End of training
Browse files- README.md +2 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +9 -0
- trainer_state.json +3104 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# train_copa_456_1768397595
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 0.
|
| 23 |
- Num Input Tokens Seen: 273936
|
| 24 |
|
| 25 |
## Model description
|
|
|
|
| 17 |
|
| 18 |
# train_copa_456_1768397595
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the copa dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.1024
|
| 23 |
- Num Input Tokens Seen: 273936
|
| 24 |
|
| 25 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 0.10243535041809082,
|
| 4 |
+
"eval_runtime": 0.9467,
|
| 5 |
+
"eval_samples_per_second": 42.25,
|
| 6 |
+
"eval_steps_per_second": 21.125,
|
| 7 |
+
"num_input_tokens_seen": 273936,
|
| 8 |
+
"total_flos": 1.3438495585861632e+16,
|
| 9 |
+
"train_loss": 0.044879560974069234,
|
| 10 |
+
"train_runtime": 814.6797,
|
| 11 |
+
"train_samples_per_second": 4.419,
|
| 12 |
+
"train_steps_per_second": 2.209
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 0.10243535041809082,
|
| 4 |
+
"eval_runtime": 0.9467,
|
| 5 |
+
"eval_samples_per_second": 42.25,
|
| 6 |
+
"eval_steps_per_second": 21.125,
|
| 7 |
+
"num_input_tokens_seen": 273936
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"num_input_tokens_seen": 273936,
|
| 4 |
+
"total_flos": 1.3438495585861632e+16,
|
| 5 |
+
"train_loss": 0.044879560974069234,
|
| 6 |
+
"train_runtime": 814.6797,
|
| 7 |
+
"train_samples_per_second": 4.419,
|
| 8 |
+
"train_steps_per_second": 2.209
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 90,
|
| 3 |
+
"best_metric": 0.10243535041809082,
|
| 4 |
+
"best_model_checkpoint": "saves_multiple/bitfit/llama-3-8b-instruct/train_copa_456_1768397595/checkpoint-90",
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
+
"eval_steps": 90,
|
| 7 |
+
"global_step": 1800,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.027777777777777776,
|
| 14 |
+
"grad_norm": 26.174911499023438,
|
| 15 |
+
"learning_rate": 1.1111111111111112e-06,
|
| 16 |
+
"loss": 0.5621,
|
| 17 |
+
"num_input_tokens_seen": 768,
|
| 18 |
+
"step": 5
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.05555555555555555,
|
| 22 |
+
"grad_norm": 27.083621978759766,
|
| 23 |
+
"learning_rate": 2.5e-06,
|
| 24 |
+
"loss": 0.5065,
|
| 25 |
+
"num_input_tokens_seen": 1520,
|
| 26 |
+
"step": 10
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.08333333333333333,
|
| 30 |
+
"grad_norm": 35.399654388427734,
|
| 31 |
+
"learning_rate": 3.888888888888889e-06,
|
| 32 |
+
"loss": 0.3998,
|
| 33 |
+
"num_input_tokens_seen": 2272,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.1111111111111111,
|
| 38 |
+
"grad_norm": 49.66708755493164,
|
| 39 |
+
"learning_rate": 5.277777777777778e-06,
|
| 40 |
+
"loss": 0.6268,
|
| 41 |
+
"num_input_tokens_seen": 3008,
|
| 42 |
+
"step": 20
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.1388888888888889,
|
| 46 |
+
"grad_norm": 17.423233032226562,
|
| 47 |
+
"learning_rate": 6.666666666666667e-06,
|
| 48 |
+
"loss": 0.5377,
|
| 49 |
+
"num_input_tokens_seen": 3776,
|
| 50 |
+
"step": 25
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.16666666666666666,
|
| 54 |
+
"grad_norm": 39.209510803222656,
|
| 55 |
+
"learning_rate": 8.055555555555557e-06,
|
| 56 |
+
"loss": 0.9891,
|
| 57 |
+
"num_input_tokens_seen": 4544,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.19444444444444445,
|
| 62 |
+
"grad_norm": 13.324094772338867,
|
| 63 |
+
"learning_rate": 9.444444444444445e-06,
|
| 64 |
+
"loss": 0.2197,
|
| 65 |
+
"num_input_tokens_seen": 5312,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2222222222222222,
|
| 70 |
+
"grad_norm": 6.746327877044678,
|
| 71 |
+
"learning_rate": 1.0833333333333334e-05,
|
| 72 |
+
"loss": 0.2677,
|
| 73 |
+
"num_input_tokens_seen": 6112,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.25,
|
| 78 |
+
"grad_norm": 4.74421501159668,
|
| 79 |
+
"learning_rate": 1.2222222222222222e-05,
|
| 80 |
+
"loss": 0.2891,
|
| 81 |
+
"num_input_tokens_seen": 6848,
|
| 82 |
+
"step": 45
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.2777777777777778,
|
| 86 |
+
"grad_norm": 5.368658065795898,
|
| 87 |
+
"learning_rate": 1.3611111111111111e-05,
|
| 88 |
+
"loss": 0.1996,
|
| 89 |
+
"num_input_tokens_seen": 7584,
|
| 90 |
+
"step": 50
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.3055555555555556,
|
| 94 |
+
"grad_norm": 3.385861396789551,
|
| 95 |
+
"learning_rate": 1.5e-05,
|
| 96 |
+
"loss": 0.2764,
|
| 97 |
+
"num_input_tokens_seen": 8368,
|
| 98 |
+
"step": 55
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.3333333333333333,
|
| 102 |
+
"grad_norm": 1.4747138023376465,
|
| 103 |
+
"learning_rate": 1.638888888888889e-05,
|
| 104 |
+
"loss": 0.0481,
|
| 105 |
+
"num_input_tokens_seen": 9104,
|
| 106 |
+
"step": 60
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.3611111111111111,
|
| 110 |
+
"grad_norm": 21.31920623779297,
|
| 111 |
+
"learning_rate": 1.777777777777778e-05,
|
| 112 |
+
"loss": 0.0801,
|
| 113 |
+
"num_input_tokens_seen": 9856,
|
| 114 |
+
"step": 65
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3888888888888889,
|
| 118 |
+
"grad_norm": 1.2555230855941772,
|
| 119 |
+
"learning_rate": 1.9166666666666667e-05,
|
| 120 |
+
"loss": 0.4616,
|
| 121 |
+
"num_input_tokens_seen": 10624,
|
| 122 |
+
"step": 70
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.4166666666666667,
|
| 126 |
+
"grad_norm": 23.720603942871094,
|
| 127 |
+
"learning_rate": 2.0555555555555555e-05,
|
| 128 |
+
"loss": 0.1396,
|
| 129 |
+
"num_input_tokens_seen": 11392,
|
| 130 |
+
"step": 75
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.4444444444444444,
|
| 134 |
+
"grad_norm": 1.8614143133163452,
|
| 135 |
+
"learning_rate": 2.1944444444444445e-05,
|
| 136 |
+
"loss": 0.0432,
|
| 137 |
+
"num_input_tokens_seen": 12160,
|
| 138 |
+
"step": 80
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.4722222222222222,
|
| 142 |
+
"grad_norm": 24.082788467407227,
|
| 143 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 144 |
+
"loss": 0.253,
|
| 145 |
+
"num_input_tokens_seen": 12896,
|
| 146 |
+
"step": 85
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.5,
|
| 150 |
+
"grad_norm": 19.710237503051758,
|
| 151 |
+
"learning_rate": 2.4722222222222223e-05,
|
| 152 |
+
"loss": 0.0976,
|
| 153 |
+
"num_input_tokens_seen": 13632,
|
| 154 |
+
"step": 90
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.5,
|
| 158 |
+
"eval_loss": 0.10243535041809082,
|
| 159 |
+
"eval_runtime": 0.8457,
|
| 160 |
+
"eval_samples_per_second": 47.297,
|
| 161 |
+
"eval_steps_per_second": 23.649,
|
| 162 |
+
"num_input_tokens_seen": 13632,
|
| 163 |
+
"step": 90
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5277777777777778,
|
| 167 |
+
"grad_norm": 25.10673713684082,
|
| 168 |
+
"learning_rate": 2.6111111111111114e-05,
|
| 169 |
+
"loss": 0.0304,
|
| 170 |
+
"num_input_tokens_seen": 14384,
|
| 171 |
+
"step": 95
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.5555555555555556,
|
| 175 |
+
"grad_norm": 1.2356877326965332,
|
| 176 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 177 |
+
"loss": 0.0045,
|
| 178 |
+
"num_input_tokens_seen": 15136,
|
| 179 |
+
"step": 100
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.5833333333333334,
|
| 183 |
+
"grad_norm": 0.11366397142410278,
|
| 184 |
+
"learning_rate": 2.8888888888888888e-05,
|
| 185 |
+
"loss": 0.0022,
|
| 186 |
+
"num_input_tokens_seen": 15920,
|
| 187 |
+
"step": 105
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.6111111111111112,
|
| 191 |
+
"grad_norm": 0.13132458925247192,
|
| 192 |
+
"learning_rate": 3.0277777777777776e-05,
|
| 193 |
+
"loss": 0.0043,
|
| 194 |
+
"num_input_tokens_seen": 16656,
|
| 195 |
+
"step": 110
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.6388888888888888,
|
| 199 |
+
"grad_norm": 0.2592090964317322,
|
| 200 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 201 |
+
"loss": 0.0029,
|
| 202 |
+
"num_input_tokens_seen": 17440,
|
| 203 |
+
"step": 115
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.6666666666666666,
|
| 207 |
+
"grad_norm": 14.52552604675293,
|
| 208 |
+
"learning_rate": 3.3055555555555553e-05,
|
| 209 |
+
"loss": 0.2463,
|
| 210 |
+
"num_input_tokens_seen": 18224,
|
| 211 |
+
"step": 120
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.6944444444444444,
|
| 215 |
+
"grad_norm": 39.94384002685547,
|
| 216 |
+
"learning_rate": 3.444444444444445e-05,
|
| 217 |
+
"loss": 0.1556,
|
| 218 |
+
"num_input_tokens_seen": 19008,
|
| 219 |
+
"step": 125
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7222222222222222,
|
| 223 |
+
"grad_norm": 0.04966762289404869,
|
| 224 |
+
"learning_rate": 3.5833333333333335e-05,
|
| 225 |
+
"loss": 0.0313,
|
| 226 |
+
"num_input_tokens_seen": 19776,
|
| 227 |
+
"step": 130
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.75,
|
| 231 |
+
"grad_norm": 0.26315122842788696,
|
| 232 |
+
"learning_rate": 3.722222222222222e-05,
|
| 233 |
+
"loss": 0.013,
|
| 234 |
+
"num_input_tokens_seen": 20576,
|
| 235 |
+
"step": 135
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.7777777777777778,
|
| 239 |
+
"grad_norm": 0.07332806289196014,
|
| 240 |
+
"learning_rate": 3.8611111111111116e-05,
|
| 241 |
+
"loss": 0.0135,
|
| 242 |
+
"num_input_tokens_seen": 21312,
|
| 243 |
+
"step": 140
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.8055555555555556,
|
| 247 |
+
"grad_norm": 0.052172716706991196,
|
| 248 |
+
"learning_rate": 4e-05,
|
| 249 |
+
"loss": 0.1598,
|
| 250 |
+
"num_input_tokens_seen": 22080,
|
| 251 |
+
"step": 145
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.8333333333333334,
|
| 255 |
+
"grad_norm": 35.53556442260742,
|
| 256 |
+
"learning_rate": 4.138888888888889e-05,
|
| 257 |
+
"loss": 0.2769,
|
| 258 |
+
"num_input_tokens_seen": 22864,
|
| 259 |
+
"step": 150
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.8611111111111112,
|
| 263 |
+
"grad_norm": 1.3189358711242676,
|
| 264 |
+
"learning_rate": 4.277777777777778e-05,
|
| 265 |
+
"loss": 0.0017,
|
| 266 |
+
"num_input_tokens_seen": 23616,
|
| 267 |
+
"step": 155
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.8888888888888888,
|
| 271 |
+
"grad_norm": 3.976815938949585,
|
| 272 |
+
"learning_rate": 4.4166666666666665e-05,
|
| 273 |
+
"loss": 0.3282,
|
| 274 |
+
"num_input_tokens_seen": 24352,
|
| 275 |
+
"step": 160
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.9166666666666666,
|
| 279 |
+
"grad_norm": 1.152937889099121,
|
| 280 |
+
"learning_rate": 4.555555555555556e-05,
|
| 281 |
+
"loss": 0.0081,
|
| 282 |
+
"num_input_tokens_seen": 25088,
|
| 283 |
+
"step": 165
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.9444444444444444,
|
| 287 |
+
"grad_norm": 0.03279455751180649,
|
| 288 |
+
"learning_rate": 4.6944444444444446e-05,
|
| 289 |
+
"loss": 0.1479,
|
| 290 |
+
"num_input_tokens_seen": 25856,
|
| 291 |
+
"step": 170
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.9722222222222222,
|
| 295 |
+
"grad_norm": 0.380422443151474,
|
| 296 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 297 |
+
"loss": 0.0089,
|
| 298 |
+
"num_input_tokens_seen": 26624,
|
| 299 |
+
"step": 175
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.0,
|
| 303 |
+
"grad_norm": 14.139666557312012,
|
| 304 |
+
"learning_rate": 4.972222222222223e-05,
|
| 305 |
+
"loss": 0.0248,
|
| 306 |
+
"num_input_tokens_seen": 27376,
|
| 307 |
+
"step": 180
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.0,
|
| 311 |
+
"eval_loss": 0.11664140224456787,
|
| 312 |
+
"eval_runtime": 0.8533,
|
| 313 |
+
"eval_samples_per_second": 46.875,
|
| 314 |
+
"eval_steps_per_second": 23.438,
|
| 315 |
+
"num_input_tokens_seen": 27376,
|
| 316 |
+
"step": 180
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.0277777777777777,
|
| 320 |
+
"grad_norm": 1.0830224752426147,
|
| 321 |
+
"learning_rate": 4.9999247861994194e-05,
|
| 322 |
+
"loss": 0.0022,
|
| 323 |
+
"num_input_tokens_seen": 28128,
|
| 324 |
+
"step": 185
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.0555555555555556,
|
| 328 |
+
"grad_norm": 0.01833321526646614,
|
| 329 |
+
"learning_rate": 4.9996192378909786e-05,
|
| 330 |
+
"loss": 0.0017,
|
| 331 |
+
"num_input_tokens_seen": 28896,
|
| 332 |
+
"step": 190
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.0833333333333333,
|
| 336 |
+
"grad_norm": 0.02257794886827469,
|
| 337 |
+
"learning_rate": 4.999078682916774e-05,
|
| 338 |
+
"loss": 0.0007,
|
| 339 |
+
"num_input_tokens_seen": 29648,
|
| 340 |
+
"step": 195
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.1111111111111112,
|
| 344 |
+
"grad_norm": 1.7842925786972046,
|
| 345 |
+
"learning_rate": 4.998303172098155e-05,
|
| 346 |
+
"loss": 0.1445,
|
| 347 |
+
"num_input_tokens_seen": 30416,
|
| 348 |
+
"step": 200
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.1388888888888888,
|
| 352 |
+
"grad_norm": 0.03761421516537666,
|
| 353 |
+
"learning_rate": 4.997292778346312e-05,
|
| 354 |
+
"loss": 0.1068,
|
| 355 |
+
"num_input_tokens_seen": 31200,
|
| 356 |
+
"step": 205
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.1666666666666667,
|
| 360 |
+
"grad_norm": 0.017799263820052147,
|
| 361 |
+
