End of training
Browse files- README.md +9 -9
- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Oct22_15-45-30_2ae384978577/events.out.tfevents.1729612359.2ae384978577.344.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1443 -0
README.md
CHANGED
@@ -26,16 +26,16 @@ model-index:
|
|
26 |
metrics:
|
27 |
- name: Accuracy
|
28 |
type: accuracy
|
29 |
-
value: 0.
|
30 |
- name: F1
|
31 |
type: f1
|
32 |
-
value: 0.
|
33 |
- name: Precision
|
34 |
type: precision
|
35 |
-
value: 0.
|
36 |
- name: Recall
|
37 |
type: recall
|
38 |
-
value: 0.
|
39 |
---
|
40 |
|
41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
45 |
|
46 |
This model is a fine-tuned version of [apple/mobilevit-xx-small](https://huggingface.co/apple/mobilevit-xx-small) on the webdataset dataset.
|
47 |
It achieves the following results on the evaluation set:
|
48 |
-
- Loss: 0.
|
49 |
-
- Accuracy: 0.
|
50 |
-
- F1: 0.
|
51 |
-
- Precision: 0.
|
52 |
-
- Recall: 0.
|
53 |
|
54 |
## Model description
|
55 |
|
|
|
26 |
metrics:
|
27 |
- name: Accuracy
|
28 |
type: accuracy
|
29 |
+
value: 0.9337777777777778
|
30 |
- name: F1
|
31 |
type: f1
|
32 |
+
value: 0.826945412311266
|
33 |
- name: Precision
|
34 |
type: precision
|
35 |
+
value: 0.8259860788863109
|
36 |
- name: Recall
|
37 |
type: recall
|
38 |
+
value: 0.827906976744186
|
39 |
---
|
40 |
|
41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
45 |
|
46 |
This model is a fine-tuned version of [apple/mobilevit-xx-small](https://huggingface.co/apple/mobilevit-xx-small) on the webdataset dataset.
|
47 |
It achieves the following results on the evaluation set:
|
48 |
+
- Loss: 0.1725
|
49 |
+
- Accuracy: 0.9338
|
50 |
+
- F1: 0.8269
|
51 |
+
- Precision: 0.8260
|
52 |
+
- Recall: 0.8279
|
53 |
|
54 |
## Model description
|
55 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 30.0,
|
3 |
+
"eval_accuracy": 0.9337777777777778,
|
4 |
+
"eval_f1": 0.826945412311266,
|
5 |
+
"eval_loss": 0.1725098043680191,
|
6 |
+
"eval_precision": 0.8259860788863109,
|
7 |
+
"eval_recall": 0.827906976744186,
|
8 |
+
"eval_runtime": 2.2237,
|
9 |
+
"eval_samples_per_second": 101.181,
|
10 |
+
"eval_steps_per_second": 13.041,
|
11 |
+
"total_flos": 3.8465920659456e+16,
|
12 |
+
"train_loss": 0.2702594916025797,
|
13 |
+
"train_runtime": 403.8981,
|
14 |
+
"train_samples_per_second": 66.849,
|
15 |
+
"train_steps_per_second": 4.234
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 30.0,
|
3 |
+
"eval_accuracy": 0.9337777777777778,
|
4 |
+
"eval_f1": 0.826945412311266,
|
5 |
+
"eval_loss": 0.1725098043680191,
|
6 |
+
"eval_precision": 0.8259860788863109,
|
7 |
+
"eval_recall": 0.827906976744186,
|
8 |
+
"eval_runtime": 2.2237,
|
9 |
+
"eval_samples_per_second": 101.181,
|
10 |
+
"eval_steps_per_second": 13.041
|
11 |
+
}
|
runs/Oct22_15-45-30_2ae384978577/events.out.tfevents.1729612359.2ae384978577.344.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:817aa14a668e23887148c3620906888b17e0c596b1cf224f9f5f48e67717e9a0
|
3 |
+
size 560
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 30.0,
|
3 |
+
"total_flos": 3.8465920659456e+16,
|
4 |
+
"train_loss": 0.2702594916025797,
|
5 |
+
"train_runtime": 403.8981,
|
6 |
+
"train_samples_per_second": 66.849,
|
7 |
+
"train_steps_per_second": 4.234
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.1725098043680191,
|
3 |
+
"best_model_checkpoint": "frost-mobile-apple/mobilevit-xx-small-v2024-10-22/checkpoint-1500",
|
4 |
+
"epoch": 30.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 1710,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.17543859649122806,
|
13 |
+
"grad_norm": 0.2625730037689209,
|
14 |
+
"learning_rate": 1.1695906432748537e-05,
|
15 |
+
"loss": 0.6928,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.3508771929824561,
|
20 |
+
"grad_norm": 0.2961116135120392,
|
21 |
+
"learning_rate": 2.3391812865497074e-05,
|
22 |
+
"loss": 0.6936,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.5263157894736842,
|
27 |
+
"grad_norm": 0.24333663284778595,
|
28 |
+
"learning_rate": 3.508771929824561e-05,
|
29 |
+
"loss": 0.6917,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.7017543859649122,
|
34 |
+
"grad_norm": 0.2218523770570755,
|
35 |
+
"learning_rate": 4.678362573099415e-05,
|
36 |
+
"loss": 0.6887,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.8771929824561403,
|
41 |
+
"grad_norm": 0.23965124785900116,
|
42 |
+
"learning_rate": 5.847953216374269e-05,
|
43 |
+
"loss": 0.685,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.0526315789473684,
|
48 |
+
"grad_norm": 0.23081418871879578,
|
49 |
+
"learning_rate": 7.017543859649122e-05,
|
50 |
+
"loss": 0.6815,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.2280701754385965,
|
55 |
+
"grad_norm": 0.23212119936943054,
|
56 |
+
"learning_rate": 8.187134502923976e-05,
|
57 |
+
"loss": 0.676,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.4035087719298245,
|
62 |
+
"grad_norm": 0.2775309383869171,
|
63 |
+
"learning_rate": 9.35672514619883e-05,
|
64 |
+
"loss": 0.6711,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.5789473684210527,
|
69 |
+
"grad_norm": 0.38230618834495544,
|
70 |
+
"learning_rate": 0.00010526315789473685,
|
71 |
+
"loss": 0.6617,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.7543859649122808,
|
76 |
+
"grad_norm": 0.29050251841545105,
|
77 |
+
"learning_rate": 0.00011695906432748539,
|
78 |
+
"loss": 0.6549,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.7543859649122808,
|
83 |
+
"eval_accuracy": 0.82,
|
84 |
+
"eval_f1": 0.6260387811634349,
|
85 |
+
"eval_loss": 0.6288657784461975,
|
86 |
+
"eval_precision": 0.5191424196018377,
|
87 |
+
"eval_recall": 0.7883720930232558,
|
88 |
+
"eval_runtime": 2.6915,
|
89 |
+
"eval_samples_per_second": 83.597,
|
90 |
+
"eval_steps_per_second": 10.775,
|
91 |
+
"step": 100
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 1.9298245614035088,
|
95 |
+
"grad_norm": 0.3310299217700958,
|
96 |
+
"learning_rate": 0.0001286549707602339,
|
97 |
+
"loss": 0.6389,
|
98 |
+
"step": 110
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.1052631578947367,
