,
|
| 771 |
+
"loss": 2.4515,
|
| 772 |
+
"step": 10900
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.22590052162484084,
|
| 776 |
+
"grad_norm": 0.4175308346748352,
|
| 777 |
+
"learning_rate": 5.645633311084869e-06,
|
| 778 |
+
"loss": 2.4372,
|
| 779 |
+
"step": 11000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.22795416273052121,
|
| 783 |
+
"grad_norm": 0.3530292809009552,
|
| 784 |
+
"learning_rate": 5.696975920316271e-06,
|
| 785 |
+
"loss": 2.4592,
|
| 786 |
+
"step": 11100
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.2300078038362016,
|
| 790 |
+
"grad_norm": 0.3534497618675232,
|
| 791 |
+
"learning_rate": 5.7483185295476715e-06,
|
| 792 |
+
"loss": 2.4463,
|
| 793 |
+
"step": 11200
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.23206144494188197,
|
| 797 |
+
"grad_norm": 0.35864877700805664,
|
| 798 |
+
"learning_rate": 5.799661138779074e-06,
|
| 799 |
+
"loss": 2.4353,
|
| 800 |
+
"step": 11300
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.23411508604756232,
|
| 804 |
+
"grad_norm": 0.39018771052360535,
|
| 805 |
+
"learning_rate": 5.851003748010474e-06,
|
| 806 |
+
"loss": 2.4398,
|
| 807 |
+
"step": 11400
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.2361687271532427,
|
| 811 |
+
"grad_norm": 0.3230128884315491,
|
| 812 |
+
"learning_rate": 5.902346357241876e-06,
|
| 813 |
+
"loss": 2.4487,
|
| 814 |
+
"step": 11500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.23822236825892307,
|
| 818 |
+
"grad_norm": 0.3367525637149811,
|
| 819 |
+
"learning_rate": 5.9536889664732765e-06,
|
| 820 |
+
"loss": 2.4688,
|
| 821 |
+
"step": 11600
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.24027600936460344,
|
| 825 |
+
"grad_norm": 0.42642784118652344,
|
| 826 |
+
"learning_rate": 6.005031575704677e-06,
|
| 827 |
+
"loss": 2.4382,
|
| 828 |
+
"step": 11700
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.24232965047028382,
|
| 832 |
+
"grad_norm": 0.3271915316581726,
|
| 833 |
+
"learning_rate": 6.0563741849360795e-06,
|
| 834 |
+
"loss": 2.4471,
|
| 835 |
+
"step": 11800
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.2443832915759642,
|
| 839 |
+
"grad_norm": 0.3612287938594818,
|
| 840 |
+
"learning_rate": 6.10771679416748e-06,
|
| 841 |
+
"loss": 2.4377,
|
| 842 |
+
"step": 11900
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.24643693268164454,
|
| 846 |
+
"grad_norm": 0.3220459520816803,
|
| 847 |
+
"learning_rate": 6.159059403398882e-06,
|
| 848 |
+
"loss": 2.4396,
|
| 849 |
+
"step": 12000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.24849057378732492,
|
| 853 |
+
"grad_norm": 0.3655225932598114,
|
| 854 |
+
"learning_rate": 6.210402012630282e-06,
|
| 855 |
+
"loss": 2.4358,
|
| 856 |
+
"step": 12100
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.2505442148930053,
|
| 860 |
+
"grad_norm": 0.3181889057159424,
|
| 861 |
+
"learning_rate": 6.261744621861684e-06,
|
| 862 |
+
"loss": 2.4427,
|
| 863 |
+
"step": 12200
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.25259785599868567,
|
| 867 |
+
"grad_norm": 0.38416174054145813,
|
| 868 |
+
"learning_rate": 6.313087231093084e-06,
|
| 869 |
+
"loss": 2.4343,
|
| 870 |
+
"step": 12300
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.254651497104366,
|
| 874 |
+
"grad_norm": 0.3695339560508728,
|
| 875 |
+
"learning_rate": 6.364429840324485e-06,
|
| 876 |
+
"loss": 2.4292,
|
| 877 |
+
"step": 12400
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.2567051382100464,
|
| 881 |
+
"grad_norm": 0.3652244508266449,
|
| 882 |
+
"learning_rate": 6.415772449555887e-06,
|
| 883 |
+
"loss": 2.4394,
|
| 884 |
+
"step": 12500
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.2587587793157268,
|
| 888 |
+
"grad_norm": 0.37237632274627686,
|
| 889 |
+
"learning_rate": 6.467115058787288e-06,
|
| 890 |
+
"loss": 2.4398,
|
| 891 |
+
"step": 12600
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.2608124204214072,
|
| 895 |
+
"grad_norm": 0.3868449628353119,
|
| 896 |
+
"learning_rate": 6.5184576680186895e-06,
|
| 897 |
+
"loss": 2.4288,
|
| 898 |
+
"step": 12700
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.2628660615270875,
|
| 902 |
+
"grad_norm": 0.33903270959854126,
|
| 903 |
+
"learning_rate": 6.56980027725009e-06,
|
| 904 |
+
"loss": 2.4344,
|
| 905 |
+
"step": 12800
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.2649197026327679,
|
| 909 |
+
"grad_norm": 0.4348714351654053,
|
| 910 |
+
"learning_rate": 6.621142886481492e-06,
|
| 911 |
+
"loss": 2.426,
|
| 912 |
+
"step": 12900
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.2669733437384483,
|
| 916 |
+
"grad_norm": 0.41190701723098755,
|
| 917 |
+
"learning_rate": 6.672485495712892e-06,
|
| 918 |
+
"loss": 2.4315,
|
| 919 |
+
"step": 13000
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.2690269848441286,
|
| 923 |
+
"grad_norm": 1.1561683416366577,
|
| 924 |
+
"learning_rate": 6.723828104944293e-06,
|
| 925 |
+
"loss": 2.4265,
|
| 926 |
+
"step": 13100
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.27108062594980903,
|
| 930 |
+
"grad_norm": 0.3453768193721771,
|
| 931 |
+
"learning_rate": 6.775170714175695e-06,
|
| 932 |
+
"loss": 2.4343,
|
| 933 |
+
"step": 13200
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.2731342670554894,
|
| 937 |
+
"grad_norm": 0.4584992527961731,
|
| 938 |
+
"learning_rate": 6.826513323407096e-06,
|
| 939 |
+
"loss": 2.4215,
|
| 940 |
+
"step": 13300
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.2751879081611698,
|
| 944 |
+
"grad_norm": 0.353597491979599,
|
| 945 |
+
"learning_rate": 6.877855932638497e-06,
|
| 946 |
+
"loss": 2.4419,
|
| 947 |
+
"step": 13400
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.27724154926685013,
|
| 951 |
+
"grad_norm": 0.36851683259010315,
|
| 952 |
+
"learning_rate": 6.929198541869898e-06,
|
| 953 |
+
"loss": 2.4295,
|
| 954 |
+
"step": 13500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.2792951903725305,
|
| 958 |
+
"grad_norm": 0.33614102005958557,
|
| 959 |
+
"learning_rate": 6.9805411511013e-06,
|
| 960 |
+
"loss": 2.4327,
|
| 961 |
+
"step": 13600
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.2813488314782109,
|
| 965 |
+
"grad_norm": 0.34625378251075745,
|
| 966 |
+
"learning_rate": 7.031883760332701e-06,
|
| 967 |
+
"loss": 2.431,
|
| 968 |
+
"step": 13700
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.28340247258389123,
|
| 972 |
+
"grad_norm": 0.38167163729667664,
|
| 973 |
+
"learning_rate": 7.083226369564102e-06,
|
| 974 |
+
"loss": 2.4317,
|
| 975 |
+
"step": 13800
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.28545611368957163,
|
| 979 |
+
"grad_norm": 0.43659523129463196,
|
| 980 |
+
"learning_rate": 7.134055552703189e-06,
|
| 981 |
+
"loss": 2.425,
|
| 982 |
+
"step": 13900
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.287509754795252,
|
| 986 |
+
"grad_norm": 0.3671591877937317,
|
| 987 |
+
"learning_rate": 7.18539816193459e-06,
|
| 988 |
+
"loss": 2.4311,
|
| 989 |
+
"step": 14000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.28956339590093233,
|
| 993 |
+
"grad_norm": 0.35820090770721436,
|
| 994 |
+
"learning_rate": 7.236740771165991e-06,
|
| 995 |
+
"loss": 2.4149,
|
| 996 |
+
"step": 14100
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.29161703700661273,
|
| 1000 |
+
"grad_norm": 0.3354686200618744,
|
| 1001 |
+
"learning_rate": 7.288083380397393e-06,
|
| 1002 |
+
"loss": 2.4312,
|
| 1003 |
+
"step": 14200
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.2936706781122931,
|
| 1007 |
+
"grad_norm": 0.4212140142917633,
|
| 1008 |
+
"learning_rate": 7.339425989628794e-06,
|
| 1009 |
+
"loss": 2.4346,
|
| 1010 |
+
"step": 14300
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.2957243192179735,
|
| 1014 |
+
"grad_norm": 0.3699200451374054,
|
| 1015 |
+
"learning_rate": 7.390768598860195e-06,
|
| 1016 |
+
"loss": 2.4237,
|
| 1017 |
+
"step": 14400
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.29777796032365383,
|
| 1021 |
+
"grad_norm": 0.46324220299720764,
|
| 1022 |
+
"learning_rate": 7.442111208091596e-06,
|
| 1023 |
+
"loss": 2.424,
|
| 1024 |
+
"step": 14500
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.2998316014293342,
|
| 1028 |
+
"grad_norm": 0.342536985874176,
|
| 1029 |
+
"learning_rate": 7.4934538173229965e-06,
|
| 1030 |
+
"loss": 2.4077,
|
| 1031 |
+
"step": 14600
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.3018852425350146,
|
| 1035 |
+
"grad_norm": 0.34816351532936096,
|
| 1036 |
+
"learning_rate": 7.544796426554398e-06,
|
| 1037 |
+
"loss": 2.4066,
|
| 1038 |
+
"step": 14700
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.30393888364069493,
|
| 1042 |
+
"grad_norm": 0.610781192779541,
|
| 1043 |
+
"learning_rate": 7.596139035785799e-06,
|
| 1044 |
+
"loss": 2.4142,
|
| 1045 |
+
"step": 14800
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.30599252474637534,
|
| 1049 |
+
"grad_norm": 0.3818989098072052,
|
| 1050 |
+
"learning_rate": 7.647481645017201e-06,
|
| 1051 |
+
"loss": 2.4216,
|
| 1052 |
+
"step": 14900
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.3080461658520557,
|
| 1056 |
+
"grad_norm": 0.33145734667778015,
|
| 1057 |
+
"learning_rate": 7.698824254248602e-06,
|
| 1058 |
+
"loss": 2.4002,
|
| 1059 |
+
"step": 15000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.3100998069577361,
|
| 1063 |
+
"grad_norm": 0.3824017643928528,
|
| 1064 |
+
"learning_rate": 7.750166863480004e-06,
|
| 1065 |
+
"loss": 2.4124,
|
| 1066 |
+
"step": 15100
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.31215344806341644,
|
| 1070 |
+
"grad_norm": 0.3489684462547302,
|
| 1071 |
+
"learning_rate": 7.801509472711405e-06,
|
| 1072 |
+
"loss": 2.409,
|
| 1073 |
+
"step": 15200
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.3142070891690968,
|
| 1077 |
+
"grad_norm": 0.33031293749809265,
|
| 1078 |
+
"learning_rate": 7.852852081942805e-06,
|
| 1079 |
+
"loss": 2.4221,
|
| 1080 |
+
"step": 15300
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.3162607302747772,
|
| 1084 |
+
"grad_norm": 0.3469293713569641,
|
| 1085 |
+
"learning_rate": 7.904194691174206e-06,
|
| 1086 |
+
"loss": 2.396,
|
| 1087 |
+
"step": 15400
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.31831437138045754,
|
| 1091 |
+
"grad_norm": 0.3552320897579193,
|
| 1092 |
+
"learning_rate": 7.955537300405606e-06,
|
| 1093 |
+
"loss": 2.4215,
|
| 1094 |
+
"step": 15500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.32036801248613794,
|
| 1098 |
+
"grad_norm": 0.4149351418018341,
|
| 1099 |
+
"learning_rate": 8.006879909637009e-06,
|
| 1100 |
+
"loss": 2.4114,
|
| 1101 |
+
"step": 15600
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.3224216535918183,
|
| 1105 |
+
"grad_norm": 0.34064000844955444,
|
| 1106 |
+
"learning_rate": 8.05822251886841e-06,
|
| 1107 |
+
"loss": 2.4179,
|
| 1108 |
+
"step": 15700