"learning_rate": 4.996047596655418e-05,
|
| 362 |
+
"loss": 0.0098,
|
| 363 |
+
"num_input_tokens_seen": 31968,
|
| 364 |
+
"step": 210
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.1944444444444444,
|
| 368 |
+
"grad_norm": 0.02381935343146324,
|
| 369 |
+
"learning_rate": 4.994567744093703e-05,
|
| 370 |
+
"loss": 0.0003,
|
| 371 |
+
"num_input_tokens_seen": 32720,
|
| 372 |
+
"step": 215
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.2222222222222223,
|
| 376 |
+
"grad_norm": 0.033814460039138794,
|
| 377 |
+
"learning_rate": 4.992853359792444e-05,
|
| 378 |
+
"loss": 0.4099,
|
| 379 |
+
"num_input_tokens_seen": 33472,
|
| 380 |
+
"step": 220
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.25,
|
| 384 |
+
"grad_norm": 0.019769281148910522,
|
| 385 |
+
"learning_rate": 4.9909046049328846e-05,
|
| 386 |
+
"loss": 0.094,
|
| 387 |
+
"num_input_tokens_seen": 34208,
|
| 388 |
+
"step": 225
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.2777777777777777,
|
| 392 |
+
"grad_norm": 12.754151344299316,
|
| 393 |
+
"learning_rate": 4.988721662731083e-05,
|
| 394 |
+
"loss": 0.2881,
|
| 395 |
+
"num_input_tokens_seen": 34960,
|
| 396 |
+
"step": 230
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.3055555555555556,
|
| 400 |
+
"grad_norm": 0.020138300955295563,
|
| 401 |
+
"learning_rate": 4.9863047384206835e-05,
|
| 402 |
+
"loss": 0.0205,
|
| 403 |
+
"num_input_tokens_seen": 35728,
|
| 404 |
+
"step": 235
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.3333333333333333,
|
| 408 |
+
"grad_norm": 1.8282607793807983,
|
| 409 |
+
"learning_rate": 4.983654059233626e-05,
|
| 410 |
+
"loss": 0.0025,
|
| 411 |
+
"num_input_tokens_seen": 36464,
|
| 412 |
+
"step": 240
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.3611111111111112,
|
| 416 |
+
"grad_norm": 0.02977779507637024,
|
| 417 |
+
"learning_rate": 4.9807698743787744e-05,
|
| 418 |
+
"loss": 0.0003,
|
| 419 |
+
"num_input_tokens_seen": 37200,
|
| 420 |
+
"step": 245
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.3888888888888888,
|
| 424 |
+
"grad_norm": 0.09747491031885147,
|
| 425 |
+
"learning_rate": 4.9776524550184965e-05,
|
| 426 |
+
"loss": 0.0006,
|
| 427 |
+
"num_input_tokens_seen": 37952,
|
| 428 |
+
"step": 250
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.4166666666666667,
|
| 432 |
+
"grad_norm": 0.02982584573328495,
|
| 433 |
+
"learning_rate": 4.974302094243164e-05,
|
| 434 |
+
"loss": 0.1759,
|
| 435 |
+
"num_input_tokens_seen": 38688,
|
| 436 |
+
"step": 255
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.4444444444444444,
|
| 440 |
+
"grad_norm": 48.68693161010742,
|
| 441 |
+
"learning_rate": 4.970719107043595e-05,
|
| 442 |
+
"loss": 0.1863,
|
| 443 |
+
"num_input_tokens_seen": 39472,
|
| 444 |
+
"step": 260
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.4722222222222223,
|
| 448 |
+
"grad_norm": 8.864044189453125,
|
| 449 |
+
"learning_rate": 4.966903830281449e-05,
|
| 450 |
+
"loss": 0.0908,
|
| 451 |
+
"num_input_tokens_seen": 40240,
|
| 452 |
+
"step": 265
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.5,
|
| 456 |
+
"grad_norm": 0.22452251613140106,
|
| 457 |
+
"learning_rate": 4.962856622657541e-05,
|
| 458 |
+
"loss": 0.0832,
|
| 459 |
+
"num_input_tokens_seen": 41008,
|
| 460 |
+
"step": 270
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.5,
|
| 464 |
+
"eval_loss": 0.14009475708007812,
|
| 465 |
+
"eval_runtime": 0.8695,
|
| 466 |
+
"eval_samples_per_second": 46.004,
|
| 467 |
+
"eval_steps_per_second": 23.002,
|
| 468 |
+
"num_input_tokens_seen": 41008,
|
| 469 |
+
"step": 270
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.5277777777777777,
|
| 473 |
+
"grad_norm": 0.038117777556180954,
|
| 474 |
+
"learning_rate": 4.9585778646781364e-05,
|
| 475 |
+
"loss": 0.0023,
|
| 476 |
+
"num_input_tokens_seen": 41744,
|
| 477 |
+
"step": 275
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.5555555555555556,
|
| 481 |
+
"grad_norm": 19.886659622192383,
|
| 482 |
+
"learning_rate": 4.9540679586191605e-05,
|
| 483 |
+
"loss": 0.4371,
|
| 484 |
+
"num_input_tokens_seen": 42528,
|
| 485 |
+
"step": 280
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.5833333333333335,
|
| 489 |
+
"grad_norm": 33.2148323059082,
|
| 490 |
+
"learning_rate": 4.9493273284883854e-05,
|
| 491 |
+
"loss": 0.1143,
|
| 492 |
+
"num_input_tokens_seen": 43280,
|
| 493 |
+
"step": 285
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.6111111111111112,
|
| 497 |
+
"grad_norm": 9.084549903869629,
|
| 498 |
+
"learning_rate": 4.9443564199855666e-05,
|
| 499 |
+
"loss": 0.1255,
|
| 500 |
+
"num_input_tokens_seen": 44016,
|
| 501 |
+
"step": 290
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.6388888888888888,
|
| 505 |
+
"grad_norm": 0.012888729572296143,
|
| 506 |
+
"learning_rate": 4.939155700460536e-05,
|
| 507 |
+
"loss": 0.2754,
|
| 508 |
+
"num_input_tokens_seen": 44800,
|
| 509 |
+
"step": 295
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.6666666666666665,
|
| 513 |
+
"grad_norm": 0.01083407737314701,
|
| 514 |
+
"learning_rate": 4.933725658869267e-05,
|
| 515 |
+
"loss": 0.0569,
|
| 516 |
+
"num_input_tokens_seen": 45584,
|
| 517 |
+
"step": 300
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 1.6944444444444444,
|
| 521 |
+
"grad_norm": 0.009935064241290092,
|
| 522 |
+
"learning_rate": 4.9280668057279014e-05,
|
| 523 |
+
"loss": 0.192,
|
| 524 |
+
"num_input_tokens_seen": 46352,
|
| 525 |
+
"step": 305
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.7222222222222223,
|
| 529 |
+
"grad_norm": 43.675479888916016,
|
| 530 |
+
"learning_rate": 4.9221796730647516e-05,
|
| 531 |
+
"loss": 0.2653,
|
| 532 |
+
"num_input_tokens_seen": 47136,
|
| 533 |
+
"step": 310
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.75,
|
| 537 |
+
"grad_norm": 0.01382085308432579,
|
| 538 |
+
"learning_rate": 4.916064814370287e-05,
|
| 539 |
+
"loss": 0.0002,
|
| 540 |
+
"num_input_tokens_seen": 47904,
|
| 541 |
+
"step": 315
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.7777777777777777,
|
| 545 |
+
"grad_norm": 0.05889115855097771,
|
| 546 |
+
"learning_rate": 4.9097228045450864e-05,
|
| 547 |
+
"loss": 0.0328,
|
| 548 |
+
"num_input_tokens_seen": 48704,
|
| 549 |
+
"step": 320
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.8055555555555556,
|
| 553 |
+
"grad_norm": 0.028889305889606476,
|
| 554 |
+
"learning_rate": 4.9031542398457974e-05,
|
| 555 |
+
"loss": 0.0228,
|
| 556 |
+
"num_input_tokens_seen": 49440,
|
| 557 |
+
"step": 325
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.8333333333333335,
|
| 561 |
+
"grad_norm": 0.016455378383398056,
|
| 562 |
+
"learning_rate": 4.896359737829071e-05,
|
| 563 |
+
"loss": 0.0645,
|
| 564 |
+
"num_input_tokens_seen": 50224,
|
| 565 |
+
"step": 330
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 1.8611111111111112,
|
| 569 |
+
"grad_norm": 2.9751687049865723,
|
| 570 |
+
"learning_rate": 4.889339937293508e-05,
|
| 571 |
+
"loss": 0.011,
|
| 572 |
+
"num_input_tokens_seen": 50976,
|
| 573 |
+
"step": 335
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.8888888888888888,
|
| 577 |
+
"grad_norm": 26.30304527282715,
|
| 578 |
+
"learning_rate": 4.8820954982195905e-05,
|
| 579 |
+
"loss": 0.0502,
|
| 580 |
+
"num_input_tokens_seen": 51760,
|
| 581 |
+
"step": 340
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.9166666666666665,
|
| 585 |
+
"grad_norm": 0.008524544537067413,
|
| 586 |
+
"learning_rate": 4.874627101707644e-05,
|
| 587 |
+
"loss": 0.1273,
|
| 588 |
+
"num_input_tokens_seen": 52496,
|
| 589 |
+
"step": 345
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.9444444444444444,
|
| 593 |
+
"grad_norm": 0.3469292223453522,
|
| 594 |
+
"learning_rate": 4.8669354499137955e-05,
|
| 595 |
+
"loss": 0.0112,
|
| 596 |
+
"num_input_tokens_seen": 53264,
|
| 597 |
+
"step": 350
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.9722222222222223,
|
| 601 |
+
"grad_norm": 0.02578221634030342,
|
| 602 |
+
"learning_rate": 4.859021265983959e-05,
|
| 603 |
+
"loss": 0.0041,
|
| 604 |
+
"num_input_tokens_seen": 54032,
|
| 605 |
+
"step": 355
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.0,
|
| 609 |
+
"grad_norm": 0.01661246083676815,
|
| 610 |
+
"learning_rate": 4.850885293985853e-05,
|
| 611 |
+
"loss": 0.0002,
|
| 612 |
+
"num_input_tokens_seen": 54800,
|
| 613 |
+
"step": 360
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.0,
|
| 617 |
+
"eval_loss": 0.13968539237976074,
|
| 618 |
+
"eval_runtime": 0.8731,
|
| 619 |
+
"eval_samples_per_second": 45.813,
|
| 620 |
+
"eval_steps_per_second": 22.906,
|
| 621 |
+
"num_input_tokens_seen": 54800,
|
| 622 |
+
"step": 360
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 2.0277777777777777,
|
| 626 |
+
"grad_norm": 0.009064249694347382,
|
| 627 |
+
"learning_rate": 4.8425282988390376e-05,
|
| 628 |
+
"loss": 0.0901,
|
| 629 |
+
"num_input_tokens_seen": 55536,
|
| 630 |
+
"step": 365
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.0555555555555554,
|
| 634 |
+
"grad_norm": 0.008344353176653385,
|
| 635 |
+
"learning_rate": 4.8339510662430046e-05,
|
| 636 |
+
"loss": 0.0004,
|
| 637 |
+
"num_input_tokens_seen": 56288,
|
| 638 |
+
"step": 370
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.0833333333333335,
|
| 642 |
+
"grad_norm": 0.6907618045806885,
|
| 643 |
+
"learning_rate": 4.825154402603308e-05,
|
| 644 |
+
"loss": 0.0072,
|
| 645 |
+
"num_input_tokens_seen": 57072,
|
| 646 |
+
"step": 375
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.111111111111111,
|
| 650 |
+
"grad_norm": 0.006057972088456154,
|
| 651 |
+
"learning_rate": 4.816139134955746e-05,
|
| 652 |
+
"loss": 0.0002,
|
| 653 |
+
"num_input_tokens_seen": 57840,
|
| 654 |
+
"step": 380
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.138888888888889,
|
| 658 |
+
"grad_norm": 0.007125409319996834,
|
| 659 |
+
"learning_rate": 4.806906110888606e-05,
|
| 660 |
+
"loss": 0.0004,
|
| 661 |
+
"num_input_tokens_seen": 58592,
|
| 662 |
+
"step": 385
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.1666666666666665,
|
| 666 |
+
"grad_norm": 0.004793958738446236,
|
| 667 |
+
"learning_rate": 4.797456198462979e-05,
|
| 668 |
+
"loss": 0.1331,
|
| 669 |
+
"num_input_tokens_seen": 59328,
|
| 670 |
+
"step": 390
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 2.1944444444444446,
|
| 674 |
+
"grad_norm": 0.009237749502062798,
|
| 675 |
+
"learning_rate": 4.7877902861311446e-05,
|
| 676 |
+
"loss": 0.0028,
|
| 677 |
+
"num_input_tokens_seen": 60080,
|
| 678 |
+
"step": 395
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 2.2222222222222223,
|
| 682 |
+
"grad_norm": 0.0056296358816325665,
|
| 683 |
+
"learning_rate": 4.777909282653042e-05,
|
| 684 |
+
"loss": 0.0002,
|
| 685 |
+
"num_input_tokens_seen": 60832,
|
| 686 |
+
"step": 400
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.25,
|
| 690 |
+
"grad_norm": 0.011304618790745735,
|
| 691 |
+
"learning_rate": 4.7678141170108345e-05,
|
| 692 |
+
"loss": 0.0029,
|
| 693 |
+
"num_input_tokens_seen": 61568,
|
| 694 |
+
"step": 405
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.2777777777777777,
|
| 698 |
+
"grad_norm": 64.0176010131836,
|
| 699 |
+
"learning_rate": 4.757505738321563e-05,
|
| 700 |
+
"loss": 0.2675,
|
| 701 |
+
"num_input_tokens_seen": 62336,
|
| 702 |
+
"step": 410
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.3055555555555554,
|
| 706 |
+
"grad_norm": 0.006608088966459036,
|
| 707 |
+
"learning_rate": 4.7469851157479177e-05,
|
| 708 |
+
"loss": 0.4822,
|
| 709 |
+
"num_input_tokens_seen": 63088,
|
| 710 |
+
"step": 415
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.3333333333333335,
|
| 714 |
+
"grad_norm": 0.012060252949595451,
|
| 715 |
+
"learning_rate": 4.736253238407119e-05,
|
| 716 |
+
"loss": 0.0014,
|
| 717 |
+
"num_input_tokens_seen": 63888,
|
| 718 |
+
"step": 420
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.361111111111111,
|
| 722 |
+
"grad_norm": 0.0077227340079844,
|
| 723 |
+
"learning_rate": 4.725311115277924e-05,
|
| 724 |
+
"loss": 0.2626,
|
| 725 |
+
"num_input_tokens_seen": 64640,
|
| 726 |
+
"step": 425
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 2.388888888888889,
|
| 730 |
+
"grad_norm": 0.1587001085281372,
|
| 731 |
+
"learning_rate": 4.714159775105765e-05,
|
| 732 |
+
"loss": 0.1269,
|
| 733 |
+
"num_input_tokens_seen": 65392,
|
| 734 |
+
"step": 430
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.4166666666666665,
|
| 738 |
+
"grad_norm": 0.029979098588228226,
|
| 739 |
+
"learning_rate": 4.70280026630603e-05,
|
| 740 |
+
"loss": 0.0013,
|
| 741 |
+
"num_input_tokens_seen": 66176,
|
| 742 |
+
"step": 435
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.4444444444444446,
|
| 746 |
+
"grad_norm": 41.430625915527344,
|
| 747 |
+
"learning_rate": 4.6912336568654925e-05,
|
| 748 |
+
"loss": 0.0537,
|
| 749 |
+
"num_input_tokens_seen": 66960,
|
| 750 |
+
"step": 440
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.4722222222222223,
|
| 754 |
+
"grad_norm": 0.01960122212767601,
|
| 755 |
+
"learning_rate": 4.679461034241906e-05,
|
| 756 |
+
"loss": 0.0001,
|
| 757 |
+
"num_input_tokens_seen": 67712,
|
| 758 |
+
"step": 445
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.5,
|
| 762 |
+
"grad_norm": 0.017095442861318588,