|
102 |
+
"grad_norm": 0.35385212302207947,
|
103 |
+
"learning_rate": 0.00014035087719298245,
|
104 |
+
"loss": 0.6276,
|
105 |
+
"step": 120
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 2.280701754385965,
|
109 |
+
"grad_norm": 0.31887122988700867,
|
110 |
+
"learning_rate": 0.00015204678362573098,
|
111 |
+
"loss": 0.6068,
|
112 |
+
"step": 130
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 2.456140350877193,
|
116 |
+
"grad_norm": 0.38656044006347656,
|
117 |
+
"learning_rate": 0.00016374269005847952,
|
118 |
+
"loss": 0.5876,
|
119 |
+
"step": 140
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 2.6315789473684212,
|
123 |
+
"grad_norm": 0.40553656220436096,
|
124 |
+
"learning_rate": 0.00017543859649122806,
|
125 |
+
"loss": 0.5782,
|
126 |
+
"step": 150
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 2.807017543859649,
|
130 |
+
"grad_norm": 0.5055739879608154,
|
131 |
+
"learning_rate": 0.0001871345029239766,
|
132 |
+
"loss": 0.546,
|
133 |
+
"step": 160
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 2.982456140350877,
|
137 |
+
"grad_norm": 0.6473321318626404,
|
138 |
+
"learning_rate": 0.00019883040935672513,
|
139 |
+
"loss": 0.5322,
|
140 |
+
"step": 170
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 3.1578947368421053,
|
144 |
+
"grad_norm": 0.5542100667953491,
|
145 |
+
"learning_rate": 0.00019883040935672513,
|
146 |
+
"loss": 0.5081,
|
147 |
+
"step": 180
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 3.3333333333333335,
|
151 |
+
"grad_norm": 0.525965690612793,
|
152 |
+
"learning_rate": 0.00019753086419753085,
|
153 |
+
"loss": 0.4906,
|
154 |
+
"step": 190
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 3.5087719298245617,
|
158 |
+
"grad_norm": 0.6686927676200867,
|
159 |
+
"learning_rate": 0.00019623131903833657,
|
160 |
+
"loss": 0.4616,
|
161 |
+
"step": 200
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 3.5087719298245617,
|
165 |
+
"eval_accuracy": 0.8866666666666667,
|
166 |
+
"eval_f1": 0.7295864262990456,
|
167 |
+
"eval_loss": 0.41918542981147766,
|
168 |
+
"eval_precision": 0.6705653021442495,
|
169 |
+
"eval_recall": 0.8,
|
170 |
+
"eval_runtime": 2.7897,
|
171 |
+
"eval_samples_per_second": 80.654,
|
172 |
+
"eval_steps_per_second": 10.395,
|
173 |
+
"step": 200
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 3.6842105263157894,
|
177 |
+
"grad_norm": 1.5412182807922363,
|
178 |
+
"learning_rate": 0.0001949317738791423,
|
179 |
+
"loss": 0.4506,
|
180 |
+
"step": 210
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 3.8596491228070176,
|
184 |
+
"grad_norm": 0.4173012375831604,
|
185 |
+
"learning_rate": 0.00019363222871994802,
|
186 |
+
"loss": 0.4371,
|
187 |
+
"step": 220
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 4.035087719298246,
|
191 |
+
"grad_norm": 0.42248570919036865,
|
192 |
+
"learning_rate": 0.00019233268356075374,
|
193 |
+
"loss": 0.4064,
|
194 |
+
"step": 230
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 4.2105263157894735,
|
198 |
+
"grad_norm": 0.5491617918014526,
|
199 |
+
"learning_rate": 0.00019103313840155946,
|
200 |
+
"loss": 0.3724,
|
201 |
+
"step": 240
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 4.385964912280702,
|
205 |
+
"grad_norm": 0.35062703490257263,
|
206 |
+
"learning_rate": 0.00018973359324236518,
|
207 |
+
"loss": 0.3671,
|
208 |
+
"step": 250
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 4.56140350877193,
|
212 |
+
"grad_norm": 0.40491071343421936,
|
213 |
+
"learning_rate": 0.0001884340480831709,
|
214 |
+
"loss": 0.3683,
|
215 |
+
"step": 260
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 4.7368421052631575,
|
219 |
+
"grad_norm": 0.9965174794197083,
|
220 |
+
"learning_rate": 0.0001871345029239766,
|
221 |
+
"loss": 0.3402,
|
222 |
+
"step": 270
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 4.912280701754386,
|
226 |
+
"grad_norm": 0.7184051275253296,
|
227 |
+
"learning_rate": 0.00018583495776478232,
|
228 |
+
"loss": 0.3348,
|
229 |
+
"step": 280
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 5.087719298245614,
|
233 |
+
"grad_norm": 1.8915038108825684,
|
234 |
+
"learning_rate": 0.00018453541260558804,
|
235 |
+
"loss": 0.32,
|
236 |
+
"step": 290
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 5.2631578947368425,
|
240 |
+
"grad_norm": 0.5761589407920837,
|
241 |
+
"learning_rate": 0.00018323586744639376,
|
242 |
+
"loss": 0.3101,
|
243 |
+
"step": 300
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 5.2631578947368425,
|
247 |
+
"eval_accuracy": 0.9035555555555556,
|
248 |
+
"eval_f1": 0.7317676143386898,
|
249 |
+
"eval_loss": 0.30708780884742737,
|
250 |
+
"eval_precision": 0.7810026385224275,
|
251 |
+
"eval_recall": 0.6883720930232559,
|
252 |
+
"eval_runtime": 2.8811,
|
253 |
+
"eval_samples_per_second": 78.095,
|
254 |
+
"eval_steps_per_second": 10.066,
|
255 |
+
"step": 300
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 5.43859649122807,
|
259 |
+
"grad_norm": 1.1592423915863037,
|
260 |
+
"learning_rate": 0.00018193632228719948,
|
261 |
+
"loss": 0.3258,
|
262 |
+
"step": 310
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 5.614035087719298,
|
266 |
+
"grad_norm": 0.8307028412818909,
|
267 |
+
"learning_rate": 0.0001806367771280052,
|
268 |
+
"loss": 0.3149,
|
269 |
+
"step": 320
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 5.7894736842105265,
|
273 |
+
"grad_norm": 0.9469823837280273,
|
274 |
+
"learning_rate": 0.00017933723196881092,
|
275 |
+
"loss": 0.3033,
|
276 |
+
"step": 330
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 5.964912280701754,
|
280 |
+
"grad_norm": 2.199500322341919,
|
281 |
+
"learning_rate": 0.00017803768680961664,
|
282 |
+
"loss": 0.3164,
|
283 |
+
"step": 340
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 6.140350877192983,
|
287 |
+
"grad_norm": 0.6772398948669434,
|
288 |
+
"learning_rate": 0.00017673814165042236,
|
289 |
+
"loss": 0.2806,
|
290 |
+
"step": 350
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 6.315789473684211,
|
294 |
+
"grad_norm": 0.4862241744995117,
