vuongnhathien
commited on
Commit
•
c3e0188
1
Parent(s):
a488e2d
End of training
Browse files- README.md +3 -3
- all_results.json +8 -0
- runs/May26_18-10-54_f45edd2af2fb/events.out.tfevents.1716765512.f45edd2af2fb.26.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1653 -0
README.md
CHANGED
@@ -22,7 +22,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.9378968253968254
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.2863
|
36 |
+
- Accuracy: 0.9379
|
37 |
|
38 |
## Model description
|
39 |
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"total_flos": 4.09349935387607e+19,
|
4 |
+
"train_loss": 0.2596938943081926,
|
5 |
+
"train_runtime": 18130.6882,
|
6 |
+
"train_samples_per_second": 9.697,
|
7 |
+
"train_steps_per_second": 1.212
|
8 |
+
}
|
runs/May26_18-10-54_f45edd2af2fb/events.out.tfevents.1716765512.f45edd2af2fb.26.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a97cec914e57d6d5bd2bd535e26523842b8d24ef5c4f9c0edb733ad4083eb64c
|
3 |
+
size 417
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"total_flos": 4.09349935387607e+19,
|
4 |
+
"train_loss": 0.2596938943081926,
|
5 |
+
"train_runtime": 18130.6882,
|
6 |
+
"train_samples_per_second": 9.697,
|
7 |
+
"train_steps_per_second": 1.212
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1653 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3029824197292328,
|
3 |
+
"best_model_checkpoint": "./convnext-base-3e-5-batch-8/checkpoint-8792",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 21980,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05,
|
13 |
+
"grad_norm": 20.464111328125,
|
14 |
+
"learning_rate": 2.999846786074732e-05,
|
15 |
+
"loss": 2.7431,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.09,
|
20 |
+
"grad_norm": 26.436141967773438,
|
21 |
+
"learning_rate": 2.999387175598269e-05,
|
22 |
+
"loss": 1.6104,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.14,
|
27 |
+
"grad_norm": 54.28024673461914,
|
28 |
+
"learning_rate": 2.998621262462245e-05,
|
29 |
+
"loss": 1.2012,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.18,
|
34 |
+
"grad_norm": 53.153194427490234,
|
35 |
+
"learning_rate": 2.9975492031314045e-05,
|
36 |
+
"loss": 0.974,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.23,
|
41 |
+
"grad_norm": 38.65731430053711,
|
42 |
+
"learning_rate": 2.996171216611638e-05,
|
43 |
+
"loss": 0.8435,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.27,
|
48 |
+
"grad_norm": 23.02427101135254,
|
49 |
+
"learning_rate": 2.994487584405244e-05,
|
50 |
+
"loss": 0.7449,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.32,
|
55 |
+
"grad_norm": 19.776226043701172,
|
56 |
+
"learning_rate": 2.992498650453421e-05,
|
57 |
+
"loss": 0.6626,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.36,
|
62 |
+
"grad_norm": 19.967565536499023,
|
63 |
+
"learning_rate": 2.990204821066006e-05,
|
64 |
+
"loss": 0.5485,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.41,
|
69 |
+
"grad_norm": 32.89971923828125,
|
70 |
+
"learning_rate": 2.9876065648384715e-05,
|
71 |
+
"loss": 0.6233,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.45,
|
76 |
+
"grad_norm": 23.158945083618164,
|
77 |
+
"learning_rate": 2.984704412556199e-05,
|
78 |
+
"loss": 0.595,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.5,
|
83 |
+
"grad_norm": 33.01531219482422,
|
84 |
+
"learning_rate": 2.981498957086044e-05,
|
85 |
+
"loss": 0.5844,
|
86 |
+
"step": 1100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.55,
|
90 |
+
"grad_norm": 36.02910614013672,
|
91 |
+
"learning_rate": 2.977990853255228e-05,
|
92 |
+
"loss": 0.4787,
|
93 |
+
"step": 1200
