End of training
Browse files- README.md +2 -2
- all_results.json +17 -0
- eval_results.json +11 -0
- train_results.json +10 -0
- trainer_state.json +1575 -0
README.md
CHANGED
@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# jamba-H1024_L12-v0.12-fineweb-100k-xlong_16k-knowledge-inoc-concat-v1-vN
|
17 |
|
18 |
-
This model is a fine-tuned version of [pszemraj/jamba-H1024_L12-v0.12-fineweb-100k-xlong_16k](https://huggingface.co/pszemraj/jamba-H1024_L12-v0.12-fineweb-100k-xlong_16k) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 3.0366
|
21 |
- Accuracy: 0.4514
|
22 |
-
- Num Input Tokens Seen:
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
15 |
|
16 |
# jamba-H1024_L12-v0.12-fineweb-100k-xlong_16k-knowledge-inoc-concat-v1-vN
|
17 |
|
18 |
+
This model is a fine-tuned version of [pszemraj/jamba-H1024_L12-v0.12-fineweb-100k-xlong_16k](https://huggingface.co/pszemraj/jamba-H1024_L12-v0.12-fineweb-100k-xlong_16k) on the BEE-spoke-data/knowledge-inoc-concat-v1 dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 3.0366
|
21 |
- Accuracy: 0.4514
|
22 |
+
- Num Input Tokens Seen: 1975517184
|
23 |
|
24 |
## Model description
|
25 |
|
all_results.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.997349589186324,
|
3 |
+
"eval_accuracy": 0.45143400679566215,
|
4 |
+
"eval_loss": 3.0366320610046387,
|
5 |
+
"eval_runtime": 36.3403,
|
6 |
+
"eval_samples": 300,
|
7 |
+
"eval_samples_per_second": 8.255,
|
8 |
+
"eval_steps_per_second": 2.064,
|
9 |
+
"num_input_tokens_seen": 1975517184,
|
10 |
+
"perplexity": 20.83495408242377,
|
11 |
+
"total_flos": 9.732316690586272e+18,
|
12 |
+
"train_loss": 3.186332613039928,
|
13 |
+
"train_runtime": 34789.3198,
|
14 |
+
"train_samples": 60368,
|
15 |
+
"train_samples_per_second": 3.47,
|
16 |
+
"train_steps_per_second": 0.027
|
17 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.997349589186324,
|
3 |
+
"eval_accuracy": 0.45143400679566215,
|
4 |
+
"eval_loss": 3.0366320610046387,
|
5 |
+
"eval_runtime": 36.3403,
|
6 |
+
"eval_samples": 300,
|
7 |
+
"eval_samples_per_second": 8.255,
|
8 |
+
"eval_steps_per_second": 2.064,
|
9 |
+
"num_input_tokens_seen": 1975517184,
|
10 |
+
"perplexity": 20.83495408242377
|
11 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.997349589186324,
|
3 |
+
"num_input_tokens_seen": 1975517184,
|
4 |
+
"total_flos": 9.732316690586272e+18,
|
5 |
+
"train_loss": 3.186332613039928,
|
6 |
+
"train_runtime": 34789.3198,
|
7 |
+
"train_samples": 60368,
|
8 |
+
"train_samples_per_second": 3.47,
|
9 |
+
"train_steps_per_second": 0.027
|
10 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1575 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.997349589186324,
|
5 |
+
"eval_steps": 200,
|
6 |
+
"global_step": 942,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.010601643254704479,
|
13 |
+
"grad_norm": 0.8797913789749146,
|
14 |
+
"learning_rate": 5.208333333333334e-06,
|
15 |
+
"loss": 3.3968,
|
16 |
+
"num_input_tokens_seen": 10485760,
|
17 |
+
"step": 5
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.021203286509408958,
|
21 |
+
"grad_norm": 0.5857719779014587,
|
22 |
+
"learning_rate": 1.0416666666666668e-05,
|
23 |
+
"loss": 3.3102,
|
24 |
+
"num_input_tokens_seen": 20971520,
|
25 |
+
"step": 10
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.031804929764113435,
|
29 |
+
"grad_norm": 0.38287150859832764,
|
30 |
+
"learning_rate": 1.5625e-05,
|
31 |
+
"loss": 3.3919,
|
32 |
+
"num_input_tokens_seen": 31457280,
|
33 |
+
"step": 15
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.042406573018817915,
|
37 |
+
"grad_norm": 0.2890233099460602,
|
38 |
+
"learning_rate": 2.0833333333333336e-05,
|
39 |
+
"loss": 3.3448,
|
40 |
+
"num_input_tokens_seen": 41943040,
|
41 |
+
"step": 20
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.053008216273522396,
|
45 |
+
"grad_norm": 0.28800511360168457,
|
46 |
+
"learning_rate": 2.604166666666667e-05,
|
47 |
+
"loss": 3.247,
|
48 |
+
"num_input_tokens_seen": 52428800,
|
49 |
+
"step": 25
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.06360985952822687,
|
53 |
+
"grad_norm": 0.5624825358390808,
|
54 |
+
"learning_rate": 3.125e-05,
|
55 |
+
"loss": 3.3736,
|
56 |
+
"num_input_tokens_seen": 62914560,
|
57 |
+
"step": 30
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.07421150278293136,
|
61 |
+
"grad_norm": 0.2708434760570526,
|
62 |
+
"learning_rate": 3.6458333333333336e-05,
|
63 |
+
"loss": 3.3105,
|
64 |
+
"num_input_tokens_seen": 73400320,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.08481314603763583,
|
69 |
+
"grad_norm": 0.26101428270339966,
|
70 |
+
"learning_rate": 4.166666666666667e-05,
|
71 |
+
"loss": 3.3523,
|
72 |
+
"num_input_tokens_seen": 83886080,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.09541478929234032,
|
77 |
+
"grad_norm": 0.22077707946300507,
|
78 |
+
"learning_rate": 4.6875e-05,
|
79 |
+
"loss": 3.3395,
|
80 |
+
"num_input_tokens_seen": 94371840,
|
81 |
+
"step": 45
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.10601643254704479,
|
85 |
+
"grad_norm": 0.2976844608783722,
|
86 |
+
"learning_rate": 4.9999382562611344e-05,
|
87 |
+
"loss": 3.2379,
|
88 |
+
"num_input_tokens_seen": 104857600,
|
89 |
+
"step": 50
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.11661807580174927,
|
93 |
+
"grad_norm": 0.32657739520072937,
|
94 |
+
"learning_rate": 4.999243674223826e-05,
|
95 |
+
"loss": 3.2281,
|
96 |
+
"num_input_tokens_seen": 115343360,
|
97 |
+
"step": 55
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.12721971905645374,
|
101 |
+
"grad_norm": 0.2382456362247467,
|
102 |
+
"learning_rate": 4.997777545616258e-05,
|
103 |
+
"loss": 3.2807,
|
104 |
+
"num_input_tokens_seen": 125829120,
|
105 |
+
"step": 60
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.13782136231115824,
|
109 |
+
"grad_norm": 0.4440530836582184,
|
110 |
+
"learning_rate": 4.99554032304996e-05,
|
111 |
+
"loss": 3.2192,
|
112 |
+
"num_input_tokens_seen": 136314880,
|
113 |
+
"step": 65
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.14842300556586271,
|
117 |
+
"grad_norm": 0.2103557139635086,
|
118 |
+
"learning_rate": 4.9925326971824345e-05,
|
119 |
+
"loss": 3.3152,
|
120 |
+
"num_input_tokens_seen": 146800640,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.1590246488205672,
|
125 |
+
"grad_norm": 0.252693772315979,
|
126 |
+
"learning_rate": 4.988755596503948e-05,
|
127 |
+
"loss": 3.2393,
|
128 |
+
"num_input_tokens_seen": 157286400,
|
129 |
+
"step": 75
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.16962629207527166,
|
133 |
+
"grad_norm": 0.21133287250995636,
|
134 |
+
"learning_rate": 4.9842101870508904e-05,
|
135 |
+
"loss": 3.2727,
|
136 |
+
"num_input_tokens_seen": 167772160,
|
137 |
+
"step": 80