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.32447529469749864,
|
| 1112 |
+
"grad_norm": 0.34136348962783813,
|
| 1113 |
+
"learning_rate": 8.109565128099812e-06,
|
| 1114 |
+
"loss": 2.3974,
|
| 1115 |
+
"step": 15800
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.32652893580317904,
|
| 1119 |
+
"grad_norm": 0.3490683138370514,
|
| 1120 |
+
"learning_rate": 8.160907737331212e-06,
|
| 1121 |
+
"loss": 2.4182,
|
| 1122 |
+
"step": 15900
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.3285825769088594,
|
| 1126 |
+
"grad_norm": 0.33765408396720886,
|
| 1127 |
+
"learning_rate": 8.212250346562613e-06,
|
| 1128 |
+
"loss": 2.405,
|
| 1129 |
+
"step": 16000
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.3306362180145398,
|
| 1133 |
+
"grad_norm": 0.3639397621154785,
|
| 1134 |
+
"learning_rate": 8.263592955794014e-06,
|
| 1135 |
+
"loss": 2.4203,
|
| 1136 |
+
"step": 16100
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.33268985912022014,
|
| 1140 |
+
"grad_norm": 0.38393139839172363,
|
| 1141 |
+
"learning_rate": 8.314935565025414e-06,
|
| 1142 |
+
"loss": 2.4124,
|
| 1143 |
+
"step": 16200
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.33474350022590055,
|
| 1147 |
+
"grad_norm": 0.37910357117652893,
|
| 1148 |
+
"learning_rate": 8.366278174256817e-06,
|
| 1149 |
+
"loss": 2.4077,
|
| 1150 |
+
"step": 16300
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.3367971413315809,
|
| 1154 |
+
"grad_norm": 0.3623708486557007,
|
| 1155 |
+
"learning_rate": 8.417620783488217e-06,
|
| 1156 |
+
"loss": 2.395,
|
| 1157 |
+
"step": 16400
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.33885078243726124,
|
| 1161 |
+
"grad_norm": 0.3724728226661682,
|
| 1162 |
+
"learning_rate": 8.46896339271962e-06,
|
| 1163 |
+
"loss": 2.4159,
|
| 1164 |
+
"step": 16500
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.34090442354294165,
|
| 1168 |
+
"grad_norm": 0.42541515827178955,
|
| 1169 |
+
"learning_rate": 8.52030600195102e-06,
|
| 1170 |
+
"loss": 2.4013,
|
| 1171 |
+
"step": 16600
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.342958064648622,
|
| 1175 |
+
"grad_norm": 0.32243165373802185,
|
| 1176 |
+
"learning_rate": 8.571648611182421e-06,
|
| 1177 |
+
"loss": 2.4136,
|
| 1178 |
+
"step": 16700
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.3450117057543024,
|
| 1182 |
+
"grad_norm": 0.38696199655532837,
|
| 1183 |
+
"learning_rate": 8.622991220413822e-06,
|
| 1184 |
+
"loss": 2.3878,
|
| 1185 |
+
"step": 16800
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.34706534685998275,
|
| 1189 |
+
"grad_norm": 0.33918097615242004,
|
| 1190 |
+
"learning_rate": 8.674333829645222e-06,
|
| 1191 |
+
"loss": 2.3913,
|
| 1192 |
+
"step": 16900
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.3491189879656631,
|
| 1196 |
+
"grad_norm": 0.3394019305706024,
|
| 1197 |
+
"learning_rate": 8.725676438876624e-06,
|
| 1198 |
+
"loss": 2.4115,
|
| 1199 |
+
"step": 17000
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.3511726290713435,
|
| 1203 |
+
"grad_norm": 0.34437182545661926,
|
| 1204 |
+
"learning_rate": 8.777019048108025e-06,
|
| 1205 |
+
"loss": 2.4051,
|
| 1206 |
+
"step": 17100
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.35322627017702385,
|
| 1210 |
+
"grad_norm": 0.3633645176887512,
|
| 1211 |
+
"learning_rate": 8.828361657339427e-06,
|
| 1212 |
+
"loss": 2.4042,
|
| 1213 |
+
"step": 17200
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.35527991128270425,
|
| 1217 |
+
"grad_norm": 0.34443187713623047,
|
| 1218 |
+
"learning_rate": 8.879704266570828e-06,
|
| 1219 |
+
"loss": 2.4096,
|
| 1220 |
+
"step": 17300
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.3573335523883846,
|
| 1224 |
+
"grad_norm": 0.34308770298957825,
|
| 1225 |
+
"learning_rate": 8.931046875802229e-06,
|
| 1226 |
+
"loss": 2.4076,
|
| 1227 |
+
"step": 17400
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.359387193494065,
|
| 1231 |
+
"grad_norm": 0.41387104988098145,
|
| 1232 |
+
"learning_rate": 8.98238948503363e-06,
|
| 1233 |
+
"loss": 2.4063,
|
| 1234 |
+
"step": 17500
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.36144083459974535,
|
| 1238 |
+
"grad_norm": 0.4212593734264374,
|
| 1239 |
+
"learning_rate": 9.03373209426503e-06,
|
| 1240 |
+
"loss": 2.3876,
|
| 1241 |
+
"step": 17600
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.3634944757054257,
|
| 1245 |
+
"grad_norm": 0.3727651536464691,
|
| 1246 |
+
"learning_rate": 9.085074703496432e-06,
|
| 1247 |
+
"loss": 2.4135,
|
| 1248 |
+
"step": 17700
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.3655481168111061,
|
| 1252 |
+
"grad_norm": 0.37746503949165344,
|
| 1253 |
+
"learning_rate": 9.136417312727833e-06,
|
| 1254 |
+
"loss": 2.3896,
|
| 1255 |
+
"step": 17800
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.36760175791678645,
|
| 1259 |
+
"grad_norm": 0.39151206612586975,
|
| 1260 |
+
"learning_rate": 9.187759921959235e-06,
|
| 1261 |
+
"loss": 2.3964,
|
| 1262 |
+
"step": 17900
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.36965539902246686,
|
| 1266 |
+
"grad_norm": 0.31597721576690674,
|
| 1267 |
+
"learning_rate": 9.239102531190636e-06,
|
| 1268 |
+
"loss": 2.3958,
|
| 1269 |
+
"step": 18000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.3717090401281472,
|
| 1273 |
+
"grad_norm": 0.4014475345611572,
|
| 1274 |
+
"learning_rate": 9.290445140422038e-06,
|
| 1275 |
+
"loss": 2.3945,
|
| 1276 |
+
"step": 18100
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.37376268123382755,
|
| 1280 |
+
"grad_norm": 0.3568170666694641,
|
| 1281 |
+
"learning_rate": 9.341787749653439e-06,
|
| 1282 |
+
"loss": 2.3976,
|
| 1283 |
+
"step": 18200
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.37581632233950796,
|
| 1287 |
+
"grad_norm": 0.3766133487224579,
|
| 1288 |
+
"learning_rate": 9.39313035888484e-06,
|
| 1289 |
+
"loss": 2.3852,
|
| 1290 |
+
"step": 18300
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.3778699634451883,
|
| 1294 |
+
"grad_norm": 0.3846842050552368,
|
| 1295 |
+
"learning_rate": 9.44447296811624e-06,
|
| 1296 |
+
"loss": 2.3918,
|
| 1297 |
+
"step": 18400
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.3799236045508687,
|
| 1301 |
+
"grad_norm": 0.36857616901397705,
|
| 1302 |
+
"learning_rate": 9.49581557734764e-06,
|
| 1303 |
+
"loss": 2.3942,
|
| 1304 |
+
"step": 18500
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.38197724565654906,
|
| 1308 |
+
"grad_norm": 0.3256061375141144,
|
| 1309 |
+
"learning_rate": 9.547158186579043e-06,
|
| 1310 |
+
"loss": 2.3939,
|
| 1311 |
+
"step": 18600
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.3840308867622294,
|
| 1315 |
+
"grad_norm": 0.4045381247997284,
|
| 1316 |
+
"learning_rate": 9.598500795810444e-06,
|
| 1317 |
+
"loss": 2.3759,
|
| 1318 |
+
"step": 18700
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.3860845278679098,
|
| 1322 |
+
"grad_norm": 0.3307647705078125,
|
| 1323 |
+
"learning_rate": 9.649843405041846e-06,
|
| 1324 |
+
"loss": 2.3887,
|
| 1325 |
+
"step": 18800
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.38813816897359016,
|
| 1329 |
+
"grad_norm": 0.3295733630657196,
|
| 1330 |
+
"learning_rate": 9.701186014273247e-06,
|
| 1331 |
+
"loss": 2.4031,
|
| 1332 |
+
"step": 18900
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.39019181007927056,
|
| 1336 |
+
"grad_norm": 0.4077715575695038,
|
| 1337 |
+
"learning_rate": 9.752528623504647e-06,
|
| 1338 |
+
"loss": 2.4072,
|
| 1339 |
+
"step": 19000
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.3922454511849509,
|
| 1343 |
+
"grad_norm": 0.3526141941547394,
|
| 1344 |
+
"learning_rate": 9.803871232736048e-06,
|
| 1345 |
+
"loss": 2.3904,
|
| 1346 |
+
"step": 19100
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.3942990922906313,
|
| 1350 |
+
"grad_norm": 0.409244179725647,
|
| 1351 |
+
"learning_rate": 9.855213841967449e-06,
|
| 1352 |
+
"loss": 2.3895,
|
| 1353 |
+
"step": 19200
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.39635273339631166,
|
| 1357 |
+
"grad_norm": 0.378805547952652,
|
| 1358 |
+
"learning_rate": 9.906556451198851e-06,
|
| 1359 |
+
"loss": 2.3807,
|
| 1360 |
+
"step": 19300
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.398406374501992,
|
| 1364 |
+
"grad_norm": 0.38345664739608765,
|
| 1365 |
+
"learning_rate": 9.957899060430252e-06,
|
| 1366 |
+
"loss": 2.3869,
|
| 1367 |
+
"step": 19400
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.4004600156076724,
|
| 1371 |
+
"grad_norm": 0.37221214175224304,
|
| 1372 |
+
"learning_rate": 1.0009241669661654e-05,
|
| 1373 |
+
"loss": 2.3866,
|
| 1374 |
+
"step": 19500
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.40251365671335276,
|
| 1378 |
+
"grad_norm": 0.3797377943992615,
|
| 1379 |
+
"learning_rate": 1.006007085280074e-05,
|
| 1380 |
+
"loss": 2.3931,
|
| 1381 |
+
"step": 19600
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.40456729781903317,
|
| 1385 |
+
"grad_norm": 0.38308799266815186,
|
| 1386 |
+
"learning_rate": 1.0111413462032141e-05,
|
| 1387 |
+
"loss": 2.3748,
|
| 1388 |
+
"step": 19700
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.4066209389247135,
|
| 1392 |
+
"grad_norm": 0.3710861802101135,
|
| 1393 |
+
"learning_rate": 1.0162756071263542e-05,
|
| 1394 |
+
"loss": 2.4001,
|
| 1395 |
+
"step": 19800
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.40867458003039386,
|
| 1399 |
+
"grad_norm": 0.3432161211967468,
|
| 1400 |
+
"learning_rate": 1.0214098680494944e-05,
|
| 1401 |
+
"loss": 2.3769,
|
| 1402 |
+
"step": 19900
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.41072822113607427,
|
| 1406 |
+
"grad_norm": 0.39753302931785583,
|
| 1407 |
+
"learning_rate": 1.0265441289726346e-05,
|
| 1408 |
+
"loss": 2.3914,
|
| 1409 |
+
"step": 20000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.4127818622417546,
|
| 1413 |
+
"grad_norm": 0.43441155552864075,
|
| 1414 |
+
"learning_rate": 1.0316783898957745e-05,
|
| 1415 |
+
"loss": 2.3649,
|
| 1416 |
+
"step": 20100
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.414835503347435,
|
| 1420 |
+
"grad_norm": 0.3198258578777313,
|
| 1421 |
+
"learning_rate": 1.0368126508189147e-05,
|
| 1422 |
+
"loss": 2.3859,
|
| 1423 |
+
"step": 20200
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.41688914445311537,
|
| 1427 |
+
"grad_norm": 0.32526281476020813,
|
| 1428 |
+
"learning_rate": 1.0419469117420548e-05,
|
| 1429 |
+
"loss": 2.3883,
|
| 1430 |
+
"step": 20300
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.41894278555879577,
|
| 1434 |
+
"grad_norm": 0.4657612144947052,
|
| 1435 |
+
"learning_rate": 1.0470811726651949e-05,
|
| 1436 |
+
"loss": 2.3811,
|
| 1437 |
+
"step": 20400
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.4209964266644761,
|
| 1441 |
+
"grad_norm": 0.3935973644256592,
|
| 1442 |
+
"learning_rate": 1.052215433588335e-05,
|
| 1443 |
+
"loss": 2.3802,
|