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.59,
|
97 |
+
"grad_norm": 25.670297622680664,
|
98 |
+
"learning_rate": 2.974180817717561e-05,
|
99 |
+
"loss": 0.6183,
|
100 |
+
"step": 1300
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.64,
|
104 |
+
"grad_norm": 16.535247802734375,
|
105 |
+
"learning_rate": 2.970069628807043e-05,
|
106 |
+
"loss": 0.509,
|
107 |
+
"step": 1400
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.68,
|
111 |
+
"grad_norm": 20.26650047302246,
|
112 |
+
"learning_rate": 2.965658126378862e-05,
|
113 |
+
"loss": 0.5619,
|
114 |
+
"step": 1500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.73,
|
118 |
+
"grad_norm": 51.08666229248047,
|
119 |
+
"learning_rate": 2.9609472116378222e-05,
|
120 |
+
"loss": 0.4814,
|
121 |
+
"step": 1600
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.77,
|
125 |
+
"grad_norm": 13.978100776672363,
|
126 |
+
"learning_rate": 2.955937846954242e-05,
|
127 |
+
"loss": 0.4695,
|
128 |
+
"step": 1700
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.82,
|
132 |
+
"grad_norm": 2.855776071548462,
|
133 |
+
"learning_rate": 2.9506310556673573e-05,
|
134 |
+
"loss": 0.5061,
|
135 |
+
"step": 1800
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.86,
|
139 |
+
"grad_norm": 5.468057155609131,
|
140 |
+
"learning_rate": 2.945027921876265e-05,
|
141 |
+
"loss": 0.5227,
|
142 |
+
"step": 1900
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.91,
|
146 |
+
"grad_norm": 2.113645315170288,
|
147 |
+
"learning_rate": 2.9391295902184625e-05,
|
148 |
+
"loss": 0.4312,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.96,
|
153 |
+
"grad_norm": 37.98606872558594,
|
154 |
+
"learning_rate": 2.93293726563601e-05,
|
155 |
+
"loss": 0.5851,
|
156 |
+
"step": 2100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.0,
|
160 |
+
"eval_accuracy": 0.8918489065606362,
|
161 |
+
"eval_loss": 0.38079071044921875,
|
162 |
+
"eval_runtime": 114.5109,
|
163 |
+
"eval_samples_per_second": 21.963,
|
164 |
+
"eval_steps_per_second": 2.751,
|
165 |
+
"step": 2198
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 1.0,
|
169 |
+
"grad_norm": 20.0971622467041,
|
170 |
+
"learning_rate": 2.9264522131293818e-05,
|
171 |
+
"loss": 0.5127,
|
172 |
+
"step": 2200
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 1.05,
|
176 |
+
"grad_norm": 26.824159622192383,
|
177 |
+
"learning_rate": 2.919675757499045e-05,
|
178 |
+
"loss": 0.3676,
|
179 |
+
"step": 2300
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 1.09,
|
183 |
+
"grad_norm": 14.176966667175293,
|
184 |
+
"learning_rate": 2.9126092830748217e-05,
|
185 |
+
"loss": 0.3944,
|
186 |
+
"step": 2400
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 1.14,
|
190 |
+
"grad_norm": 31.566120147705078,
|
191 |
+
"learning_rate": 2.9052542334330916e-05,
|
192 |
+
"loss": 0.3678,
|
193 |
+
"step": 2500
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 1.18,
|
197 |
+
"grad_norm": 30.576416015625,
|
198 |
+
"learning_rate": 2.897612111101888e-05,
|
199 |
+
"loss": 0.465,
|
200 |
+
"step": 2600
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.23,
|
204 |
+
"grad_norm": 52.94912338256836,
|
205 |
+
"learning_rate": 2.889684477253959e-05,
|
206 |
+
"loss": 0.3741,
|
207 |
+
"step": 2700
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 1.27,
|
211 |
+
"grad_norm": 26.88067054748535,
|
212 |
+
"learning_rate": 2.8814729513878365e-05,
|
213 |
+
"loss": 0.3993,
|
214 |
+
"step": 2800
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 1.32,
|
218 |
+
"grad_norm": 26.82840919494629,
|
219 |
+
"learning_rate": 2.8729792109970015e-05,
|
220 |
+
"loss": 0.3801,
|
221 |
+
"step": 2900