|
| 763 |
+
"learning_rate": 4.667483505261762e-05,
|
| 764 |
+
"loss": 0.1191,
|
| 765 |
+
"num_input_tokens_seen": 68480,
|
| 766 |
+
"step": 450
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.5,
|
| 770 |
+
"eval_loss": 0.14334793388843536,
|
| 771 |
+
"eval_runtime": 0.8472,
|
| 772 |
+
"eval_samples_per_second": 47.214,
|
| 773 |
+
"eval_steps_per_second": 23.607,
|
| 774 |
+
"num_input_tokens_seen": 68480,
|
| 775 |
+
"step": 450
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.5277777777777777,
|
| 779 |
+
"grad_norm": 0.8339170217514038,
|
| 780 |
+
"learning_rate": 4.655302196016228e-05,
|
| 781 |
+
"loss": 0.0006,
|
| 782 |
+
"num_input_tokens_seen": 69248,
|
| 783 |
+
"step": 455
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 2.5555555555555554,
|
| 787 |
+
"grad_norm": 0.007273822091519833,
|
| 788 |
+
"learning_rate": 4.642918251755281e-05,
|
| 789 |
+
"loss": 0.0003,
|
| 790 |
+
"num_input_tokens_seen": 70016,
|
| 791 |
+
"step": 460
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.5833333333333335,
|
| 795 |
+
"grad_norm": 0.10730123519897461,
|
| 796 |
+
"learning_rate": 4.6303328367800284e-05,
|
| 797 |
+
"loss": 0.0032,
|
| 798 |
+
"num_input_tokens_seen": 70784,
|
| 799 |
+
"step": 465
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 2.611111111111111,
|
| 803 |
+
"grad_norm": 0.00880274549126625,
|
| 804 |
+
"learning_rate": 4.6175471343332485e-05,
|
| 805 |
+
"loss": 0.0016,
|
| 806 |
+
"num_input_tokens_seen": 71552,
|
| 807 |
+
"step": 470
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.638888888888889,
|
| 811 |
+
"grad_norm": 0.0065057664178311825,
|
| 812 |
+
"learning_rate": 4.604562346488144e-05,
|
| 813 |
+
"loss": 0.0131,
|
| 814 |
+
"num_input_tokens_seen": 72288,
|
| 815 |
+
"step": 475
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 2.6666666666666665,
|
| 819 |
+
"grad_norm": 0.009263488464057446,
|
| 820 |
+
"learning_rate": 4.591379694035325e-05,
|
| 821 |
+
"loss": 0.0409,
|
| 822 |
+
"num_input_tokens_seen": 73072,
|
| 823 |
+
"step": 480
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.6944444444444446,
|
| 827 |
+
"grad_norm": 0.005506084766238928,
|
| 828 |
+
"learning_rate": 4.5780004163680365e-05,
|
| 829 |
+
"loss": 0.0004,
|
| 830 |
+
"num_input_tokens_seen": 73856,
|
| 831 |
+
"step": 485
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.7222222222222223,
|
| 835 |
+
"grad_norm": 19.782270431518555,
|
| 836 |
+
"learning_rate": 4.5644257713656356e-05,
|
| 837 |
+
"loss": 0.0572,
|
| 838 |
+
"num_input_tokens_seen": 74624,
|
| 839 |
+
"step": 490
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 2.75,
|
| 843 |
+
"grad_norm": 0.009718476794660091,
|
| 844 |
+
"learning_rate": 4.550657035275323e-05,
|
| 845 |
+
"loss": 0.0002,
|
| 846 |
+
"num_input_tokens_seen": 75392,
|
| 847 |
+
"step": 495
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 2.7777777777777777,
|
| 851 |
+
"grad_norm": 0.006279336288571358,
|
| 852 |
+
"learning_rate": 4.536695502592162e-05,
|
| 853 |
+
"loss": 0.0001,
|
| 854 |
+
"num_input_tokens_seen": 76160,
|
| 855 |
+
"step": 500
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.8055555555555554,
|
| 859 |
+
"grad_norm": 0.00757136195898056,
|
| 860 |
+
"learning_rate": 4.522542485937369e-05,
|
| 861 |
+
"loss": 0.0326,
|
| 862 |
+
"num_input_tokens_seen": 76912,
|
| 863 |
+
"step": 505
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.8333333333333335,
|
| 867 |
+
"grad_norm": 0.016545820981264114,
|
| 868 |
+
"learning_rate": 4.5081993159349056e-05,
|
| 869 |
+
"loss": 0.0001,
|
| 870 |
+
"num_input_tokens_seen": 77680,
|
| 871 |
+
"step": 510
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 2.861111111111111,
|
| 875 |
+
"grad_norm": 0.00826545711606741,
|
| 876 |
+
"learning_rate": 4.493667341086379e-05,
|
| 877 |
+
"loss": 0.0002,
|
| 878 |
+
"num_input_tokens_seen": 78464,
|
| 879 |
+
"step": 515
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.888888888888889,
|
| 883 |
+
"grad_norm": 0.005500601138919592,
|
| 884 |
+
"learning_rate": 4.478947927644258e-05,
|
| 885 |
+
"loss": 0.0569,
|
| 886 |
+
"num_input_tokens_seen": 79232,
|
| 887 |
+
"step": 520
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 2.9166666666666665,
|
| 891 |
+
"grad_norm": 0.005263440310955048,
|
| 892 |
+
"learning_rate": 4.464042459483425e-05,
|
| 893 |
+
"loss": 0.1451,
|
| 894 |
+
"num_input_tokens_seen": 79968,
|
| 895 |
+
"step": 525
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 2.9444444444444446,
|
| 899 |
+
"grad_norm": 0.008182135410606861,
|
| 900 |
+
"learning_rate": 4.448952337971064e-05,
|
| 901 |
+
"loss": 0.0001,
|
| 902 |
+
"num_input_tokens_seen": 80736,
|
| 903 |
+
"step": 530
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 2.9722222222222223,
|
| 907 |
+
"grad_norm": 0.06003406643867493,
|
| 908 |
+
"learning_rate": 4.43367898183491e-05,
|
| 909 |
+
"loss": 0.2445,
|
| 910 |
+
"num_input_tokens_seen": 81488,
|
| 911 |
+
"step": 535
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.0,
|
| 915 |
+
"grad_norm": 0.010744345374405384,
|
| 916 |
+
"learning_rate": 4.418223827029867e-05,
|
| 917 |
+
"loss": 0.0747,
|
| 918 |
+
"num_input_tokens_seen": 82256,
|
| 919 |
+
"step": 540
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 3.0,
|
| 923 |
+
"eval_loss": 0.1585792750120163,
|
| 924 |
+
"eval_runtime": 0.8639,
|
| 925 |
+
"eval_samples_per_second": 46.299,
|
| 926 |
+
"eval_steps_per_second": 23.15,
|
| 927 |
+
"num_input_tokens_seen": 82256,
|
| 928 |
+
"step": 540
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 3.0277777777777777,
|
| 932 |
+
"grad_norm": 0.004692050628364086,
|
| 933 |
+
"learning_rate": 4.402588326603002e-05,
|
| 934 |
+
"loss": 0.0068,
|
| 935 |
+
"num_input_tokens_seen": 83008,
|
| 936 |
+
"step": 545
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 3.0555555555555554,
|
| 940 |
+
"grad_norm": 0.008360066451132298,
|
| 941 |
+
"learning_rate": 4.386773950556931e-05,
|
| 942 |
+
"loss": 0.0001,
|
| 943 |
+
"num_input_tokens_seen": 83760,
|
| 944 |
+
"step": 550
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.0833333333333335,
|
| 948 |
+
"grad_norm": 0.003476613201200962,
|
| 949 |
+
"learning_rate": 4.3707821857116176e-05,
|
| 950 |
+
"loss": 0.1888,
|
| 951 |
+
"num_input_tokens_seen": 84512,
|
| 952 |
+
"step": 555
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 3.111111111111111,
|
| 956 |
+
"grad_norm": 0.005749064963310957,
|
| 957 |
+
"learning_rate": 4.354614535564588e-05,
|
| 958 |
+
"loss": 0.0001,
|
| 959 |
+
"num_input_tokens_seen": 85264,
|
| 960 |
+
"step": 560
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.138888888888889,
|
| 964 |
+
"grad_norm": 0.039910800755023956,
|
| 965 |
+
"learning_rate": 4.3382725201495723e-05,
|
| 966 |
+
"loss": 0.0003,
|
| 967 |
+
"num_input_tokens_seen": 86048,
|
| 968 |
+
"step": 565
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 3.1666666666666665,
|
| 972 |
+
"grad_norm": 0.010388891212642193,
|
| 973 |
+
"learning_rate": 4.321757675893596e-05,
|
| 974 |
+
"loss": 0.0001,
|
| 975 |
+
"num_input_tokens_seen": 86784,
|
| 976 |
+
"step": 570
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 3.1944444444444446,
|
| 980 |
+
"grad_norm": 0.009365994483232498,
|
| 981 |
+
"learning_rate": 4.305071555472534e-05,
|
| 982 |
+
"loss": 0.0061,
|
| 983 |
+
"num_input_tokens_seen": 87568,
|
| 984 |
+
"step": 575
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 3.2222222222222223,
|
| 988 |
+
"grad_norm": 0.003861945355311036,
|
| 989 |
+
"learning_rate": 4.288215727665129e-05,
|
| 990 |
+
"loss": 0.0017,
|
| 991 |
+
"num_input_tokens_seen": 88320,
|
| 992 |
+
"step": 580
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.25,
|
| 996 |
+
"grad_norm": 0.0033517684787511826,
|
| 997 |
+
"learning_rate": 4.2711917772055e-05,
|
| 998 |
+
"loss": 0.2939,
|
| 999 |
+
"num_input_tokens_seen": 89072,
|
| 1000 |
+
"step": 585
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 3.2777777777777777,
|
| 1004 |
+
"grad_norm": 0.0706770047545433,
|
| 1005 |
+
"learning_rate": 4.254001304634151e-05,
|
| 1006 |
+
"loss": 0.0001,
|
| 1007 |
+
"num_input_tokens_seen": 89872,
|
| 1008 |
+
"step": 590
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.3055555555555554,
|
| 1012 |
+
"grad_norm": 12.658806800842285,
|
| 1013 |
+
"learning_rate": 4.2366459261474933e-05,
|
| 1014 |
+
"loss": 0.005,
|
| 1015 |
+
"num_input_tokens_seen": 90640,
|
| 1016 |
+
"step": 595
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.3333333333333335,
|
| 1020 |
+
"grad_norm": 0.6362056732177734,
|
| 1021 |
+
"learning_rate": 4.2191272734458955e-05,
|
| 1022 |
+
"loss": 0.0005,
|
| 1023 |
+
"num_input_tokens_seen": 91376,
|
| 1024 |
+
"step": 600
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.361111111111111,
|
| 1028 |
+
"grad_norm": 0.008696366101503372,
|
| 1029 |
+
"learning_rate": 4.201446993580276e-05,
|
| 1030 |
+
"loss": 0.0193,
|
| 1031 |
+
"num_input_tokens_seen": 92128,
|
| 1032 |
+
"step": 605
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 3.388888888888889,
|
| 1036 |
+
"grad_norm": 0.013609865680336952,
|
| 1037 |
+
"learning_rate": 4.183606748797251e-05,
|
| 1038 |
+
"loss": 0.0001,
|
| 1039 |
+
"num_input_tokens_seen": 92912,
|
| 1040 |
+
"step": 610
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.4166666666666665,
|
| 1044 |
+
"grad_norm": 0.0021089082583785057,
|
| 1045 |
+
"learning_rate": 4.1656082163828566e-05,
|
| 1046 |
+
"loss": 0.0002,
|
| 1047 |
+
"num_input_tokens_seen": 93632,
|
| 1048 |
+
"step": 615
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 3.4444444444444446,
|
| 1052 |
+
"grad_norm": 0.004418779164552689,
|
| 1053 |
+
"learning_rate": 4.147453088504854e-05,
|
| 1054 |
+
"loss": 0.0002,
|
| 1055 |
+
"num_input_tokens_seen": 94384,
|
| 1056 |
+
"step": 620
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 3.4722222222222223,
|
| 1060 |
+
"grad_norm": 0.004805439617484808,
|
| 1061 |
+
"learning_rate": 4.129143072053638e-05,
|
| 1062 |
+
"loss": 0.0001,
|
| 1063 |
+
"num_input_tokens_seen": 95152,
|
| 1064 |
+
"step": 625
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.5,
|
| 1068 |
+
"grad_norm": 0.005893156863749027,
|
| 1069 |
+
"learning_rate": 4.110679888481763e-05,
|
| 1070 |
+
"loss": 0.0001,
|
| 1071 |
+
"num_input_tokens_seen": 95920,
|
| 1072 |
+
"step": 630
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 3.5,
|
| 1076 |
+
"eval_loss": 0.15426704287528992,
|
| 1077 |
+
"eval_runtime": 0.9961,
|
| 1078 |
+
"eval_samples_per_second": 40.157,
|
| 1079 |
+
"eval_steps_per_second": 20.079,
|
| 1080 |
+
"num_input_tokens_seen": 95920,
|
| 1081 |
+
"step": 630
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 3.5277777777777777,
|
| 1085 |
+
"grad_norm": 0.21285879611968994,
|
| 1086 |
+
"learning_rate": 4.09206527364209e-05,
|
| 1087 |
+
"loss": 0.0003,
|
| 1088 |
+
"num_input_tokens_seen": 96704,
|
| 1089 |
+
"step": 635
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 3.5555555555555554,
|
| 1093 |
+
"grad_norm": 0.004686427302658558,
|
| 1094 |
+
"learning_rate": 4.073300977624594e-05,
|
| 1095 |
+
"loss": 0.0496,
|
| 1096 |
+
"num_input_tokens_seen": 97456,
|
| 1097 |
+
"step": 640
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 3.5833333333333335,
|
| 1101 |
+
"grad_norm": 0.006941783241927624,
|
| 1102 |
+
"learning_rate": 4.054388764591822e-05,
|
| 1103 |
+
"loss": 0.0001,
|
| 1104 |
+
"num_input_tokens_seen": 98192,
|
| 1105 |
+
"step": 645
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 3.611111111111111,
|
| 1109 |
+
"grad_norm": 0.003678448498249054,
|
| 1110 |
+
"learning_rate": 4.035330412613035e-05,
|
| 1111 |
+
"loss": 0.0003,
|
| 1112 |
+
"num_input_tokens_seen": 98944,
|
| 1113 |
+
"step": 650
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 3.638888888888889,
|
| 1117 |
+
"grad_norm": 0.0034077675081789494,
|
| 1118 |
+
"learning_rate": 4.0161277134970345e-05,
|
| 1119 |
+
"loss": 0.0019,
|
| 1120 |
+
"num_input_tokens_seen": 99712,
|
| 1121 |
+
"step": 655
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 3.6666666666666665,
|
| 1125 |
+
"grad_norm": 0.003917415160685778,
|
| 1126 |
+
"learning_rate": 3.996782472623705e-05,
|
| 1127 |
+
"loss": 0.0002,
|
| 1128 |
+
"num_input_tokens_seen": 100496,
|
| 1129 |
+
"step": 660
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 3.6944444444444446,
|
| 1133 |
+
"grad_norm": 0.004346042405813932,
|
| 1134 |
+
"learning_rate": 3.977296508774278e-05,
|
| 1135 |
+
"loss": 0.0003,
|
| 1136 |
+
"num_input_tokens_seen": 101232,
|
| 1137 |
+
"step": 665
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 3.7222222222222223,
|
| 1141 |
+
"grad_norm": 0.03601907566189766,
|
| 1142 |
+
"learning_rate": 3.957671653960337e-05,
|
| 1143 |
+
"loss": 0.1836,
|
| 1144 |
+
"num_input_tokens_seen": 102000,
|
| 1145 |
+
"step": 670
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 3.75,
|
| 1149 |
+
"grad_norm": 0.029370684176683426,
|
| 1150 |
+
"learning_rate": 3.9379097532515725e-05,
|
| 1151 |
+
"loss": 0.3127,
|
| 1152 |
+
"num_input_tokens_seen": 102784,
|
| 1153 |
+
"step": 675
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 3.7777777777777777,
|
| 1157 |
+
"grad_norm": 0.02692316845059395,
|
| 1158 |
+