| 1444 |
+
"step": 20500
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.42305006777015647,
|
| 1448 |
+
"grad_norm": 0.3486153185367584,
|
| 1449 |
+
"learning_rate": 1.0573496945114752e-05,
|
| 1450 |
+
"loss": 2.3978,
|
| 1451 |
+
"step": 20600
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.42510370887583687,
|
| 1455 |
+
"grad_norm": 0.3253055810928345,
|
| 1456 |
+
"learning_rate": 1.0624839554346154e-05,
|
| 1457 |
+
"loss": 2.3711,
|
| 1458 |
+
"step": 20700
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.4271573499815172,
|
| 1462 |
+
"grad_norm": 0.38064277172088623,
|
| 1463 |
+
"learning_rate": 1.0676182163577553e-05,
|
| 1464 |
+
"loss": 2.3872,
|
| 1465 |
+
"step": 20800
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.4292109910871976,
|
| 1469 |
+
"grad_norm": 0.3544224798679352,
|
| 1470 |
+
"learning_rate": 1.0727524772808955e-05,
|
| 1471 |
+
"loss": 2.3767,
|
| 1472 |
+
"step": 20900
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.431264632192878,
|
| 1476 |
+
"grad_norm": 0.3528095483779907,
|
| 1477 |
+
"learning_rate": 1.0778867382040356e-05,
|
| 1478 |
+
"loss": 2.3749,
|
| 1479 |
+
"step": 21000
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.4333182732985583,
|
| 1483 |
+
"grad_norm": 0.32742294669151306,
|
| 1484 |
+
"learning_rate": 1.0830209991271757e-05,
|
| 1485 |
+
"loss": 2.3789,
|
| 1486 |
+
"step": 21100
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.4353719144042387,
|
| 1490 |
+
"grad_norm": 0.41027572751045227,
|
| 1491 |
+
"learning_rate": 1.0881552600503157e-05,
|
| 1492 |
+
"loss": 2.3772,
|
| 1493 |
+
"step": 21200
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.4374255555099191,
|
| 1497 |
+
"grad_norm": 0.39350056648254395,
|
| 1498 |
+
"learning_rate": 1.093289520973456e-05,
|
| 1499 |
+
"loss": 2.3748,
|
| 1500 |
+
"step": 21300
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.4394791966155995,
|
| 1504 |
+
"grad_norm": 0.3493388593196869,
|
| 1505 |
+
"learning_rate": 1.0984237818965962e-05,
|
| 1506 |
+
"loss": 2.3692,
|
| 1507 |
+
"step": 21400
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.4415328377212798,
|
| 1511 |
+
"grad_norm": 0.37564030289649963,
|
| 1512 |
+
"learning_rate": 1.103558042819736e-05,
|
| 1513 |
+
"loss": 2.378,
|
| 1514 |
+
"step": 21500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.4435864788269602,
|
| 1518 |
+
"grad_norm": 0.3591530919075012,
|
| 1519 |
+
"learning_rate": 1.1086923037428763e-05,
|
| 1520 |
+
"loss": 2.3804,
|
| 1521 |
+
"step": 21600
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.4456401199326406,
|
| 1525 |
+
"grad_norm": 0.33735260367393494,
|
| 1526 |
+
"learning_rate": 1.1138265646660165e-05,
|
| 1527 |
+
"loss": 2.3748,
|
| 1528 |
+
"step": 21700
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.4476937610383209,
|
| 1532 |
+
"grad_norm": 0.36125385761260986,
|
| 1533 |
+
"learning_rate": 1.1189608255891566e-05,
|
| 1534 |
+
"loss": 2.3772,
|
| 1535 |
+
"step": 21800
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.44974740214400133,
|
| 1539 |
+
"grad_norm": 0.3484746217727661,
|
| 1540 |
+
"learning_rate": 1.1240950865122967e-05,
|
| 1541 |
+
"loss": 2.3606,
|
| 1542 |
+
"step": 21900
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.4518010432496817,
|
| 1546 |
+
"grad_norm": 0.3787308633327484,
|
| 1547 |
+
"learning_rate": 1.1292293474354367e-05,
|
| 1548 |
+
"loss": 2.3763,
|
| 1549 |
+
"step": 22000
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.4538546843553621,
|
| 1553 |
+
"grad_norm": 0.4395260512828827,
|
| 1554 |
+
"learning_rate": 1.134363608358577e-05,
|
| 1555 |
+
"loss": 2.3767,
|
| 1556 |
+
"step": 22100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.45590832546104243,
|
| 1560 |
+
"grad_norm": 0.36431971192359924,
|
| 1561 |
+
"learning_rate": 1.1394978692817169e-05,
|
| 1562 |
+
"loss": 2.3751,
|
| 1563 |
+
"step": 22200
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.4579619665667228,
|
| 1567 |
+
"grad_norm": 0.3303099572658539,
|
| 1568 |
+
"learning_rate": 1.1446321302048571e-05,
|
| 1569 |
+
"loss": 2.3685,
|
| 1570 |
+
"step": 22300
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.4600156076724032,
|
| 1574 |
+
"grad_norm": 0.38295629620552063,
|
| 1575 |
+
"learning_rate": 1.1497663911279973e-05,
|
| 1576 |
+
"loss": 2.3733,
|
| 1577 |
+
"step": 22400
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.46206924877808353,
|
| 1581 |
+
"grad_norm": 0.4163651168346405,
|
| 1582 |
+
"learning_rate": 1.1549006520511374e-05,
|
| 1583 |
+
"loss": 2.3749,
|
| 1584 |
+
"step": 22500
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.46412288988376393,
|
| 1588 |
+
"grad_norm": 0.3156313896179199,
|
| 1589 |
+
"learning_rate": 1.1600349129742775e-05,
|
| 1590 |
+
"loss": 2.3828,
|
| 1591 |
+
"step": 22600
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.4661765309894443,
|
| 1595 |
+
"grad_norm": 0.3450685143470764,
|
| 1596 |
+
"learning_rate": 1.1651691738974175e-05,
|
| 1597 |
+
"loss": 2.3757,
|
| 1598 |
+
"step": 22700
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.46823017209512463,
|
| 1602 |
+
"grad_norm": 0.3975922167301178,
|
| 1603 |
+
"learning_rate": 1.1703034348205578e-05,
|
| 1604 |
+
"loss": 2.3781,
|
| 1605 |
+
"step": 22800
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.47028381320080503,
|
| 1609 |
+
"grad_norm": 0.3509731590747833,
|
| 1610 |
+
"learning_rate": 1.1754376957436976e-05,
|
| 1611 |
+
"loss": 2.3631,
|
| 1612 |
+
"step": 22900
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.4723374543064854,
|
| 1616 |
+
"grad_norm": 0.39486098289489746,
|
| 1617 |
+
"learning_rate": 1.1805719566668379e-05,
|
| 1618 |
+
"loss": 2.3611,
|
| 1619 |
+
"step": 23000
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.4743910954121658,
|
| 1623 |
+
"grad_norm": 0.36185601353645325,
|
| 1624 |
+
"learning_rate": 1.1857062175899781e-05,
|
| 1625 |
+
"loss": 2.3796,
|
| 1626 |
+
"step": 23100
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.47644473651784613,
|
| 1630 |
+
"grad_norm": 0.320353239774704,
|
| 1631 |
+
"learning_rate": 1.1908404785131182e-05,
|
| 1632 |
+
"loss": 2.3682,
|
| 1633 |
+
"step": 23200
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.47849837762352654,
|
| 1637 |
+
"grad_norm": 0.3344223201274872,
|
| 1638 |
+
"learning_rate": 1.1959747394362582e-05,
|
| 1639 |
+
"loss": 2.3697,
|
| 1640 |
+
"step": 23300
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.4805520187292069,
|
| 1644 |
+
"grad_norm": 0.3662751317024231,
|
| 1645 |
+
"learning_rate": 1.2011090003593983e-05,
|
| 1646 |
+
"loss": 2.3668,
|
| 1647 |
+
"step": 23400
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.48260565983488724,
|
| 1651 |
+
"grad_norm": 0.3565272092819214,
|
| 1652 |
+
"learning_rate": 1.2062432612825385e-05,
|
| 1653 |
+
"loss": 2.3736,
|
| 1654 |
+
"step": 23500
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.48465930094056764,
|
| 1658 |
+
"grad_norm": 0.3303636610507965,
|
| 1659 |
+
"learning_rate": 1.2113775222056784e-05,
|
| 1660 |
+
"loss": 2.3627,
|
| 1661 |
+
"step": 23600
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.486712942046248,
|
| 1665 |
+
"grad_norm": 0.36273279786109924,
|
| 1666 |
+
"learning_rate": 1.2164604405195872e-05,
|
| 1667 |
+
"loss": 2.3724,
|
| 1668 |
+
"step": 23700
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.4887665831519284,
|
| 1672 |
+
"grad_norm": 0.430507093667984,
|
| 1673 |
+
"learning_rate": 1.2215947014427275e-05,
|
| 1674 |
+
"loss": 2.3465,
|
| 1675 |
+
"step": 23800
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.49082022425760874,
|
| 1679 |
+
"grad_norm": 0.3049435019493103,
|
| 1680 |
+
"learning_rate": 1.2267289623658675e-05,
|
| 1681 |
+
"loss": 2.3556,
|
| 1682 |
+
"step": 23900
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.4928738653632891,
|
| 1686 |
+
"grad_norm": 0.3294410705566406,
|
| 1687 |
+
"learning_rate": 1.2318632232890078e-05,
|
| 1688 |
+
"loss": 2.3656,
|
| 1689 |
+
"step": 24000
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.4949275064689695,
|
| 1693 |
+
"grad_norm": 0.3687862753868103,
|
| 1694 |
+
"learning_rate": 1.2369974842121477e-05,
|
| 1695 |
+
"loss": 2.3528,
|
| 1696 |
+
"step": 24100
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.49698114757464984,
|
| 1700 |
+
"grad_norm": 0.4036162793636322,
|
| 1701 |
+
"learning_rate": 1.2421317451352879e-05,
|
| 1702 |
+
"loss": 2.3507,
|
| 1703 |
+
"step": 24200
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.49903478868033024,
|
| 1707 |
+
"grad_norm": 0.3792286813259125,
|
| 1708 |
+
"learning_rate": 1.2472660060584281e-05,
|
| 1709 |
+
"loss": 2.3791,
|
| 1710 |
+
"step": 24300
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.5010884297860106,
|
| 1714 |
+
"grad_norm": 0.3227761387825012,
|
| 1715 |
+
"learning_rate": 1.252400266981568e-05,
|
| 1716 |
+
"loss": 2.3642,
|
| 1717 |
+
"step": 24400
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.5031420708916909,
|
| 1721 |
+
"grad_norm": 0.36653387546539307,
|
| 1722 |
+
"learning_rate": 1.2575345279047082e-05,
|
| 1723 |
+
"loss": 2.3598,
|
| 1724 |
+
"step": 24500
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.5051957119973713,
|
| 1728 |
+
"grad_norm": 0.34727388620376587,
|
| 1729 |
+
"learning_rate": 1.2626687888278483e-05,
|
| 1730 |
+
"loss": 2.3413,
|
| 1731 |
+
"step": 24600
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.5072493531030517,
|
| 1735 |
+
"grad_norm": 0.3642292320728302,
|
| 1736 |
+
"learning_rate": 1.2678030497509885e-05,
|
| 1737 |
+
"loss": 2.3488,
|
| 1738 |
+
"step": 24700
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.509302994208732,
|
| 1742 |
+
"grad_norm": 0.41909259557724,
|
| 1743 |
+
"learning_rate": 1.2729373106741284e-05,
|
| 1744 |
+
"loss": 2.3545,
|
| 1745 |
+
"step": 24800
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.5113566353144124,
|
| 1749 |
+
"grad_norm": 0.36911770701408386,
|
| 1750 |
+
"learning_rate": 1.2780715715972687e-05,
|
| 1751 |
+
"loss": 2.3434,
|
| 1752 |
+
"step": 24900
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.5134102764200928,
|
| 1756 |
+
"grad_norm": 0.3182419538497925,
|
| 1757 |
+
"learning_rate": 1.2832058325204089e-05,
|
| 1758 |
+
"loss": 2.3643,
|
| 1759 |
+
"step": 25000
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.5154639175257731,
|
| 1763 |
+
"grad_norm": 0.3142630457878113,
|
| 1764 |
+
"learning_rate": 1.2883400934435488e-05,
|
| 1765 |
+
"loss": 2.347,
|
| 1766 |
+
"step": 25100
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.5175175586314535,
|
| 1770 |
+
"grad_norm": 0.3598061203956604,
|
| 1771 |
+
"learning_rate": 1.293474354366689e-05,
|
| 1772 |
+
"loss": 2.3668,
|
| 1773 |
+
"step": 25200
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.519571199737134,
|
| 1777 |
+
"grad_norm": 0.37434425950050354,
|
| 1778 |