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.36,
|
225 |
+
"grad_norm": 52.661399841308594,
|
226 |
+
"learning_rate": 2.864204991227195e-05,
|
227 |
+
"loss": 0.326,
|
228 |
+
"step": 3000
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 1.41,
|
232 |
+
"grad_norm": 11.977348327636719,
|
233 |
+
"learning_rate": 2.855152084521953e-05,
|
234 |
+
"loss": 0.3646,
|
235 |
+
"step": 3100
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 1.46,
|
239 |
+
"grad_norm": 28.014543533325195,
|
240 |
+
"learning_rate": 2.8458223402564366e-05,
|
241 |
+
"loss": 0.3409,
|
242 |
+
"step": 3200
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.5,
|
246 |
+
"grad_norm": 1.3806567192077637,
|
247 |
+
"learning_rate": 2.836217664359634e-05,
|
248 |
+
"loss": 0.467,
|
249 |
+
"step": 3300
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 1.55,
|
253 |
+
"grad_norm": 33.71268844604492,
|
254 |
+
"learning_rate": 2.826340018925006e-05,
|
255 |
+
"loss": 0.4337,
|
256 |
+
"step": 3400
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 1.59,
|
260 |
+
"grad_norm": 34.983802795410156,
|
261 |
+
"learning_rate": 2.8161914218096568e-05,
|
262 |
+
"loss": 0.3762,
|
263 |
+
"step": 3500
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 1.64,
|
267 |
+
"grad_norm": 23.66938591003418,
|
268 |
+
"learning_rate": 2.8057739462221215e-05,
|
269 |
+
"loss": 0.4465,
|
270 |
+
"step": 3600
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 1.68,
|
274 |
+
"grad_norm": 16.07572364807129,
|
275 |
+
"learning_rate": 2.7950897202988338e-05,
|
276 |
+
"loss": 0.3359,
|
277 |
+
"step": 3700
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 1.73,
|
281 |
+
"grad_norm": 25.094499588012695,
|
282 |
+
"learning_rate": 2.7841409266693838e-05,
|
283 |
+
"loss": 0.4376,
|
284 |
+
"step": 3800
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.77,
|
288 |
+
"grad_norm": 44.122901916503906,
|
289 |
+
"learning_rate": 2.7729298020106363e-05,
|
290 |
+
"loss": 0.3529,
|
291 |
+
"step": 3900
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 1.82,
|
295 |
+
"grad_norm": 29.057430267333984,
|
296 |
+
"learning_rate": 2.761458636589813e-05,
|
297 |
+
"loss": 0.3423,
|
298 |
+
"step": 4000
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 1.87,
|
302 |
+
"grad_norm": 39.68132019042969,
|
303 |
+
"learning_rate": 2.7497297737966217e-05,
|
304 |
+
"loss": 0.3745,
|
305 |
+
"step": 4100
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 1.91,
|
309 |
+
"grad_norm": 25.461807250976562,
|
310 |
+
"learning_rate": 2.7377456096645395e-05,
|
311 |
+
"loss": 0.4214,
|
312 |
+
"step": 4200
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 1.96,
|
316 |
+
"grad_norm": 34.991153717041016,
|
317 |
+
"learning_rate": 2.725508592381337e-05,
|
318 |
+
"loss": 0.3975,
|
319 |
+
"step": 4300
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 2.0,
|
323 |
+
"eval_accuracy": 0.9093439363817097,
|
324 |
+
"eval_loss": 0.3232283592224121,
|
325 |
+
"eval_runtime": 114.6327,
|
326 |
+
"eval_samples_per_second": 21.94,
|
327 |
+
"eval_steps_per_second": 2.748,
|
328 |
+
"step": 4396
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 2.0,
|
332 |
+
"grad_norm": 23.15580177307129,
|
333 |
+
"learning_rate": 2.7130212217889484e-05,
|
334 |
+
"loss": 0.3681,
|
335 |
+
"step": 4400
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 2.05,
|
339 |
+
"grad_norm": 28.531185150146484,
|
340 |
+
"learning_rate": 2.7002860488727944e-05,
|
341 |
+
"loss": 0.3262,
|
342 |
+
"step": 4500
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 2.09,
|
346 |
+
"grad_norm": 38.52848434448242,
|
347 |
+