"learning_rate": 3.918012664602317e-05,
|
| 1159 |
+
"loss": 0.0013,
|
| 1160 |
+
"num_input_tokens_seen": 103584,
|
| 1161 |
+
"step": 680
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 3.8055555555555554,
|
| 1165 |
+
"grad_norm": 0.003177183447405696,
|
| 1166 |
+
"learning_rate": 3.897982258676867e-05,
|
| 1167 |
+
"loss": 0.0001,
|
| 1168 |
+
"num_input_tokens_seen": 104368,
|
| 1169 |
+
"step": 685
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 3.8333333333333335,
|
| 1173 |
+
"grad_norm": 0.003096670377999544,
|
| 1174 |
+
"learning_rate": 3.8778204186736076e-05,
|
| 1175 |
+
"loss": 0.0001,
|
| 1176 |
+
"num_input_tokens_seen": 105104,
|
| 1177 |
+
"step": 690
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 3.861111111111111,
|
| 1181 |
+
"grad_norm": 0.004423821810632944,
|
| 1182 |
+
"learning_rate": 3.8575290401479586e-05,
|
| 1183 |
+
"loss": 0.0411,
|
| 1184 |
+
"num_input_tokens_seen": 105856,
|
| 1185 |
+
"step": 695
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.888888888888889,
|
| 1189 |
+
"grad_norm": 0.009440253488719463,
|
| 1190 |
+
"learning_rate": 3.837110030834161e-05,
|
| 1191 |
+
"loss": 0.099,
|
| 1192 |
+
"num_input_tokens_seen": 106624,
|
| 1193 |
+
"step": 700
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 3.9166666666666665,
|
| 1197 |
+
"grad_norm": 0.003973190672695637,
|
| 1198 |
+
"learning_rate": 3.8165653104659185e-05,
|
| 1199 |
+
"loss": 0.0108,
|
| 1200 |
+
"num_input_tokens_seen": 107408,
|
| 1201 |
+
"step": 705
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 3.9444444444444446,
|
| 1205 |
+
"grad_norm": 0.006104958709329367,
|
| 1206 |
+
"learning_rate": 3.79589681059591e-05,
|
| 1207 |
+
"loss": 0.0232,
|
| 1208 |
+
"num_input_tokens_seen": 108160,
|
| 1209 |
+
"step": 710
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 3.9722222222222223,
|
| 1213 |
+
"grad_norm": 0.0029671171214431524,
|
| 1214 |
+
"learning_rate": 3.775106474414188e-05,
|
| 1215 |
+
"loss": 0.0001,
|
| 1216 |
+
"num_input_tokens_seen": 108928,
|
| 1217 |
+
"step": 715
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 4.0,
|
| 1221 |
+
"grad_norm": 0.006943428888916969,
|
| 1222 |
+
"learning_rate": 3.75419625656549e-05,
|
| 1223 |
+
"loss": 0.0276,
|
| 1224 |
+
"num_input_tokens_seen": 109680,
|
| 1225 |
+
"step": 720
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 4.0,
|
| 1229 |
+
"eval_loss": 0.1733400523662567,
|
| 1230 |
+
"eval_runtime": 0.8977,
|
| 1231 |
+
"eval_samples_per_second": 44.56,
|
| 1232 |
+
"eval_steps_per_second": 22.28,
|
| 1233 |
+
"num_input_tokens_seen": 109680,
|
| 1234 |
+
"step": 720
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 4.027777777777778,
|
| 1238 |
+
"grad_norm": 0.35043978691101074,
|
| 1239 |
+
"learning_rate": 3.7331681229654635e-05,
|
| 1240 |
+
"loss": 0.122,
|
| 1241 |
+
"num_input_tokens_seen": 110448,
|
| 1242 |
+
"step": 725
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 4.055555555555555,
|
| 1246 |
+
"grad_norm": 0.009929414838552475,
|
| 1247 |
+
"learning_rate": 3.712024050615843e-05,
|
| 1248 |
+
"loss": 0.0017,
|
| 1249 |
+
"num_input_tokens_seen": 111216,
|
| 1250 |
+
"step": 730
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 4.083333333333333,
|
| 1254 |
+
"grad_norm": 0.004455262329429388,
|
| 1255 |
+
"learning_rate": 3.690766027418573e-05,
|
| 1256 |
+
"loss": 0.0002,
|
| 1257 |
+
"num_input_tokens_seen": 111968,
|
| 1258 |
+
"step": 735
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 4.111111111111111,
|
| 1262 |
+
"grad_norm": 74.90491485595703,
|
| 1263 |
+
"learning_rate": 3.6693960519889106e-05,
|
| 1264 |
+
"loss": 0.0829,
|
| 1265 |
+
"num_input_tokens_seen": 112736,
|
| 1266 |
+
"step": 740
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 4.138888888888889,
|
| 1270 |
+
"grad_norm": 0.005577894859015942,
|
| 1271 |
+
"learning_rate": 3.6479161334675296e-05,
|
| 1272 |
+
"loss": 0.0069,
|
| 1273 |
+
"num_input_tokens_seen": 113488,
|
| 1274 |
+
"step": 745
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 4.166666666666667,
|
| 1278 |
+
"grad_norm": 0.0027480549179017544,
|
| 1279 |
+
"learning_rate": 3.626328291331618e-05,
|
| 1280 |
+
"loss": 0.0001,
|
| 1281 |
+
"num_input_tokens_seen": 114256,
|
| 1282 |
+
"step": 750
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 4.194444444444445,
|
| 1286 |
+
"grad_norm": 0.002460277173668146,
|
| 1287 |
+
"learning_rate": 3.60463455520502e-05,
|
| 1288 |
+
"loss": 0.0005,
|
| 1289 |
+
"num_input_tokens_seen": 115024,
|
| 1290 |
+
"step": 755
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 4.222222222222222,
|
| 1294 |
+
"grad_norm": 4.454160690307617,
|
| 1295 |
+
"learning_rate": 3.582836964667408e-05,
|
| 1296 |
+
"loss": 0.2813,
|
| 1297 |
+
"num_input_tokens_seen": 115776,
|
| 1298 |
+
"step": 760
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 4.25,
|
| 1302 |
+
"grad_norm": 0.0043601770885288715,
|
| 1303 |
+
"learning_rate": 3.560937569062538e-05,
|
| 1304 |
+
"loss": 0.2045,
|
| 1305 |
+
"num_input_tokens_seen": 116560,
|
| 1306 |
+
"step": 765
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 4.277777777777778,
|
| 1310 |
+
"grad_norm": 0.020831065252423286,
|
| 1311 |
+
"learning_rate": 3.538938427305573e-05,
|
| 1312 |
+
"loss": 0.0006,
|
| 1313 |
+
"num_input_tokens_seen": 117344,
|
| 1314 |
+
"step": 770
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 4.305555555555555,
|
| 1318 |
+
"grad_norm": 0.0023294168058782816,
|
| 1319 |
+
"learning_rate": 3.516841607689501e-05,
|
| 1320 |
+
"loss": 0.0001,
|
| 1321 |
+
"num_input_tokens_seen": 118080,
|
| 1322 |
+
"step": 775
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 4.333333333333333,
|
| 1326 |
+
"grad_norm": 0.011770294979214668,
|
| 1327 |
+
"learning_rate": 3.494649187690695e-05,
|
| 1328 |
+
"loss": 0.0001,
|
| 1329 |
+
"num_input_tokens_seen": 118848,
|
| 1330 |
+
"step": 780
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 4.361111111111111,
|
| 1334 |
+
"grad_norm": 0.002268734388053417,
|
| 1335 |
+
"learning_rate": 3.4723632537735846e-05,
|
| 1336 |
+
"loss": 0.0019,
|
| 1337 |
+
"num_input_tokens_seen": 119632,
|
| 1338 |
+
"step": 785
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 4.388888888888889,
|
| 1342 |
+
"grad_norm": 0.0043189446441829205,
|
| 1343 |
+
"learning_rate": 3.449985901194498e-05,
|
| 1344 |
+
"loss": 0.0015,
|
| 1345 |
+
"num_input_tokens_seen": 120368,
|
| 1346 |
+
"step": 790
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 4.416666666666667,
|
| 1350 |
+
"grad_norm": 0.003947732038795948,
|
| 1351 |
+
"learning_rate": 3.427519233804667e-05,
|
| 1352 |
+
"loss": 0.0021,
|
| 1353 |
+
"num_input_tokens_seen": 121136,
|
| 1354 |
+
"step": 795
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 4.444444444444445,
|
| 1358 |
+
"grad_norm": 0.007481610402464867,
|
| 1359 |
+
"learning_rate": 3.404965363852437e-05,
|
| 1360 |
+
"loss": 0.0001,
|
| 1361 |
+
"num_input_tokens_seen": 121888,
|
| 1362 |
+
"step": 800
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 4.472222222222222,
|
| 1366 |
+
"grad_norm": 0.006325196009129286,
|
| 1367 |
+
"learning_rate": 3.382326411784672e-05,
|
| 1368 |
+
"loss": 0.0004,
|
| 1369 |
+
"num_input_tokens_seen": 122656,
|
| 1370 |
+
"step": 805
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 4.5,
|
| 1374 |
+
"grad_norm": 0.0031090332195162773,
|
| 1375 |
+
"learning_rate": 3.359604506047403e-05,
|
| 1376 |
+
"loss": 0.0001,
|
| 1377 |
+
"num_input_tokens_seen": 123408,
|
| 1378 |
+
"step": 810
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 4.5,
|
| 1382 |
+
"eval_loss": 0.17834582924842834,
|
| 1383 |
+
"eval_runtime": 0.9091,
|
| 1384 |
+
"eval_samples_per_second": 43.998,
|
| 1385 |
+
"eval_steps_per_second": 21.999,
|
| 1386 |
+
"num_input_tokens_seen": 123408,
|
| 1387 |
+
"step": 810
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 4.527777777777778,
|
| 1391 |
+
"grad_norm": 0.003541292157024145,
|
| 1392 |
+
"learning_rate": 3.336801782885712e-05,
|
| 1393 |
+
"loss": 0.0001,
|
| 1394 |
+
"num_input_tokens_seen": 124160,
|
| 1395 |
+
"step": 815
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 4.555555555555555,
|
| 1399 |
+
"grad_norm": 0.0038108064327389,
|
| 1400 |
+
"learning_rate": 3.313920386142892e-05,
|
| 1401 |
+
"loss": 0.0001,
|
| 1402 |
+
"num_input_tokens_seen": 124928,
|
| 1403 |
+
"step": 820
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 4.583333333333333,
|
| 1407 |
+
"grad_norm": 0.28179842233657837,
|
| 1408 |
+
"learning_rate": 3.290962467058891e-05,
|
| 1409 |
+
"loss": 0.0002,
|
| 1410 |
+
"num_input_tokens_seen": 125696,
|
| 1411 |
+
"step": 825
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 4.611111111111111,
|
| 1415 |
+
"grad_norm": 0.0035293474793434143,
|
| 1416 |
+
"learning_rate": 3.267930184068057e-05,
|
| 1417 |
+
"loss": 0.0001,
|
| 1418 |
+
"num_input_tokens_seen": 126448,
|
| 1419 |
+
"step": 830
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 4.638888888888889,
|
| 1423 |
+
"grad_norm": 0.00379269034601748,
|
| 1424 |
+
"learning_rate": 3.244825702596205e-05,
|
| 1425 |
+
"loss": 0.0,
|
| 1426 |
+
"num_input_tokens_seen": 127184,
|
| 1427 |
+
"step": 835
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 4.666666666666667,
|
| 1431 |
+
"grad_norm": 0.0022270483896136284,
|
| 1432 |
+
"learning_rate": 3.2216511948570374e-05,
|
| 1433 |
+
"loss": 0.0002,
|
| 1434 |
+
"num_input_tokens_seen": 127936,
|
| 1435 |
+
"step": 840
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 4.694444444444445,
|
| 1439 |
+
"grad_norm": 0.017402423545718193,
|
| 1440 |
+
"learning_rate": 3.198408839647911e-05,
|
| 1441 |
+
"loss": 0.0004,
|
| 1442 |
+
"num_input_tokens_seen": 128688,
|
| 1443 |
+
"step": 845
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 4.722222222222222,
|
| 1447 |
+
"grad_norm": 0.00284409336745739,
|
| 1448 |
+
"learning_rate": 3.1751008221450025e-05,
|
| 1449 |
+
"loss": 0.0,
|
| 1450 |
+
"num_input_tokens_seen": 129456,
|
| 1451 |
+
"step": 850
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 4.75,
|
| 1455 |
+
"grad_norm": 0.0019377171993255615,
|
| 1456 |
+
"learning_rate": 3.151729333697854e-05,
|
| 1457 |
+
"loss": 0.0001,
|
| 1458 |
+
"num_input_tokens_seen": 130192,
|
| 1459 |
+
"step": 855
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 4.777777777777778,
|
| 1463 |
+
"grad_norm": 0.005334069021046162,
|
| 1464 |
+
"learning_rate": 3.1282965716233594e-05,
|
| 1465 |
+
"loss": 0.0001,
|
| 1466 |
+
"num_input_tokens_seen": 130976,
|
| 1467 |
+
"step": 860
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 4.805555555555555,
|
| 1471 |
+
"grad_norm": 0.00939280353486538,
|
| 1472 |
+
"learning_rate": 3.104804738999169e-05,
|
| 1473 |
+
"loss": 0.0001,
|
| 1474 |
+
"num_input_tokens_seen": 131728,
|
| 1475 |
+
"step": 865
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 4.833333333333333,
|
| 1479 |
+
"grad_norm": 0.005722450092434883,
|
| 1480 |
+
"learning_rate": 3.0812560444565745e-05,
|
| 1481 |
+
"loss": 0.0,
|
| 1482 |
+
"num_input_tokens_seen": 132480,
|
| 1483 |
+
"step": 870
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 4.861111111111111,
|
| 1487 |
+
"grad_norm": 0.02254972793161869,
|
| 1488 |
+
"learning_rate": 3.057652701972848e-05,
|
| 1489 |
+
"loss": 0.0002,
|
| 1490 |
+
"num_input_tokens_seen": 133264,
|
| 1491 |
+
"step": 875
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 4.888888888888889,
|
| 1495 |
+
"grad_norm": 0.001465034089051187,
|
| 1496 |
+
"learning_rate": 3.0339969306631005e-05,
|
| 1497 |
+
"loss": 0.0064,
|
| 1498 |
+
"num_input_tokens_seen": 134032,
|
| 1499 |
+
"step": 880
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 4.916666666666667,
|
| 1503 |
+
"grad_norm": 0.03533560410141945,
|
| 1504 |
+
"learning_rate": 3.0102909545716396e-05,
|
| 1505 |
+
"loss": 0.0001,
|
| 1506 |
+
"num_input_tokens_seen": 134800,
|
| 1507 |
+
"step": 885
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 4.944444444444445,
|
| 1511 |
+
"grad_norm": 0.0021763457916677,
|
| 1512 |
+
"learning_rate": 2.9865370024628775e-05,
|
| 1513 |
+
"loss": 0.0008,
|
| 1514 |
+
"num_input_tokens_seen": 135536,
|
| 1515 |
+
"step": 890
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 4.972222222222222,
|
| 1519 |
+
"grad_norm": 0.0021308716386556625,
|
| 1520 |
+
"learning_rate": 2.9627373076117863e-05,
|
| 1521 |
+
"loss": 0.0,
|
| 1522 |
+
"num_input_tokens_seen": 136272,
|
| 1523 |
+
"step": 895
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 5.0,
|
| 1527 |
+
"grad_norm": 0.0033213908318430185,
|
| 1528 |
+
"learning_rate": 2.9388941075939334e-05,
|
| 1529 |
+
"loss": 0.0034,
|
| 1530 |
+
"num_input_tokens_seen": 137040,
|
| 1531 |
+
"step": 900
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 5.0,
|
| 1535 |
+
"eval_loss": 0.18915815651416779,
|
| 1536 |
+
"eval_runtime": 0.8637,
|
| 1537 |
+
"eval_samples_per_second": 46.312,
|
| 1538 |
+
"eval_steps_per_second": 23.156,
|
| 1539 |
+
"num_input_tokens_seen": 137040,
|
| 1540 |
+
"step": 900
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 5.027777777777778,
|
| 1544 |
+
"grad_norm": 0.056632209569215775,
|
| 1545 |
+
"learning_rate": 2.9150096440751107e-05,
|
| 1546 |
+
"loss": 0.0002,
|
| 1547 |
+