|
295 |
+
"learning_rate": 0.00017543859649122806,
|
296 |
+
"loss": 0.2817,
|
297 |
+
"step": 360
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 6.491228070175438,
|
301 |
+
"grad_norm": 1.2349482774734497,
|
302 |
+
"learning_rate": 0.00017413905133203378,
|
303 |
+
"loss": 0.288,
|
304 |
+
"step": 370
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 6.666666666666667,
|
308 |
+
"grad_norm": 2.9781813621520996,
|
309 |
+
"learning_rate": 0.00017296946068875895,
|
310 |
+
"loss": 0.3039,
|
311 |
+
"step": 380
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 6.842105263157895,
|
315 |
+
"grad_norm": 0.7632750272750854,
|
316 |
+
"learning_rate": 0.00017166991552956468,
|
317 |
+
"loss": 0.2836,
|
318 |
+
"step": 390
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 7.017543859649122,
|
322 |
+
"grad_norm": 1.2420198917388916,
|
323 |
+
"learning_rate": 0.00017037037037037037,
|
324 |
+
"loss": 0.2932,
|
325 |
+
"step": 400
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 7.017543859649122,
|
329 |
+
"eval_accuracy": 0.908,
|
330 |
+
"eval_f1": 0.7460122699386503,
|
331 |
+
"eval_loss": 0.24856920540332794,
|
332 |
+
"eval_precision": 0.7896103896103897,
|
333 |
+
"eval_recall": 0.7069767441860465,
|
334 |
+
"eval_runtime": 2.8347,
|
335 |
+
"eval_samples_per_second": 79.373,
|
336 |
+
"eval_steps_per_second": 10.23,
|
337 |
+
"step": 400
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 7.192982456140351,
|
341 |
+
"grad_norm": 0.8554529547691345,
|
342 |
+
"learning_rate": 0.0001690708252111761,
|
343 |
+
"loss": 0.2583,
|
344 |
+
"step": 410
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 7.368421052631579,
|
348 |
+
"grad_norm": 0.5736662745475769,
|
349 |
+
"learning_rate": 0.0001677712800519818,
|
350 |
+
"loss": 0.2809,
|
351 |
+
"step": 420
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 7.543859649122807,
|
355 |
+
"grad_norm": 0.7552086114883423,
|
356 |
+
"learning_rate": 0.00016647173489278753,
|
357 |
+
"loss": 0.2774,
|
358 |
+
"step": 430
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 7.719298245614035,
|
362 |
+
"grad_norm": 0.6094131469726562,
|
363 |
+
"learning_rate": 0.00016517218973359325,
|
364 |
+
"loss": 0.2771,
|
365 |
+
"step": 440
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 7.894736842105263,
|
369 |
+
"grad_norm": 0.5392113924026489,
|
370 |
+
"learning_rate": 0.00016387264457439898,
|
371 |
+
"loss": 0.2755,
|
372 |
+
"step": 450
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 8.070175438596491,
|
376 |
+
"grad_norm": 0.4927959740161896,
|
377 |
+
"learning_rate": 0.0001625730994152047,
|
378 |
+
"loss": 0.2572,
|
379 |
+
"step": 460
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 8.24561403508772,
|
383 |
+
"grad_norm": 0.9484465718269348,
|
384 |
+
"learning_rate": 0.00016127355425601042,
|
385 |
+
"loss": 0.2354,
|
386 |
+
"step": 470
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 8.421052631578947,
|
390 |
+
"grad_norm": 0.71286940574646,
|
391 |
+
"learning_rate": 0.0001599740090968161,
|
392 |
+
"loss": 0.2611,
|
393 |
+
"step": 480
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 8.596491228070175,
|
397 |
+
"grad_norm": 1.9641995429992676,
|
398 |
+
"learning_rate": 0.00015867446393762183,
|
399 |
+
"loss": 0.2547,
|
400 |
+
"step": 490
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 8.771929824561404,
|
404 |
+
"grad_norm": 1.1893583536148071,
|
405 |
+
"learning_rate": 0.00015737491877842755,
|
406 |
+
"loss": 0.2652,
|
407 |
+
"step": 500
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 8.771929824561404,
|
411 |
+
"eval_accuracy": 0.9137777777777778,
|
412 |
+
"eval_f1": 0.7673860911270983,
|
413 |
+
"eval_loss": 0.22792504727840424,
|
414 |
+
"eval_precision": 0.7920792079207921,
|
415 |
+
"eval_recall": 0.7441860465116279,
|
416 |
+
"eval_runtime": 1.8141,
|
417 |
+
"eval_samples_per_second": 124.03,
|
418 |
+
"eval_steps_per_second": 15.986,
|
419 |
+
"step": 500
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 8.947368421052632,
|
423 |
+
"grad_norm": 1.0071460008621216,
|
424 |
+
"learning_rate": 0.00015607537361923327,
|
425 |
+
"loss": 0.244,
|
426 |
+
"step": 510
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 9.12280701754386,
|
430 |
+
"grad_norm": 1.22650146484375,
|
431 |
+
"learning_rate": 0.000154775828460039,
|
432 |
+
"loss": 0.2377,
|
433 |
+
"step": 520
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 9.298245614035087,
|
437 |
+
"grad_norm": 2.428567886352539,
|
438 |
+
"learning_rate": 0.00015347628330084472,
|
439 |
+
"loss": 0.2494,
|
440 |
+
"step": 530
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 9.473684210526315,
|
444 |
+
"grad_norm": 1.8254860639572144,
|
445 |
+
"learning_rate": 0.00015217673814165044,
|
446 |
+
"loss": 0.2603,
|
447 |
+
"step": 540
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 9.649122807017545,
|
451 |
+
"grad_norm": 0.6592786908149719,
|
452 |
+
"learning_rate": 0.00015087719298245616,
|
453 |
+
"loss": 0.2597,
|
454 |
+
"step": 550
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 9.824561403508772,
|
458 |
+
"grad_norm": 1.3194756507873535,
|
459 |
+
"learning_rate": 0.00014957764782326188,
|
460 |
+
"loss": 0.2313,
|
461 |
+
"step": 560
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 10.0,
|
465 |
+
"grad_norm": 2.1871612071990967,
|
466 |
+
"learning_rate": 0.00014827810266406757,
|
467 |
+
"loss": 0.282,
|
468 |
+
"step": 570
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 10.175438596491228,
|
472 |
+
"grad_norm": 0.759860098361969,
|
473 |
+
"learning_rate": 0.0001469785575048733,
|
474 |
+
"loss": 0.2319,
|
475 |
+
"step": 580
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 10.350877192982455,
|
479 |
+
"grad_norm": 1.447387933731079,
|
480 |
+
"learning_rate": 0.00014567901234567902,
|
481 |
+
"loss": 0.2457,
|
482 |
+
"step": 590
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 10.526315789473685,
|
486 |
+
"grad_norm": 0.9954220056533813,
|
487 |
+
"learning_rate": 0.00014437946718648474,
|
488 |
+
"loss": 0.2253,