"learning_rate": 2.6873056752406504e-05,
|
348 |
+
"loss": 0.3097,
|
349 |
+
"step": 4600
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 2.14,
|
353 |
+
"grad_norm": 1.2146570682525635,
|
354 |
+
"learning_rate": 2.6740827525911766e-05,
|
355 |
+
"loss": 0.4274,
|
356 |
+
"step": 4700
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 2.18,
|
360 |
+
"grad_norm": 19.732980728149414,
|
361 |
+
"learning_rate": 2.6606199821722166e-05,
|
362 |
+
"loss": 0.268,
|
363 |
+
"step": 4800
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 2.23,
|
367 |
+
"grad_norm": 15.875640869140625,
|
368 |
+
"learning_rate": 2.646920114228972e-05,
|
369 |
+
"loss": 0.2734,
|
370 |
+
"step": 4900
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 2.27,
|
374 |
+
"grad_norm": 18.1243953704834,
|
375 |
+
"learning_rate": 2.632985947442167e-05,
|
376 |
+
"loss": 0.2739,
|
377 |
+
"step": 5000
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 2.32,
|
381 |
+
"grad_norm": 17.237104415893555,
|
382 |
+
"learning_rate": 2.6188203283563198e-05,
|
383 |
+
"loss": 0.2917,
|
384 |
+
"step": 5100
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 2.37,
|
388 |
+
"grad_norm": 18.371570587158203,
|
389 |
+
"learning_rate": 2.6044261507982356e-05,
|
390 |
+
"loss": 0.3551,
|
391 |
+
"step": 5200
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 2.41,
|
395 |
+
"grad_norm": 14.930416107177734,
|
396 |
+
"learning_rate": 2.589806355285841e-05,
|
397 |
+
"loss": 0.3264,
|
398 |
+
"step": 5300
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 2.46,
|
402 |
+
"grad_norm": 30.236698150634766,
|
403 |
+
"learning_rate": 2.5749639284274782e-05,
|
404 |
+
"loss": 0.3388,
|
405 |
+
"step": 5400
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 2.5,
|
409 |
+
"grad_norm": 0.13715609908103943,
|
410 |
+
"learning_rate": 2.5599019023117872e-05,
|
411 |
+
"loss": 0.2575,
|
412 |
+
"step": 5500
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 2.55,
|
416 |
+
"grad_norm": 6.84519624710083,
|
417 |
+
"learning_rate": 2.5446233538882924e-05,
|
418 |
+
"loss": 0.3263,
|
419 |
+
"step": 5600
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 2.59,
|
423 |
+
"grad_norm": 58.51634979248047,
|
424 |
+
"learning_rate": 2.5291314043388295e-05,
|
425 |
+
"loss": 0.3716,
|
426 |
+
"step": 5700
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 2.64,
|
430 |
+
"grad_norm": 0.961408257484436,
|
431 |
+
"learning_rate": 2.513429218439932e-05,
|
432 |
+
"loss": 0.3012,
|
433 |
+
"step": 5800
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 2.68,
|
437 |
+
"grad_norm": 13.59073257446289,
|
438 |
+
"learning_rate": 2.497520003916316e-05,
|
439 |
+
"loss": 0.2911,
|
440 |
+
"step": 5900
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 2.73,
|
444 |
+
"grad_norm": 12.26279354095459,
|
445 |
+
"learning_rate": 2.4814070107855878e-05,
|
446 |
+
"loss": 0.279,
|
447 |
+
"step": 6000
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 2.78,
|
451 |
+
"grad_norm": 30.789432525634766,
|
452 |
+
"learning_rate": 2.465093530694315e-05,
|
453 |
+
"loss": 0.29,
|
454 |
+
"step": 6100
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 2.82,
|
458 |
+
"grad_norm": 0.28742390871047974,
|
459 |
+
"learning_rate": 2.448582896245591e-05,
|
460 |
+
"loss": 0.3051,
|
461 |
+
"step": 6200
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 2.87,
|
465 |
+
"grad_norm": 2.97086501121521,
|
466 |
+
"learning_rate": 2.4318784803182317e-05,
|
467 |
+
"loss": 0.2735,
|
468 |
+
"step": 6300
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 2.91,
|
472 |
+
"grad_norm": 32.147727966308594,
|
473 |
+