"num_input_tokens_seen": 137808,
|
| 1548 |
+
"step": 905
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 5.055555555555555,
|
| 1552 |
+
"grad_norm": 0.14479988813400269,
|
| 1553 |
+
"learning_rate": 2.8910861626005776e-05,
|
| 1554 |
+
"loss": 0.0002,
|
| 1555 |
+
"num_input_tokens_seen": 138560,
|
| 1556 |
+
"step": 910
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 5.083333333333333,
|
| 1560 |
+
"grad_norm": 0.004574320744723082,
|
| 1561 |
+
"learning_rate": 2.8671259123839472e-05,
|
| 1562 |
+
"loss": 0.0,
|
| 1563 |
+
"num_input_tokens_seen": 139312,
|
| 1564 |
+
"step": 915
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 5.111111111111111,
|
| 1568 |
+
"grad_norm": 0.006690006237477064,
|
| 1569 |
+
"learning_rate": 2.843131146095719e-05,
|
| 1570 |
+
"loss": 0.0,
|
| 1571 |
+
"num_input_tokens_seen": 140032,
|
| 1572 |
+
"step": 920
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 5.138888888888889,
|
| 1576 |
+
"grad_norm": 0.04315263405442238,
|
| 1577 |
+
"learning_rate": 2.8191041196514873e-05,
|
| 1578 |
+
"loss": 0.0001,
|
| 1579 |
+
"num_input_tokens_seen": 140768,
|
| 1580 |
+
"step": 925
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 5.166666666666667,
|
| 1584 |
+
"grad_norm": 0.002650605281814933,
|
| 1585 |
+
"learning_rate": 2.795047091999849e-05,
|
| 1586 |
+
"loss": 0.0001,
|
| 1587 |
+
"num_input_tokens_seen": 141536,
|
| 1588 |
+
"step": 930
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 5.194444444444445,
|
| 1592 |
+
"grad_norm": 0.04034039378166199,
|
| 1593 |
+
"learning_rate": 2.770962324910027e-05,
|
| 1594 |
+
"loss": 0.0001,
|
| 1595 |
+
"num_input_tokens_seen": 142320,
|
| 1596 |
+
"step": 935
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 5.222222222222222,
|
| 1600 |
+
"grad_norm": 0.0023825839161872864,
|
| 1601 |
+
"learning_rate": 2.7468520827592197e-05,
|
| 1602 |
+
"loss": 0.0002,
|
| 1603 |
+
"num_input_tokens_seen": 143088,
|
| 1604 |
+
"step": 940
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 5.25,
|
| 1608 |
+
"grad_norm": 0.002679111436009407,
|
| 1609 |
+
"learning_rate": 2.7227186323197162e-05,
|
| 1610 |
+
"loss": 0.0001,
|
| 1611 |
+
"num_input_tokens_seen": 143840,
|
| 1612 |
+
"step": 945
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 5.277777777777778,
|
| 1616 |
+
"grad_norm": 0.002105121733620763,
|
| 1617 |
+
"learning_rate": 2.6985642425457757e-05,
|
| 1618 |
+
"loss": 0.229,
|
| 1619 |
+
"num_input_tokens_seen": 144592,
|
| 1620 |
+
"step": 950
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 5.305555555555555,
|
| 1624 |
+
"grad_norm": 0.0029831964056938887,
|
| 1625 |
+
"learning_rate": 2.674391184360313e-05,
|
| 1626 |
+
"loss": 0.0001,
|
| 1627 |
+
"num_input_tokens_seen": 145328,
|
| 1628 |
+
"step": 955
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 5.333333333333333,
|
| 1632 |
+
"grad_norm": 0.008866608142852783,
|
| 1633 |
+
"learning_rate": 2.650201730441392e-05,
|
| 1634 |
+
"loss": 0.0021,
|
| 1635 |
+
"num_input_tokens_seen": 146080,
|
| 1636 |
+
"step": 960
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 5.361111111111111,
|
| 1640 |
+
"grad_norm": 0.1157485768198967,
|
| 1641 |
+
"learning_rate": 2.6259981550085504e-05,
|
| 1642 |
+
"loss": 0.0001,
|
| 1643 |
+
"num_input_tokens_seen": 146864,
|
| 1644 |
+
"step": 965
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 5.388888888888889,
|
| 1648 |
+
"grad_norm": 0.02147284708917141,
|
| 1649 |
+
"learning_rate": 2.60178273360899e-05,
|
| 1650 |
+
"loss": 0.1137,
|
| 1651 |
+
"num_input_tokens_seen": 147632,
|
| 1652 |
+
"step": 970
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 5.416666666666667,
|
| 1656 |
+
"grad_norm": 0.050694871693849564,
|
| 1657 |
+
"learning_rate": 2.5775577429036345e-05,
|
| 1658 |
+
"loss": 0.0001,
|
| 1659 |
+
"num_input_tokens_seen": 148416,
|
| 1660 |
+
"step": 975
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 5.444444444444445,
|
| 1664 |
+
"grad_norm": 0.00253108749166131,
|
| 1665 |
+
"learning_rate": 2.553325460453086e-05,
|
| 1666 |
+
"loss": 0.0002,
|
| 1667 |
+
"num_input_tokens_seen": 149152,
|
| 1668 |
+
"step": 980
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 5.472222222222222,
|
| 1672 |
+
"grad_norm": 0.0020968341268599033,
|
| 1673 |
+
"learning_rate": 2.5290881645034932e-05,
|
| 1674 |
+
"loss": 0.0,
|
| 1675 |
+
"num_input_tokens_seen": 149920,
|
| 1676 |
+
"step": 985
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 5.5,
|
| 1680 |
+
"grad_norm": 0.0030508909840136766,
|
| 1681 |
+
"learning_rate": 2.504848133772358e-05,
|
| 1682 |
+
"loss": 0.0001,
|
| 1683 |
+
"num_input_tokens_seen": 150672,
|
| 1684 |
+
"step": 990
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 5.5,
|
| 1688 |
+
"eval_loss": 0.19481489062309265,
|
| 1689 |
+
"eval_runtime": 0.898,
|
| 1690 |
+
"eval_samples_per_second": 44.542,
|
| 1691 |
+
"eval_steps_per_second": 22.271,
|
| 1692 |
+
"num_input_tokens_seen": 150672,
|
| 1693 |
+
"step": 990
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 5.527777777777778,
|
| 1697 |
+
"grad_norm": 0.0028975855093449354,
|
| 1698 |
+
"learning_rate": 2.4806076472342997e-05,
|
| 1699 |
+
"loss": 0.0001,
|
| 1700 |
+
"num_input_tokens_seen": 151424,
|
| 1701 |
+
"step": 995
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 5.555555555555555,
|
| 1705 |
+
"grad_norm": 0.0023356874007731676,
|
| 1706 |
+
"learning_rate": 2.4563689839067913e-05,
|
| 1707 |
+
"loss": 0.0001,
|
| 1708 |
+
"num_input_tokens_seen": 152160,
|
| 1709 |
+
"step": 1000
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 5.583333333333333,
|
| 1713 |
+
"grad_norm": 0.002313376637175679,
|
| 1714 |
+
"learning_rate": 2.432134422635893e-05,
|
| 1715 |
+
"loss": 0.0005,
|
| 1716 |
+
"num_input_tokens_seen": 152960,
|
| 1717 |
+
"step": 1005
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 5.611111111111111,
|
| 1721 |
+
"grad_norm": 0.0026274356059730053,
|
| 1722 |
+
"learning_rate": 2.4079062418820002e-05,
|
| 1723 |
+
"loss": 0.0001,
|
| 1724 |
+
"num_input_tokens_seen": 153728,
|
| 1725 |
+
"step": 1010
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 5.638888888888889,
|
| 1729 |
+
"grad_norm": 0.0016156655037775636,
|
| 1730 |
+
"learning_rate": 2.3836867195056335e-05,
|
| 1731 |
+
"loss": 0.0,
|
| 1732 |
+
"num_input_tokens_seen": 154496,
|
| 1733 |
+
"step": 1015
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 5.666666666666667,
|
| 1737 |
+
"grad_norm": 0.011947419494390488,
|
| 1738 |
+
"learning_rate": 2.3594781325532784e-05,
|
| 1739 |
+
"loss": 0.0002,
|
| 1740 |
+
"num_input_tokens_seen": 155280,
|
| 1741 |
+
"step": 1020
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 5.694444444444445,
|
| 1745 |
+
"grad_norm": 0.02961958572268486,
|
| 1746 |
+
"learning_rate": 2.3352827570433036e-05,
|
| 1747 |
+
"loss": 0.0001,
|
| 1748 |
+
"num_input_tokens_seen": 156064,
|
| 1749 |
+
"step": 1025
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 5.722222222222222,
|
| 1753 |
+
"grad_norm": 0.07261377573013306,
|
| 1754 |
+
"learning_rate": 2.3111028677519804e-05,
|
| 1755 |
+
"loss": 0.0001,
|
| 1756 |
+
"num_input_tokens_seen": 156816,
|
| 1757 |
+
"step": 1030
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 5.75,
|
| 1761 |
+
"grad_norm": 0.003121615620329976,
|
| 1762 |
+
"learning_rate": 2.2869407379996088e-05,
|
| 1763 |
+
"loss": 0.0,
|
| 1764 |
+
"num_input_tokens_seen": 157568,
|
| 1765 |
+
"step": 1035
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 5.777777777777778,
|
| 1769 |
+
"grad_norm": 0.003354340326040983,
|
| 1770 |
+
"learning_rate": 2.2627986394367938e-05,
|
| 1771 |
+
"loss": 0.0,
|
| 1772 |
+
"num_input_tokens_seen": 158320,
|
| 1773 |
+
"step": 1040
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 5.805555555555555,
|
| 1777 |
+
"grad_norm": 0.005908883176743984,
|
| 1778 |
+
"learning_rate": 2.238678841830867e-05,
|
| 1779 |
+
"loss": 0.0,
|
| 1780 |
+
"num_input_tokens_seen": 159056,
|
| 1781 |
+
"step": 1045
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 5.833333333333333,
|
| 1785 |
+
"grad_norm": 0.16055719554424286,
|
| 1786 |
+
"learning_rate": 2.2145836128524902e-05,
|
| 1787 |
+
"loss": 0.0003,
|
| 1788 |
+
"num_input_tokens_seen": 159792,
|
| 1789 |
+
"step": 1050
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 5.861111111111111,
|
| 1793 |
+
"grad_norm": 0.001806123647838831,
|
| 1794 |
+
"learning_rate": 2.1905152178624595e-05,
|
| 1795 |
+
"loss": 0.0,
|
| 1796 |
+
"num_input_tokens_seen": 160544,
|
| 1797 |
+
"step": 1055
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 5.888888888888889,
|
| 1801 |
+
"grad_norm": 0.00291000516153872,
|
| 1802 |
+
"learning_rate": 2.1664759196987182e-05,
|
| 1803 |
+
"loss": 0.0784,
|
| 1804 |
+
"num_input_tokens_seen": 161296,
|
| 1805 |
+
"step": 1060
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 5.916666666666667,
|
| 1809 |
+
"grad_norm": 0.11329387873411179,
|
| 1810 |
+
"learning_rate": 2.1424679784636144e-05,
|
| 1811 |
+
"loss": 0.0002,
|
| 1812 |
+
"num_input_tokens_seen": 162048,
|
| 1813 |
+
"step": 1065
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 5.944444444444445,
|
| 1817 |
+
"grad_norm": 0.001582896220497787,
|
| 1818 |
+
"learning_rate": 2.118493651311413e-05,
|
| 1819 |
+
"loss": 0.0,
|
| 1820 |
+
"num_input_tokens_seen": 162816,
|
| 1821 |
+
"step": 1070
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 5.972222222222222,
|
| 1825 |
+
"grad_norm": 0.0024200803600251675,
|
| 1826 |
+
"learning_rate": 2.0945551922360818e-05,
|
| 1827 |
+
"loss": 0.0002,
|
| 1828 |
+
"num_input_tokens_seen": 163584,
|
| 1829 |
+
"step": 1075
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 6.0,
|
| 1833 |
+
"grad_norm": 0.0025788673665374517,
|
| 1834 |
+
"learning_rate": 2.070654851859383e-05,
|
| 1835 |
+
"loss": 0.0,
|
| 1836 |
+
"num_input_tokens_seen": 164336,
|
| 1837 |
+
"step": 1080
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 6.0,
|
| 1841 |
+
"eval_loss": 0.20146259665489197,
|
| 1842 |
+
"eval_runtime": 0.8911,
|
| 1843 |
+
"eval_samples_per_second": 44.887,
|
| 1844 |
+
"eval_steps_per_second": 22.444,
|
| 1845 |
+
"num_input_tokens_seen": 164336,
|
| 1846 |
+
"step": 1080
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 6.027777777777778,
|
| 1850 |
+
"grad_norm": 0.0012250063009560108,
|
| 1851 |
+
"learning_rate": 2.0467948772192713e-05,
|
| 1852 |
+
"loss": 0.0,
|
| 1853 |
+
"num_input_tokens_seen": 165088,
|
| 1854 |
+
"step": 1085
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 6.055555555555555,
|
| 1858 |
+
"grad_norm": 0.002738215960562229,
|
| 1859 |
+
"learning_rate": 2.022977511558638e-05,
|
| 1860 |
+
"loss": 0.0,
|
| 1861 |
+
"num_input_tokens_seen": 165856,
|
| 1862 |
+
"step": 1090
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 6.083333333333333,
|
| 1866 |
+
"grad_norm": 0.05658820644021034,
|
| 1867 |
+
"learning_rate": 1.9992049941144066e-05,
|
| 1868 |
+
"loss": 0.0001,
|
| 1869 |
+
"num_input_tokens_seen": 166624,
|
| 1870 |
+
"step": 1095
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 6.111111111111111,
|
| 1874 |
+
"grad_norm": 0.0015246145194396377,
|
| 1875 |
+
"learning_rate": 1.9754795599070068e-05,
|
| 1876 |
+
"loss": 0.0001,
|
| 1877 |
+
"num_input_tokens_seen": 167360,
|
| 1878 |
+
"step": 1100
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 6.138888888888889,
|
| 1882 |
+
"grad_norm": 0.00705633033066988,
|
| 1883 |
+
"learning_rate": 1.9518034395302414e-05,
|
| 1884 |
+
"loss": 0.0,
|
| 1885 |
+
"num_input_tokens_seen": 168112,
|
| 1886 |
+
"step": 1105
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 6.166666666666667,
|
| 1890 |
+
"grad_norm": 0.0018693690653890371,
|
| 1891 |
+
"learning_rate": 1.9281788589415804e-05,
|
| 1892 |
+
"loss": 0.0,
|
| 1893 |
+
"num_input_tokens_seen": 168864,
|
| 1894 |
+
"step": 1110
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 6.194444444444445,
|
| 1898 |
+
"grad_norm": 0.002476233523339033,
|
| 1899 |
+
"learning_rate": 1.9046080392528735e-05,
|
| 1900 |
+
"loss": 0.0001,
|
| 1901 |
+
"num_input_tokens_seen": 169616,
|
| 1902 |
+
"step": 1115
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 6.222222222222222,
|
| 1906 |
+
"grad_norm": 0.0015990459360182285,
|
| 1907 |
+
"learning_rate": 1.8810931965215356e-05,
|
| 1908 |
+
"loss": 0.0001,
|
| 1909 |
+
"num_input_tokens_seen": 170416,
|
| 1910 |
+
"step": 1120
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 6.25,
|
| 1914 |
+
"grad_norm": 0.07700612396001816,
|
| 1915 |
+
"learning_rate": 1.857636541542195e-05,
|
| 1916 |
+
"loss": 0.0002,
|
| 1917 |
+
"num_input_tokens_seen": 171184,
|
| 1918 |
+
"step": 1125
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 6.277777777777778,
|
| 1922 |
+
"grad_norm": 0.002112372312694788,
|
| 1923 |
+
"learning_rate": 1.8342402796388445e-05,
|
| 1924 |
+
"loss": 0.1835,
|
| 1925 |
+
"num_input_tokens_seen": 171936,
|
| 1926 |
+
"step": 1130
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 6.305555555555555,
|
| 1930 |
+
"grad_norm": 0.8381811380386353,
|
| 1931 |
+
"learning_rate": 1.8109066104575023e-05,
|
| 1932 |
+
"loss": 0.0007,
|
| 1933 |
+
"num_input_tokens_seen": 172688,
|
| 1934 |
+
"step": 1135
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 6.333333333333333,