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.18022793532997614,
|
141 |
+
"grad_norm": 0.24876847863197327,
|
142 |
+
"learning_rate": 4.9788978720458104e-05,
|
143 |
+
"loss": 3.2566,
|
144 |
+
"num_input_tokens_seen": 178257920,
|
145 |
+
"step": 85
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.19082957858468064,
|
149 |
+
"grad_norm": 0.2968827486038208,
|
150 |
+
"learning_rate": 4.9728202914642183e-05,
|
151 |
+
"loss": 3.3258,
|
152 |
+
"num_input_tokens_seen": 188743680,
|
153 |
+
"step": 90
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.2014312218393851,
|
157 |
+
"grad_norm": 0.17700955271720886,
|
158 |
+
"learning_rate": 4.965979321528309e-05,
|
159 |
+
"loss": 3.2355,
|
160 |
+
"num_input_tokens_seen": 199229440,
|
161 |
+
"step": 95
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.21203286509408958,
|
165 |
+
"grad_norm": 0.20748387277126312,
|
166 |
+
"learning_rate": 4.9583770741277505e-05,
|
167 |
+
"loss": 3.195,
|
168 |
+
"num_input_tokens_seen": 209715200,
|
169 |
+
"step": 100
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.22263450834879406,
|
173 |
+
"grad_norm": 1.2878308296203613,
|
174 |
+
"learning_rate": 4.950015896167716e-05,
|
175 |
+
"loss": 3.3275,
|
176 |
+
"num_input_tokens_seen": 220200960,
|
177 |
+
"step": 105
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.23323615160349853,
|
181 |
+
"grad_norm": 0.26103636622428894,
|
182 |
+
"learning_rate": 4.9408983688443654e-05,
|
183 |
+
"loss": 3.3154,
|
184 |
+
"num_input_tokens_seen": 230686720,
|
185 |
+
"step": 110
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.24383779485820303,
|
189 |
+
"grad_norm": 0.2692287266254425,
|
190 |
+
"learning_rate": 4.931027306848004e-05,
|
191 |
+
"loss": 3.2573,
|
192 |
+
"num_input_tokens_seen": 241172480,
|
193 |
+
"step": 115
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.2544394381129075,
|
197 |
+
"grad_norm": 0.2487805187702179,
|
198 |
+
"learning_rate": 4.920405757494147e-05,
|
199 |
+
"loss": 3.2915,
|
200 |
+
"num_input_tokens_seen": 251658240,
|
201 |
+
"step": 120
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.26504108136761195,
|
205 |
+
"grad_norm": 0.17953425645828247,
|
206 |
+
"learning_rate": 4.9090369997827826e-05,
|
207 |
+
"loss": 3.1941,
|
208 |
+
"num_input_tokens_seen": 262144000,
|
209 |
+
"step": 125
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.2756427246223165,
|
213 |
+
"grad_norm": 0.19957853853702545,
|
214 |
+
"learning_rate": 4.896924543386099e-05,
|
215 |
+
"loss": 3.3033,
|
216 |
+
"num_input_tokens_seen": 272629760,
|
217 |
+
"step": 130
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.28624436787702096,
|
221 |
+
"grad_norm": 0.22015607357025146,
|
222 |
+
"learning_rate": 4.884072127565014e-05,
|
223 |
+
"loss": 3.2327,
|
224 |
+
"num_input_tokens_seen": 283115520,
|
225 |
+
"step": 135
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.29684601113172543,
|
229 |
+
"grad_norm": 0.241306334733963,
|
230 |
+
"learning_rate": 4.870483720014814e-05,
|
231 |
+
"loss": 3.2124,
|
232 |
+
"num_input_tokens_seen": 293601280,
|
233 |
+
"step": 140
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.3074476543864299,
|
237 |
+
"grad_norm": 0.49794742465019226,
|
238 |
+
"learning_rate": 4.85616351564028e-05,
|
239 |
+
"loss": 3.312,
|
240 |
+
"num_input_tokens_seen": 304087040,
|
241 |
+
"step": 145
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.3180492976411344,
|
245 |
+
"grad_norm": 0.18301662802696228,
|
246 |
+
"learning_rate": 4.8411159352606734e-05,
|
247 |
+
"loss": 3.295,
|
248 |
+
"num_input_tokens_seen": 314572800,
|
249 |
+
"step": 150
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.32865094089583885,
|
253 |
+
"grad_norm": 0.23481640219688416,
|
254 |
+
"learning_rate": 4.8253456242449704e-05,
|
255 |
+
"loss": 3.2555,
|
256 |
+
"num_input_tokens_seen": 325058560,
|
257 |
+
"step": 155
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.3392525841505433,
|
261 |
+
"grad_norm": 0.2195325493812561,
|
262 |
+
"learning_rate": 4.808857451077788e-05,
|
263 |
+
"loss": 3.1667,
|
264 |
+
"num_input_tokens_seen": 335544320,
|
265 |
+
"step": 160
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.3498542274052478,
|
269 |
+
"grad_norm": 0.23738664388656616,
|
270 |
+
"learning_rate": 4.7916565058564155e-05,
|
271 |
+
"loss": 3.2499,
|
272 |
+
"num_input_tokens_seen": 346030080,
|
273 |
+
"step": 165
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.36045587065995227,
|
277 |
+
"grad_norm": 0.3056640028953552,
|
278 |
+
"learning_rate": 4.7737480987194484e-05,
|
279 |
+
"loss": 3.2478,
|
280 |
+
"num_input_tokens_seen": 356515840,
|
281 |
+
"step": 170
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.37105751391465674,
|
285 |
+
"grad_norm": 0.18291524052619934,
|
286 |
+
"learning_rate": 4.755137758207479e-05,
|
287 |
+
"loss": 3.2648,
|
288 |
+
"num_input_tokens_seen": 367001600,
|
289 |
+
"step": 175
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.3816591571693613,
|
293 |
+
"grad_norm": 0.20183615386486053,
|
294 |
+
"learning_rate": 4.7358312295563734e-05,
|
295 |
+
"loss": 3.1717,
|
296 |
+
"num_input_tokens_seen": 377487360,
|
297 |
+
"step": 180
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.39226080042406575,
|
301 |
+
"grad_norm": 0.19222132861614227,
|
302 |
+
"learning_rate": 4.7158344729236454e-05,
|
303 |
+
"loss": 3.2288,
|
304 |
+
"num_input_tokens_seen": 387973120,
|
305 |
+
"step": 185
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.4028624436787702,
|
309 |
+
"grad_norm": 0.16234181821346283,
|
310 |
+
"learning_rate": 4.6951536615484854e-05,
|
311 |
+
"loss": 3.2316,
|
312 |
+
"num_input_tokens_seen": 398458880,
|
313 |
+
"step": 190
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.4134640869334747,
|
317 |
+
"grad_norm": 0.21459302306175232,
|
318 |
+
"learning_rate": 4.673795179846007e-05,
|
319 |
+
"loss": 3.1703,
|
320 |
+
"num_input_tokens_seen": 408944640,
|
321 |
+
"step": 195
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.42406573018817917,
|
325 |
+
"grad_norm": 0.1751609593629837,
|
326 |
+
"learning_rate": 4.651765621436303e-05,
|
327 |
+
"loss": 3.2013,
|
328 |
+
"num_input_tokens_seen": 419430400,
|
329 |
+
"step": 200
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.42406573018817917,
|
333 |
+
"eval_accuracy": 0.44791084254003133,
|
334 |
+
"eval_loss": 3.0653164386749268,
|
335 |
+
"eval_runtime": 36.089,
|
336 |
+
"eval_samples_per_second": 8.313,
|
337 |
+
"eval_steps_per_second": 2.078,
|
338 |
+
"num_input_tokens_seen": 419430400,
|
339 |
+
"step": 200
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.43466737344288364,
|
343 |
+
"grad_norm": 0.15440785884857178,
|
344 |
+
"learning_rate": 4.62907178710891e-05,
|
345 |
+
"loss": 3.2764,