|
489 |
+
"step": 600
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 10.526315789473685,
|
493 |
+
"eval_accuracy": 0.9217777777777778,
|
494 |
+
"eval_f1": 0.7858880778588808,
|
495 |
+
"eval_loss": 0.21004962921142578,
|
496 |
+
"eval_precision": 0.8239795918367347,
|
497 |
+
"eval_recall": 0.7511627906976744,
|
498 |
+
"eval_runtime": 4.2925,
|
499 |
+
"eval_samples_per_second": 52.417,
|
500 |
+
"eval_steps_per_second": 6.756,
|
501 |
+
"step": 600
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 10.701754385964913,
|
505 |
+
"grad_norm": 0.715815544128418,
|
506 |
+
"learning_rate": 0.00014307992202729046,
|
507 |
+
"loss": 0.2391,
|
508 |
+
"step": 610
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 10.87719298245614,
|
512 |
+
"grad_norm": 0.6449007391929626,
|
513 |
+
"learning_rate": 0.00014178037686809618,
|
514 |
+
"loss": 0.2516,
|
515 |
+
"step": 620
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 11.052631578947368,
|
519 |
+
"grad_norm": 0.9613096117973328,
|
520 |
+
"learning_rate": 0.0001404808317089019,
|
521 |
+
"loss": 0.2157,
|
522 |
+
"step": 630
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 11.228070175438596,
|
526 |
+
"grad_norm": 2.206623077392578,
|
527 |
+
"learning_rate": 0.00013918128654970762,
|
528 |
+
"loss": 0.2365,
|
529 |
+
"step": 640
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 11.403508771929825,
|
533 |
+
"grad_norm": 1.8694980144500732,
|
534 |
+
"learning_rate": 0.00013788174139051334,
|
535 |
+
"loss": 0.2263,
|
536 |
+
"step": 650
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 11.578947368421053,
|
540 |
+
"grad_norm": 0.7060205340385437,
|
541 |
+
"learning_rate": 0.00013658219623131904,
|
542 |
+
"loss": 0.2173,
|
543 |
+
"step": 660
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 11.75438596491228,
|
547 |
+
"grad_norm": 0.8581671714782715,
|
548 |
+
"learning_rate": 0.00013528265107212476,
|
549 |
+
"loss": 0.2204,
|
550 |
+
"step": 670
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 11.929824561403509,
|
554 |
+
"grad_norm": 1.196590781211853,
|
555 |
+
"learning_rate": 0.00013398310591293048,
|
556 |
+
"loss": 0.2519,
|
557 |
+
"step": 680
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 12.105263157894736,
|
561 |
+
"grad_norm": 1.0726817846298218,
|
562 |
+
"learning_rate": 0.0001326835607537362,
|
563 |
+
"loss": 0.2184,
|
564 |
+
"step": 690
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 12.280701754385966,
|
568 |
+
"grad_norm": 0.6241493821144104,
|
569 |
+
"learning_rate": 0.00013138401559454192,
|
570 |
+
"loss": 0.2257,
|
571 |
+
"step": 700
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 12.280701754385966,
|
575 |
+
"eval_accuracy": 0.9248888888888889,
|
576 |
+
"eval_f1": 0.8018757327080891,
|
577 |
+
"eval_loss": 0.19510744512081146,
|
578 |
+
"eval_precision": 0.8085106382978723,
|
579 |
+
"eval_recall": 0.7953488372093023,
|
580 |
+
"eval_runtime": 2.9139,
|
581 |
+
"eval_samples_per_second": 77.217,
|
582 |
+
"eval_steps_per_second": 9.952,
|
583 |
+
"step": 700
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 12.456140350877194,
|
587 |
+
"grad_norm": 1.382541298866272,
|
588 |
+
"learning_rate": 0.00013008447043534764,
|
589 |
+
"loss": 0.217,
|
590 |
+
"step": 710
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 12.631578947368421,
|
594 |
+
"grad_norm": 0.7372106909751892,
|
595 |
+
"learning_rate": 0.00012878492527615336,
|
596 |
+
"loss": 0.2209,
|
597 |
+
"step": 720
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 12.807017543859649,
|
601 |
+
"grad_norm": 1.3437495231628418,
|
602 |
+
"learning_rate": 0.00012748538011695908,
|
603 |
+
"loss": 0.2215,
|
604 |
+
"step": 730
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 12.982456140350877,
|
608 |
+
"grad_norm": 0.8328105807304382,
|
609 |
+
"learning_rate": 0.0001261858349577648,
|
610 |
+
"loss": 0.247,
|
611 |
+
"step": 740
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 13.157894736842104,
|
615 |
+
"grad_norm": 1.166037917137146,
|
616 |
+
"learning_rate": 0.0001248862897985705,
|
617 |
+
"loss": 0.2362,
|
618 |
+
"step": 750
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 13.333333333333334,
|
622 |
+
"grad_norm": 1.8687838315963745,
|
623 |
+
"learning_rate": 0.00012358674463937622,
|
624 |
+
"loss": 0.2247,
|
625 |
+
"step": 760
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 13.508771929824562,
|
629 |
+
"grad_norm": 1.2782139778137207,
|
630 |
+
"learning_rate": 0.00012228719948018194,
|
631 |
+
"loss": 0.2134,
|
632 |
+
"step": 770
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 13.68421052631579,
|
636 |
+
"grad_norm": 1.114933967590332,
|
637 |
+
"learning_rate": 0.00012098765432098766,
|
638 |
+
"loss": 0.1965,
|
639 |
+
"step": 780
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 13.859649122807017,
|
643 |
+
"grad_norm": 1.7937145233154297,
|
644 |
+
"learning_rate": 0.00011968810916179338,
|
645 |
+
"loss": 0.2124,
|
646 |
+
"step": 790
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 14.035087719298245,
|
650 |
+
"grad_norm": 1.6698014736175537,
|
651 |
+
"learning_rate": 0.0001183885640025991,
|
652 |
+
"loss": 0.2468,
|
653 |
+
"step": 800
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 14.035087719298245,
|
657 |
+
"eval_accuracy": 0.9306666666666666,
|
658 |
+
"eval_f1": 0.8198614318706697,
|
659 |
+
"eval_loss": 0.19064003229141235,
|
660 |
+
"eval_precision": 0.8142201834862385,
|
661 |
+
"eval_recall": 0.8255813953488372,
|
662 |
+
"eval_runtime": 2.8315,
|
663 |
+
"eval_samples_per_second": 79.464,
|
664 |
+
"eval_steps_per_second": 10.242,
|
665 |
+
"step": 800
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 14.210526315789474,
|
669 |
+
"grad_norm": 0.6950424313545227,
|
670 |
+
"learning_rate": 0.00011708901884340481,
|
671 |
+
"loss": 0.2004,
|
672 |
+
"step": 810
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 14.385964912280702,
|
676 |
+
"grad_norm": 1.5043634176254272,
|
677 |
+
"learning_rate": 0.00011578947368421053,
|
678 |
+
"loss": 0.2317,
|
679 |
+