|
| 1938 |
+
"grad_norm": 0.003225484397262335,
|
| 1939 |
+
"learning_rate": 1.7876377277594053e-05,
|
| 1940 |
+
"loss": 0.0106,
|
| 1941 |
+
"num_input_tokens_seen": 173456,
|
| 1942 |
+
"step": 1140
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 6.361111111111111,
|
| 1946 |
+
"grad_norm": 0.0008982580038718879,
|
| 1947 |
+
"learning_rate": 1.764435819214762e-05,
|
| 1948 |
+
"loss": 0.0,
|
| 1949 |
+
"num_input_tokens_seen": 174176,
|
| 1950 |
+
"step": 1145
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 6.388888888888889,
|
| 1954 |
+
"grad_norm": 0.0012918318388983607,
|
| 1955 |
+
"learning_rate": 1.7413030661970742e-05,
|
| 1956 |
+
"loss": 0.0,
|
| 1957 |
+
"num_input_tokens_seen": 174912,
|
| 1958 |
+
"step": 1150
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 6.416666666666667,
|
| 1962 |
+
"grad_norm": 0.0027255413588136435,
|
| 1963 |
+
"learning_rate": 1.7182416435780454e-05,
|
| 1964 |
+
"loss": 0.0,
|
| 1965 |
+
"num_input_tokens_seen": 175680,
|
| 1966 |
+
"step": 1155
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 6.444444444444445,
|
| 1970 |
+
"grad_norm": 0.052055828273296356,
|
| 1971 |
+
"learning_rate": 1.695253719523115e-05,
|
| 1972 |
+
"loss": 0.0001,
|
| 1973 |
+
"num_input_tokens_seen": 176448,
|
| 1974 |
+
"step": 1160
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 6.472222222222222,
|
| 1978 |
+
"grad_norm": 0.00360573991201818,
|
| 1979 |
+
"learning_rate": 1.672341455287605e-05,
|
| 1980 |
+
"loss": 0.0,
|
| 1981 |
+
"num_input_tokens_seen": 177216,
|
| 1982 |
+
"step": 1165
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 6.5,
|
| 1986 |
+
"grad_norm": 0.020261406898498535,
|
| 1987 |
+
"learning_rate": 1.649507005013532e-05,
|
| 1988 |
+
"loss": 0.0001,
|
| 1989 |
+
"num_input_tokens_seen": 177968,
|
| 1990 |
+
"step": 1170
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 6.5,
|
| 1994 |
+
"eval_loss": 0.19643399119377136,
|
| 1995 |
+
"eval_runtime": 0.895,
|
| 1996 |
+
"eval_samples_per_second": 44.695,
|
| 1997 |
+
"eval_steps_per_second": 22.347,
|
| 1998 |
+
"num_input_tokens_seen": 177968,
|
| 1999 |
+
"step": 1170
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 6.527777777777778,
|
| 2003 |
+
"grad_norm": 0.013305317610502243,
|
| 2004 |
+
"learning_rate": 1.6267525155270773e-05,
|
| 2005 |
+
"loss": 0.0001,
|
| 2006 |
+
"num_input_tokens_seen": 178768,
|
| 2007 |
+
"step": 1175
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 6.555555555555555,
|
| 2011 |
+
"grad_norm": 0.0017271782271564007,
|
| 2012 |
+
"learning_rate": 1.6040801261367493e-05,
|
| 2013 |
+
"loss": 0.0,
|
| 2014 |
+
"num_input_tokens_seen": 179488,
|
| 2015 |
+
"step": 1180
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 6.583333333333333,
|
| 2019 |
+
"grad_norm": 0.001645921729505062,
|
| 2020 |
+
"learning_rate": 1.5814919684322545e-05,
|
| 2021 |
+
"loss": 0.0001,
|
| 2022 |
+
"num_input_tokens_seen": 180240,
|
| 2023 |
+
"step": 1185
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 6.611111111111111,
|
| 2027 |
+
"grad_norm": 0.04658055305480957,
|
| 2028 |
+
"learning_rate": 1.5589901660840896e-05,
|
| 2029 |
+
"loss": 0.0001,
|
| 2030 |
+
"num_input_tokens_seen": 180992,
|
| 2031 |
+
"step": 1190
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 6.638888888888889,
|
| 2035 |
+
"grad_norm": 6.15234899520874,
|
| 2036 |
+
"learning_rate": 1.5365768346438797e-05,
|
| 2037 |
+
"loss": 0.0024,
|
| 2038 |
+
"num_input_tokens_seen": 181760,
|
| 2039 |
+
"step": 1195
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 6.666666666666667,
|
| 2043 |
+
"grad_norm": 0.0030860521364957094,
|
| 2044 |
+
"learning_rate": 1.5142540813454836e-05,
|
| 2045 |
+
"loss": 0.0,
|
| 2046 |
+
"num_input_tokens_seen": 182528,
|
| 2047 |
+
"step": 1200
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 6.694444444444445,
|
| 2051 |
+
"grad_norm": 0.002572861034423113,
|
| 2052 |
+
"learning_rate": 1.4920240049068748e-05,
|
| 2053 |
+
"loss": 0.0001,
|
| 2054 |
+
"num_input_tokens_seen": 183344,
|
| 2055 |
+
"step": 1205
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 6.722222222222222,
|
| 2059 |
+
"grad_norm": 0.021335948258638382,
|
| 2060 |
+
"learning_rate": 1.4698886953328292e-05,
|
| 2061 |
+
"loss": 0.0003,
|
| 2062 |
+
"num_input_tokens_seen": 184096,
|
| 2063 |
+
"step": 1210
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 6.75,
|
| 2067 |
+
"grad_norm": 43.77614212036133,
|
| 2068 |
+
"learning_rate": 1.4478502337184274e-05,
|
| 2069 |
+
"loss": 0.013,
|
| 2070 |
+
"num_input_tokens_seen": 184832,
|
| 2071 |
+
"step": 1215
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 6.777777777777778,
|
| 2075 |
+
"grad_norm": 0.0024675296153873205,
|
| 2076 |
+
"learning_rate": 1.4259106920533955e-05,
|
| 2077 |
+
"loss": 0.0,
|
| 2078 |
+
"num_input_tokens_seen": 185600,
|
| 2079 |
+
"step": 1220
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 6.805555555555555,
|
| 2083 |
+
"grad_norm": 0.003566775470972061,
|
| 2084 |
+
"learning_rate": 1.4040721330273062e-05,
|
| 2085 |
+
"loss": 0.0,
|
| 2086 |
+
"num_input_tokens_seen": 186336,
|
| 2087 |
+
"step": 1225
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 6.833333333333333,
|
| 2091 |
+
"grad_norm": 0.029065780341625214,
|
| 2092 |
+
"learning_rate": 1.3823366098356487e-05,
|
| 2093 |
+
"loss": 0.0002,
|
| 2094 |
+
"num_input_tokens_seen": 187120,
|
| 2095 |
+
"step": 1230
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 6.861111111111111,
|
| 2099 |
+
"grad_norm": 0.0016439430182799697,
|
| 2100 |
+
"learning_rate": 1.3607061659867892e-05,
|
| 2101 |
+
"loss": 0.0,
|
| 2102 |
+
"num_input_tokens_seen": 187872,
|
| 2103 |
+
"step": 1235
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 6.888888888888889,
|
| 2107 |
+
"grad_norm": 0.0015073842369019985,
|
| 2108 |
+
"learning_rate": 1.3391828351098578e-05,
|
| 2109 |
+
"loss": 0.0001,
|
| 2110 |
+
"num_input_tokens_seen": 188640,
|
| 2111 |
+
"step": 1240
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 6.916666666666667,
|
| 2115 |
+
"grad_norm": 0.0016068222466856241,
|
| 2116 |
+
"learning_rate": 1.3177686407635417e-05,
|
| 2117 |
+
"loss": 0.0001,
|
| 2118 |
+
"num_input_tokens_seen": 189424,
|
| 2119 |
+
"step": 1245
|
| 2120 |
+
},
|
| 2121 |
+
{
|
| 2122 |
+
"epoch": 6.944444444444445,
|
| 2123 |
+
"grad_norm": 0.0016325548058375716,
|
| 2124 |
+
"learning_rate": 1.29646559624584e-05,
|
| 2125 |
+
"loss": 0.0001,
|
| 2126 |
+
"num_input_tokens_seen": 190224,
|
| 2127 |
+
"step": 1250
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 6.972222222222222,
|
| 2131 |
+
"grad_norm": 0.0021291859447956085,
|
| 2132 |
+
"learning_rate": 1.2752757044047827e-05,
|
| 2133 |
+
"loss": 0.0,
|
| 2134 |
+
"num_input_tokens_seen": 190992,
|
| 2135 |
+
"step": 1255
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 7.0,
|
| 2139 |
+
"grad_norm": 0.002036020625382662,
|
| 2140 |
+
"learning_rate": 1.2542009574501246e-05,
|
| 2141 |
+
"loss": 0.0001,
|
| 2142 |
+
"num_input_tokens_seen": 191760,
|
| 2143 |
+
"step": 1260
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 7.0,
|
| 2147 |
+
"eval_loss": 0.19721972942352295,
|
| 2148 |
+
"eval_runtime": 0.9179,
|
| 2149 |
+
"eval_samples_per_second": 43.576,
|
| 2150 |
+
"eval_steps_per_second": 21.788,
|
| 2151 |
+
"num_input_tokens_seen": 191760,
|
| 2152 |
+
"step": 1260
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 7.027777777777778,
|
| 2156 |
+
"grad_norm": 0.0014772972790524364,
|
| 2157 |
+
"learning_rate": 1.2332433367660442e-05,
|
| 2158 |
+
"loss": 0.0,
|
| 2159 |
+
"num_input_tokens_seen": 192528,
|
| 2160 |
+
"step": 1265
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 7.055555555555555,
|
| 2164 |
+
"grad_norm": 0.0010045369854196906,
|
| 2165 |
+
"learning_rate": 1.2124048127248644e-05,
|
| 2166 |
+
"loss": 0.0001,
|
| 2167 |
+
"num_input_tokens_seen": 193312,
|
| 2168 |
+
"step": 1270
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 7.083333333333333,
|
| 2172 |
+
"grad_norm": 0.006242353934794664,
|
| 2173 |
+
"learning_rate": 1.1916873445017982e-05,
|
| 2174 |
+
"loss": 0.0001,
|
| 2175 |
+
"num_input_tokens_seen": 194064,
|
| 2176 |
+
"step": 1275
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 7.111111111111111,
|
| 2180 |
+
"grad_norm": 0.02573557011783123,
|
| 2181 |
+
"learning_rate": 1.1710928798907556e-05,
|
| 2182 |
+
"loss": 0.0001,
|
| 2183 |
+
"num_input_tokens_seen": 194832,
|
| 2184 |
+
"step": 1280
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 7.138888888888889,
|
| 2188 |
+
"grad_norm": 0.04534817487001419,
|
| 2189 |
+
"learning_rate": 1.1506233551212186e-05,
|
| 2190 |
+
"loss": 0.0003,
|
| 2191 |
+
"num_input_tokens_seen": 195600,
|
| 2192 |
+
"step": 1285
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 7.166666666666667,
|
| 2196 |
+
"grad_norm": 0.006147115025669336,
|
| 2197 |
+
"learning_rate": 1.1302806946762004e-05,
|
| 2198 |
+
"loss": 0.0,
|
| 2199 |
+
"num_input_tokens_seen": 196352,
|
| 2200 |
+
"step": 1290
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 7.194444444444445,
|
| 2204 |
+
"grad_norm": 0.0012354146456345916,
|
| 2205 |
+
"learning_rate": 1.1100668111113166e-05,
|
| 2206 |
+
"loss": 0.0,
|
| 2207 |
+
"num_input_tokens_seen": 197104,
|
| 2208 |
+
"step": 1295
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 7.222222222222222,
|
| 2212 |
+
"grad_norm": 0.07404682040214539,
|
| 2213 |
+
"learning_rate": 1.0899836048749645e-05,
|
| 2214 |
+
"loss": 0.0002,
|
| 2215 |
+
"num_input_tokens_seen": 197856,
|
| 2216 |
+
"step": 1300
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 7.25,
|
| 2220 |
+
"grad_norm": 0.0017910490278154612,
|
| 2221 |
+
"learning_rate": 1.0700329641296541e-05,
|
| 2222 |
+
"loss": 0.0,
|
| 2223 |
+
"num_input_tokens_seen": 198592,
|
| 2224 |
+
"step": 1305
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 7.277777777777778,
|
| 2228 |
+
"grad_norm": 5.348869800567627,
|
| 2229 |
+
"learning_rate": 1.0502167645744895e-05,
|
| 2230 |
+
"loss": 0.0013,
|
| 2231 |
+
"num_input_tokens_seen": 199360,
|
| 2232 |
+
"step": 1310
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 7.305555555555555,
|
| 2236 |
+
"grad_norm": 0.0018137628212571144,
|
| 2237 |
+
"learning_rate": 1.0305368692688174e-05,
|
| 2238 |
+
"loss": 0.0001,
|
| 2239 |
+
"num_input_tokens_seen": 200128,
|
| 2240 |
+
"step": 1315
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 7.333333333333333,
|
| 2244 |
+
"grad_norm": 0.0015285219997167587,
|
| 2245 |
+
"learning_rate": 1.01099512845707e-05,
|
| 2246 |
+
"loss": 0.0,
|
| 2247 |
+
"num_input_tokens_seen": 200912,
|
| 2248 |
+
"step": 1320
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 7.361111111111111,
|
| 2252 |
+
"grad_norm": 0.002978443168103695,
|
| 2253 |
+
"learning_rate": 9.91593379394811e-06,
|
| 2254 |
+
"loss": 0.0,
|
| 2255 |
+
"num_input_tokens_seen": 201664,
|
| 2256 |
+
"step": 1325
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 7.388888888888889,
|
| 2260 |
+
"grad_norm": 0.001245899242348969,
|
| 2261 |
+
"learning_rate": 9.723334461760006e-06,
|
| 2262 |
+
"loss": 0.0,
|
| 2263 |
+
"num_input_tokens_seen": 202416,
|
| 2264 |
+
"step": 1330
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 7.416666666666667,
|
| 2268 |
+
"grad_norm": 0.0016263187862932682,
|
| 2269 |
+
"learning_rate": 9.532171395615036e-06,
|
| 2270 |
+
"loss": 0.0,
|
| 2271 |
+
"num_input_tokens_seen": 203184,
|
| 2272 |
+
"step": 1335
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 7.444444444444445,
|
| 2276 |
+
"grad_norm": 0.0017977867973968387,
|
| 2277 |
+
"learning_rate": 9.342462568088416e-06,
|
| 2278 |
+
"loss": 0.0,
|
| 2279 |
+
"num_input_tokens_seen": 203968,
|
| 2280 |
+
"step": 1340
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 7.472222222222222,
|
| 2284 |
+
"grad_norm": 0.0018679365748539567,
|
| 2285 |
+
"learning_rate": 9.154225815032242e-06,
|
| 2286 |
+
"loss": 0.0,
|
| 2287 |
+
"num_input_tokens_seen": 204736,
|
| 2288 |
+
"step": 1345
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 7.5,
|
| 2292 |
+
"grad_norm": 0.0016537755727767944,
|
| 2293 |
+
"learning_rate": 8.967478833898612e-06,
|
| 2294 |
+
"loss": 0.0001,
|
| 2295 |
+
"num_input_tokens_seen": 205504,
|
| 2296 |
+
"step": 1350
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 7.5,
|
| 2300 |
+
"eval_loss": 0.20054903626441956,
|
| 2301 |
+
"eval_runtime": 1.0173,
|
| 2302 |
+
"eval_samples_per_second": 39.32,
|
| 2303 |
+
"eval_steps_per_second": 19.66,
|
| 2304 |
+
"num_input_tokens_seen": 205504,
|
| 2305 |
+
"step": 1350
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 7.527777777777778,
|
| 2309 |
+
"grad_norm": 0.07628758251667023,
|
| 2310 |
+
"learning_rate": 8.78223918207575e-06,
|
| 2311 |
+
"loss": 0.0001,
|
| 2312 |
+
"num_input_tokens_seen": 206288,
|
| 2313 |
+
"step": 1355
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 7.555555555555555,
|
| 2317 |
+
"grad_norm": 0.001097225584089756,
|
| 2318 |
+
"learning_rate": 8.598524275237322e-06,
|
| 2319 |
+
"loss": 0.1587,
|
| 2320 |
+
"num_input_tokens_seen": 207008,
|
| 2321 |
+
"step": 1360
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 7.583333333333333,
|
| 2325 |
+
"grad_norm": 0.0016023390926420689,
|