|
346 |
+
"num_input_tokens_seen": 429916160,
|
347 |
+
"step": 205
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.4452690166975881,
|
351 |
+
"grad_norm": 0.19598723948001862,
|
352 |
+
"learning_rate": 4.60572068272333e-05,
|
353 |
+
"loss": 3.2128,
|
354 |
+
"num_input_tokens_seen": 440401920,
|
355 |
+
"step": 210
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 0.4558706599522926,
|
359 |
+
"grad_norm": 0.21214532852172852,
|
360 |
+
"learning_rate": 4.581719517046236e-05,
|
361 |
+
"loss": 3.1353,
|
362 |
+
"num_input_tokens_seen": 450887680,
|
363 |
+
"step": 215
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.46647230320699706,
|
367 |
+
"grad_norm": 0.181034654378891,
|
368 |
+
"learning_rate": 4.557075699526032e-05,
|
369 |
+
"loss": 3.2866,
|
370 |
+
"num_input_tokens_seen": 461373440,
|
371 |
+
"step": 220
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.47707394646170154,
|
375 |
+
"grad_norm": 0.16727791726589203,
|
376 |
+
"learning_rate": 4.531796838005477e-05,
|
377 |
+
"loss": 3.2111,
|
378 |
+
"num_input_tokens_seen": 471859200,
|
379 |
+
"step": 225
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 0.48767558971640607,
|
383 |
+
"grad_norm": 0.1804332137107849,
|
384 |
+
"learning_rate": 4.505890736373045e-05,
|
385 |
+
"loss": 3.297,
|
386 |
+
"num_input_tokens_seen": 482344960,
|
387 |
+
"step": 230
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.49827723297111054,
|
391 |
+
"grad_norm": 0.21492359042167664,
|
392 |
+
"learning_rate": 4.479365392153776e-05,
|
393 |
+
"loss": 3.1203,
|
394 |
+
"num_input_tokens_seen": 492830720,
|
395 |
+
"step": 235
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.508878876225815,
|
399 |
+
"grad_norm": 0.2664985656738281,
|
400 |
+
"learning_rate": 4.4522289940403404e-05,
|
401 |
+
"loss": 3.1352,
|
402 |
+
"num_input_tokens_seen": 503316480,
|
403 |
+
"step": 240
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.5194805194805194,
|
407 |
+
"grad_norm": 0.18706196546554565,
|
408 |
+
"learning_rate": 4.4244899193650933e-05,
|
409 |
+
"loss": 3.1747,
|
410 |
+
"num_input_tokens_seen": 513802240,
|
411 |
+
"step": 245
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.5300821627352239,
|
415 |
+
"grad_norm": 0.2427309900522232,
|
416 |
+
"learning_rate": 4.3961567315138885e-05,
|
417 |
+
"loss": 3.1677,
|
418 |
+
"num_input_tokens_seen": 524288000,
|
419 |
+
"step": 250
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.5406838059899285,
|
423 |
+
"grad_norm": 0.17540065944194794,
|
424 |
+
"learning_rate": 4.3672381772824615e-05,
|
425 |
+
"loss": 3.2012,
|
426 |
+
"num_input_tokens_seen": 534773760,
|
427 |
+
"step": 255
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 0.551285449244633,
|
431 |
+
"grad_norm": 0.31619423627853394,
|
432 |
+
"learning_rate": 4.3377431841761875e-05,
|
433 |
+
"loss": 3.1498,
|
434 |
+
"num_input_tokens_seen": 545259520,
|
435 |
+
"step": 260
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.5618870924993374,
|
439 |
+
"grad_norm": 0.24162785708904266,
|
440 |
+
"learning_rate": 4.307680857654052e-05,
|
441 |
+
"loss": 3.1703,
|
442 |
+
"num_input_tokens_seen": 555745280,
|
443 |
+
"step": 265
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.5724887357540419,
|
447 |
+
"grad_norm": 0.22926253080368042,
|
448 |
+
"learning_rate": 4.277060478317687e-05,
|
449 |
+
"loss": 3.2395,
|
450 |
+
"num_input_tokens_seen": 566231040,
|
451 |
+
"step": 270
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.5830903790087464,
|
455 |
+
"grad_norm": 0.23989850282669067,
|
456 |
+
"learning_rate": 4.245891499046338e-05,
|
457 |
+
"loss": 3.2383,
|
458 |
+
"num_input_tokens_seen": 576716800,
|
459 |
+
"step": 275
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.5936920222634509,
|
463 |
+
"grad_norm": 0.20367790758609772,
|
464 |
+
"learning_rate": 4.214183542078646e-05,
|
465 |
+
"loss": 3.1489,
|
466 |
+
"num_input_tokens_seen": 587202560,
|
467 |
+
"step": 280
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.6042936655181553,
|
471 |
+
"grad_norm": 0.22007331252098083,
|
472 |
+
"learning_rate": 4.1819463960421454e-05,
|
473 |
+
"loss": 3.1707,
|
474 |
+
"num_input_tokens_seen": 597688320,
|
475 |
+
"step": 285
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 0.6148953087728598,
|
479 |
+
"grad_norm": 0.19839680194854736,
|
480 |
+
"learning_rate": 4.149190012931402e-05,
|
481 |
+
"loss": 3.1679,
|
482 |
+
"num_input_tokens_seen": 608174080,
|
483 |
+
"step": 290
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.6254969520275643,
|
487 |
+
"grad_norm": 0.23358359932899475,
|
488 |
+
"learning_rate": 4.1159245050357065e-05,
|
489 |
+
"loss": 3.1629,
|
490 |
+
"num_input_tokens_seen": 618659840,
|
491 |
+
"step": 295
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.6360985952822688,
|
495 |
+
"grad_norm": 0.16982465982437134,
|
496 |
+
"learning_rate": 4.082160141817293e-05,
|
497 |
+
"loss": 3.16,
|
498 |
+
"num_input_tokens_seen": 629145600,
|
499 |
+
"step": 300
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.6467002385369732,
|
503 |
+
"grad_norm": 0.3546576201915741,
|
504 |
+
"learning_rate": 4.0479073467410286e-05,
|
505 |
+
"loss": 3.2448,
|
506 |
+
"num_input_tokens_seen": 639631360,
|
507 |
+
"step": 305
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.6573018817916777,
|
511 |
+
"grad_norm": 0.16487599909305573,
|
512 |
+
"learning_rate": 4.0131766940565715e-05,
|
513 |
+
"loss": 3.1789,
|
514 |
+
"num_input_tokens_seen": 650117120,
|
515 |
+
"step": 310
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.6679035250463822,
|
519 |
+
"grad_norm": 0.26232755184173584,
|
520 |
+
"learning_rate": 3.9779789055339656e-05,
|
521 |
+
"loss": 3.1994,
|
522 |
+
"num_input_tokens_seen": 660602880,
|
523 |
+
"step": 315
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 0.6785051683010866,
|
527 |
+
"grad_norm": 0.17949418723583221,
|
528 |
+
"learning_rate": 3.9423248471537065e-05,
|
529 |
+
"loss": 3.1464,
|
530 |
+
"num_input_tokens_seen": 671088640,
|
531 |
+
"step": 320
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.6891068115557911,
|
535 |
+
"grad_norm": 0.22808890044689178,
|
536 |
+
"learning_rate": 3.9062255257522794e-05,
|
537 |
+
"loss": 3.2207,
|
538 |
+
"num_input_tokens_seen": 681574400,
|
539 |
+
"step": 325
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.6997084548104956,
|
543 |
+
"grad_norm": 0.20621077716350555,
|
544 |
+
"learning_rate": 3.8696920856242174e-05,
|
545 |
+
"loss": 3.1688,
|
546 |
+
"num_input_tokens_seen": 692060160,
|
547 |
+
"step": 330
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 0.7103100980652001,
|
551 |
+
"grad_norm": 0.20659266412258148,
|
552 |
+
"learning_rate": 3.8327358050817234e-05,
|
553 |
+