+
"learning_rate": 1.2986086152898291e-05,
|
| 1779 |
+
"loss": 2.3516,
|
| 1780 |
+
"step": 25300
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.5216248408428144,
|
| 1784 |
+
"grad_norm": 0.317167729139328,
|
| 1785 |
+
"learning_rate": 1.3037428762129693e-05,
|
| 1786 |
+
"loss": 2.3568,
|
| 1787 |
+
"step": 25400
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.5236784819484946,
|
| 1791 |
+
"grad_norm": 0.3758144974708557,
|
| 1792 |
+
"learning_rate": 1.3088771371361094e-05,
|
| 1793 |
+
"loss": 2.3596,
|
| 1794 |
+
"step": 25500
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.525732123054175,
|
| 1798 |
+
"grad_norm": 0.36871057748794556,
|
| 1799 |
+
"learning_rate": 1.3140113980592495e-05,
|
| 1800 |
+
"loss": 2.3531,
|
| 1801 |
+
"step": 25600
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.5277857641598555,
|
| 1805 |
+
"grad_norm": 0.3507154583930969,
|
| 1806 |
+
"learning_rate": 1.3190943163731583e-05,
|
| 1807 |
+
"loss": 2.3371,
|
| 1808 |
+
"step": 25700
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.5298394052655357,
|
| 1812 |
+
"grad_norm": 0.34643495082855225,
|
| 1813 |
+
"learning_rate": 1.3242285772962983e-05,
|
| 1814 |
+
"loss": 2.3632,
|
| 1815 |
+
"step": 25800
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.5318930463712161,
|
| 1819 |
+
"grad_norm": 0.3581657111644745,
|
| 1820 |
+
"learning_rate": 1.3293628382194384e-05,
|
| 1821 |
+
"loss": 2.3514,
|
| 1822 |
+
"step": 25900
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.5339466874768966,
|
| 1826 |
+
"grad_norm": 0.3276652693748474,
|
| 1827 |
+
"learning_rate": 1.3344970991425784e-05,
|
| 1828 |
+
"loss": 2.3538,
|
| 1829 |
+
"step": 26000
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.536000328582577,
|
| 1833 |
+
"grad_norm": 0.41689813137054443,
|
| 1834 |
+
"learning_rate": 1.3395800174564872e-05,
|
| 1835 |
+
"loss": 2.348,
|
| 1836 |
+
"step": 26100
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.5380539696882572,
|
| 1840 |
+
"grad_norm": 0.36025965213775635,
|
| 1841 |
+
"learning_rate": 1.3447142783796275e-05,
|
| 1842 |
+
"loss": 2.3424,
|
| 1843 |
+
"step": 26200
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.5401076107939377,
|
| 1847 |
+
"grad_norm": 0.332599401473999,
|
| 1848 |
+
"learning_rate": 1.3498485393027674e-05,
|
| 1849 |
+
"loss": 2.3403,
|
| 1850 |
+
"step": 26300
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.5421612518996181,
|
| 1854 |
+
"grad_norm": 0.347744345664978,
|
| 1855 |
+
"learning_rate": 1.3549828002259076e-05,
|
| 1856 |
+
"loss": 2.347,
|
| 1857 |
+
"step": 26400
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.5442148930052984,
|
| 1861 |
+
"grad_norm": 0.3268183469772339,
|
| 1862 |
+
"learning_rate": 1.3601170611490477e-05,
|
| 1863 |
+
"loss": 2.3481,
|
| 1864 |
+
"step": 26500
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.5462685341109788,
|
| 1868 |
+
"grad_norm": 0.33261337876319885,
|
| 1869 |
+
"learning_rate": 1.3652513220721879e-05,
|
| 1870 |
+
"loss": 2.3386,
|
| 1871 |
+
"step": 26600
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.5483221752166592,
|
| 1875 |
+
"grad_norm": 0.300615131855011,
|
| 1876 |
+
"learning_rate": 1.3703855829953278e-05,
|
| 1877 |
+
"loss": 2.3514,
|
| 1878 |
+
"step": 26700
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.5503758163223396,
|
| 1882 |
+
"grad_norm": 0.3238273859024048,
|
| 1883 |
+
"learning_rate": 1.375519843918468e-05,
|
| 1884 |
+
"loss": 2.3482,
|
| 1885 |
+
"step": 26800
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.5524294574280199,
|
| 1889 |
+
"grad_norm": 0.3851374685764313,
|
| 1890 |
+
"learning_rate": 1.3806541048416083e-05,
|
| 1891 |
+
"loss": 2.3439,
|
| 1892 |
+
"step": 26900
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.5544830985337003,
|
| 1896 |
+
"grad_norm": 0.3803921937942505,
|
| 1897 |
+
"learning_rate": 1.3857883657647482e-05,
|
| 1898 |
+
"loss": 2.3394,
|
| 1899 |
+
"step": 27000
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.5565367396393807,
|
| 1903 |
+
"grad_norm": 0.2982763648033142,
|
| 1904 |
+
"learning_rate": 1.3909226266878884e-05,
|
| 1905 |
+
"loss": 2.3542,
|
| 1906 |
+
"step": 27100
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.558590380745061,
|
| 1910 |
+
"grad_norm": 0.3701958954334259,
|
| 1911 |
+
"learning_rate": 1.3960568876110285e-05,
|
| 1912 |
+
"loss": 2.332,
|
| 1913 |
+
"step": 27200
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.5606440218507414,
|
| 1917 |
+
"grad_norm": 0.3478206694126129,
|
| 1918 |
+
"learning_rate": 1.4011911485341687e-05,
|
| 1919 |
+
"loss": 2.3519,
|
| 1920 |
+
"step": 27300
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.5626976629564218,
|
| 1924 |
+
"grad_norm": 0.3451727628707886,
|
| 1925 |
+
"learning_rate": 1.4063254094573087e-05,
|
| 1926 |
+
"loss": 2.3408,
|
| 1927 |
+
"step": 27400
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.564751304062102,
|
| 1931 |
+
"grad_norm": 0.3585469722747803,
|
| 1932 |
+
"learning_rate": 1.4114596703804488e-05,
|
| 1933 |
+
"loss": 2.3339,
|
| 1934 |
+
"step": 27500
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.5668049451677825,
|
| 1938 |
+
"grad_norm": 0.33733317255973816,
|
| 1939 |
+
"learning_rate": 1.416593931303589e-05,
|
| 1940 |
+
"loss": 2.3337,
|
| 1941 |
+
"step": 27600
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.5688585862734629,
|
| 1945 |
+
"grad_norm": 0.3282623887062073,
|
| 1946 |
+
"learning_rate": 1.421728192226729e-05,
|
| 1947 |
+
"loss": 2.3476,
|
| 1948 |
+
"step": 27700
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.5709122273791433,
|
| 1952 |
+
"grad_norm": 0.3337123394012451,
|
| 1953 |
+
"learning_rate": 1.4268624531498692e-05,
|
| 1954 |
+
"loss": 2.3231,
|
| 1955 |
+
"step": 27800
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.5729658684848236,
|
| 1959 |
+
"grad_norm": 0.3303765058517456,
|
| 1960 |
+
"learning_rate": 1.4319967140730094e-05,
|
| 1961 |
+
"loss": 2.3405,
|
| 1962 |
+
"step": 27900
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.575019509590504,
|
| 1966 |
+
"grad_norm": 0.33878931403160095,
|
| 1967 |
+
"learning_rate": 1.4371309749961495e-05,
|
| 1968 |
+
"loss": 2.3241,
|
| 1969 |
+
"step": 28000
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.5770731506961844,
|
| 1973 |
+
"grad_norm": 0.413727730512619,
|
| 1974 |
+
"learning_rate": 1.4422652359192895e-05,
|
| 1975 |
+
"loss": 2.3351,
|
| 1976 |
+
"step": 28100
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.5791267918018647,
|
| 1980 |
+
"grad_norm": 0.3310682475566864,
|
| 1981 |
+
"learning_rate": 1.4473994968424296e-05,
|
| 1982 |
+
"loss": 2.3514,
|
| 1983 |
+
"step": 28200
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.5811804329075451,
|
| 1987 |
+
"grad_norm": 0.3990001678466797,
|
| 1988 |
+
"learning_rate": 1.4525337577655698e-05,
|
| 1989 |
+
"loss": 2.3507,
|
| 1990 |
+
"step": 28300
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.5832340740132255,
|
| 1994 |
+
"grad_norm": 0.3185250759124756,
|
| 1995 |
+
"learning_rate": 1.4576680186887097e-05,
|
| 1996 |
+
"loss": 2.346,
|
| 1997 |
+
"step": 28400
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.5852877151189059,
|
| 2001 |
+
"grad_norm": 0.3528919219970703,
|
| 2002 |
+
"learning_rate": 1.46280227961185e-05,
|
| 2003 |
+
"loss": 2.3332,
|
| 2004 |
+
"step": 28500
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.5873413562245862,
|
| 2008 |
+
"grad_norm": 0.33269989490509033,
|
| 2009 |
+
"learning_rate": 1.4679365405349902e-05,
|
| 2010 |
+
"loss": 2.3452,
|
| 2011 |
+
"step": 28600
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.5893949973302666,
|
| 2015 |
+
"grad_norm": 0.32537370920181274,
|
| 2016 |
+
"learning_rate": 1.4730708014581303e-05,
|
| 2017 |
+
"loss": 2.3348,
|
| 2018 |
+
"step": 28700
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.591448638435947,
|
| 2022 |
+
"grad_norm": 0.3389699459075928,
|
| 2023 |
+
"learning_rate": 1.4782050623812703e-05,
|
| 2024 |
+
"loss": 2.3358,
|
| 2025 |
+
"step": 28800
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.5935022795416273,
|
| 2029 |
+
"grad_norm": 0.31307852268218994,
|
| 2030 |
+
"learning_rate": 1.4833393233044104e-05,
|
| 2031 |
+
"loss": 2.3385,
|
| 2032 |
+
"step": 28900
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.5955559206473077,
|
| 2036 |
+
"grad_norm": 0.31487369537353516,
|
| 2037 |
+
"learning_rate": 1.4884735842275506e-05,
|
| 2038 |
+
"loss": 2.3348,
|
| 2039 |
+
"step": 29000
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.5976095617529881,
|
| 2043 |
+
"grad_norm": 0.3001077473163605,
|
| 2044 |
+
"learning_rate": 1.4936078451506905e-05,
|
| 2045 |
+
"loss": 2.3345,
|
| 2046 |
+
"step": 29100
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.5996632028586684,
|
| 2050 |
+
"grad_norm": 0.341888427734375,
|
| 2051 |
+
"learning_rate": 1.4987421060738307e-05,
|
| 2052 |
+
"loss": 2.3317,
|
| 2053 |
+
"step": 29200
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.6017168439643488,
|
| 2057 |
+
"grad_norm": 0.27773818373680115,
|
| 2058 |
+
"learning_rate": 1.503876366996971e-05,
|
| 2059 |
+
"loss": 2.3308,
|
| 2060 |
+
"step": 29300
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.6037704850700292,
|
| 2064 |
+
"grad_norm": 0.3100406527519226,
|
| 2065 |
+
"learning_rate": 1.509010627920111e-05,
|
| 2066 |
+
"loss": 2.3262,
|
| 2067 |
+
"step": 29400
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.6058241261757096,
|
| 2071 |
+
"grad_norm": 0.32779422402381897,
|
| 2072 |
+
"learning_rate": 1.5141448888432511e-05,
|
| 2073 |
+
"loss": 2.3241,
|
| 2074 |
+
"step": 29500
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.6078777672813899,
|
| 2078 |
+
"grad_norm": 0.31545841693878174,
|
| 2079 |
+
"learning_rate": 1.5192791497663912e-05,
|
| 2080 |
+
"loss": 2.3376,
|
| 2081 |
+
"step": 29600
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.6099314083870703,
|
| 2085 |
+
"grad_norm": 0.29925644397735596,
|
| 2086 |
+
"learning_rate": 1.5244134106895314e-05,
|
| 2087 |
+
"loss": 2.348,
|
| 2088 |
+
"step": 29700
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.6119850494927507,
|
| 2092 |
+
"grad_norm": 0.3336638808250427,
|
| 2093 |
+
"learning_rate": 1.5295476716126716e-05,
|
| 2094 |
+
"loss": 2.308,
|
| 2095 |
+
"step": 29800
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.614038690598431,
|
| 2099 |
+
"grad_norm": 0.34575214982032776,
|
| 2100 |
+
"learning_rate": 1.5346819325358117e-05,
|
| 2101 |
+
"loss": 2.3302,
|
| 2102 |
+
"step": 29900
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.6160923317041114,
|
| 2106 |
+
"grad_norm": 0.3727119565010071,
|
| 2107 |
+
"learning_rate": 1.5398161934589518e-05,
|
| 2108 |
+
"loss": 2.341,
|
| 2109 |
+
"step": 30000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.6181459728097918,
|