"learning_rate": 2.4149836953777488e-05,
|
474 |
+
"loss": 0.2992,
|
475 |
+
"step": 6400
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 2.96,
|
479 |
+
"grad_norm": 28.64170265197754,
|
480 |
+
"learning_rate": 2.3979019927792315e-05,
|
481 |
+
"loss": 0.3337,
|
482 |
+
"step": 6500
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 3.0,
|
486 |
+
"eval_accuracy": 0.925248508946322,
|
487 |
+
"eval_loss": 0.3209765553474426,
|
488 |
+
"eval_runtime": 113.6693,
|
489 |
+
"eval_samples_per_second": 22.126,
|
490 |
+
"eval_steps_per_second": 2.771,
|
491 |
+
"step": 6594
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 3.0,
|
495 |
+
"grad_norm": 14.05492115020752,
|
496 |
+
"learning_rate": 2.3806368620622876e-05,
|
497 |
+
"loss": 0.3353,
|
498 |
+
"step": 6600
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 3.05,
|
502 |
+
"grad_norm": 5.791962623596191,
|
503 |
+
"learning_rate": 2.3631918302381803e-05,
|
504 |
+
"loss": 0.2148,
|
505 |
+
"step": 6700
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 3.09,
|
509 |
+
"grad_norm": 0.8230623602867126,
|
510 |
+
"learning_rate": 2.345570461069312e-05,
|
511 |
+
"loss": 0.267,
|
512 |
+
"step": 6800
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 3.14,
|
516 |
+
"grad_norm": 0.2485540211200714,
|
517 |
+
"learning_rate": 2.327776354341202e-05,
|
518 |
+
"loss": 0.2472,
|
519 |
+
"step": 6900
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 3.18,
|
523 |
+
"grad_norm": 0.06697408854961395,
|
524 |
+
"learning_rate": 2.3098131451271016e-05,
|
525 |
+
"loss": 0.2568,
|
526 |
+
"step": 7000
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 3.23,
|
530 |
+
"grad_norm": 5.22568941116333,
|
531 |
+
"learning_rate": 2.291684503045402e-05,
|
532 |
+
"loss": 0.2392,
|
533 |
+
"step": 7100
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 3.28,
|
537 |
+
"grad_norm": 58.771671295166016,
|
538 |
+
"learning_rate": 2.2733941315099883e-05,
|
539 |
+
"loss": 0.2867,
|
540 |
+
"step": 7200
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 3.32,
|
544 |
+
"grad_norm": 21.552099227905273,
|
545 |
+
"learning_rate": 2.2549457669736836e-05,
|
546 |
+
"loss": 0.2652,
|
547 |
+
"step": 7300
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 3.37,
|
551 |
+
"grad_norm": 1.265632152557373,
|
552 |
+
"learning_rate": 2.2363431781649483e-05,
|
553 |
+
"loss": 0.2284,
|
554 |
+
"step": 7400
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 3.41,
|
558 |
+
"grad_norm": 5.533514499664307,
|
559 |
+
"learning_rate": 2.2175901653179847e-05,
|
560 |
+
"loss": 0.232,
|
561 |
+
"step": 7500
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 3.46,
|
565 |
+
"grad_norm": 0.05318501219153404,
|
566 |
+
"learning_rate": 2.1986905593964048e-05,
|
567 |
+
"loss": 0.2094,
|
568 |
+
"step": 7600
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 3.5,
|
572 |
+
"grad_norm": 20.877737045288086,
|
573 |
+
"learning_rate": 2.1796482213106203e-05,
|
574 |
+
"loss": 0.3036,
|
575 |
+
"step": 7700
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 3.55,
|
579 |
+
"grad_norm": 43.25149917602539,
|
580 |
+
"learning_rate": 2.1604670411291174e-05,
|
581 |
+
"loss": 0.2388,
|
582 |
+
"step": 7800
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 3.59,
|
586 |
+
"grad_norm": 15.92627239227295,
|
587 |
+
"learning_rate": 2.1411509372837724e-05,
|
588 |
+
"loss": 0.3357,
|
589 |
+
"step": 7900
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 3.64,
|
593 |
+
"grad_norm": 12.71852970123291,
|
594 |
+
"learning_rate": 2.121703855769373e-05,
|
595 |
+
"loss": 0.2069,
|
596 |
+
"step": 8000
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 3.69,