"loss": 3.1726,
|
554 |
+
"num_input_tokens_seen": 702545920,
|
555 |
+
"step": 335
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.7209117413199045,
|
559 |
+
"grad_norm": 0.23239997029304504,
|
560 |
+
"learning_rate": 3.7953680929729215e-05,
|
561 |
+
"loss": 3.2254,
|
562 |
+
"num_input_tokens_seen": 713031680,
|
563 |
+
"step": 340
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.731513384574609,
|
567 |
+
"grad_norm": 0.15853458642959595,
|
568 |
+
"learning_rate": 3.757600485159805e-05,
|
569 |
+
"loss": 3.1453,
|
570 |
+
"num_input_tokens_seen": 723517440,
|
571 |
+
"step": 345
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.7421150278293135,
|
575 |
+
"grad_norm": 0.28123387694358826,
|
576 |
+
"learning_rate": 3.719444640956981e-05,
|
577 |
+
"loss": 3.1849,
|
578 |
+
"num_input_tokens_seen": 734003200,
|
579 |
+
"step": 350
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.7527166710840181,
|
583 |
+
"grad_norm": 0.16030676662921906,
|
584 |
+
"learning_rate": 3.680912339532296e-05,
|
585 |
+
"loss": 3.187,
|
586 |
+
"num_input_tokens_seen": 744488960,
|
587 |
+
"step": 355
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.7633183143387225,
|
591 |
+
"grad_norm": 0.1698087602853775,
|
592 |
+
"learning_rate": 3.6420154762704686e-05,
|
593 |
+
"loss": 3.1603,
|
594 |
+
"num_input_tokens_seen": 754974720,
|
595 |
+
"step": 360
|
596 |
+
},
|
597 |
+
{
|
598 |
+
"epoch": 0.773919957593427,
|
599 |
+
"grad_norm": 0.1804792284965515,
|
600 |
+
"learning_rate": 3.602766059100838e-05,
|
601 |
+
"loss": 3.1501,
|
602 |
+
"num_input_tokens_seen": 765460480,
|
603 |
+
"step": 365
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.7845216008481315,
|
607 |
+
"grad_norm": 0.22060543298721313,
|
608 |
+
"learning_rate": 3.563176204790374e-05,
|
609 |
+
"loss": 3.2135,
|
610 |
+
"num_input_tokens_seen": 775946240,
|
611 |
+
"step": 370
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.795123244102836,
|
615 |
+
"grad_norm": 0.2411007434129715,
|
616 |
+
"learning_rate": 3.523258135203087e-05,
|
617 |
+
"loss": 3.1263,
|
618 |
+
"num_input_tokens_seen": 786432000,
|
619 |
+
"step": 375
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.8057248873575404,
|
623 |
+
"grad_norm": 0.17039397358894348,
|
624 |
+
"learning_rate": 3.483024173526985e-05,
|
625 |
+
"loss": 3.1278,
|
626 |
+
"num_input_tokens_seen": 796917760,
|
627 |
+
"step": 380
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.8163265306122449,
|
631 |
+
"grad_norm": 0.17096886038780212,
|
632 |
+
"learning_rate": 3.442486740469766e-05,
|
633 |
+
"loss": 3.1805,
|
634 |
+
"num_input_tokens_seen": 807403520,
|
635 |
+
"step": 385
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 0.8269281738669494,
|
639 |
+
"grad_norm": 0.20285804569721222,
|
640 |
+
"learning_rate": 3.401658350424389e-05,
|
641 |
+
"loss": 3.1093,
|
642 |
+
"num_input_tokens_seen": 817889280,
|
643 |
+
"step": 390
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.8375298171216539,
|
647 |
+
"grad_norm": 0.17684973776340485,
|
648 |
+
"learning_rate": 3.360551607605735e-05,
|
649 |
+
"loss": 3.1336,
|
650 |
+
"num_input_tokens_seen": 828375040,
|
651 |
+
"step": 395
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.8481314603763583,
|
655 |
+
"grad_norm": 0.16076605021953583,
|
656 |
+
"learning_rate": 3.3191792021595316e-05,
|
657 |
+
"loss": 3.1976,
|
658 |
+
"num_input_tokens_seen": 838860800,
|
659 |
+
"step": 400
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 0.8481314603763583,
|
663 |
+
"eval_accuracy": 0.4506036745406824,
|
664 |
+
"eval_loss": 3.043421983718872,
|
665 |
+
"eval_runtime": 36.2661,
|
666 |
+
"eval_samples_per_second": 8.272,
|
667 |
+
"eval_steps_per_second": 2.068,
|
668 |
+
"num_input_tokens_seen": 838860800,
|
669 |
+
"step": 400
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.8587331036310628,
|
673 |
+
"grad_norm": 0.1959790736436844,
|
674 |
+
"learning_rate": 3.277553906244756e-05,
|
675 |
+
"loss": 3.2013,
|
676 |
+
"num_input_tokens_seen": 849346560,
|
677 |
+
"step": 405
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 0.8693347468857673,
|
681 |
+
"grad_norm": 0.15397347509860992,
|
682 |
+
"learning_rate": 3.23568857009071e-05,
|
683 |
+
"loss": 3.124,
|
684 |
+
"num_input_tokens_seen": 859832320,
|
685 |
+
"step": 410
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.8799363901404718,
|
689 |
+
"grad_norm": 0.22286681830883026,
|
690 |
+
"learning_rate": 3.193596118030005e-05,
|
691 |
+
"loss": 3.1723,
|
692 |
+
"num_input_tokens_seen": 870318080,
|
693 |
+
"step": 415
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.8905380333951762,
|
697 |
+
"grad_norm": 0.22909095883369446,
|
698 |
+
"learning_rate": 3.1512895445086636e-05,
|
699 |
+
"loss": 3.1068,
|
700 |
+
"num_input_tokens_seen": 880803840,
|
701 |
+
"step": 420
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 0.9011396766498807,
|
705 |
+
"grad_norm": 0.24190495908260345,
|
706 |
+
"learning_rate": 3.108781910074578e-05,
|
707 |
+
"loss": 3.143,
|
708 |
+
"num_input_tokens_seen": 891289600,
|
709 |
+
"step": 425
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.9117413199045852,
|
713 |
+
"grad_norm": 0.24453699588775635,
|
714 |
+
"learning_rate": 3.0660863373455595e-05,
|
715 |
+
"loss": 3.1667,
|
716 |
+
"num_input_tokens_seen": 901775360,
|
717 |
+
"step": 430
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.9223429631592897,
|
721 |
+
"grad_norm": 0.1636463701725006,
|
722 |
+
"learning_rate": 3.0232160069582332e-05,
|
723 |
+
"loss": 3.1123,
|
724 |
+
"num_input_tokens_seen": 912261120,
|
725 |
+
"step": 435
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.9329446064139941,
|
729 |
+
"grad_norm": 0.14330972731113434,
|
730 |
+
"learning_rate": 2.9801841534990115e-05,
|
731 |
+
"loss": 3.1616,
|
732 |
+
"num_input_tokens_seen": 922746880,
|
733 |
+
"step": 440
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.9435462496686986,
|
737 |
+
"grad_norm": 0.14314919710159302,
|
738 |
+
"learning_rate": 2.9370040614184245e-05,
|
739 |
+
"loss": 3.1241,
|
740 |
+
"num_input_tokens_seen": 933232640,
|
741 |
+
"step": 445
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.9541478929234031,
|
745 |
+
"grad_norm": 0.15261518955230713,
|
746 |
+
"learning_rate": 2.893689060930045e-05,
|
747 |
+
"loss": 3.1573,
|
748 |
+
"num_input_tokens_seen": 943718400,
|
749 |
+
"step": 450
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 0.9647495361781077,
|
753 |
+
"grad_norm": 0.14767758548259735,
|
754 |
+
"learning_rate": 2.8502525238952916e-05,
|
755 |
+
"loss": 3.2165,
|
756 |
+
"num_input_tokens_seen": 954204160,
|
757 |
+
"step": 455
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"epoch": 0.9753511794328121,
|
761 |
+