| 2113 |
+
"grad_norm": 0.3629727363586426,
|
| 2114 |
+
"learning_rate": 1.5448991117728604e-05,
|
| 2115 |
+
"loss": 2.3495,
|
| 2116 |
+
"step": 30100
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.6201996139154722,
|
| 2120 |
+
"grad_norm": 0.3435654938220978,
|
| 2121 |
+
"learning_rate": 1.5500333726960008e-05,
|
| 2122 |
+
"loss": 2.324,
|
| 2123 |
+
"step": 30200
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.6222532550211525,
|
| 2127 |
+
"grad_norm": 0.31150856614112854,
|
| 2128 |
+
"learning_rate": 1.5551676336191405e-05,
|
| 2129 |
+
"loss": 2.3377,
|
| 2130 |
+
"step": 30300
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.6243068961268329,
|
| 2134 |
+
"grad_norm": 0.34640446305274963,
|
| 2135 |
+
"learning_rate": 1.560301894542281e-05,
|
| 2136 |
+
"loss": 2.3409,
|
| 2137 |
+
"step": 30400
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.6263605372325133,
|
| 2141 |
+
"grad_norm": 0.3132672607898712,
|
| 2142 |
+
"learning_rate": 1.565436155465421e-05,
|
| 2143 |
+
"loss": 2.3134,
|
| 2144 |
+
"step": 30500
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.6284141783381936,
|
| 2148 |
+
"grad_norm": 0.30333834886550903,
|
| 2149 |
+
"learning_rate": 1.570570416388561e-05,
|
| 2150 |
+
"loss": 2.3184,
|
| 2151 |
+
"step": 30600
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.630467819443874,
|
| 2155 |
+
"grad_norm": 0.33071044087409973,
|
| 2156 |
+
"learning_rate": 1.575704677311701e-05,
|
| 2157 |
+
"loss": 2.3179,
|
| 2158 |
+
"step": 30700
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.6325214605495544,
|
| 2162 |
+
"grad_norm": 0.36644718050956726,
|
| 2163 |
+
"learning_rate": 1.5807875956256097e-05,
|
| 2164 |
+
"loss": 2.3192,
|
| 2165 |
+
"step": 30800
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.6345751016552348,
|
| 2169 |
+
"grad_norm": 0.35669848322868347,
|
| 2170 |
+
"learning_rate": 1.58592185654875e-05,
|
| 2171 |
+
"loss": 2.3148,
|
| 2172 |
+
"step": 30900
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.6366287427609151,
|
| 2176 |
+
"grad_norm": 0.38791370391845703,
|
| 2177 |
+
"learning_rate": 1.5910561174718902e-05,
|
| 2178 |
+
"loss": 2.3363,
|
| 2179 |
+
"step": 31000
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.6386823838665955,
|
| 2183 |
+
"grad_norm": 0.3058807849884033,
|
| 2184 |
+
"learning_rate": 1.5961903783950303e-05,
|
| 2185 |
+
"loss": 2.3166,
|
| 2186 |
+
"step": 31100
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.6407360249722759,
|
| 2190 |
+
"grad_norm": 0.322482705116272,
|
| 2191 |
+
"learning_rate": 1.6013246393181703e-05,
|
| 2192 |
+
"loss": 2.3303,
|
| 2193 |
+
"step": 31200
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.6427896660779562,
|
| 2197 |
+
"grad_norm": 0.3512401580810547,
|
| 2198 |
+
"learning_rate": 1.6064589002413104e-05,
|
| 2199 |
+
"loss": 2.3381,
|
| 2200 |
+
"step": 31300
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.6448433071836366,
|
| 2204 |
+
"grad_norm": 0.2774820327758789,
|
| 2205 |
+
"learning_rate": 1.6115931611644505e-05,
|
| 2206 |
+
"loss": 2.3118,
|
| 2207 |
+
"step": 31400
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.646896948289317,
|
| 2211 |
+
"grad_norm": 0.3425484895706177,
|
| 2212 |
+
"learning_rate": 1.6167274220875905e-05,
|
| 2213 |
+
"loss": 2.3157,
|
| 2214 |
+
"step": 31500
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.6489505893949973,
|
| 2218 |
+
"grad_norm": 0.29664793610572815,
|
| 2219 |
+
"learning_rate": 1.621861683010731e-05,
|
| 2220 |
+
"loss": 2.3329,
|
| 2221 |
+
"step": 31600
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.6510042305006777,
|
| 2225 |
+
"grad_norm": 0.30625107884407043,
|
| 2226 |
+
"learning_rate": 1.626995943933871e-05,
|
| 2227 |
+
"loss": 2.3201,
|
| 2228 |
+
"step": 31700
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.6530578716063581,
|
| 2232 |
+
"grad_norm": 0.3507521152496338,
|
| 2233 |
+
"learning_rate": 1.632130204857011e-05,
|
| 2234 |
+
"loss": 2.3356,
|
| 2235 |
+
"step": 31800
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.6551115127120385,
|
| 2239 |
+
"grad_norm": 0.30985724925994873,
|
| 2240 |
+
"learning_rate": 1.637264465780151e-05,
|
| 2241 |
+
"loss": 2.3282,
|
| 2242 |
+
"step": 31900
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.6571651538177188,
|
| 2246 |
+
"grad_norm": 0.28693100810050964,
|
| 2247 |
+
"learning_rate": 1.6423987267032912e-05,
|
| 2248 |
+
"loss": 2.32,
|
| 2249 |
+
"step": 32000
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.6592187949233992,
|
| 2253 |
+
"grad_norm": 0.32145893573760986,
|
| 2254 |
+
"learning_rate": 1.6475329876264312e-05,
|
| 2255 |
+
"loss": 2.3205,
|
| 2256 |
+
"step": 32100
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.6612724360290796,
|
| 2260 |
+
"grad_norm": 0.31438565254211426,
|
| 2261 |
+
"learning_rate": 1.6526672485495713e-05,
|
| 2262 |
+
"loss": 2.3278,
|
| 2263 |
+
"step": 32200
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.6633260771347599,
|
| 2267 |
+
"grad_norm": 0.35508400201797485,
|
| 2268 |
+
"learning_rate": 1.6578015094727117e-05,
|
| 2269 |
+
"loss": 2.3163,
|
| 2270 |
+
"step": 32300
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.6653797182404403,
|
| 2274 |
+
"grad_norm": 0.3731987774372101,
|
| 2275 |
+
"learning_rate": 1.6629357703958518e-05,
|
| 2276 |
+
"loss": 2.3145,
|
| 2277 |
+
"step": 32400
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.6674333593461207,
|
| 2281 |
+
"grad_norm": 0.4086899161338806,
|
| 2282 |
+
"learning_rate": 1.668070031318992e-05,
|
| 2283 |
+
"loss": 2.3116,
|
| 2284 |
+
"step": 32500
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.6694870004518011,
|
| 2288 |
+
"grad_norm": 0.30360934138298035,
|
| 2289 |
+
"learning_rate": 1.673204292242132e-05,
|
| 2290 |
+
"loss": 2.3254,
|
| 2291 |
+
"step": 32600
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.6715406415574814,
|
| 2295 |
+
"grad_norm": 0.2974546551704407,
|
| 2296 |
+
"learning_rate": 1.678338553165272e-05,
|
| 2297 |
+
"loss": 2.3108,
|
| 2298 |
+
"step": 32700
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.6735942826631618,
|
| 2302 |
+
"grad_norm": 0.2781977653503418,
|
| 2303 |
+
"learning_rate": 1.683472814088412e-05,
|
| 2304 |
+
"loss": 2.3185,
|
| 2305 |
+
"step": 32800
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.6756479237688422,
|
| 2309 |
+
"grad_norm": 0.27183133363723755,
|
| 2310 |
+
"learning_rate": 1.688607075011552e-05,
|
| 2311 |
+
"loss": 2.323,
|
| 2312 |
+
"step": 32900
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.6777015648745225,
|
| 2316 |
+
"grad_norm": 0.31458455324172974,
|
| 2317 |
+
"learning_rate": 1.6937413359346925e-05,
|
| 2318 |
+
"loss": 2.3341,
|
| 2319 |
+
"step": 33000
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.6797552059802029,
|
| 2323 |
+
"grad_norm": 0.2890998125076294,
|
| 2324 |
+
"learning_rate": 1.6988755968578326e-05,
|
| 2325 |
+
"loss": 2.3303,
|
| 2326 |
+
"step": 33100
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.6818088470858833,
|
| 2330 |
+
"grad_norm": 0.3643539249897003,
|
| 2331 |
+
"learning_rate": 1.7040098577809726e-05,
|
| 2332 |
+
"loss": 2.3245,
|
| 2333 |
+
"step": 33200
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.6838624881915636,
|
| 2337 |
+
"grad_norm": 0.3139105439186096,
|
| 2338 |
+
"learning_rate": 1.7091441187041127e-05,
|
| 2339 |
+
"loss": 2.3326,
|
| 2340 |
+
"step": 33300
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.685916129297244,
|
| 2344 |
+
"grad_norm": 0.3779376447200775,
|
| 2345 |
+
"learning_rate": 1.7142783796272527e-05,
|
| 2346 |
+
"loss": 2.3172,
|
| 2347 |
+
"step": 33400
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.6879697704029244,
|
| 2351 |
+
"grad_norm": 0.33126363158226013,
|
| 2352 |
+
"learning_rate": 1.7194126405503928e-05,
|
| 2353 |
+
"loss": 2.2988,
|
| 2354 |
+
"step": 33500
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.6900234115086048,
|
| 2358 |
+
"grad_norm": 0.30163052678108215,
|
| 2359 |
+
"learning_rate": 1.724546901473533e-05,
|
| 2360 |
+
"loss": 2.3168,
|
| 2361 |
+
"step": 33600
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.6920770526142851,
|
| 2365 |
+
"grad_norm": 0.27880924940109253,
|
| 2366 |
+
"learning_rate": 1.7296811623966733e-05,
|
| 2367 |
+
"loss": 2.332,
|
| 2368 |
+
"step": 33700
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.6941306937199655,
|
| 2372 |
+
"grad_norm": 0.35442423820495605,
|
| 2373 |
+
"learning_rate": 1.7348154233198133e-05,
|
| 2374 |
+
"loss": 2.3135,
|
| 2375 |
+
"step": 33800
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.6961843348256459,
|
| 2379 |
+
"grad_norm": 0.5074792504310608,
|
| 2380 |
+
"learning_rate": 1.7399496842429534e-05,
|
| 2381 |
+
"loss": 2.3044,
|
| 2382 |
+
"step": 33900
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.6982379759313262,
|
| 2386 |
+
"grad_norm": 0.3344689905643463,
|
| 2387 |
+
"learning_rate": 1.7450839451660935e-05,
|
| 2388 |
+
"loss": 2.3233,
|
| 2389 |
+
"step": 34000
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.7002916170370066,
|
| 2393 |
+
"grad_norm": 0.3612523078918457,
|
| 2394 |
+
"learning_rate": 1.7502182060892335e-05,
|
| 2395 |
+
"loss": 2.3131,
|
| 2396 |
+
"step": 34100
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.702345258142687,
|
| 2400 |
+
"grad_norm": 0.3519062399864197,
|
| 2401 |
+
"learning_rate": 1.7553524670123736e-05,
|
| 2402 |
+
"loss": 2.3149,
|
| 2403 |
+
"step": 34200
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.7043988992483674,
|
| 2407 |
+
"grad_norm": 0.3331790566444397,
|
| 2408 |
+
"learning_rate": 1.7604867279355137e-05,
|
| 2409 |
+
"loss": 2.3112,
|
| 2410 |
+
"step": 34300
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.7064525403540477,
|
| 2414 |
+
"grad_norm": 0.31473588943481445,
|
| 2415 |
+
"learning_rate": 1.765620988858654e-05,
|
| 2416 |
+
"loss": 2.3192,
|
| 2417 |
+
"step": 34400
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.7085061814597281,
|
| 2421 |
+
"grad_norm": 0.33996033668518066,
|
| 2422 |
+
"learning_rate": 1.770755249781794e-05,
|
| 2423 |
+
"loss": 2.3192,
|
| 2424 |
+
"step": 34500
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.7105598225654085,
|
| 2428 |
+
"grad_norm": 0.3652447462081909,
|
| 2429 |
+
"learning_rate": 1.7758895107049342e-05,
|
| 2430 |
+
"loss": 2.3317,
|
| 2431 |
+
"step": 34600
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.7126134636710888,
|
| 2435 |
+
"grad_norm": 0.3270864188671112,
|
| 2436 |
+
"learning_rate": 1.7810237716280742e-05,
|
| 2437 |
+
"loss": 2.2942,
|
| 2438 |
+
"step": 34700
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.7146671047767692,
|
| 2442 |
+
"grad_norm": 0.29053524136543274,
|
| 2443 |
+
"learning_rate": 1.7861580325512143e-05,
|
| 2444 |
+
"loss": 2.3198,
|
| 2445 |
+
"step": 34800