"step": 820
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 14.56140350877193,
|
683 |
+
"grad_norm": 1.2491843700408936,
|
684 |
+
"learning_rate": 0.00011448992852501626,
|
685 |
+
"loss": 0.2027,
|
686 |
+
"step": 830
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 14.736842105263158,
|
690 |
+
"grad_norm": 0.6502349376678467,
|
691 |
+
"learning_rate": 0.00011319038336582198,
|
692 |
+
"loss": 0.2112,
|
693 |
+
"step": 840
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 14.912280701754385,
|
697 |
+
"grad_norm": 0.40061789751052856,
|
698 |
+
"learning_rate": 0.0001118908382066277,
|
699 |
+
"loss": 0.1756,
|
700 |
+
"step": 850
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 15.087719298245615,
|
704 |
+
"grad_norm": 2.8378994464874268,
|
705 |
+
"learning_rate": 0.0001105912930474334,
|
706 |
+
"loss": 0.2216,
|
707 |
+
"step": 860
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 15.263157894736842,
|
711 |
+
"grad_norm": 1.7187498807907104,
|
712 |
+
"learning_rate": 0.00010929174788823913,
|
713 |
+
"loss": 0.2072,
|
714 |
+
"step": 870
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 15.43859649122807,
|
718 |
+
"grad_norm": 1.774376392364502,
|
719 |
+
"learning_rate": 0.00010799220272904485,
|
720 |
+
"loss": 0.239,
|
721 |
+
"step": 880
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 15.614035087719298,
|
725 |
+
"grad_norm": 1.5812989473342896,
|
726 |
+
"learning_rate": 0.00010669265756985057,
|
727 |
+
"loss": 0.2191,
|
728 |
+
"step": 890
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 15.789473684210526,
|
732 |
+
"grad_norm": 0.9877386689186096,
|
733 |
+
"learning_rate": 0.00010539311241065628,
|
734 |
+
"loss": 0.1796,
|
735 |
+
"step": 900
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 15.789473684210526,
|
739 |
+
"eval_accuracy": 0.9275555555555556,
|
740 |
+
"eval_f1": 0.81199538638985,
|
741 |
+
"eval_loss": 0.19485591351985931,
|
742 |
+
"eval_precision": 0.8054919908466819,
|
743 |
+
"eval_recall": 0.8186046511627907,
|
744 |
+
"eval_runtime": 1.8216,
|
745 |
+
"eval_samples_per_second": 123.517,
|
746 |
+
"eval_steps_per_second": 15.92,
|
747 |
+
"step": 900
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 15.964912280701755,
|
751 |
+
"grad_norm": 1.059669017791748,
|
752 |
+
"learning_rate": 0.000104093567251462,
|
753 |
+
"loss": 0.1838,
|
754 |
+
"step": 910
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 16.140350877192983,
|
758 |
+
"grad_norm": 1.4218086004257202,
|
759 |
+
"learning_rate": 0.00010279402209226772,
|
760 |
+
"loss": 0.2281,
|
761 |
+
"step": 920
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 16.31578947368421,
|
765 |
+
"grad_norm": 1.2070213556289673,
|
766 |
+
"learning_rate": 0.00010149447693307344,
|
767 |
+
"loss": 0.1997,
|
768 |
+
"step": 930
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 16.49122807017544,
|
772 |
+
"grad_norm": 2.351250410079956,
|
773 |
+
"learning_rate": 0.00010019493177387915,
|
774 |
+
"loss": 0.1843,
|
775 |
+
"step": 940
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 16.666666666666668,
|
779 |
+
"grad_norm": 0.8852570056915283,
|
780 |
+
"learning_rate": 9.889538661468485e-05,
|
781 |
+
"loss": 0.2357,
|
782 |
+
"step": 950
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 16.842105263157894,
|
786 |
+
"grad_norm": 2.0466091632843018,
|
787 |
+
"learning_rate": 9.759584145549058e-05,
|
788 |
+
"loss": 0.2277,
|
789 |
+
"step": 960
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 17.017543859649123,
|
793 |
+
"grad_norm": 5.798379898071289,
|
794 |
+
"learning_rate": 9.62962962962963e-05,
|
795 |
+
"loss": 0.2246,
|
796 |
+
"step": 970
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 17.19298245614035,
|
800 |
+
"grad_norm": 1.6754958629608154,
|
801 |
+
"learning_rate": 9.499675113710202e-05,
|
802 |
+
"loss": 0.1904,
|
803 |
+
"step": 980
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 17.36842105263158,
|
807 |
+
"grad_norm": 0.6962611675262451,
|
808 |
+
"learning_rate": 9.369720597790773e-05,
|
809 |
+
"loss": 0.202,
|
810 |
+
"step": 990
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 17.54385964912281,
|
814 |
+
"grad_norm": 0.5351881384849548,
|
815 |
+
"learning_rate": 9.239766081871345e-05,
|
816 |
+
"loss": 0.1888,
|
817 |
+
"step": 1000
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 17.54385964912281,
|
821 |
+
"eval_accuracy": 0.9306666666666666,
|
822 |
+
"eval_f1": 0.8177570093457944,
|
823 |
+
"eval_loss": 0.18066002428531647,
|
824 |
+
"eval_precision": 0.8215962441314554,
|
825 |
+
"eval_recall": 0.813953488372093,
|
826 |
+
"eval_runtime": 1.8596,
|
827 |
+
"eval_samples_per_second": 120.996,
|
828 |
+
"eval_steps_per_second": 15.595,
|
829 |
+
"step": 1000
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 17.719298245614034,
|
833 |
+
"grad_norm": 1.2162110805511475,
|
834 |
+
"learning_rate": 9.109811565951917e-05,
|
835 |
+
"loss": 0.1789,
|
836 |
+
"step": 1010
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 17.894736842105264,
|
840 |
+
"grad_norm": 1.2040334939956665,
|
841 |
+
"learning_rate": 8.979857050032489e-05,
|
842 |
+
"loss": 0.2109,
|
843 |
+
"step": 1020
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 18.07017543859649,
|
847 |
+
"grad_norm": 0.8599823117256165,
|
848 |
+
"learning_rate": 8.849902534113061e-05,
|
849 |
+
"loss": 0.2113,
|
850 |
+
"step": 1030
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 18.24561403508772,
|
854 |
+
"grad_norm": 1.0291296243667603,
|
855 |
+
"learning_rate": 8.719948018193632e-05,
|
856 |
+
"loss": 0.1981,
|
857 |
+
"step": 1040
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 18.42105263157895,
|
861 |
+
"grad_norm": 3.214996576309204,
|
862 |
+
"learning_rate": 8.589993502274204e-05,
|
863 |
+
"loss": 0.1903,
|
864 |
+
"step": 1050
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 18.596491228070175,
|
868 |
+
"grad_norm": 1.1698780059814453,
|
869 |
+
"learning_rate": 8.460038986354776e-05,
|
870 |
+
"loss": 0.192,
|
871 |
+
"step": 1060