"grad_norm": 0.161110982298851,
|
762 |
+
"learning_rate": 2.8067078596953796e-05,
|
763 |
+
"loss": 3.1457,
|
764 |
+
"num_input_tokens_seen": 964689920,
|
765 |
+
"step": 460
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.9859528226875166,
|
769 |
+
"grad_norm": 0.15843427181243896,
|
770 |
+
"learning_rate": 2.7630685110916778e-05,
|
771 |
+
"loss": 3.143,
|
772 |
+
"num_input_tokens_seen": 975175680,
|
773 |
+
"step": 465
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.9965544659422211,
|
777 |
+
"grad_norm": 0.24187405407428741,
|
778 |
+
"learning_rate": 2.7193479500757685e-05,
|
779 |
+
"loss": 3.2156,
|
780 |
+
"num_input_tokens_seen": 985661440,
|
781 |
+
"step": 470
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 1.0071561091969254,
|
785 |
+
"grad_norm": 0.15035971999168396,
|
786 |
+
"learning_rate": 2.675559673710485e-05,
|
787 |
+
"loss": 3.0852,
|
788 |
+
"num_input_tokens_seen": 996147200,
|
789 |
+
"step": 475
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 1.01775775245163,
|
793 |
+
"grad_norm": 0.17717382311820984,
|
794 |
+
"learning_rate": 2.631717199963199e-05,
|
795 |
+
"loss": 3.1221,
|
796 |
+
"num_input_tokens_seen": 1006632960,
|
797 |
+
"step": 480
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 1.0283593957063344,
|
801 |
+
"grad_norm": 0.1390335112810135,
|
802 |
+
"learning_rate": 2.5878340635326686e-05,
|
803 |
+
"loss": 3.1358,
|
804 |
+
"num_input_tokens_seen": 1017118720,
|
805 |
+
"step": 485
|
806 |
+
},
|
807 |
+
{
|
808 |
+
"epoch": 1.0389610389610389,
|
809 |
+
"grad_norm": 0.14454010128974915,
|
810 |
+
"learning_rate": 2.5439238116707102e-05,
|
811 |
+
"loss": 3.1307,
|
812 |
+
"num_input_tokens_seen": 1027604480,
|
813 |
+
"step": 490
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 1.0495626822157433,
|
817 |
+
"grad_norm": 0.19984786212444305,
|
818 |
+
"learning_rate": 2.5e-05,
|
819 |
+
"loss": 3.1269,
|
820 |
+
"num_input_tokens_seen": 1038090240,
|
821 |
+
"step": 495
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 1.0601643254704478,
|
825 |
+
"grad_norm": 0.263656347990036,
|
826 |
+
"learning_rate": 2.45607618832929e-05,
|
827 |
+
"loss": 3.1076,
|
828 |
+
"num_input_tokens_seen": 1048576000,
|
829 |
+
"step": 500
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 1.0707659687251523,
|
833 |
+
"grad_norm": 0.15432648360729218,
|
834 |
+
"learning_rate": 2.412165936467332e-05,
|
835 |
+
"loss": 3.1218,
|
836 |
+
"num_input_tokens_seen": 1059061760,
|
837 |
+
"step": 505
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 1.081367611979857,
|
841 |
+
"grad_norm": 0.24721471965312958,
|
842 |
+
"learning_rate": 2.368282800036801e-05,
|
843 |
+
"loss": 3.1035,
|
844 |
+
"num_input_tokens_seen": 1069547520,
|
845 |
+
"step": 510
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 1.0919692552345615,
|
849 |
+
"grad_norm": 0.1441834270954132,
|
850 |
+
"learning_rate": 2.3244403262895153e-05,
|
851 |
+
"loss": 3.1801,
|
852 |
+
"num_input_tokens_seen": 1080033280,
|
853 |
+
"step": 515
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 1.102570898489266,
|
857 |
+
"grad_norm": 0.1535598337650299,
|
858 |
+
"learning_rate": 2.280652049924232e-05,
|
859 |
+
"loss": 3.2002,
|
860 |
+
"num_input_tokens_seen": 1090519040,
|
861 |
+
"step": 520
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 1.1131725417439704,
|
865 |
+
"grad_norm": 0.15322482585906982,
|
866 |
+
"learning_rate": 2.2369314889083235e-05,
|
867 |
+
"loss": 3.1208,
|
868 |
+
"num_input_tokens_seen": 1101004800,
|
869 |
+
"step": 525
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 1.1237741849986749,
|
873 |
+
"grad_norm": 0.1468251496553421,
|
874 |
+
"learning_rate": 2.1932921403046207e-05,
|
875 |
+
"loss": 3.1917,
|
876 |
+
"num_input_tokens_seen": 1111490560,
|
877 |
+
"step": 530
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 1.1343758282533793,
|
881 |
+
"grad_norm": 0.1530437469482422,
|
882 |
+
"learning_rate": 2.1497474761047086e-05,
|
883 |
+
"loss": 3.0797,
|
884 |
+
"num_input_tokens_seen": 1121976320,
|
885 |
+
"step": 535
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 1.1449774715080838,
|
889 |
+
"grad_norm": 0.1411171704530716,
|
890 |
+
"learning_rate": 2.106310939069956e-05,
|
891 |
+
"loss": 3.1136,
|
892 |
+
"num_input_tokens_seen": 1132462080,
|
893 |
+
"step": 540
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 1.1555791147627883,
|
897 |
+
"grad_norm": 0.14499180018901825,
|
898 |
+
"learning_rate": 2.0629959385815757e-05,
|
899 |
+
"loss": 3.1427,
|
900 |
+
"num_input_tokens_seen": 1142947840,
|
901 |
+
"step": 545
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 1.1661807580174928,
|
905 |
+
"grad_norm": 0.14953380823135376,
|
906 |
+
"learning_rate": 2.019815846500988e-05,
|
907 |
+
"loss": 3.1948,
|
908 |
+
"num_input_tokens_seen": 1153433600,
|
909 |
+
"step": 550
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 1.1767824012721972,
|
913 |
+
"grad_norm": 0.1349666863679886,
|
914 |
+
"learning_rate": 1.9767839930417673e-05,
|
915 |
+
"loss": 3.1605,
|
916 |
+
"num_input_tokens_seen": 1163919360,
|
917 |
+
"step": 555
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 1.1873840445269017,
|
921 |
+
"grad_norm": 0.144802987575531,
|
922 |
+
"learning_rate": 1.9339136626544407e-05,
|
923 |
+
"loss": 3.1857,
|
924 |
+
"num_input_tokens_seen": 1174405120,
|
925 |
+
"step": 560
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 1.1979856877816062,
|
929 |
+
"grad_norm": 0.16848242282867432,
|
930 |
+
"learning_rate": 1.891218089925423e-05,
|
931 |
+
"loss": 3.18,
|
932 |
+
"num_input_tokens_seen": 1184890880,
|
933 |
+
"step": 565
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 1.2085873310363107,
|
937 |
+
"grad_norm": 0.15472151339054108,
|
938 |
+
"learning_rate": 1.8487104554913363e-05,
|
939 |
+
"loss": 3.1939,
|
940 |
+
"num_input_tokens_seen": 1195376640,
|
941 |
+
"step": 570
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 1.2191889742910151,
|
945 |
+
"grad_norm": 0.1529063582420349,
|
946 |
+
"learning_rate": 1.806403881969996e-05,
|
947 |
+
"loss": 3.142,
|
948 |
+
"num_input_tokens_seen": 1205862400,
|
949 |
+
"step": 575
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 1.2297906175457196,
|
953 |
+
"grad_norm": 0.1687614619731903,
|
954 |
+
"learning_rate": 1.764311429909291e-05,
|
955 |
+
"loss": 3.1344,
|
956 |
+
"num_input_tokens_seen": 1216348160,
|
957 |
+
"step": 580
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 1.240392260800424,
|
961 |
+
"grad_norm": 0.13812561333179474,
|
962 |
+
"learning_rate": 1.7224460937552446e-05,
|
963 |
+
"loss": 3.1626,
|
964 |
+
"num_input_tokens_seen": 1226833920,
|
965 |
+
"step": 585
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 1.2509939040551286,