| 2326 |
+
"learning_rate": 8.41635138570507e-06,
|
| 2327 |
+
"loss": 0.0001,
|
| 2328 |
+
"num_input_tokens_seen": 207776,
|
| 2329 |
+
"step": 1365
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 7.611111111111111,
|
| 2333 |
+
"grad_norm": 0.0016416008584201336,
|
| 2334 |
+
"learning_rate": 8.235737640824908e-06,
|
| 2335 |
+
"loss": 0.0,
|
| 2336 |
+
"num_input_tokens_seen": 208528,
|
| 2337 |
+
"step": 1370
|
| 2338 |
+
},
|
| 2339 |
+
{
|
| 2340 |
+
"epoch": 7.638888888888889,
|
| 2341 |
+
"grad_norm": 0.0014643091708421707,
|
| 2342 |
+
"learning_rate": 8.056700021356694e-06,
|
| 2343 |
+
"loss": 0.0001,
|
| 2344 |
+
"num_input_tokens_seen": 209280,
|
| 2345 |
+
"step": 1375
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 7.666666666666667,
|
| 2349 |
+
"grad_norm": 0.0008804944809526205,
|
| 2350 |
+
"learning_rate": 7.879255359877705e-06,
|
| 2351 |
+
"loss": 0.0001,
|
| 2352 |
+
"num_input_tokens_seen": 210080,
|
| 2353 |
+
"step": 1380
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 7.694444444444445,
|
| 2357 |
+
"grad_norm": 0.002069121925160289,
|
| 2358 |
+
"learning_rate": 7.703420339200101e-06,
|
| 2359 |
+
"loss": 0.0,
|
| 2360 |
+
"num_input_tokens_seen": 210832,
|
| 2361 |
+
"step": 1385
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 7.722222222222222,
|
| 2365 |
+
"grad_norm": 0.0012066976632922888,
|
| 2366 |
+
"learning_rate": 7.529211490802498e-06,
|
| 2367 |
+
"loss": 0.0002,
|
| 2368 |
+
"num_input_tokens_seen": 211568,
|
| 2369 |
+
"step": 1390
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 7.75,
|
| 2373 |
+
"grad_norm": 0.015535800717771053,
|
| 2374 |
+
"learning_rate": 7.3566451932756744e-06,
|
| 2375 |
+
"loss": 0.0,
|
| 2376 |
+
"num_input_tokens_seen": 212320,
|
| 2377 |
+
"step": 1395
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 7.777777777777778,
|
| 2381 |
+
"grad_norm": 0.001121603767387569,
|
| 2382 |
+
"learning_rate": 7.185737670782727e-06,
|
| 2383 |
+
"loss": 0.0001,
|
| 2384 |
+
"num_input_tokens_seen": 213088,
|
| 2385 |
+
"step": 1400
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 7.805555555555555,
|
| 2389 |
+
"grad_norm": 0.009458635933697224,
|
| 2390 |
+
"learning_rate": 7.016504991533726e-06,
|
| 2391 |
+
"loss": 0.0,
|
| 2392 |
+
"num_input_tokens_seen": 213808,
|
| 2393 |
+
"step": 1405
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 7.833333333333333,
|
| 2397 |
+
"grad_norm": 0.07546650618314743,
|
| 2398 |
+
"learning_rate": 6.848963066275027e-06,
|
| 2399 |
+
"loss": 0.0003,
|
| 2400 |
+
"num_input_tokens_seen": 214544,
|
| 2401 |
+
"step": 1410
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"epoch": 7.861111111111111,
|
| 2405 |
+
"grad_norm": 0.0016303466400131583,
|
| 2406 |
+
"learning_rate": 6.683127646793411e-06,
|
| 2407 |
+
"loss": 0.0001,
|
| 2408 |
+
"num_input_tokens_seen": 215328,
|
| 2409 |
+
"step": 1415
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 7.888888888888889,
|
| 2413 |
+
"grad_norm": 0.0015782971167936921,
|
| 2414 |
+
"learning_rate": 6.519014324435102e-06,
|
| 2415 |
+
"loss": 0.0,
|
| 2416 |
+
"num_input_tokens_seen": 216080,
|
| 2417 |
+
"step": 1420
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 7.916666666666667,
|
| 2421 |
+
"grad_norm": 0.0021568036172538996,
|
| 2422 |
+
"learning_rate": 6.356638528639955e-06,
|
| 2423 |
+
"loss": 0.0,
|
| 2424 |
+
"num_input_tokens_seen": 216848,
|
| 2425 |
+
"step": 1425
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 7.944444444444445,
|
| 2429 |
+
"grad_norm": 0.03259359672665596,
|
| 2430 |
+
"learning_rate": 6.196015525490825e-06,
|
| 2431 |
+
"loss": 0.0012,
|
| 2432 |
+
"num_input_tokens_seen": 217632,
|
| 2433 |
+
"step": 1430
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 7.972222222222222,
|
| 2437 |
+
"grad_norm": 0.04973651096224785,
|
| 2438 |
+
"learning_rate": 6.037160416278278e-06,
|
| 2439 |
+
"loss": 0.0001,
|
| 2440 |
+
"num_input_tokens_seen": 218400,
|
| 2441 |
+
"step": 1435
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 8.0,
|
| 2445 |
+
"grad_norm": 0.0013207773445174098,
|
| 2446 |
+
"learning_rate": 5.880088136080814e-06,
|
| 2447 |
+
"loss": 0.0,
|
| 2448 |
+
"num_input_tokens_seen": 219200,
|
| 2449 |
+
"step": 1440
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"epoch": 8.0,
|
| 2453 |
+
"eval_loss": 0.20432357490062714,
|
| 2454 |
+
"eval_runtime": 0.8946,
|
| 2455 |
+
"eval_samples_per_second": 44.712,
|
| 2456 |
+
"eval_steps_per_second": 22.356,
|
| 2457 |
+
"num_input_tokens_seen": 219200,
|
| 2458 |
+
"step": 1440
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 8.027777777777779,
|
| 2462 |
+
"grad_norm": 0.004510511644184589,
|
| 2463 |
+
"learning_rate": 5.724813452360736e-06,
|
| 2464 |
+
"loss": 0.0001,
|
| 2465 |
+
"num_input_tokens_seen": 219984,
|
| 2466 |
+
"step": 1445
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 8.055555555555555,
|
| 2470 |
+
"grad_norm": 0.052503470331430435,
|
| 2471 |
+
"learning_rate": 5.571350963575728e-06,
|
| 2472 |
+
"loss": 0.0003,
|
| 2473 |
+
"num_input_tokens_seen": 220784,
|
| 2474 |
+
"step": 1450
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 8.083333333333334,
|
| 2478 |
+
"grad_norm": 0.0020534901414066553,
|
| 2479 |
+
"learning_rate": 5.4197150978063965e-06,
|
| 2480 |
+
"loss": 0.0,
|
| 2481 |
+
"num_input_tokens_seen": 221536,
|
| 2482 |
+
"step": 1455
|
| 2483 |
+
},
|
| 2484 |
+
{
|
| 2485 |
+
"epoch": 8.11111111111111,
|
| 2486 |
+
"grad_norm": 0.0017636361299082637,
|
| 2487 |
+
"learning_rate": 5.269920111399732e-06,
|
| 2488 |
+
"loss": 0.0,
|
| 2489 |
+
"num_input_tokens_seen": 222256,
|
| 2490 |
+
"step": 1460
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 8.13888888888889,
|
| 2494 |
+
"grad_norm": 0.0010547855636104941,
|
| 2495 |
+
"learning_rate": 5.121980087628803e-06,
|
| 2496 |
+
"loss": 0.0,
|
| 2497 |
+
"num_input_tokens_seen": 223024,
|
| 2498 |
+
"step": 1465
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 8.166666666666666,
|
| 2502 |
+
"grad_norm": 0.008152388036251068,
|
| 2503 |
+
"learning_rate": 4.975908935368701e-06,
|
| 2504 |
+
"loss": 0.0001,
|
| 2505 |
+
"num_input_tokens_seen": 223760,
|
| 2506 |
+
"step": 1470
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 8.194444444444445,
|
| 2510 |
+
"grad_norm": 0.8113831281661987,
|
| 2511 |
+
"learning_rate": 4.831720387788827e-06,
|
| 2512 |
+
"loss": 0.0003,
|
| 2513 |
+
"num_input_tokens_seen": 224528,
|
| 2514 |
+
"step": 1475
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 8.222222222222221,
|
| 2518 |
+
"grad_norm": 0.002010009717196226,
|
| 2519 |
+
"learning_rate": 4.689428001061774e-06,
|
| 2520 |
+
"loss": 0.0001,
|
| 2521 |
+
"num_input_tokens_seen": 225296,
|
| 2522 |
+
"step": 1480
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 8.25,
|
| 2526 |
+
"grad_norm": 0.22730909287929535,
|
| 2527 |
+
"learning_rate": 4.549045153088813e-06,
|
| 2528 |
+
"loss": 0.0002,
|
| 2529 |
+
"num_input_tokens_seen": 226032,
|
| 2530 |
+
"step": 1485
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 8.277777777777779,
|
| 2534 |
+
"grad_norm": 0.0012671926524490118,
|
| 2535 |
+
"learning_rate": 4.410585042242124e-06,
|
| 2536 |
+
"loss": 0.0001,
|
| 2537 |
+
"num_input_tokens_seen": 226768,
|
| 2538 |
+
"step": 1490
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 8.305555555555555,
|
| 2542 |
+
"grad_norm": 0.0022841296158730984,
|
| 2543 |
+
"learning_rate": 4.274060686123959e-06,
|
| 2544 |
+
"loss": 0.0001,
|
| 2545 |
+
"num_input_tokens_seen": 227552,
|
| 2546 |
+
"step": 1495
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 8.333333333333334,
|
| 2550 |
+
"grad_norm": 0.0012009363854303956,
|
| 2551 |
+
"learning_rate": 4.1394849203427284e-06,
|
| 2552 |
+
"loss": 0.0,
|
| 2553 |
+
"num_input_tokens_seen": 228336,
|
| 2554 |
+
"step": 1500
|
| 2555 |
+
},
|
| 2556 |
+
{
|
| 2557 |
+
"epoch": 8.36111111111111,
|
| 2558 |
+
"grad_norm": 0.021565040573477745,
|
| 2559 |
+
"learning_rate": 4.006870397306256e-06,
|
| 2560 |
+
"loss": 0.0002,
|
| 2561 |
+
"num_input_tokens_seen": 229088,
|
| 2562 |
+
"step": 1505
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 8.38888888888889,
|
| 2566 |
+
"grad_norm": 0.0008409732836298645,
|
| 2567 |
+
"learning_rate": 3.876229585032245e-06,
|
| 2568 |
+
"loss": 0.0,
|
| 2569 |
+
"num_input_tokens_seen": 229840,
|
| 2570 |
+
"step": 1510
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 8.416666666666666,
|
| 2574 |
+
"grad_norm": 0.0019264855654910207,
|
| 2575 |
+
"learning_rate": 3.7475747659760502e-06,
|
| 2576 |
+
"loss": 0.0,
|
| 2577 |
+
"num_input_tokens_seen": 230608,
|
| 2578 |
+
"step": 1515
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 8.444444444444445,
|
| 2582 |
+
"grad_norm": 0.0012031939113512635,
|
| 2583 |
+
"learning_rate": 3.6209180358759394e-06,
|
| 2584 |
+
"loss": 0.0,
|
| 2585 |
+
"num_input_tokens_seen": 231360,
|
| 2586 |
+
"step": 1520
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 8.472222222222221,
|
| 2590 |
+
"grad_norm": 0.0017787732649594545,
|
| 2591 |
+
"learning_rate": 3.4962713026158694e-06,
|
| 2592 |
+
"loss": 0.0002,
|
| 2593 |
+
"num_input_tokens_seen": 232160,
|
| 2594 |
+
"step": 1525
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 8.5,
|
| 2598 |
+
"grad_norm": 0.02529619075357914,
|
| 2599 |
+
"learning_rate": 3.373646285105958e-06,
|
| 2600 |
+
"loss": 0.0,
|
| 2601 |
+
"num_input_tokens_seen": 232896,
|
| 2602 |
+
"step": 1530
|
| 2603 |
+
},
|
| 2604 |
+
{
|
| 2605 |
+
"epoch": 8.5,
|
| 2606 |
+
"eval_loss": 0.1972600668668747,
|
| 2607 |
+
"eval_runtime": 0.8977,
|
| 2608 |
+
"eval_samples_per_second": 44.558,
|
| 2609 |
+
"eval_steps_per_second": 22.279,
|
| 2610 |
+
"num_input_tokens_seen": 232896,
|
| 2611 |
+
"step": 1530
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 8.527777777777779,
|
| 2615 |
+
"grad_norm": 0.0014007817953824997,
|
| 2616 |
+
"learning_rate": 3.2530545121807145e-06,
|
| 2617 |
+
"loss": 0.0001,
|
| 2618 |
+
"num_input_tokens_seen": 233680,
|
| 2619 |
+
"step": 1535
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 8.555555555555555,
|
| 2623 |
+
"grad_norm": 0.014800156466662884,
|
| 2624 |
+
"learning_rate": 3.1345073215151066e-06,
|
| 2625 |
+
"loss": 0.0,
|
| 2626 |
+
"num_input_tokens_seen": 234464,
|
| 2627 |
+
"step": 1540
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 8.583333333333334,
|
| 2631 |
+
"grad_norm": 0.0012088757939636707,
|
| 2632 |
+
"learning_rate": 3.0180158585586397e-06,
|
| 2633 |
+
"loss": 0.0001,
|
| 2634 |
+
"num_input_tokens_seen": 235184,
|
| 2635 |
+
"step": 1545
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 8.61111111111111,
|
| 2639 |
+
"grad_norm": 0.0011525284498929977,
|
| 2640 |
+
"learning_rate": 2.9035910754875136e-06,
|
| 2641 |
+
"loss": 0.0001,
|
| 2642 |
+
"num_input_tokens_seen": 235984,
|
| 2643 |
+
"step": 1550
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 8.63888888888889,
|
| 2647 |
+
"grad_norm": 0.06784788519144058,
|
| 2648 |
+
"learning_rate": 2.7912437301749026e-06,
|
| 2649 |
+
"loss": 0.0001,
|
| 2650 |
+
"num_input_tokens_seen": 236720,
|
| 2651 |
+
"step": 1555
|
| 2652 |
+
},
|
| 2653 |
+
{
|
| 2654 |
+
"epoch": 8.666666666666666,
|
| 2655 |
+
"grad_norm": 0.024774013087153435,
|
| 2656 |
+
"learning_rate": 2.6809843851795357e-06,
|
| 2657 |
+
"loss": 0.0,
|
| 2658 |
+
"num_input_tokens_seen": 237456,
|
| 2659 |
+
"step": 1560
|
| 2660 |
+
},
|
| 2661 |
+
{
|
| 2662 |
+
"epoch": 8.694444444444445,
|
| 2663 |
+
"grad_norm": 0.0015475035179406404,
|
| 2664 |
+
"learning_rate": 2.57282340675267e-06,
|
| 2665 |
+
"loss": 0.0,
|
| 2666 |
+
"num_input_tokens_seen": 238240,
|
| 2667 |
+
"step": 1565
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 8.722222222222221,
|
| 2671 |
+
"grad_norm": 0.0015052126254886389,
|
| 2672 |
+
"learning_rate": 2.4667709638634434e-06,
|
| 2673 |
+
"loss": 0.134,
|
| 2674 |
+
"num_input_tokens_seen": 238992,
|
| 2675 |
+
"step": 1570
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 8.75,
|
| 2679 |
+
"grad_norm": 0.002601168816909194,
|
| 2680 |
+
"learning_rate": 2.3628370272428564e-06,
|
| 2681 |
+
"loss": 0.0,
|
| 2682 |
+
"num_input_tokens_seen": 239776,
|
| 2683 |
+
"step": 1575
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 8.777777777777779,
|
| 2687 |
+
"grad_norm": 0.0026071418542414904,
|
| 2688 |
+
"learning_rate": 2.2610313684463177e-06,
|
| 2689 |
+
"loss": 0.0,
|
| 2690 |
+
"num_input_tokens_seen": 240528,
|
| 2691 |
+
"step": 1580
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 8.805555555555555,
|
| 2695 |
+
"grad_norm": 0.0014425113331526518,
|
| 2696 |
+
"learning_rate": 2.1613635589349756e-06,
|
| 2697 |
+
"loss": 0.0,
|
| 2698 |
+
"num_input_tokens_seen": 241280,
|
| 2699 |
+
"step": 1585
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 8.833333333333334,
|
| 2703 |
+
"grad_norm": 0.0016695759259164333,
|
| 2704 |
+
"learning_rate": 2.063842969175847e-06,
|
| 2705 |
+
"loss": 0.0,
|
| 2706 |
+
"num_input_tokens_seen": 242048,
|
| 2707 |
+
"step": 1590
|
| 2708 |
+
},
|
| 2709 |
+
{
|
| 2710 |
+
"epoch": 8.86111111111111,
|
| 2711 |
+
"grad_norm": 0.009643935598433018,
|
| 2712 |
+
"learning_rate": 1.968478767760812e-06,
|
| 2713 |
+
"loss": 0.0,
|
| 2714 |
+