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.7167207458824496,
|
| 2449 |
+
"grad_norm": 0.2877756655216217,
|
| 2450 |
+
"learning_rate": 1.7912409508651233e-05,
|
| 2451 |
+
"loss": 2.3018,
|
| 2452 |
+
"step": 34900
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.71877438698813,
|
| 2456 |
+
"grad_norm": 0.31412777304649353,
|
| 2457 |
+
"learning_rate": 1.796375211788263e-05,
|
| 2458 |
+
"loss": 2.3233,
|
| 2459 |
+
"step": 35000
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.7208280280938103,
|
| 2463 |
+
"grad_norm": 0.320453405380249,
|
| 2464 |
+
"learning_rate": 1.8015094727114034e-05,
|
| 2465 |
+
"loss": 2.3101,
|
| 2466 |
+
"step": 35100
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.7228816691994907,
|
| 2470 |
+
"grad_norm": 0.3189476728439331,
|
| 2471 |
+
"learning_rate": 1.8066437336345435e-05,
|
| 2472 |
+
"loss": 2.2944,
|
| 2473 |
+
"step": 35200
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.7249353103051711,
|
| 2477 |
+
"grad_norm": 0.34689202904701233,
|
| 2478 |
+
"learning_rate": 1.8117779945576835e-05,
|
| 2479 |
+
"loss": 2.3124,
|
| 2480 |
+
"step": 35300
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.7269889514108514,
|
| 2484 |
+
"grad_norm": 0.2810226082801819,
|
| 2485 |
+
"learning_rate": 1.8169122554808236e-05,
|
| 2486 |
+
"loss": 2.3175,
|
| 2487 |
+
"step": 35400
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.7290425925165318,
|
| 2491 |
+
"grad_norm": 0.32906574010849,
|
| 2492 |
+
"learning_rate": 1.8220465164039637e-05,
|
| 2493 |
+
"loss": 2.3065,
|
| 2494 |
+
"step": 35500
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.7310962336222122,
|
| 2498 |
+
"grad_norm": 0.294303834438324,
|
| 2499 |
+
"learning_rate": 1.827180777327104e-05,
|
| 2500 |
+
"loss": 2.302,
|
| 2501 |
+
"step": 35600
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.7331498747278925,
|
| 2505 |
+
"grad_norm": 0.3125101625919342,
|
| 2506 |
+
"learning_rate": 1.8323150382502438e-05,
|
| 2507 |
+
"loss": 2.327,
|
| 2508 |
+
"step": 35700
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.7352035158335729,
|
| 2512 |
+
"grad_norm": 0.2892644703388214,
|
| 2513 |
+
"learning_rate": 1.8374492991733842e-05,
|
| 2514 |
+
"loss": 2.2907,
|
| 2515 |
+
"step": 35800
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.7372571569392533,
|
| 2519 |
+
"grad_norm": 0.2948015034198761,
|
| 2520 |
+
"learning_rate": 1.8425835600965243e-05,
|
| 2521 |
+
"loss": 2.3028,
|
| 2522 |
+
"step": 35900
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.7393107980449337,
|
| 2526 |
+
"grad_norm": 0.4089581072330475,
|
| 2527 |
+
"learning_rate": 1.8477178210196643e-05,
|
| 2528 |
+
"loss": 2.305,
|
| 2529 |
+
"step": 36000
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.741364439150614,
|
| 2533 |
+
"grad_norm": 0.3298622667789459,
|
| 2534 |
+
"learning_rate": 1.8528520819428044e-05,
|
| 2535 |
+
"loss": 2.3046,
|
| 2536 |
+
"step": 36100
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.7434180802562944,
|
| 2540 |
+
"grad_norm": 0.2934931516647339,
|
| 2541 |
+
"learning_rate": 1.8579863428659444e-05,
|
| 2542 |
+
"loss": 2.3157,
|
| 2543 |
+
"step": 36200
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.7454717213619748,
|
| 2547 |
+
"grad_norm": 0.2937401831150055,
|
| 2548 |
+
"learning_rate": 1.863120603789085e-05,
|
| 2549 |
+
"loss": 2.3182,
|
| 2550 |
+
"step": 36300
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.7475253624676551,
|
| 2554 |
+
"grad_norm": 0.28882211446762085,
|
| 2555 |
+
"learning_rate": 1.8682548647122246e-05,
|
| 2556 |
+
"loss": 2.2937,
|
| 2557 |
+
"step": 36400
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.7495790035733355,
|
| 2561 |
+
"grad_norm": 0.3334536552429199,
|
| 2562 |
+
"learning_rate": 1.873389125635365e-05,
|
| 2563 |
+
"loss": 2.2891,
|
| 2564 |
+
"step": 36500
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.7516326446790159,
|
| 2568 |
+
"grad_norm": 0.3489097058773041,
|
| 2569 |
+
"learning_rate": 1.878523386558505e-05,
|
| 2570 |
+
"loss": 2.2966,
|
| 2571 |
+
"step": 36600
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.7536862857846963,
|
| 2575 |
+
"grad_norm": 0.31993556022644043,
|
| 2576 |
+
"learning_rate": 1.883657647481645e-05,
|
| 2577 |
+
"loss": 2.3081,
|
| 2578 |
+
"step": 36700
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.7557399268903766,
|
| 2582 |
+
"grad_norm": 0.3145769238471985,
|
| 2583 |
+
"learning_rate": 1.888791908404785e-05,
|
| 2584 |
+
"loss": 2.3104,
|
| 2585 |
+
"step": 36800
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.757793567996057,
|
| 2589 |
+
"grad_norm": 0.3455965220928192,
|
| 2590 |
+
"learning_rate": 1.8939261693279252e-05,
|
| 2591 |
+
"loss": 2.3081,
|
| 2592 |
+
"step": 36900
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.7598472091017374,
|
| 2596 |
+
"grad_norm": 0.2940099835395813,
|
| 2597 |
+
"learning_rate": 1.8990604302510656e-05,
|
| 2598 |
+
"loss": 2.3026,
|
| 2599 |
+
"step": 37000
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.7619008502074177,
|
| 2603 |
+
"grad_norm": 0.27472448348999023,
|
| 2604 |
+
"learning_rate": 1.9041946911742054e-05,
|
| 2605 |
+
"loss": 2.3133,
|
| 2606 |
+
"step": 37100
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.7639544913130981,
|
| 2610 |
+
"grad_norm": 0.3036133348941803,
|
| 2611 |
+
"learning_rate": 1.9093289520973458e-05,
|
| 2612 |
+
"loss": 2.2992,
|
| 2613 |
+
"step": 37200
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.7660081324187785,
|
| 2617 |
+
"grad_norm": 0.37697499990463257,
|
| 2618 |
+
"learning_rate": 1.9144632130204858e-05,
|
| 2619 |
+
"loss": 2.2862,
|
| 2620 |
+
"step": 37300
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.7680617735244588,
|
| 2624 |
+
"grad_norm": 0.29148775339126587,
|
| 2625 |
+
"learning_rate": 1.919597473943626e-05,
|
| 2626 |
+
"loss": 2.3029,
|
| 2627 |
+
"step": 37400
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.7701154146301392,
|
| 2631 |
+
"grad_norm": 0.33674708008766174,
|
| 2632 |
+
"learning_rate": 1.924680392257535e-05,
|
| 2633 |
+
"loss": 2.296,
|
| 2634 |
+
"step": 37500
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.7721690557358196,
|
| 2638 |
+
"grad_norm": 0.2859843075275421,
|
| 2639 |
+
"learning_rate": 1.9298146531806746e-05,
|
| 2640 |
+
"loss": 2.2987,
|
| 2641 |
+
"step": 37600
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.7742226968415,
|
| 2645 |
+
"grad_norm": 0.31656181812286377,
|
| 2646 |
+
"learning_rate": 1.934948914103815e-05,
|
| 2647 |
+
"loss": 2.2994,
|
| 2648 |
+
"step": 37700
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.7762763379471803,
|
| 2652 |
+
"grad_norm": 0.3428076207637787,
|
| 2653 |
+
"learning_rate": 1.940083175026955e-05,
|
| 2654 |
+
"loss": 2.3095,
|
| 2655 |
+
"step": 37800
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.7783299790528607,
|
| 2659 |
+
"grad_norm": 0.2949564456939697,
|
| 2660 |
+
"learning_rate": 1.945217435950095e-05,
|
| 2661 |
+
"loss": 2.312,
|
| 2662 |
+
"step": 37900
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.7803836201585411,
|
| 2666 |
+
"grad_norm": 0.3242889940738678,
|
| 2667 |
+
"learning_rate": 1.9503516968732352e-05,
|
| 2668 |
+
"loss": 2.2805,
|
| 2669 |
+
"step": 38000
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.7824372612642214,
|
| 2673 |
+
"grad_norm": 0.272155225276947,
|
| 2674 |
+
"learning_rate": 1.9554859577963752e-05,
|
| 2675 |
+
"loss": 2.2828,
|
| 2676 |
+
"step": 38100
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.7844909023699018,
|
| 2680 |
+
"grad_norm": 0.26965823769569397,
|
| 2681 |
+
"learning_rate": 1.9606202187195156e-05,
|
| 2682 |
+
"loss": 2.3056,
|
| 2683 |
+
"step": 38200
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.7865445434755822,
|
| 2687 |
+
"grad_norm": 0.3355703353881836,
|
| 2688 |
+
"learning_rate": 1.9657544796426557e-05,
|
| 2689 |
+
"loss": 2.2918,
|
| 2690 |
+
"step": 38300
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.7885981845812626,
|
| 2694 |
+
"grad_norm": 0.3137889802455902,
|
| 2695 |
+
"learning_rate": 1.9708887405657958e-05,
|
| 2696 |
+
"loss": 2.3035,
|
| 2697 |
+
"step": 38400
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.7906518256869429,
|
| 2701 |
+
"grad_norm": 0.3009161055088043,
|
| 2702 |
+
"learning_rate": 1.9760230014889358e-05,
|
| 2703 |
+
"loss": 2.2846,
|
| 2704 |
+
"step": 38500
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.7927054667926233,
|
| 2708 |
+
"grad_norm": 0.3273535370826721,
|
| 2709 |
+
"learning_rate": 1.981157262412076e-05,
|
| 2710 |
+
"loss": 2.2979,
|
| 2711 |
+
"step": 38600
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.7947591078983037,
|
| 2715 |
+
"grad_norm": 0.3200952410697937,
|
| 2716 |
+
"learning_rate": 1.986291523335216e-05,
|
| 2717 |
+
"loss": 2.2958,
|
| 2718 |
+
"step": 38700
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.796812749003984,
|
| 2722 |
+
"grad_norm": 0.2996315062046051,
|
| 2723 |
+
"learning_rate": 1.9914257842583564e-05,
|
| 2724 |
+
"loss": 2.3025,
|
| 2725 |
+
"step": 38800
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.7988663901096644,
|
| 2729 |
+
"grad_norm": 0.3265666365623474,
|
| 2730 |
+
"learning_rate": 1.9965600451814964e-05,
|
| 2731 |
+
"loss": 2.289,
|
| 2732 |
+
"step": 38900
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.8009200312153448,
|
| 2736 |
+
"grad_norm": 0.28108805418014526,
|
| 2737 |
+
"learning_rate": 1.9999433531694762e-05,
|
| 2738 |
+
"loss": 2.2814,
|
| 2739 |
+
"step": 39000
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.8029736723210251,
|
| 2743 |
+
"grad_norm": 0.30217304825782776,
|
| 2744 |
+
"learning_rate": 1.9990799985438364e-05,
|
| 2745 |
+
"loss": 2.2932,
|
| 2746 |
+
"step": 39100
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.8050273134267055,
|
| 2750 |
+
"grad_norm": 0.2876952290534973,
|
| 2751 |
+
"learning_rate": 1.9971773355021205e-05,
|
| 2752 |
+
"loss": 2.3049,
|
| 2753 |
+
"step": 39200
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.8070809545323859,
|
| 2757 |
+
"grad_norm": 0.35703495144844055,
|
| 2758 |
+
"learning_rate": 1.994237343318977e-05,
|
| 2759 |
+
"loss": 2.2847,
|
| 2760 |
+
"step": 39300
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 0.8091345956380663,
|
| 2764 |
+
"grad_norm": 0.34101271629333496,
|
| 2765 |
+
"learning_rate": 1.9902630803667314e-05,
|
| 2766 |
+
"loss": 2.3025,
|
| 2767 |
+
"step": 39400
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.8111882367437466,
|
| 2771 |
+
"grad_norm": 0.31167465448379517,
|
| 2772 |
+
"learning_rate": 1.985258680933869e-05,
|
| 2773 |
+
"loss": 2.2989,
|
| 2774 |
+
"step": 39500
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.813241877849427,
|
| 2778 |
+
"grad_norm": 0.324226438999176,
|
| 2779 |
+
"learning_rate": 1.9792293509242772e-05,
|
| 2780 |
+
"loss": 2.2958,