|
969 |
+
"grad_norm": 0.16453585028648376,
|
970 |
+
"learning_rate": 1.6808207978404683e-05,
|
971 |
+
"loss": 3.1616,
|
972 |
+
"num_input_tokens_seen": 1237319680,
|
973 |
+
"step": 590
|
974 |
+
},
|
975 |
+
{
|
976 |
+
"epoch": 1.261595547309833,
|
977 |
+
"grad_norm": 0.13337315618991852,
|
978 |
+
"learning_rate": 1.6394483923942655e-05,
|
979 |
+
"loss": 3.1413,
|
980 |
+
"num_input_tokens_seen": 1247805440,
|
981 |
+
"step": 595
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 1.2721971905645375,
|
985 |
+
"grad_norm": 0.2029571831226349,
|
986 |
+
"learning_rate": 1.5983416495756116e-05,
|
987 |
+
"loss": 3.1485,
|
988 |
+
"num_input_tokens_seen": 1258291200,
|
989 |
+
"step": 600
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 1.2721971905645375,
|
993 |
+
"eval_accuracy": 0.45126899835195017,
|
994 |
+
"eval_loss": 3.0374794006347656,
|
995 |
+
"eval_runtime": 36.1798,
|
996 |
+
"eval_samples_per_second": 8.292,
|
997 |
+
"eval_steps_per_second": 2.073,
|
998 |
+
"num_input_tokens_seen": 1258291200,
|
999 |
+
"step": 600
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 1.282798833819242,
|
1003 |
+
"grad_norm": 0.21333394944667816,
|
1004 |
+
"learning_rate": 1.5575132595302352e-05,
|
1005 |
+
"loss": 3.1131,
|
1006 |
+
"num_input_tokens_seen": 1268776960,
|
1007 |
+
"step": 605
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 1.2934004770739465,
|
1011 |
+
"grad_norm": 0.1743020862340927,
|
1012 |
+
"learning_rate": 1.516975826473015e-05,
|
1013 |
+
"loss": 3.1177,
|
1014 |
+
"num_input_tokens_seen": 1279262720,
|
1015 |
+
"step": 610
|
1016 |
+
},
|
1017 |
+
{
|
1018 |
+
"epoch": 1.304002120328651,
|
1019 |
+
"grad_norm": 0.15571139752864838,
|
1020 |
+
"learning_rate": 1.4767418647969133e-05,
|
1021 |
+
"loss": 3.1626,
|
1022 |
+
"num_input_tokens_seen": 1289748480,
|
1023 |
+
"step": 615
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 1.3146037635833554,
|
1027 |
+
"grad_norm": 0.16648022830486298,
|
1028 |
+
"learning_rate": 1.4368237952096258e-05,
|
1029 |
+
"loss": 3.1987,
|
1030 |
+
"num_input_tokens_seen": 1300234240,
|
1031 |
+
"step": 620
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 1.3252054068380599,
|
1035 |
+
"grad_norm": 0.2865128219127655,
|
1036 |
+
"learning_rate": 1.3972339408991626e-05,
|
1037 |
+
"loss": 3.176,
|
1038 |
+
"num_input_tokens_seen": 1310720000,
|
1039 |
+
"step": 625
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 1.3358070500927643,
|
1043 |
+
"grad_norm": 0.14998364448547363,
|
1044 |
+
"learning_rate": 1.357984523729533e-05,
|
1045 |
+
"loss": 3.1568,
|
1046 |
+
"num_input_tokens_seen": 1321205760,
|
1047 |
+
"step": 630
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 1.3464086933474688,
|
1051 |
+
"grad_norm": 0.14780345559120178,
|
1052 |
+
"learning_rate": 1.3190876604677043e-05,
|
1053 |
+
"loss": 3.1895,
|
1054 |
+
"num_input_tokens_seen": 1331691520,
|
1055 |
+
"step": 635
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 1.3570103366021733,
|
1059 |
+
"grad_norm": 0.15796662867069244,
|
1060 |
+
"learning_rate": 1.2805553590430197e-05,
|
1061 |
+
"loss": 3.1708,
|
1062 |
+
"num_input_tokens_seen": 1342177280,
|
1063 |
+
"step": 640
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 1.3676119798568778,
|
1067 |
+
"grad_norm": 0.14260126650333405,
|
1068 |
+
"learning_rate": 1.2423995148401954e-05,
|
1069 |
+
"loss": 3.1649,
|
1070 |
+
"num_input_tokens_seen": 1352663040,
|
1071 |
+
"step": 645
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 1.3782136231115822,
|
1075 |
+
"grad_norm": 0.16667188704013824,
|
1076 |
+
"learning_rate": 1.2046319070270792e-05,
|
1077 |
+
"loss": 3.1345,
|
1078 |
+
"num_input_tokens_seen": 1363148800,
|
1079 |
+
"step": 650
|
1080 |
+
},
|
1081 |
+
{
|
1082 |
+
"epoch": 1.3888152663662867,
|
1083 |
+
"grad_norm": 0.13283655047416687,
|
1084 |
+
"learning_rate": 1.1672641949182769e-05,
|
1085 |
+
"loss": 3.1653,
|
1086 |
+
"num_input_tokens_seen": 1373634560,
|
1087 |
+
"step": 655
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 1.3994169096209912,
|
1091 |
+
"grad_norm": 0.1479809582233429,
|
1092 |
+
"learning_rate": 1.130307914375783e-05,
|
1093 |
+
"loss": 3.2014,
|
1094 |
+
"num_input_tokens_seen": 1384120320,
|
1095 |
+
"step": 660
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 1.4100185528756957,
|
1099 |
+
"grad_norm": 0.1443646103143692,
|
1100 |
+
"learning_rate": 1.093774474247721e-05,
|
1101 |
+
"loss": 3.1561,
|
1102 |
+
"num_input_tokens_seen": 1394606080,
|
1103 |
+
"step": 665
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 1.4206201961304001,
|
1107 |
+
"grad_norm": 0.15595485270023346,
|
1108 |
+
"learning_rate": 1.0576751528462935e-05,
|
1109 |
+
"loss": 3.1774,
|
1110 |
+
"num_input_tokens_seen": 1405091840,
|
1111 |
+
"step": 670
|
1112 |
+
},
|
1113 |
+
{
|
1114 |
+
"epoch": 1.4312218393851046,
|
1115 |
+
"grad_norm": 0.1376049816608429,
|
1116 |
+
"learning_rate": 1.0220210944660338e-05,
|
1117 |
+
"loss": 3.1102,
|
1118 |
+
"num_input_tokens_seen": 1415577600,
|
1119 |
+
"step": 675
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 1.4418234826398093,
|
1123 |
+
"grad_norm": 0.14685603976249695,
|
1124 |
+
"learning_rate": 9.868233059434288e-06,
|
1125 |
+
"loss": 3.2077,
|
1126 |
+
"num_input_tokens_seen": 1426063360,
|
1127 |
+
"step": 680
|
1128 |
+
},
|
1129 |
+
{
|
1130 |
+
"epoch": 1.4524251258945138,
|
1131 |
+
"grad_norm": 0.13503292202949524,
|
1132 |
+
"learning_rate": 9.520926532589725e-06,
|
1133 |
+
"loss": 3.1899,
|
1134 |
+
"num_input_tokens_seen": 1436549120,
|
1135 |
+
"step": 685
|
1136 |
+
},
|
1137 |
+
{
|
1138 |
+
"epoch": 1.4630267691492183,
|
1139 |
+
"grad_norm": 0.18555864691734314,
|
1140 |
+
"learning_rate": 9.178398581827085e-06,
|
1141 |
+
"loss": 3.2424,
|
1142 |
+
"num_input_tokens_seen": 1447034880,
|
1143 |
+
"step": 690
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 1.4736284124039227,
|
1147 |
+
"grad_norm": 0.26128634810447693,
|
1148 |
+
"learning_rate": 8.840754949642935e-06,
|
1149 |
+
"loss": 3.1609,
|
1150 |
+
"num_input_tokens_seen": 1457520640,
|
1151 |
+
"step": 695
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 1.4842300556586272,
|
1155 |
+
"grad_norm": 0.13384391367435455,
|
1156 |
+
"learning_rate": 8.50809987068598e-06,
|
1157 |
+
"loss": 3.1455,
|
1158 |
+
"num_input_tokens_seen": 1468006400,
|
1159 |
+
"step": 700
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 1.4948316989133317,
|
1163 |
+
"grad_norm": 0.20566639304161072,
|
1164 |
+
"learning_rate": 8.180536039578545e-06,
|
1165 |
+
"loss": 3.1995,
|
1166 |
+
"num_input_tokens_seen": 1478492160,
|
1167 |
+
"step": 705
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 1.5054333421680361,
|
1171 |
+