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 18.771929824561404,
|
875 |
+
"grad_norm": 3.0040793418884277,
|
876 |
+
"learning_rate": 8.330084470435348e-05,
|
877 |
+
"loss": 0.2062,
|
878 |
+
"step": 1070
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 18.94736842105263,
|
882 |
+
"grad_norm": 1.365694522857666,
|
883 |
+
"learning_rate": 8.200129954515919e-05,
|
884 |
+
"loss": 0.1885,
|
885 |
+
"step": 1080
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 19.12280701754386,
|
889 |
+
"grad_norm": 0.5183665156364441,
|
890 |
+
"learning_rate": 8.070175438596491e-05,
|
891 |
+
"loss": 0.2089,
|
892 |
+
"step": 1090
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 19.29824561403509,
|
896 |
+
"grad_norm": 0.6474595069885254,
|
897 |
+
"learning_rate": 7.940220922677063e-05,
|
898 |
+
"loss": 0.202,
|
899 |
+
"step": 1100
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 19.29824561403509,
|
903 |
+
"eval_accuracy": 0.9342222222222222,
|
904 |
+
"eval_f1": 0.8287037037037037,
|
905 |
+
"eval_loss": 0.1772110015153885,
|
906 |
+
"eval_precision": 0.8248847926267281,
|
907 |
+
"eval_recall": 0.8325581395348837,
|
908 |
+
"eval_runtime": 2.2017,
|
909 |
+
"eval_samples_per_second": 102.193,
|
910 |
+
"eval_steps_per_second": 13.171,
|
911 |
+
"step": 1100
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 19.473684210526315,
|
915 |
+
"grad_norm": 0.7569323778152466,
|
916 |
+
"learning_rate": 7.810266406757635e-05,
|
917 |
+
"loss": 0.2037,
|
918 |
+
"step": 1110
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 19.649122807017545,
|
922 |
+
"grad_norm": 1.068310260772705,
|
923 |
+
"learning_rate": 7.680311890838207e-05,
|
924 |
+
"loss": 0.1842,
|
925 |
+
"step": 1120
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 19.82456140350877,
|
929 |
+
"grad_norm": 1.1388903856277466,
|
930 |
+
"learning_rate": 7.550357374918778e-05,
|
931 |
+
"loss": 0.2057,
|
932 |
+
"step": 1130
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 20.0,
|
936 |
+
"grad_norm": 5.906609535217285,
|
937 |
+
"learning_rate": 7.42040285899935e-05,
|
938 |
+
"loss": 0.2088,
|
939 |
+
"step": 1140
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 20.17543859649123,
|
943 |
+
"grad_norm": 0.9702988862991333,
|
944 |
+
"learning_rate": 7.290448343079922e-05,
|
945 |
+
"loss": 0.1939,
|
946 |
+
"step": 1150
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 20.350877192982455,
|
950 |
+
"grad_norm": 3.627027988433838,
|
951 |
+
"learning_rate": 7.160493827160494e-05,
|
952 |
+
"loss": 0.1953,
|
953 |
+
"step": 1160
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 20.526315789473685,
|
957 |
+
"grad_norm": 1.11257004737854,
|
958 |
+
"learning_rate": 7.030539311241065e-05,
|
959 |
+
"loss": 0.1908,
|
960 |
+
"step": 1170
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 20.70175438596491,
|
964 |
+
"grad_norm": 1.626079797744751,
|
965 |
+
"learning_rate": 6.900584795321637e-05,
|
966 |
+
"loss": 0.2011,
|
967 |
+
"step": 1180
|
968 |
+
},
|
969 |
+
{
|
970 |
+
"epoch": 20.87719298245614,
|
971 |
+
"grad_norm": 1.8711522817611694,
|
972 |
+
"learning_rate": 6.770630279402209e-05,
|
973 |
+
"loss": 0.2106,
|
974 |
+
"step": 1190
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 21.05263157894737,
|
978 |
+
"grad_norm": 2.9188010692596436,
|
979 |
+
"learning_rate": 6.640675763482781e-05,
|
980 |
+
"loss": 0.1824,
|
981 |
+
"step": 1200
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 21.05263157894737,
|
985 |
+
"eval_accuracy": 0.9275555555555556,
|
986 |
+
"eval_f1": 0.8080094228504122,
|
987 |
+
"eval_loss": 0.18258829414844513,
|
988 |
+
"eval_precision": 0.8186157517899761,
|
989 |
+
"eval_recall": 0.7976744186046512,
|
990 |
+
"eval_runtime": 1.8368,
|
991 |
+
"eval_samples_per_second": 122.496,
|
992 |
+
"eval_steps_per_second": 15.788,
|
993 |
+
"step": 1200
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 21.228070175438596,
|
997 |
+
"grad_norm": 1.2156211137771606,
|
998 |
+
"learning_rate": 6.510721247563352e-05,
|
999 |
+
"loss": 0.1926,
|
1000 |
+
"step": 1210
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 21.403508771929825,
|
1004 |
+
"grad_norm": 0.5184522271156311,
|
1005 |
+
"learning_rate": 6.380766731643924e-05,
|
1006 |
+
"loss": 0.1695,
|
1007 |
+
"step": 1220
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 21.57894736842105,
|
1011 |
+
"grad_norm": 1.8020312786102295,
|
1012 |
+
"learning_rate": 6.250812215724496e-05,
|
1013 |
+
"loss": 0.2222,
|
1014 |
+
"step": 1230
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 21.75438596491228,
|
1018 |
+
"grad_norm": 1.808860421180725,
|
1019 |
+
"learning_rate": 6.120857699805068e-05,
|
1020 |
+
"loss": 0.2026,
|
1021 |
+
"step": 1240
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 21.92982456140351,
|
1025 |
+
"grad_norm": 0.5891908407211304,
|
1026 |
+
"learning_rate": 5.99090318388564e-05,
|
1027 |
+
"loss": 0.1861,
|
1028 |
+
"step": 1250
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 22.105263157894736,
|
1032 |
+
"grad_norm": 0.7829120755195618,
|
1033 |
+
"learning_rate": 5.860948667966212e-05,
|
1034 |
+
"loss": 0.1911,
|
1035 |
+
"step": 1260
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 22.280701754385966,
|
1039 |
+
"grad_norm": 0.8304038643836975,
|
1040 |
+
"learning_rate": 5.7309941520467835e-05,
|
1041 |
+
"loss": 0.1595,
|
1042 |
+
"step": 1270
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 22.45614035087719,
|
1046 |
+
"grad_norm": 0.9477715492248535,
|
1047 |
+
"learning_rate": 5.6010396361273556e-05,
|
1048 |
+
"loss": 0.2207,
|
1049 |
+
"step": 1280
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 22.63157894736842,
|
1053 |
+
"grad_norm": 1.6679517030715942,
|
1054 |
+
"learning_rate": 5.471085120207927e-05,
|
1055 |
+
"loss": 0.1885,
|
1056 |
+
"step": 1290
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 22.80701754385965,
|
1060 |
+
"grad_norm": 1.945037603378296,
|
1061 |
+
"learning_rate": 5.341130604288499e-05,
|
1062 |
+
"loss": 0.1808,
|
1063 |
+
"step": 1300
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 22.80701754385965,