|
| 2781 |
+
"step": 39600
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.8152955189551074,
|
| 2785 |
+
"grad_norm": 0.397238165140152,
|
| 2786 |
+
"learning_rate": 1.9721813624417226e-05,
|
| 2787 |
+
"loss": 2.2905,
|
| 2788 |
+
"step": 39700
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 0.8173491600607877,
|
| 2792 |
+
"grad_norm": 0.2819819450378418,
|
| 2793 |
+
"learning_rate": 1.9641220472651993e-05,
|
| 2794 |
+
"loss": 2.2942,
|
| 2795 |
+
"step": 39800
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.8194028011664681,
|
| 2799 |
+
"grad_norm": 0.3091094493865967,
|
| 2800 |
+
"learning_rate": 1.955059789221931e-05,
|
| 2801 |
+
"loss": 2.3104,
|
| 2802 |
+
"step": 39900
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 0.8214564422721485,
|
| 2806 |
+
"grad_norm": 0.28247886896133423,
|
| 2807 |
+
"learning_rate": 1.9450040154659662e-05,
|
| 2808 |
+
"loss": 2.2756,
|
| 2809 |
+
"step": 40000
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 0.8235100833778289,
|
| 2813 |
+
"grad_norm": 0.2822871804237366,
|
| 2814 |
+
"learning_rate": 1.933965186671435e-05,
|
| 2815 |
+
"loss": 2.2839,
|
| 2816 |
+
"step": 40100
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 0.8255637244835092,
|
| 2820 |
+
"grad_norm": 0.3817256689071655,
|
| 2821 |
+
"learning_rate": 1.9219547861506717e-05,
|
| 2822 |
+
"loss": 2.2945,
|
| 2823 |
+
"step": 40200
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 0.8276173655891896,
|
| 2827 |
+
"grad_norm": 0.27785882353782654,
|
| 2828 |
+
"learning_rate": 1.90898530790852e-05,
|
| 2829 |
+
"loss": 2.3063,
|
| 2830 |
+
"step": 40300
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 0.82967100669487,
|
| 2834 |
+
"grad_norm": 0.27143430709838867,
|
| 2835 |
+
"learning_rate": 1.8952140282170833e-05,
|
| 2836 |
+
"loss": 2.2901,
|
| 2837 |
+
"step": 40400
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 0.8317246478005503,
|
| 2841 |
+
"grad_norm": 0.2884088456630707,
|
| 2842 |
+
"learning_rate": 1.8803770895536292e-05,
|
| 2843 |
+
"loss": 2.2827,
|
| 2844 |
+
"step": 40500
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 0.8337782889062307,
|
| 2848 |
+
"grad_norm": 0.2864854633808136,
|
| 2849 |
+
"learning_rate": 1.8646243250105386e-05,
|
| 2850 |
+
"loss": 2.2895,
|
| 2851 |
+
"step": 40600
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 0.8358319300119111,
|
| 2855 |
+
"grad_norm": 0.27910563349723816,
|
| 2856 |
+
"learning_rate": 1.8479721216446943e-05,
|
| 2857 |
+
"loss": 2.2952,
|
| 2858 |
+
"step": 40700
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 0.8378855711175915,
|
| 2862 |
+
"grad_norm": 0.31993594765663147,
|
| 2863 |
+
"learning_rate": 1.8304378021681204e-05,
|
| 2864 |
+
"loss": 2.2895,
|
| 2865 |
+
"step": 40800
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 0.8399392122232718,
|
| 2869 |
+
"grad_norm": 0.3024818003177643,
|
| 2870 |
+
"learning_rate": 1.812039606927765e-05,
|
| 2871 |
+
"loss": 2.2904,
|
| 2872 |
+
"step": 40900
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 0.8419928533289522,
|
| 2876 |
+
"grad_norm": 0.2930296063423157,
|
| 2877 |
+
"learning_rate": 1.7927966749306964e-05,
|
| 2878 |
+
"loss": 2.2839,
|
| 2879 |
+
"step": 41000
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 0.8440464944346326,
|
| 2883 |
+
"grad_norm": 0.3246935307979584,
|
| 2884 |
+
"learning_rate": 1.772729023934455e-05,
|
| 2885 |
+
"loss": 2.2959,
|
| 2886 |
+
"step": 41100
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 0.8461001355403129,
|
| 2890 |
+
"grad_norm": 0.31378665566444397,
|
| 2891 |
+
"learning_rate": 1.751857529623272e-05,
|
| 2892 |
+
"loss": 2.2911,
|
| 2893 |
+
"step": 41200
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 0.8481537766459933,
|
| 2897 |
+
"grad_norm": 0.3152724504470825,
|
| 2898 |
+
"learning_rate": 1.730203903891816e-05,
|
| 2899 |
+
"loss": 2.2788,
|
| 2900 |
+
"step": 41300
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 0.8502074177516737,
|
| 2904 |
+
"grad_norm": 0.292479008436203,
|
| 2905 |
+
"learning_rate": 1.7077906722590588e-05,
|
| 2906 |
+
"loss": 2.2835,
|
| 2907 |
+
"step": 41400
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 0.852261058857354,
|
| 2911 |
+
"grad_norm": 0.30000823736190796,
|
| 2912 |
+
"learning_rate": 1.684641150435755e-05,
|
| 2913 |
+
"loss": 2.2855,
|
| 2914 |
+
"step": 41500
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 0.8543146999630344,
|
| 2918 |
+
"grad_norm": 0.3349578380584717,
|
| 2919 |
+
"learning_rate": 1.660779420069915e-05,
|
| 2920 |
+
"loss": 2.2857,
|
| 2921 |
+
"step": 41600
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 0.8563683410687148,
|
| 2925 |
+
"grad_norm": 0.2586715519428253,
|
| 2926 |
+
"learning_rate": 1.636230303695498e-05,
|
| 2927 |
+
"loss": 2.2885,
|
| 2928 |
+
"step": 41700
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 0.8584219821743952,
|
| 2932 |
+
"grad_norm": 0.30945494771003723,
|
| 2933 |
+
"learning_rate": 1.611019338910386e-05,
|
| 2934 |
+
"loss": 2.2819,
|
| 2935 |
+
"step": 41800
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 0.8604756232800755,
|
| 2939 |
+
"grad_norm": 0.27949652075767517,
|
| 2940 |
+
"learning_rate": 1.5851727518105043e-05,
|
| 2941 |
+
"loss": 2.2744,
|
| 2942 |
+
"step": 41900
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 0.862529264385756,
|
| 2946 |
+
"grad_norm": 0.3108949363231659,
|
| 2947 |
+
"learning_rate": 1.5587174297077183e-05,
|
| 2948 |
+
"loss": 2.2863,
|
| 2949 |
+
"step": 42000
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 0.8645829054914363,
|
| 2953 |
+
"grad_norm": 0.4034084975719452,
|
| 2954 |
+
"learning_rate": 1.5316808931598935e-05,
|
| 2955 |
+
"loss": 2.2677,
|
| 2956 |
+
"step": 42100
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 0.8666365465971166,
|
| 2960 |
+
"grad_norm": 0.30645135045051575,
|
| 2961 |
+
"learning_rate": 1.5040912673422065e-05,
|
| 2962 |
+
"loss": 2.2802,
|
| 2963 |
+
"step": 42200
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 0.868690187702797,
|
| 2967 |
+
"grad_norm": 0.28119203448295593,
|
| 2968 |
+
"learning_rate": 1.4759772527895011e-05,
|
| 2969 |
+
"loss": 2.2819,
|
| 2970 |
+
"step": 42300
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 0.8707438288084774,
|
| 2974 |
+
"grad_norm": 0.2753514349460602,
|
| 2975 |
+
"learning_rate": 1.4473680955401086e-05,
|
| 2976 |
+
"loss": 2.2858,
|
| 2977 |
+
"step": 42400
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 0.8727974699141579,
|
| 2981 |
+
"grad_norm": 0.31174930930137634,
|
| 2982 |
+
"learning_rate": 1.4182935567122079e-05,
|
| 2983 |
+
"loss": 2.2869,
|
| 2984 |
+
"step": 42500
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 0.8748511110198381,
|
| 2988 |
+
"grad_norm": 0.29387080669403076,
|
| 2989 |
+
"learning_rate": 1.3890810317839125e-05,
|
| 2990 |
+
"loss": 2.2834,
|
| 2991 |
+
"step": 42600
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 0.8769047521255185,
|
| 2995 |
+
"grad_norm": 0.3072341978549957,
|
| 2996 |
+
"learning_rate": 1.3591708091936952e-05,
|
| 2997 |
+
"loss": 2.2878,
|
| 2998 |
+
"step": 42700
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 0.878958393231199,
|
| 3002 |
+
"grad_norm": 0.30026888847351074,
|
| 3003 |
+
"learning_rate": 1.3288869536157816e-05,
|
| 3004 |
+
"loss": 2.2953,
|
| 3005 |
+
"step": 42800
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 0.8810120343368792,
|
| 3009 |
+
"grad_norm": 0.32910215854644775,
|
| 3010 |
+
"learning_rate": 1.2982609682991796e-05,
|
| 3011 |
+
"loss": 2.2775,
|
| 3012 |
+
"step": 42900
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 0.8830656754425596,
|
| 3016 |
+
"grad_norm": 0.3203257918357849,
|
| 3017 |
+
"learning_rate": 1.267324712398648e-05,
|
| 3018 |
+
"loss": 2.2869,
|
| 3019 |
+
"step": 43000
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 0.88511931654824,
|
| 3023 |
+
"grad_norm": 0.34515684843063354,
|
| 3024 |
+
"learning_rate": 1.2361103678327189e-05,
|
| 3025 |
+
"loss": 2.277,
|
| 3026 |
+
"step": 43100
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 0.8871729576539203,
|
| 3030 |
+
"grad_norm": 0.2750638723373413,
|
| 3031 |
+
"learning_rate": 1.2046504058059565e-05,
|
| 3032 |
+
"loss": 2.2722,
|
| 3033 |
+
"step": 43200
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 0.8892265987596008,
|
| 3037 |
+
"grad_norm": 0.31067952513694763,
|
| 3038 |
+
"learning_rate": 1.1729775530302879e-05,
|
| 3039 |
+
"loss": 2.2763,
|
| 3040 |
+
"step": 43300
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 0.8912802398652812,
|
| 3044 |
+
"grad_norm": 0.2809985280036926,
|
| 3045 |
+
"learning_rate": 1.141124757680532e-05,
|
| 3046 |
+
"loss": 2.2746,
|
| 3047 |
+
"step": 43400
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 0.8933338809709616,
|
| 3051 |
+
"grad_norm": 0.2850824296474457,
|
| 3052 |
+
"learning_rate": 1.1091251551195543e-05,
|
| 3053 |
+
"loss": 2.2688,
|
| 3054 |
+
"step": 43500
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 0.8953875220766419,
|
| 3058 |
+
"grad_norm": 0.2884581387042999,
|
| 3059 |
+
"learning_rate": 1.0770120334286904e-05,
|
| 3060 |
+
"loss": 2.2957,
|
| 3061 |
+
"step": 43600
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 0.8974411631823223,
|
| 3065 |
+
"grad_norm": 0.30846843123435974,
|
| 3066 |
+
"learning_rate": 1.0448187987793066e-05,
|
| 3067 |
+
"loss": 2.2849,
|
| 3068 |
+
"step": 43700
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 0.8994948042880027,
|
| 3072 |
+
"grad_norm": 0.32289132475852966,
|
| 3073 |
+
"learning_rate": 1.0125789406815126e-05,
|
| 3074 |
+
"loss": 2.3148,
|
| 3075 |
+
"step": 43800
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 0.901548445393683,
|
| 3079 |
+
"grad_norm": 0.2920849621295929,
|
| 3080 |
+
"learning_rate": 9.803259971461812e-06,
|
| 3081 |
+
"loss": 2.2606,
|
| 3082 |
+
"step": 43900
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 0.9036020864993634,
|
| 3086 |
+
"grad_norm": 0.2882274091243744,
|
| 3087 |
+
"learning_rate": 9.480935197965144e-06,
|
| 3088 |
+
"loss": 2.2846,
|
| 3089 |
+
"step": 44000
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 0.9056557276050438,
|
| 3093 |
+
"grad_norm": 0.29778212308883667,
|
| 3094 |
+
"learning_rate": 9.159150389654477e-06,
|
| 3095 |
+
"loss": 2.2584,
|
| 3096 |
+
"step": 44100
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 0.9077093687107242,
|
| 3100 |
+
"grad_norm": 0.2668134570121765,
|
| 3101 |
+
"learning_rate": 8.838240288152034e-06,
|
| 3102 |
+
"loss": 2.2762,
|
| 3103 |
+
"step": 44200
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 0.9097630098164045,
|
| 3107 |
+
"grad_norm": 0.28250423073768616,
|
| 3108 |
+
"learning_rate": 8.51853872515275e-06,
|
| 3109 |
+
"loss": 2.2878,
|
| 3110 |
+
"step": 44300
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 0.9118166509220849,