"grad_norm": 0.13730423152446747,
|
1172 |
+
"learning_rate": 7.858164579213547e-06,
|
1173 |
+
"loss": 3.134,
|
1174 |
+
"num_input_tokens_seen": 1488977920,
|
1175 |
+
"step": 710
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"epoch": 1.5160349854227406,
|
1179 |
+
"grad_norm": 0.14655794203281403,
|
1180 |
+
"learning_rate": 7.541085009536625e-06,
|
1181 |
+
"loss": 3.0949,
|
1182 |
+
"num_input_tokens_seen": 1499463680,
|
1183 |
+
"step": 715
|
1184 |
+
},
|
1185 |
+
{
|
1186 |
+
"epoch": 1.526636628677445,
|
1187 |
+
"grad_norm": 0.12526313960552216,
|
1188 |
+
"learning_rate": 7.2293952168231316e-06,
|
1189 |
+
"loss": 3.1615,
|
1190 |
+
"num_input_tokens_seen": 1509949440,
|
1191 |
+
"step": 720
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 1.5372382719321496,
|
1195 |
+
"grad_norm": 0.1351662427186966,
|
1196 |
+
"learning_rate": 6.923191423459482e-06,
|
1197 |
+
"loss": 3.1805,
|
1198 |
+
"num_input_tokens_seen": 1520435200,
|
1199 |
+
"step": 725
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 1.547839915186854,
|
1203 |
+
"grad_norm": 0.1686793714761734,
|
1204 |
+
"learning_rate": 6.622568158238126e-06,
|
1205 |
+
"loss": 3.1779,
|
1206 |
+
"num_input_tokens_seen": 1530920960,
|
1207 |
+
"step": 730
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 1.5584415584415585,
|
1211 |
+
"grad_norm": 0.14492954313755035,
|
1212 |
+
"learning_rate": 6.327618227175389e-06,
|
1213 |
+
"loss": 3.1046,
|
1214 |
+
"num_input_tokens_seen": 1541406720,
|
1215 |
+
"step": 735
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 1.569043201696263,
|
1219 |
+
"grad_norm": 0.14910686016082764,
|
1220 |
+
"learning_rate": 6.0384326848611225e-06,
|
1221 |
+
"loss": 3.0803,
|
1222 |
+
"num_input_tokens_seen": 1551892480,
|
1223 |
+
"step": 740
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 1.5796448449509675,
|
1227 |
+
"grad_norm": 0.1342857927083969,
|
1228 |
+
"learning_rate": 5.755100806349076e-06,
|
1229 |
+
"loss": 3.062,
|
1230 |
+
"num_input_tokens_seen": 1562378240,
|
1231 |
+
"step": 745
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"epoch": 1.590246488205672,
|
1235 |
+
"grad_norm": 0.1598527878522873,
|
1236 |
+
"learning_rate": 5.4777100595965994e-06,
|
1237 |
+
"loss": 3.2036,
|
1238 |
+
"num_input_tokens_seen": 1572864000,
|
1239 |
+
"step": 750
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 1.6008481314603764,
|
1243 |
+
"grad_norm": 0.1773335188627243,
|
1244 |
+
"learning_rate": 5.206346078462249e-06,
|
1245 |
+
"loss": 3.1892,
|
1246 |
+
"num_input_tokens_seen": 1583349760,
|
1247 |
+
"step": 755
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 1.6114497747150809,
|
1251 |
+
"grad_norm": 0.17586533725261688,
|
1252 |
+
"learning_rate": 4.941092636269554e-06,
|
1253 |
+
"loss": 3.1995,
|
1254 |
+
"num_input_tokens_seen": 1593835520,
|
1255 |
+
"step": 760
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 1.6220514179697854,
|
1259 |
+
"grad_norm": 0.16583110392093658,
|
1260 |
+
"learning_rate": 4.682031619945238e-06,
|
1261 |
+
"loss": 3.1309,
|
1262 |
+
"num_input_tokens_seen": 1604321280,
|
1263 |
+
"step": 765
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 1.6326530612244898,
|
1267 |
+
"grad_norm": 0.1462288796901703,
|
1268 |
+
"learning_rate": 4.4292430047396914e-06,
|
1269 |
+
"loss": 3.1376,
|
1270 |
+
"num_input_tokens_seen": 1614807040,
|
1271 |
+
"step": 770
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 1.6432547044791943,
|
1275 |
+
"grad_norm": 0.13279996812343597,
|
1276 |
+
"learning_rate": 4.182804829537654e-06,
|
1277 |
+
"loss": 3.1541,
|
1278 |
+
"num_input_tokens_seen": 1625292800,
|
1279 |
+
"step": 775
|
1280 |
+
},
|
1281 |
+
{
|
1282 |
+
"epoch": 1.6538563477338988,
|
1283 |
+
"grad_norm": 0.18102097511291504,
|
1284 |
+
"learning_rate": 3.942793172766699e-06,
|
1285 |
+
"loss": 3.1894,
|
1286 |
+
"num_input_tokens_seen": 1635778560,
|
1287 |
+
"step": 780
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 1.6644579909886033,
|
1291 |
+
"grad_norm": 0.16354134678840637,
|
1292 |
+
"learning_rate": 3.709282128910907e-06,
|
1293 |
+
"loss": 3.1664,
|
1294 |
+
"num_input_tokens_seen": 1646264320,
|
1295 |
+
"step": 785
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 1.6750596342433077,
|
1299 |
+
"grad_norm": 0.32594841718673706,
|
1300 |
+
"learning_rate": 3.4823437856369794e-06,
|
1301 |
+
"loss": 3.1721,
|
1302 |
+
"num_input_tokens_seen": 1656750080,
|
1303 |
+
"step": 790
|
1304 |
+
},
|
1305 |
+
{
|
1306 |
+
"epoch": 1.6856612774980122,
|
1307 |
+
"grad_norm": 0.13957597315311432,
|
1308 |
+
"learning_rate": 3.2620482015399302e-06,
|
1309 |
+
"loss": 3.2471,
|
1310 |
+
"num_input_tokens_seen": 1667235840,
|
1311 |
+
"step": 795
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 1.6962629207527167,
|
1315 |
+
"grad_norm": 0.13924147188663483,
|
1316 |
+
"learning_rate": 3.0484633845151488e-06,
|
1317 |
+
"loss": 3.1871,
|
1318 |
+
"num_input_tokens_seen": 1677721600,
|
1319 |
+
"step": 800
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 1.6962629207527167,
|
1323 |
+
"eval_accuracy": 0.4514018596512645,
|
1324 |
+
"eval_loss": 3.0366272926330566,
|
1325 |
+
"eval_runtime": 36.0138,
|
1326 |
+
"eval_samples_per_second": 8.33,
|
1327 |
+
"eval_steps_per_second": 2.083,
|
1328 |
+
"num_input_tokens_seen": 1677721600,
|
1329 |
+
"step": 800
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 1.7068645640074211,
|
1333 |
+
"grad_norm": 0.14513356983661652,
|
1334 |
+
"learning_rate": 2.841655270763549e-06,
|
1335 |
+
"loss": 3.066,
|
1336 |
+
"num_input_tokens_seen": 1688207360,
|
1337 |
+
"step": 805
|
1338 |
+
},
|
1339 |
+
{
|
1340 |
+
"epoch": 1.7174662072621256,
|
1341 |
+
"grad_norm": 0.14862333238124847,
|
1342 |
+
"learning_rate": 2.6416877044362685e-06,
|
1343 |
+
"loss": 3.1206,
|
1344 |
+
"num_input_tokens_seen": 1698693120,
|
1345 |
+
"step": 810
|
1346 |
+
},
|
1347 |
+
{
|
1348 |
+
"epoch": 1.72806785051683,
|
1349 |
+
"grad_norm": 0.13608209788799286,
|
1350 |
+
"learning_rate": 2.448622417925214e-06,
|
1351 |
+
"loss": 3.2281,
|
1352 |
+
"num_input_tokens_seen": 1709178880,
|
1353 |
+
"step": 815
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 1.7386694937715346,
|
1357 |
+
"grad_norm": 0.1472754031419754,
|
1358 |
+
"learning_rate": 2.2625190128055168e-06,
|
1359 |
+
"loss": 3.2023,
|
1360 |
+
"num_input_tokens_seen": 1719664640,
|
1361 |
+
"step": 820
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 1.749271137026239,
|
1365 |
+
"grad_norm": 0.17672620713710785,
|
1366 |
+
"learning_rate": 2.0834349414358495e-06,
|
1367 |
+
"loss": 3.2217,
|
1368 |
+
"num_input_tokens_seen": 1730150400,
|
1369 |
+
"step": 825
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"epoch": 1.7598727802809435,
|
1373 |
+