|
1067 |
+
"eval_accuracy": 0.9346666666666666,
|
1068 |
+
"eval_f1": 0.8296639629200464,
|
1069 |
+
"eval_loss": 0.16815528273582458,
|
1070 |
+
"eval_precision": 0.8267898383371824,
|
1071 |
+
"eval_recall": 0.8325581395348837,
|
1072 |
+
"eval_runtime": 2.4881,
|
1073 |
+
"eval_samples_per_second": 90.429,
|
1074 |
+
"eval_steps_per_second": 11.655,
|
1075 |
+
"step": 1300
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 22.982456140350877,
|
1079 |
+
"grad_norm": 0.7030972242355347,
|
1080 |
+
"learning_rate": 5.2111760883690706e-05,
|
1081 |
+
"loss": 0.1717,
|
1082 |
+
"step": 1310
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 23.157894736842106,
|
1086 |
+
"grad_norm": 1.0622111558914185,
|
1087 |
+
"learning_rate": 5.081221572449643e-05,
|
1088 |
+
"loss": 0.2162,
|
1089 |
+
"step": 1320
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 23.333333333333332,
|
1093 |
+
"grad_norm": 1.3687249422073364,
|
1094 |
+
"learning_rate": 4.951267056530214e-05,
|
1095 |
+
"loss": 0.197,
|
1096 |
+
"step": 1330
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 23.50877192982456,
|
1100 |
+
"grad_norm": 1.218827724456787,
|
1101 |
+
"learning_rate": 4.821312540610786e-05,
|
1102 |
+
"loss": 0.1811,
|
1103 |
+
"step": 1340
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 23.68421052631579,
|
1107 |
+
"grad_norm": 3.9379024505615234,
|
1108 |
+
"learning_rate": 4.691358024691358e-05,
|
1109 |
+
"loss": 0.1896,
|
1110 |
+
"step": 1350
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 23.859649122807017,
|
1114 |
+
"grad_norm": 0.9299766421318054,
|
1115 |
+
"learning_rate": 4.56140350877193e-05,
|
1116 |
+
"loss": 0.1663,
|
1117 |
+
"step": 1360
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 24.035087719298247,
|
1121 |
+
"grad_norm": 4.373446941375732,
|
1122 |
+
"learning_rate": 4.431448992852502e-05,
|
1123 |
+
"loss": 0.1883,
|
1124 |
+
"step": 1370
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 24.210526315789473,
|
1128 |
+
"grad_norm": 1.0416285991668701,
|
1129 |
+
"learning_rate": 4.301494476933073e-05,
|
1130 |
+
"loss": 0.1884,
|
1131 |
+
"step": 1380
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 24.385964912280702,
|
1135 |
+
"grad_norm": 1.9816950559616089,
|
1136 |
+
"learning_rate": 4.1715399610136454e-05,
|
1137 |
+
"loss": 0.1949,
|
1138 |
+
"step": 1390
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 24.56140350877193,
|
1142 |
+
"grad_norm": 1.6888455152511597,
|
1143 |
+
"learning_rate": 4.041585445094217e-05,
|
1144 |
+
"loss": 0.1792,
|
1145 |
+
"step": 1400
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 24.56140350877193,
|
1149 |
+
"eval_accuracy": 0.9364444444444444,
|
1150 |
+
"eval_f1": 0.8323563892145369,
|
1151 |
+
"eval_loss": 0.16882646083831787,
|
1152 |
+
"eval_precision": 0.8392434988179669,
|
1153 |
+
"eval_recall": 0.8255813953488372,
|
1154 |
+
"eval_runtime": 1.8209,
|
1155 |
+
"eval_samples_per_second": 123.562,
|
1156 |
+
"eval_steps_per_second": 15.926,
|
1157 |
+
"step": 1400
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 24.736842105263158,
|
1161 |
+
"grad_norm": 0.6522326469421387,
|
1162 |
+
"learning_rate": 3.911630929174789e-05,
|
1163 |
+
"loss": 0.149,
|
1164 |
+
"step": 1410
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 24.912280701754387,
|
1168 |
+
"grad_norm": 1.053612470626831,
|
1169 |
+
"learning_rate": 3.7816764132553604e-05,
|
1170 |
+
"loss": 0.1983,
|
1171 |
+
"step": 1420
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 25.087719298245613,
|
1175 |
+
"grad_norm": 1.025525689125061,
|
1176 |
+
"learning_rate": 3.664717348927875e-05,
|
1177 |
+
"loss": 0.1973,
|
1178 |
+
"step": 1430
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 25.263157894736842,
|
1182 |
+
"grad_norm": 2.1537649631500244,
|
1183 |
+
"learning_rate": 3.534762833008447e-05,
|
1184 |
+
"loss": 0.1797,
|
1185 |
+
"step": 1440
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 25.43859649122807,
|
1189 |
+
"grad_norm": 2.6327617168426514,
|
1190 |
+
"learning_rate": 3.404808317089019e-05,
|
1191 |
+
"loss": 0.1693,
|
1192 |
+
"step": 1450
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 25.614035087719298,
|
1196 |
+
"grad_norm": 1.1369807720184326,
|
1197 |
+
"learning_rate": 3.274853801169591e-05,
|
1198 |
+
"loss": 0.1826,
|
1199 |
+
"step": 1460
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 25.789473684210527,
|
1203 |
+
"grad_norm": 2.0842247009277344,
|
1204 |
+
"learning_rate": 3.1448992852501624e-05,
|
1205 |
+
"loss": 0.1778,
|
1206 |
+
"step": 1470
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 25.964912280701753,
|
1210 |
+
"grad_norm": 0.8993640542030334,
|
1211 |
+
"learning_rate": 3.014944769330734e-05,
|
1212 |
+
"loss": 0.1688,
|
1213 |
+
"step": 1480
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 26.140350877192983,
|
1217 |
+
"grad_norm": 0.9640088677406311,
|
1218 |
+
"learning_rate": 2.8979857050032487e-05,
|
1219 |
+
"loss": 0.2139,
|
1220 |
+
"step": 1490
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 26.31578947368421,
|
1224 |
+
"grad_norm": 1.134974718093872,
|
1225 |
+
"learning_rate": 2.7680311890838205e-05,
|
1226 |
+
"loss": 0.1852,
|
1227 |
+
"step": 1500
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 26.31578947368421,
|
1231 |
+
"eval_accuracy": 0.9337777777777778,
|
1232 |
+
"eval_f1": 0.826945412311266,
|
1233 |
+
"eval_loss": 0.1725098043680191,
|
1234 |
+
"eval_precision": 0.8259860788863109,
|
1235 |
+
"eval_recall": 0.827906976744186,
|
1236 |
+
"eval_runtime": 1.8397,
|
1237 |
+
"eval_samples_per_second": 122.305,
|
1238 |
+
"eval_steps_per_second": 15.764,
|
1239 |
+
"step": 1500
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 26.49122807017544,
|
1243 |
+
"grad_norm": 0.3995600640773773,
|
1244 |
+
"learning_rate": 2.6380766731643926e-05,
|
1245 |
+
"loss": 0.1703,
|
1246 |
+
"step": 1510
|
1247 |
+
},
|
1248 |
+
{
|
1249 |
+
"epoch": 26.666666666666668,
|
1250 |
+
"grad_norm": 1.8065487146377563,
|
1251 |
+
"learning_rate": 2.5081221572449644e-05,
|
1252 |