|
| 3114 |
+
"grad_norm": 0.2944965362548828,
|
| 3115 |
+
"learning_rate": 8.200378275150713e-06,
|
| 3116 |
+
"loss": 2.2685,
|
| 3117 |
+
"step": 44400
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 0.9138702920277653,
|
| 3121 |
+
"grad_norm": 0.30124709010124207,
|
| 3122 |
+
"learning_rate": 7.884089909473368e-06,
|
| 3123 |
+
"loss": 2.2703,
|
| 3124 |
+
"step": 44500
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 0.9159239331334456,
|
| 3128 |
+
"grad_norm": 0.32274484634399414,
|
| 3129 |
+
"learning_rate": 7.570002651983506e-06,
|
| 3130 |
+
"loss": 2.2773,
|
| 3131 |
+
"step": 44600
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 0.917977574239126,
|
| 3135 |
+
"grad_norm": 0.2996600568294525,
|
| 3136 |
+
"learning_rate": 7.258443236807088e-06,
|
| 3137 |
+
"loss": 2.2772,
|
| 3138 |
+
"step": 44700
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 0.9200312153448064,
|
| 3142 |
+
"grad_norm": 0.33671292662620544,
|
| 3143 |
+
"learning_rate": 6.949735768443027e-06,
|
| 3144 |
+
"loss": 2.2681,
|
| 3145 |
+
"step": 44800
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 0.9220848564504868,
|
| 3149 |
+
"grad_norm": 0.29412752389907837,
|
| 3150 |
+
"learning_rate": 6.644201384608466e-06,
|
| 3151 |
+
"loss": 2.2784,
|
| 3152 |
+
"step": 44900
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 0.9241384975561671,
|
| 3156 |
+
"grad_norm": 0.3358917832374573,
|
| 3157 |
+
"learning_rate": 6.342157922170306e-06,
|
| 3158 |
+
"loss": 2.2622,
|
| 3159 |
+
"step": 45000
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 0.9261921386618475,
|
| 3163 |
+
"grad_norm": 0.2703853249549866,
|
| 3164 |
+
"learning_rate": 6.046882112350851e-06,
|
| 3165 |
+
"loss": 2.2865,
|
| 3166 |
+
"step": 45100
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 0.9282457797675279,
|
| 3170 |
+
"grad_norm": 0.32069769501686096,
|
| 3171 |
+
"learning_rate": 5.752716474839826e-06,
|
| 3172 |
+
"loss": 2.2714,
|
| 3173 |
+
"step": 45200
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 0.9302994208732082,
|
| 3177 |
+
"grad_norm": 0.33117198944091797,
|
| 3178 |
+
"learning_rate": 5.462969139686562e-06,
|
| 3179 |
+
"loss": 2.278,
|
| 3180 |
+
"step": 45300
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 0.9323530619788886,
|
| 3184 |
+
"grad_norm": 0.29988622665405273,
|
| 3185 |
+
"learning_rate": 5.177941521036469e-06,
|
| 3186 |
+
"loss": 2.2649,
|
| 3187 |
+
"step": 45400
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 0.934406703084569,
|
| 3191 |
+
"grad_norm": 0.3126521408557892,
|
| 3192 |
+
"learning_rate": 4.897930123276901e-06,
|
| 3193 |
+
"loss": 2.2725,
|
| 3194 |
+
"step": 45500
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 0.9364603441902493,
|
| 3198 |
+
"grad_norm": 0.28117185831069946,
|
| 3199 |
+
"learning_rate": 4.6232262325938585e-06,
|
| 3200 |
+
"loss": 2.281,
|
| 3201 |
+
"step": 45600
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 0.9385139852959297,
|
| 3205 |
+
"grad_norm": 0.29236385226249695,
|
| 3206 |
+
"learning_rate": 4.354115613957044e-06,
|
| 3207 |
+
"loss": 2.2873,
|
| 3208 |
+
"step": 45700
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 0.9405676264016101,
|
| 3212 |
+
"grad_norm": 0.29896336793899536,
|
| 3213 |
+
"learning_rate": 4.090878213848434e-06,
|
| 3214 |
+
"loss": 2.2697,
|
| 3215 |
+
"step": 45800
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 0.9426212675072905,
|
| 3219 |
+
"grad_norm": 0.30456385016441345,
|
| 3220 |
+
"learning_rate": 3.833787869043619e-06,
|
| 3221 |
+
"loss": 2.2691,
|
| 3222 |
+
"step": 45900
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 0.9446749086129708,
|
| 3226 |
+
"grad_norm": 0.31344568729400635,
|
| 3227 |
+
"learning_rate": 3.583112021748868e-06,
|
| 3228 |
+
"loss": 2.2778,
|
| 3229 |
+
"step": 46000
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 0.9467285497186512,
|
| 3233 |
+
"grad_norm": 0.28700950741767883,
|
| 3234 |
+
"learning_rate": 3.339111441390229e-06,
|
| 3235 |
+
"loss": 2.2725,
|
| 3236 |
+
"step": 46100
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 0.9487821908243316,
|
| 3240 |
+
"grad_norm": 0.28607872128486633,
|
| 3241 |
+
"learning_rate": 3.1020399533441157e-06,
|
| 3242 |
+
"loss": 2.254,
|
| 3243 |
+
"step": 46200
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 0.9508358319300119,
|
| 3247 |
+
"grad_norm": 0.28324002027511597,
|
| 3248 |
+
"learning_rate": 2.872144174891521e-06,
|
| 3249 |
+
"loss": 2.2781,
|
| 3250 |
+
"step": 46300
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 0.9528894730356923,
|
| 3254 |
+
"grad_norm": 0.28786829113960266,
|
| 3255 |
+
"learning_rate": 2.6496632586705894e-06,
|
| 3256 |
+
"loss": 2.2769,
|
| 3257 |
+
"step": 46400
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 0.9549431141413727,
|
| 3261 |
+
"grad_norm": 0.28459101915359497,
|
| 3262 |
+
"learning_rate": 2.434828643894376e-06,
|
| 3263 |
+
"loss": 2.2705,
|
| 3264 |
+
"step": 46500
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 0.9569967552470531,
|
| 3268 |
+
"grad_norm": 0.3280186653137207,
|
| 3269 |
+
"learning_rate": 2.227863815592636e-06,
|
| 3270 |
+
"loss": 2.2842,
|
| 3271 |
+
"step": 46600
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 0.9590503963527334,
|
| 3275 |
+
"grad_norm": 0.3347383141517639,
|
| 3276 |
+
"learning_rate": 2.0289840721280606e-06,
|
| 3277 |
+
"loss": 2.2666,
|
| 3278 |
+
"step": 46700
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 0.9611040374584138,
|
| 3282 |
+
"grad_norm": 0.29502809047698975,
|
| 3283 |
+
"learning_rate": 1.838396301228834e-06,
|
| 3284 |
+
"loss": 2.2692,
|
| 3285 |
+
"step": 46800
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 0.9631576785640942,
|
| 3289 |
+
"grad_norm": 0.2993612587451935,
|
| 3290 |
+
"learning_rate": 1.6562987647704621e-06,
|
| 3291 |
+
"loss": 2.2761,
|
| 3292 |
+
"step": 46900
|
| 3293 |
+
},
|
| 3294 |
+
{
|
| 3295 |
+
"epoch": 0.9652113196697745,
|
| 3296 |
+
"grad_norm": 0.29247549176216125,
|
| 3297 |
+
"learning_rate": 1.4828808925308103e-06,
|
| 3298 |
+
"loss": 2.268,
|
| 3299 |
+
"step": 47000
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 0.9672649607754549,
|
| 3303 |
+
"grad_norm": 0.35342568159103394,
|
| 3304 |
+
"learning_rate": 1.3183230851328289e-06,
|
| 3305 |
+
"loss": 2.2743,
|
| 3306 |
+
"step": 47100
|
| 3307 |
+
},
|
| 3308 |
+
{
|
| 3309 |
+
"epoch": 0.9693186018811353,
|
| 3310 |
+
"grad_norm": 0.32324814796447754,
|
| 3311 |
+
"learning_rate": 1.1627965263800245e-06,
|
| 3312 |
+
"loss": 2.2899,
|
| 3313 |
+
"step": 47200
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 0.9713722429868156,
|
| 3317 |
+
"grad_norm": 0.2993561923503876,
|
| 3318 |
+
"learning_rate": 1.0164630051798629e-06,
|
| 3319 |
+
"loss": 2.2616,
|
| 3320 |
+
"step": 47300
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 0.973425884092496,
|
| 3324 |
+
"grad_norm": 0.2622087001800537,
|
| 3325 |
+
"learning_rate": 8.794747472403564e-07,
|
| 3326 |
+
"loss": 2.2934,
|
| 3327 |
+
"step": 47400
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 0.9754795251981764,
|
| 3331 |
+
"grad_norm": 0.29449987411499023,
|
| 3332 |
+
"learning_rate": 7.519742567149124e-07,
|
| 3333 |
+
"loss": 2.2763,
|
| 3334 |
+
"step": 47500
|
| 3335 |
+
},
|
| 3336 |
+
{
|
| 3337 |
+
"epoch": 0.9775331663038568,
|
| 3338 |
+
"grad_norm": 0.303148090839386,
|
| 3339 |
+
"learning_rate": 6.340941679601898e-07,
|
| 3340 |
+
"loss": 2.2784,
|
| 3341 |
+
"step": 47600
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 0.9795868074095371,
|
| 3345 |
+
"grad_norm": 0.2734745740890503,
|
| 3346 |
+
"learning_rate": 5.259571075611525e-07,
|
| 3347 |
+
"loss": 2.2894,
|
| 3348 |
+
"step": 47700
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"epoch": 0.9816404485152175,
|
| 3352 |
+
"grad_norm": 0.32225048542022705,
|
| 3353 |
+
"learning_rate": 4.286092530968022e-07,
|
| 3354 |
+
"loss": 2.2755,
|
| 3355 |
+
"step": 47800
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 0.9836940896208979,
|
| 3359 |
+
"grad_norm": 0.317860871553421,
|
| 3360 |
+
"learning_rate": 3.401854210622069e-07,
|
| 3361 |
+
"loss": 2.2764,
|
| 3362 |
+
"step": 47900
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 0.9857477307265782,
|
| 3366 |
+
"grad_norm": 0.29958489537239075,
|
| 3367 |
+
"learning_rate": 2.61810360501622e-07,
|
| 3368 |
+
"loss": 2.2704,
|
| 3369 |
+
"step": 48000
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 0.9878013718322586,
|
| 3373 |
+
"grad_norm": 0.28780597448349,
|
| 3374 |
+
"learning_rate": 1.9356560228361854e-07,
|
| 3375 |
+
"loss": 2.2651,
|
| 3376 |
+
"step": 48100
|
| 3377 |
+
},
|
| 3378 |
+
{
|
| 3379 |
+
"epoch": 0.989855012937939,
|
| 3380 |
+
"grad_norm": 0.323916494846344,
|
| 3381 |
+
"learning_rate": 1.3552213907311873e-07,
|
| 3382 |
+
"loss": 2.2773,
|
| 3383 |
+
"step": 48200
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 0.9919086540436194,
|
| 3387 |
+
"grad_norm": 0.30257830023765564,
|
| 3388 |
+
"learning_rate": 8.774035148018666e-08,
|
| 3389 |
+
"loss": 2.2616,
|
| 3390 |
+
"step": 48300
|
| 3391 |
+
},
|
| 3392 |
+
{
|
| 3393 |
+
"epoch": 0.9939622951492997,
|
| 3394 |
+
"grad_norm": 0.3220650553703308,
|
| 3395 |
+
"learning_rate": 5.026994524815698e-08,
|
| 3396 |
+
"loss": 2.2554,
|
| 3397 |
+
"step": 48400
|
| 3398 |
+
},
|
| 3399 |
+
{
|
| 3400 |
+
"epoch": 0.9960159362549801,
|
| 3401 |
+
"grad_norm": 0.31886255741119385,
|
| 3402 |
+
"learning_rate": 2.3149899546475174e-08,
|
| 3403 |
+
"loss": 2.2791,
|
| 3404 |
+
"step": 48500
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 0.9980695773606605,
|
| 3408 |
+
"grad_norm": 0.28650590777397156,
|
| 3409 |
+
"learning_rate": 6.524401072920405e-09,
|
| 3410 |
+
"loss": 2.2685,
|
| 3411 |
+
"step": 48600
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 1.0,
|
| 3415 |
+
"step": 48694,
|
| 3416 |
+
"total_flos": 7.322050088623145e+18,
|
| 3417 |
+
"train_loss": 2.3946414439395287,
|
| 3418 |
+
"train_runtime": 14836.2948,
|
| 3419 |
+
"train_samples_per_second": 52.513,
|
| 3420 |
+
"train_steps_per_second": 3.282
|
| 3421 |
+
}
|
| 3422 |
+
],
|
| 3423 |
+
"logging_steps": 100,
|
| 3424 |
+
"max_steps": 48694,
|
| 3425 |
+
"num_input_tokens_seen": 0,
|
| 3426 |
+
"num_train_epochs": 1,
|
| 3427 |
+
"save_steps": 500,
|
| 3428 |
+
"stateful_callbacks": {
|
| 3429 |
+
"TrainerControl": {
|
| 3430 |
+
"args": {
|
| 3431 |
+
"should_epoch_stop": false,
|
| 3432 |
+
"should_evaluate": false,
|
| 3433 |
+
"should_log": false,
|
| 3434 |
+
"should_save": true,
|
| 3435 |
+
"should_training_stop": true
|
| 3436 |
+
},
|
| 3437 |
+
"attributes": {}
|
| 3438 |
+
}
|
| 3439 |
+
},
|
| 3440 |
+
"total_flos": 7.322050088623145e+18,
|
| 3441 |
+
"train_batch_size": 2,
|
| 3442 |
+
"trial_name": null,
|
| 3443 |
+
"trial_params": null
|
| 3444 |
+
}
|