"grad_norm": 0.14799125492572784,
|
1374 |
+
"learning_rate": 1.911425489222127e-06,
|
1375 |
+
"loss": 3.2231,
|
1376 |
+
"num_input_tokens_seen": 1740636160,
|
1377 |
+
"step": 830
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 1.770474423535648,
|
1381 |
+
"grad_norm": 0.14448776841163635,
|
1382 |
+
"learning_rate": 1.7465437575502952e-06,
|
1383 |
+
"loss": 3.1126,
|
1384 |
+
"num_input_tokens_seen": 1751121920,
|
1385 |
+
"step": 835
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 1.7810760667903525,
|
1389 |
+
"grad_norm": 0.14082539081573486,
|
1390 |
+
"learning_rate": 1.5888406473932692e-06,
|
1391 |
+
"loss": 3.0933,
|
1392 |
+
"num_input_tokens_seen": 1761607680,
|
1393 |
+
"step": 840
|
1394 |
+
},
|
1395 |
+
{
|
1396 |
+
"epoch": 1.791677710045057,
|
1397 |
+
"grad_norm": 0.18886087834835052,
|
1398 |
+
"learning_rate": 1.4383648435972007e-06,
|
1399 |
+
"loss": 3.2596,
|
1400 |
+
"num_input_tokens_seen": 1772093440,
|
1401 |
+
"step": 845
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 1.8022793532997614,
|
1405 |
+
"grad_norm": 0.14818327128887177,
|
1406 |
+
"learning_rate": 1.2951627998518623e-06,
|
1407 |
+
"loss": 3.1292,
|
1408 |
+
"num_input_tokens_seen": 1782579200,
|
1409 |
+
"step": 850
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 1.8128809965544659,
|
1413 |
+
"grad_norm": 0.14874930679798126,
|
1414 |
+
"learning_rate": 1.1592787243498631e-06,
|
1415 |
+
"loss": 3.1284,
|
1416 |
+
"num_input_tokens_seen": 1793064960,
|
1417 |
+
"step": 855
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 1.8234826398091704,
|
1421 |
+
"grad_norm": 0.16616405546665192,
|
1422 |
+
"learning_rate": 1.0307545661390139e-06,
|
1423 |
+
"loss": 3.1422,
|
1424 |
+
"num_input_tokens_seen": 1803550720,
|
1425 |
+
"step": 860
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 1.8340842830638748,
|
1429 |
+
"grad_norm": 0.15211746096611023,
|
1430 |
+
"learning_rate": 9.09630002172182e-07,
|
1431 |
+
"loss": 3.1793,
|
1432 |
+
"num_input_tokens_seen": 1814036480,
|
1433 |
+
"step": 865
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 1.8446859263185793,
|
1437 |
+
"grad_norm": 0.14233224093914032,
|
1438 |
+
"learning_rate": 7.959424250585323e-07,
|
1439 |
+
"loss": 3.1624,
|
1440 |
+
"num_input_tokens_seen": 1824522240,
|
1441 |
+
"step": 870
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 1.8552875695732838,
|
1445 |
+
"grad_norm": 0.13079190254211426,
|
1446 |
+
"learning_rate": 6.897269315199628e-07,
|
1447 |
+
"loss": 3.2029,
|
1448 |
+
"num_input_tokens_seen": 1835008000,
|
1449 |
+
"step": 875
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 1.8658892128279883,
|
1453 |
+
"grad_norm": 0.1364782601594925,
|
1454 |
+
"learning_rate": 5.910163115563471e-07,
|
1455 |
+
"loss": 3.1872,
|
1456 |
+
"num_input_tokens_seen": 1845493760,
|
1457 |
+
"step": 880
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 1.8764908560826927,
|
1461 |
+
"grad_norm": 0.22711250185966492,
|
1462 |
+
"learning_rate": 4.998410383228458e-07,
|
1463 |
+
"loss": 3.1676,
|
1464 |
+
"num_input_tokens_seen": 1855979520,
|
1465 |
+
"step": 885
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 1.8870924993373972,
|
1469 |
+
"grad_norm": 0.21140585839748383,
|
1470 |
+
"learning_rate": 4.162292587224947e-07,
|
1471 |
+
"loss": 3.1227,
|
1472 |
+
"num_input_tokens_seen": 1866465280,
|
1473 |
+
"step": 890
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 1.8976941425921017,
|
1477 |
+
"grad_norm": 0.2973221242427826,
|
1478 |
+
"learning_rate": 3.4020678471690934e-07,
|
1479 |
+
"loss": 3.1285,
|
1480 |
+
"num_input_tokens_seen": 1876951040,
|
1481 |
+
"step": 895
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 1.9082957858468061,
|
1485 |
+
"grad_norm": 0.15094168484210968,
|
1486 |
+
"learning_rate": 2.7179708535781943e-07,
|
1487 |
+
"loss": 3.152,
|
1488 |
+
"num_input_tokens_seen": 1887436800,
|
1489 |
+
"step": 900
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 1.9188974291015106,
|
1493 |
+
"grad_norm": 0.14399217069149017,
|
1494 |
+
"learning_rate": 2.110212795418953e-07,
|
1495 |
+
"loss": 3.1971,
|
1496 |
+
"num_input_tokens_seen": 1897922560,
|
1497 |
+
"step": 905
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 1.929499072356215,
|
1501 |
+
"grad_norm": 0.15141591429710388,
|
1502 |
+
"learning_rate": 1.578981294910936e-07,
|
1503 |
+
"loss": 3.1604,
|
1504 |
+
"num_input_tokens_seen": 1908408320,
|
1505 |
+
"step": 910
|
1506 |
+
},
|
1507 |
+
{
|
1508 |
+
"epoch": 1.9401007156109196,
|
1509 |
+
"grad_norm": 0.15116803348064423,
|
1510 |
+
"learning_rate": 1.1244403496052658e-07,
|
1511 |
+
"loss": 3.0712,
|
1512 |
+
"num_input_tokens_seen": 1918894080,
|
1513 |
+
"step": 915
|
1514 |
+
},
|
1515 |
+
{
|
1516 |
+
"epoch": 1.950702358865624,
|
1517 |
+
"grad_norm": 0.1515650451183319,
|
1518 |
+
"learning_rate": 7.46730281756619e-08,
|
1519 |
+
"loss": 3.0719,
|
1520 |
+
"num_input_tokens_seen": 1929379840,
|
1521 |
+
"step": 920
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 1.9613040021203285,
|
1525 |
+
"grad_norm": 0.1448003053665161,
|
1526 |
+
"learning_rate": 4.4596769500407366e-08,
|
1527 |
+
"loss": 3.2699,
|
1528 |
+
"num_input_tokens_seen": 1939865600,
|
1529 |
+
"step": 925
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 1.971905645375033,
|
1533 |
+
"grad_norm": 0.18116047978401184,
|
1534 |
+
"learning_rate": 2.2224543837423562e-08,
|
1535 |
+
"loss": 3.1134,
|
1536 |
+
"num_input_tokens_seen": 1950351360,
|
1537 |
+
"step": 930
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 1.9825072886297375,
|
1541 |
+
"grad_norm": 0.3333103358745575,
|
1542 |
+
"learning_rate": 7.563257761744601e-09,
|
1543 |
+
"loss": 3.1083,
|
1544 |
+
"num_input_tokens_seen": 1960837120,
|
1545 |
+
"step": 935
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 1.993108931884442,
|
1549 |
+
"grad_norm": 0.15106463432312012,
|
1550 |
+
"learning_rate": 6.174373886586037e-10,
|
1551 |
+
"loss": 3.2087,
|
1552 |
+
"num_input_tokens_seen": 1971322880,
|
1553 |
+
"step": 940
|
1554 |
+
},
|
1555 |
+
{
|
1556 |
+
"epoch": 1.997349589186324,
|
1557 |
+
"num_input_tokens_seen": 1975517184,
|
1558 |
+
"step": 942,
|
1559 |
+
"total_flos": 9.732316690586272e+18,
|
1560 |
+
"train_loss": 3.186332613039928,
|
1561 |
+
"train_runtime": 34789.3198,
|
1562 |
+
"train_samples_per_second": 3.47,
|
1563 |
+
"train_steps_per_second": 0.027
|
1564 |
+
}
|
1565 |
+
],
|
1566 |
+
"logging_steps": 5,
|
1567 |
+
"max_steps": 942,
|
1568 |
+
"num_input_tokens_seen": 1975517184,
|
1569 |
+
"num_train_epochs": 2,
|
1570 |
+
"save_steps": 100,
|
1571 |
+
"total_flos": 9.732316690586272e+18,
|
1572 |
+
"train_batch_size": 4,
|
1573 |
+
"trial_name": null,
|
1574 |
+
"trial_params": null
|
1575 |
+
}
|