+
"loss": 0.2017,
|
1253 |
+
"step": 1520
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 26.842105263157894,
|
1257 |
+
"grad_norm": 2.3725926876068115,
|
1258 |
+
"learning_rate": 2.378167641325536e-05,
|
1259 |
+
"loss": 0.1926,
|
1260 |
+
"step": 1530
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"epoch": 27.017543859649123,
|
1264 |
+
"grad_norm": 1.9128490686416626,
|
1265 |
+
"learning_rate": 2.248213125406108e-05,
|
1266 |
+
"loss": 0.1771,
|
1267 |
+
"step": 1540
|
1268 |
+
},
|
1269 |
+
{
|
1270 |
+
"epoch": 27.19298245614035,
|
1271 |
+
"grad_norm": 1.2254141569137573,
|
1272 |
+
"learning_rate": 2.1182586094866797e-05,
|
1273 |
+
"loss": 0.1791,
|
1274 |
+
"step": 1550
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 27.36842105263158,
|
1278 |
+
"grad_norm": 1.3266674280166626,
|
1279 |
+
"learning_rate": 1.9883040935672515e-05,
|
1280 |
+
"loss": 0.1671,
|
1281 |
+
"step": 1560
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 27.54385964912281,
|
1285 |
+
"grad_norm": 1.2818776369094849,
|
1286 |
+
"learning_rate": 1.8583495776478232e-05,
|
1287 |
+
"loss": 0.17,
|
1288 |
+
"step": 1570
|
1289 |
+
},
|
1290 |
+
{
|
1291 |
+
"epoch": 27.719298245614034,
|
1292 |
+
"grad_norm": 1.0659555196762085,
|
1293 |
+
"learning_rate": 1.728395061728395e-05,
|
1294 |
+
"loss": 0.1712,
|
1295 |
+
"step": 1580
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 27.894736842105264,
|
1299 |
+
"grad_norm": 1.0451716184616089,
|
1300 |
+
"learning_rate": 1.5984405458089668e-05,
|
1301 |
+
"loss": 0.1854,
|
1302 |
+
"step": 1590
|
1303 |
+
},
|
1304 |
+
{
|
1305 |
+
"epoch": 28.07017543859649,
|
1306 |
+
"grad_norm": 2.3844401836395264,
|
1307 |
+
"learning_rate": 1.4684860298895387e-05,
|
1308 |
+
"loss": 0.177,
|
1309 |
+
"step": 1600
|
1310 |
+
},
|
1311 |
+
{
|
1312 |
+
"epoch": 28.07017543859649,
|
1313 |
+
"eval_accuracy": 0.9351111111111111,
|
1314 |
+
"eval_f1": 0.8282352941176471,
|
1315 |
+
"eval_loss": 0.16903221607208252,
|
1316 |
+
"eval_precision": 0.8380952380952381,
|
1317 |
+
"eval_recall": 0.8186046511627907,
|
1318 |
+
"eval_runtime": 2.2907,
|
1319 |
+
"eval_samples_per_second": 98.225,
|
1320 |
+
"eval_steps_per_second": 12.66,
|
1321 |
+
"step": 1600
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 28.24561403508772,
|
1325 |
+
"grad_norm": 1.8458149433135986,
|
1326 |
+
"learning_rate": 1.3385315139701105e-05,
|
1327 |
+
"loss": 0.2091,
|
1328 |
+
"step": 1610
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 28.42105263157895,
|
1332 |
+
"grad_norm": 0.7621822953224182,
|
1333 |
+
"learning_rate": 1.2085769980506823e-05,
|
1334 |
+
"loss": 0.1626,
|
1335 |
+
"step": 1620
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 28.596491228070175,
|
1339 |
+
"grad_norm": 0.9533030986785889,
|
1340 |
+
"learning_rate": 1.078622482131254e-05,
|
1341 |
+
"loss": 0.1872,
|
1342 |
+
"step": 1630
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 28.771929824561404,
|
1346 |
+
"grad_norm": 1.495856761932373,
|
1347 |
+
"learning_rate": 9.486679662118258e-06,
|
1348 |
+
"loss": 0.1816,
|
1349 |
+
"step": 1640
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 28.94736842105263,
|
1353 |
+
"grad_norm": 1.397376537322998,
|
1354 |
+
"learning_rate": 8.187134502923977e-06,
|
1355 |
+
"loss": 0.1821,
|
1356 |
+
"step": 1650
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 29.12280701754386,
|
1360 |
+
"grad_norm": 2.07928729057312,
|
1361 |
+
"learning_rate": 6.887589343729694e-06,
|
1362 |
+
"loss": 0.1801,
|
1363 |
+
"step": 1660
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"epoch": 29.29824561403509,
|
1367 |
+
"grad_norm": 1.2872428894042969,
|
1368 |
+
"learning_rate": 5.588044184535413e-06,
|
1369 |
+
"loss": 0.1835,
|
1370 |
+
"step": 1670
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 29.473684210526315,
|
1374 |
+
"grad_norm": 0.40397679805755615,
|
1375 |
+
"learning_rate": 4.2884990253411305e-06,
|
1376 |
+
"loss": 0.1597,
|
1377 |
+
"step": 1680
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 29.649122807017545,
|
1381 |
+
"grad_norm": 1.12138032913208,
|
1382 |
+
"learning_rate": 2.9889538661468487e-06,
|
1383 |
+
"loss": 0.1771,
|
1384 |
+
"step": 1690
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 29.82456140350877,
|
1388 |
+
"grad_norm": 1.8918460607528687,
|
1389 |
+
"learning_rate": 1.6894087069525666e-06,
|
1390 |
+
"loss": 0.1857,
|
1391 |
+
"step": 1700
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 29.82456140350877,
|
1395 |
+
"eval_accuracy": 0.9297777777777778,
|
1396 |
+
"eval_f1": 0.8175519630484989,
|
1397 |
+
"eval_loss": 0.17081834375858307,
|
1398 |
+
"eval_precision": 0.8119266055045872,
|
1399 |
+
"eval_recall": 0.8232558139534883,
|
1400 |
+
"eval_runtime": 1.7795,
|
1401 |
+
"eval_samples_per_second": 126.443,
|
1402 |
+
"eval_steps_per_second": 16.297,
|
1403 |
+
"step": 1700
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 30.0,
|
1407 |
+
"grad_norm": 1.7220489978790283,
|
1408 |
+
"learning_rate": 3.898635477582846e-07,
|
1409 |
+
"loss": 0.166,
|
1410 |
+
"step": 1710
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 30.0,
|
1414 |
+
"step": 1710,
|
1415 |
+
"total_flos": 3.8465920659456e+16,
|
1416 |
+
"train_loss": 0.2702594916025797,
|
1417 |
+
"train_runtime": 403.8981,
|
1418 |
+
"train_samples_per_second": 66.849,
|
1419 |
+
"train_steps_per_second": 4.234
|
1420 |
+
}
|
1421 |
+
],
|
1422 |
+
"logging_steps": 10,
|
1423 |
+
"max_steps": 1710,
|
1424 |
+
"num_input_tokens_seen": 0,
|
1425 |
+
"num_train_epochs": 30,
|
1426 |
+
"save_steps": 500,
|
1427 |
+
"stateful_callbacks": {
|
1428 |
+
"TrainerControl": {
|
1429 |
+
"args": {
|
1430 |
+
"should_epoch_stop": false,
|
1431 |
+
"should_evaluate": false,
|
1432 |
+
"should_log": false,
|
1433 |
+
"should_save": true,
|
1434 |
+
"should_training_stop": true
|
1435 |
+
},
|
1436 |
+
"attributes": {}
|
1437 |
+
}
|
1438 |
+
},
|
1439 |
+
"total_flos": 3.8465920659456e+16,
|
1440 |
+
"train_batch_size": 16,
|
1441 |
+
"trial_name": null,
|
1442 |
+
"trial_params": null
|
1443 |
+
}
|