"num_input_tokens_seen": 242816,
|
| 2715 |
+
"step": 1595
|
| 2716 |
+
},
|
| 2717 |
+
{
|
| 2718 |
+
"epoch": 8.88888888888889,
|
| 2719 |
+
"grad_norm": 0.001525353523902595,
|
| 2720 |
+
"learning_rate": 1.8752799205445982e-06,
|
| 2721 |
+
"loss": 0.0,
|
| 2722 |
+
"num_input_tokens_seen": 243584,
|
| 2723 |
+
"step": 1600
|
| 2724 |
+
},
|
| 2725 |
+
{
|
| 2726 |
+
"epoch": 8.916666666666666,
|
| 2727 |
+
"grad_norm": 0.002979699755087495,
|
| 2728 |
+
"learning_rate": 1.784255189801895e-06,
|
| 2729 |
+
"loss": 0.0,
|
| 2730 |
+
"num_input_tokens_seen": 244336,
|
| 2731 |
+
"step": 1605
|
| 2732 |
+
},
|
| 2733 |
+
{
|
| 2734 |
+
"epoch": 8.944444444444445,
|
| 2735 |
+
"grad_norm": 0.008621761575341225,
|
| 2736 |
+
"learning_rate": 1.6954131334034922e-06,
|
| 2737 |
+
"loss": 0.0001,
|
| 2738 |
+
"num_input_tokens_seen": 245072,
|
| 2739 |
+
"step": 1610
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 8.972222222222221,
|
| 2743 |
+
"grad_norm": 0.0019121435470879078,
|
| 2744 |
+
"learning_rate": 1.6087621040117157e-06,
|
| 2745 |
+
"loss": 0.0,
|
| 2746 |
+
"num_input_tokens_seen": 245824,
|
| 2747 |
+
"step": 1615
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 9.0,
|
| 2751 |
+
"grad_norm": 0.039212632924318314,
|
| 2752 |
+
"learning_rate": 1.524310248295152e-06,
|
| 2753 |
+
"loss": 0.0001,
|
| 2754 |
+
"num_input_tokens_seen": 246592,
|
| 2755 |
+
"step": 1620
|
| 2756 |
+
},
|
| 2757 |
+
{
|
| 2758 |
+
"epoch": 9.0,
|
| 2759 |
+
"eval_loss": 0.20404863357543945,
|
| 2760 |
+
"eval_runtime": 0.9073,
|
| 2761 |
+
"eval_samples_per_second": 44.087,
|
| 2762 |
+
"eval_steps_per_second": 22.044,
|
| 2763 |
+
"num_input_tokens_seen": 246592,
|
| 2764 |
+
"step": 1620
|
| 2765 |
+
},
|
| 2766 |
+
{
|
| 2767 |
+
"epoch": 9.027777777777779,
|
| 2768 |
+
"grad_norm": 0.0018777285004034638,
|
| 2769 |
+
"learning_rate": 1.4420655061626932e-06,
|
| 2770 |
+
"loss": 0.0,
|
| 2771 |
+
"num_input_tokens_seen": 247360,
|
| 2772 |
+
"step": 1625
|
| 2773 |
+
},
|
| 2774 |
+
{
|
| 2775 |
+
"epoch": 9.055555555555555,
|
| 2776 |
+
"grad_norm": 0.02277091145515442,
|
| 2777 |
+
"learning_rate": 1.362035610017079e-06,
|
| 2778 |
+
"loss": 0.0001,
|
| 2779 |
+
"num_input_tokens_seen": 248160,
|
| 2780 |
+
"step": 1630
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 9.083333333333334,
|
| 2784 |
+
"grad_norm": 0.0013543771347030997,
|
| 2785 |
+
"learning_rate": 1.2842280840278997e-06,
|
| 2786 |
+
"loss": 0.0001,
|
| 2787 |
+
"num_input_tokens_seen": 248912,
|
| 2788 |
+
"step": 1635
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 9.11111111111111,
|
| 2792 |
+
"grad_norm": 0.001997560728341341,
|
| 2793 |
+
"learning_rate": 1.2086502434241865e-06,
|
| 2794 |
+
"loss": 0.0,
|
| 2795 |
+
"num_input_tokens_seen": 249680,
|
| 2796 |
+
"step": 1640
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 9.13888888888889,
|
| 2800 |
+
"grad_norm": 0.00147831451613456,
|
| 2801 |
+
"learning_rate": 1.1353091938067023e-06,
|
| 2802 |
+
"loss": 0.0,
|
| 2803 |
+
"num_input_tokens_seen": 250400,
|
| 2804 |
+
"step": 1645
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 9.166666666666666,
|
| 2808 |
+
"grad_norm": 0.03436870872974396,
|
| 2809 |
+
"learning_rate": 1.0642118304798442e-06,
|
| 2810 |
+
"loss": 0.0001,
|
| 2811 |
+
"num_input_tokens_seen": 251136,
|
| 2812 |
+
"step": 1650
|
| 2813 |
+
},
|
| 2814 |
+
{
|
| 2815 |
+
"epoch": 9.194444444444445,
|
| 2816 |
+
"grad_norm": 0.0011072098277509212,
|
| 2817 |
+
"learning_rate": 9.95364837803392e-07,
|
| 2818 |
+
"loss": 0.0,
|
| 2819 |
+
"num_input_tokens_seen": 251920,
|
| 2820 |
+
"step": 1655
|
| 2821 |
+
},
|
| 2822 |
+
{
|
| 2823 |
+
"epoch": 9.222222222222221,
|
| 2824 |
+
"grad_norm": 0.012758857570588589,
|
| 2825 |
+
"learning_rate": 9.287746885640603e-07,
|
| 2826 |
+
"loss": 0.0,
|
| 2827 |
+
"num_input_tokens_seen": 252656,
|
| 2828 |
+
"step": 1660
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"epoch": 9.25,
|
| 2832 |
+
"grad_norm": 0.0020957046654075384,
|
| 2833 |
+
"learning_rate": 8.64447643366953e-07,
|
| 2834 |
+
"loss": 0.0,
|
| 2835 |
+
"num_input_tokens_seen": 253456,
|
| 2836 |
+
"step": 1665
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 9.277777777777779,
|
| 2840 |
+
"grad_norm": 0.0014656794955953956,
|
| 2841 |
+
"learning_rate": 8.023897500469391e-07,
|
| 2842 |
+
"loss": 0.0,
|
| 2843 |
+
"num_input_tokens_seen": 254208,
|
| 2844 |
+
"step": 1670
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 9.305555555555555,
|
| 2848 |
+
"grad_norm": 0.0010977443307638168,
|
| 2849 |
+
"learning_rate": 7.426068431000882e-07,
|
| 2850 |
+
"loss": 0.0001,
|
| 2851 |
+
"num_input_tokens_seen": 254976,
|
| 2852 |
+
"step": 1675
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 9.333333333333334,
|
| 2856 |
+
"grad_norm": 0.0014999699778854847,
|
| 2857 |
+
"learning_rate": 6.851045431350927e-07,
|
| 2858 |
+
"loss": 0.0002,
|
| 2859 |
+
"num_input_tokens_seen": 255728,
|
| 2860 |
+
"step": 1680
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 9.36111111111111,
|
| 2864 |
+
"grad_norm": 0.00202179211191833,
|
| 2865 |
+
"learning_rate": 6.298882563448599e-07,
|
| 2866 |
+
"loss": 0.1258,
|
| 2867 |
+
"num_input_tokens_seen": 256464,
|
| 2868 |
+
"step": 1685
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 9.38888888888889,
|
| 2872 |
+
"grad_norm": 0.003387672360986471,
|
| 2873 |
+
"learning_rate": 5.769631739982267e-07,
|
| 2874 |
+
"loss": 0.0,
|
| 2875 |
+
"num_input_tokens_seen": 257216,
|
| 2876 |
+
"step": 1690
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 9.416666666666666,
|
| 2880 |
+
"grad_norm": 0.0013138880021870136,
|
| 2881 |
+
"learning_rate": 5.263342719518921e-07,
|
| 2882 |
+
"loss": 0.0,
|
| 2883 |
+
"num_input_tokens_seen": 258000,
|
| 2884 |
+
"step": 1695
|
| 2885 |
+
},
|
| 2886 |
+
{
|
| 2887 |
+
"epoch": 9.444444444444445,
|
| 2888 |
+
"grad_norm": 0.004265029914677143,
|
| 2889 |
+
"learning_rate": 4.780063101826132e-07,
|
| 2890 |
+
"loss": 0.0001,
|
| 2891 |
+
"num_input_tokens_seen": 258768,
|
| 2892 |
+
"step": 1700
|
| 2893 |
+
},
|
| 2894 |
+
{
|
| 2895 |
+
"epoch": 9.472222222222221,
|
| 2896 |
+
"grad_norm": 0.0014389421558007598,
|
| 2897 |
+
"learning_rate": 4.319838323396691e-07,
|
| 2898 |
+
"loss": 0.0,
|
| 2899 |
+
"num_input_tokens_seen": 259536,
|
| 2900 |
+
"step": 1705
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 9.5,
|
| 2904 |
+
"grad_norm": 0.0019381530582904816,
|
| 2905 |
+
"learning_rate": 3.88271165317694e-07,
|
| 2906 |
+
"loss": 0.0,
|
| 2907 |
+
"num_input_tokens_seen": 260320,
|
| 2908 |
+
"step": 1710
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 9.5,
|
| 2912 |
+
"eval_loss": 0.1979570835828781,
|
| 2913 |
+
"eval_runtime": 0.8827,
|
| 2914 |
+
"eval_samples_per_second": 45.316,
|
| 2915 |
+
"eval_steps_per_second": 22.658,
|
| 2916 |
+
"num_input_tokens_seen": 260320,
|
| 2917 |
+
"step": 1710
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 9.527777777777779,
|
| 2921 |
+
"grad_norm": 0.001763106556609273,
|
| 2922 |
+
"learning_rate": 3.468724188498751e-07,
|
| 2923 |
+
"loss": 0.0002,
|
| 2924 |
+
"num_input_tokens_seen": 261056,
|
| 2925 |
+
"step": 1715
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 9.555555555555555,
|
| 2929 |
+
"grad_norm": 0.0015600565820932388,
|
| 2930 |
+
"learning_rate": 3.077914851215585e-07,
|
| 2931 |
+
"loss": 0.0,
|
| 2932 |
+
"num_input_tokens_seen": 261808,
|
| 2933 |
+
"step": 1720
|
| 2934 |
+
},
|
| 2935 |
+
{
|
| 2936 |
+
"epoch": 9.583333333333334,
|
| 2937 |
+
"grad_norm": 0.02792200818657875,
|
| 2938 |
+
"learning_rate": 2.71032038404323e-07,
|
| 2939 |
+
"loss": 0.0002,
|
| 2940 |
+
"num_input_tokens_seen": 262576,
|
| 2941 |
+
"step": 1725
|
| 2942 |
+
},
|
| 2943 |
+
{
|
| 2944 |
+
"epoch": 9.61111111111111,
|
| 2945 |
+
"grad_norm": 0.0016239579999819398,
|
| 2946 |
+
"learning_rate": 2.365975347105448e-07,
|
| 2947 |
+
"loss": 0.0001,
|
| 2948 |
+
"num_input_tokens_seen": 263312,
|
| 2949 |
+
"step": 1730
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 9.63888888888889,
|
| 2953 |
+
"grad_norm": 0.052164334803819656,
|
| 2954 |
+
"learning_rate": 2.0449121146845774e-07,
|
| 2955 |
+
"loss": 0.0001,
|
| 2956 |
+
"num_input_tokens_seen": 264064,
|
| 2957 |
+
"step": 1735
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 9.666666666666666,
|
| 2961 |
+
"grad_norm": 0.0016509494744241238,
|
| 2962 |
+
"learning_rate": 1.747160872177883e-07,
|
| 2963 |
+
"loss": 0.0001,
|
| 2964 |
+
"num_input_tokens_seen": 264816,
|
| 2965 |
+
"step": 1740
|
| 2966 |
+
},
|
| 2967 |
+
{
|
| 2968 |
+
"epoch": 9.694444444444445,
|
| 2969 |
+
"grad_norm": 0.06074906513094902,
|
| 2970 |
+
"learning_rate": 1.472749613259661e-07,
|
| 2971 |
+
"loss": 0.0001,
|
| 2972 |
+
"num_input_tokens_seen": 265584,
|
| 2973 |
+
"step": 1745
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 9.722222222222221,
|
| 2977 |
+
"grad_norm": 0.002588711678981781,
|
| 2978 |
+
"learning_rate": 1.22170413724923e-07,
|
| 2979 |
+
"loss": 0.0,
|
| 2980 |
+
"num_input_tokens_seen": 266320,
|
| 2981 |
+
"step": 1750
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 9.75,
|
| 2985 |
+
"grad_norm": 0.019099904224276543,
|
| 2986 |
+
"learning_rate": 9.940480466855417e-08,
|
| 2987 |
+
"loss": 0.0,
|
| 2988 |
+
"num_input_tokens_seen": 267072,
|
| 2989 |
+
"step": 1755
|
| 2990 |
+
},
|
| 2991 |
+
{
|
| 2992 |
+
"epoch": 9.777777777777779,
|
| 2993 |
+
"grad_norm": 0.0015253141755238175,
|
| 2994 |
+
"learning_rate": 7.898027451078982e-08,
|
| 2995 |
+
"loss": 0.0,
|
| 2996 |
+
"num_input_tokens_seen": 267840,
|
| 2997 |
+
"step": 1760
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 9.805555555555555,
|
| 3001 |
+
"grad_norm": 0.0014633400132879615,
|
| 3002 |
+
"learning_rate": 6.089874350439506e-08,
|
| 3003 |
+
"loss": 0.0,
|
| 3004 |
+
"num_input_tokens_seen": 268592,
|
| 3005 |
+
"step": 1765
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 9.833333333333334,
|
| 3009 |
+
"grad_norm": 0.0010498091578483582,
|
| 3010 |
+
"learning_rate": 4.516191162040051e-08,
|
| 3011 |
+
"loss": 0.0001,
|
| 3012 |
+
"num_input_tokens_seen": 269344,
|
| 3013 |
+
"step": 1770
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 9.86111111111111,
|
| 3017 |
+
"grad_norm": 0.003073125844821334,
|
| 3018 |
+
"learning_rate": 3.177125838830786e-08,
|
| 3019 |
+
"loss": 0.0001,
|
| 3020 |
+
"num_input_tokens_seen": 270112,
|
| 3021 |
+
"step": 1775
|
| 3022 |
+
},
|
| 3023 |
+
{
|
| 3024 |
+
"epoch": 9.88888888888889,
|
| 3025 |
+
"grad_norm": 0.032370708882808685,
|
| 3026 |
+
"learning_rate": 2.0728042756967824e-08,
|
| 3027 |
+
"loss": 0.0001,
|
| 3028 |
+
"num_input_tokens_seen": 270880,
|
| 3029 |
+
"step": 1780
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 9.916666666666666,
|
| 3033 |
+
"grad_norm": 0.26500117778778076,
|
| 3034 |
+
"learning_rate": 1.2033302976222071e-08,
|
| 3035 |
+
"loss": 0.0001,
|
| 3036 |
+
"num_input_tokens_seen": 271664,
|
| 3037 |
+
"step": 1785
|
| 3038 |
+
},
|
| 3039 |
+
{
|
| 3040 |
+
"epoch": 9.944444444444445,
|
| 3041 |
+
"grad_norm": 0.008083530701696873,
|
| 3042 |
+
"learning_rate": 5.687856499297928e-09,
|
| 3043 |
+
"loss": 0.0001,
|
| 3044 |
+
"num_input_tokens_seen": 272384,
|
| 3045 |
+
"step": 1790
|
| 3046 |
+
},
|
| 3047 |
+
{
|
| 3048 |
+
"epoch": 9.972222222222221,
|
| 3049 |
+
"grad_norm": 0.0012048567878082395,
|
| 3050 |
+
"learning_rate": 1.692299905944883e-09,
|
| 3051 |
+
"loss": 0.0001,
|
| 3052 |
+
"num_input_tokens_seen": 273168,
|
| 3053 |
+
"step": 1795
|
| 3054 |
+
},
|
| 3055 |
+
{
|
| 3056 |
+
"epoch": 10.0,
|
| 3057 |
+
"grad_norm": 0.0026044242549687624,
|
| 3058 |
+
"learning_rate": 4.700884634611935e-11,
|
| 3059 |
+
"loss": 0.0002,
|
| 3060 |
+
"num_input_tokens_seen": 273936,
|
| 3061 |
+
"step": 1800
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 10.0,
|
| 3065 |
+
"eval_loss": 0.19950854778289795,
|
| 3066 |
+
"eval_runtime": 0.8838,
|
| 3067 |
+
"eval_samples_per_second": 45.26,
|
| 3068 |
+
"eval_steps_per_second": 22.63,
|
| 3069 |
+
"num_input_tokens_seen": 273936,
|
| 3070 |
+
"step": 1800
|
| 3071 |
+
},
|
| 3072 |
+
{
|
| 3073 |
+
"epoch": 10.0,
|
| 3074 |
+
"num_input_tokens_seen": 273936,
|
| 3075 |
+
"step": 1800,
|
| 3076 |
+
"total_flos": 1.3438495585861632e+16,
|
| 3077 |
+
"train_loss": 0.044879560974069234,
|
| 3078 |
+
"train_runtime": 814.6797,
|
| 3079 |
+
"train_samples_per_second": 4.419,
|
| 3080 |
+
"train_steps_per_second": 2.209
|
| 3081 |
+
}
|
| 3082 |
+
],
|
| 3083 |
+
"logging_steps": 5,
|
| 3084 |
+
"max_steps": 1800,
|
| 3085 |
+
"num_input_tokens_seen": 273936,
|
| 3086 |
+
"num_train_epochs": 10,
|
| 3087 |
+
"save_steps": 90,
|
| 3088 |
+
"stateful_callbacks": {
|
| 3089 |
+
"TrainerControl": {
|
| 3090 |
+
"args": {
|
| 3091 |
+
"should_epoch_stop": false,
|
| 3092 |
+
"should_evaluate": false,
|
| 3093 |
+
"should_log": false,
|
| 3094 |
+
"should_save": true,
|
| 3095 |
+
"should_training_stop": true
|
| 3096 |
+
},
|
| 3097 |
+
"attributes": {}
|
| 3098 |
+
}
|
| 3099 |
+
},
|
| 3100 |
+
"total_flos": 1.3438495585861632e+16,
|
| 3101 |
+
"train_batch_size": 2,
|
| 3102 |
+
"trial_name": null,
|
| 3103 |
+
"trial_params": null
|
| 3104 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|