|
600 |
+
"grad_norm": 12.913580894470215,
|
601 |
+
"learning_rate": 2.102129769337511e-05,
|
602 |
+
"loss": 0.2867,
|
603 |
+
"step": 8100
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 3.73,
|
607 |
+
"grad_norm": 0.06732411682605743,
|
608 |
+
"learning_rate": 2.0824326766850072e-05,
|
609 |
+
"loss": 0.28,
|
610 |
+
"step": 8200
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 3.78,
|
614 |
+
"grad_norm": 12.845504760742188,
|
615 |
+
"learning_rate": 2.0626166016370375e-05,
|
616 |
+
"loss": 0.2245,
|
617 |
+
"step": 8300
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 3.82,
|
621 |
+
"grad_norm": 0.00928166788071394,
|
622 |
+
"learning_rate": 2.042685592325123e-05,
|
623 |
+
"loss": 0.2359,
|
624 |
+
"step": 8400
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 3.87,
|
628 |
+
"grad_norm": 9.65197467803955,
|
629 |
+
"learning_rate": 2.0226437203601602e-05,
|
630 |
+
"loss": 0.2984,
|
631 |
+
"step": 8500
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 3.91,
|
635 |
+
"grad_norm": 25.082759857177734,
|
636 |
+
"learning_rate": 2.0024950800006463e-05,
|
637 |
+
"loss": 0.2164,
|
638 |
+
"step": 8600
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 3.96,
|
642 |
+
"grad_norm": 9.887031555175781,
|
643 |
+
"learning_rate": 1.9822437873162863e-05,
|
644 |
+
"loss": 0.2279,
|
645 |
+
"step": 8700
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 4.0,
|
649 |
+
"eval_accuracy": 0.9308151093439364,
|
650 |
+
"eval_loss": 0.3029824197292328,
|
651 |
+
"eval_runtime": 112.1873,
|
652 |
+
"eval_samples_per_second": 22.418,
|
653 |
+
"eval_steps_per_second": 2.808,
|
654 |
+
"step": 8792
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 4.0,
|
658 |
+
"grad_norm": 6.438531398773193,
|
659 |
+
"learning_rate": 1.961893979347137e-05,
|
660 |
+
"loss": 0.2683,
|
661 |
+
"step": 8800
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 4.05,
|
665 |
+
"grad_norm": 0.2623905837535858,
|
666 |
+
"learning_rate": 1.9414498132584773e-05,
|
667 |
+
"loss": 0.2297,
|
668 |
+
"step": 8900
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 4.09,
|
672 |
+
"grad_norm": 13.5099515914917,
|
673 |
+
"learning_rate": 1.9209154654915524e-05,
|
674 |
+
"loss": 0.1985,
|
675 |
+
"step": 9000
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 4.14,
|
679 |
+
"grad_norm": 0.006642199121415615,
|
680 |
+
"learning_rate": 1.900295130910396e-05,
|
681 |
+
"loss": 0.2145,
|
682 |
+
"step": 9100
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 4.19,
|
686 |
+
"grad_norm": 41.91756057739258,
|
687 |
+
"learning_rate": 1.879593021944875e-05,
|
688 |
+
"loss": 0.2221,
|
689 |
+
"step": 9200
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 4.23,
|
693 |
+
"grad_norm": 21.074771881103516,
|
694 |
+
"learning_rate": 1.8588133677301595e-05,
|
695 |
+
"loss": 0.2129,
|
696 |
+
"step": 9300
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 4.28,
|
700 |
+
"grad_norm": 0.3562418520450592,
|
701 |
+
"learning_rate": 1.837960413242765e-05,
|
702 |
+
"loss": 0.2438,
|
703 |
+
"step": 9400
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 4.32,
|
707 |
+
"grad_norm": 40.30086898803711,
|
708 |
+
"learning_rate": 1.817038418433373e-05,
|
709 |
+
"loss": 0.2036,
|
710 |
+
"step": 9500
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 4.37,
|
714 |
+
"grad_norm": 0.014717689715325832,
|
715 |
+
"learning_rate": 1.796051657356582e-05,
|
716 |
+
"loss": 0.2003,
|
717 |
+
"step": 9600
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 4.41,
|
721 |
+
"grad_norm": 17.778074264526367,
|
722 |
+
"learning_rate": 1.7750044172977838e-05,
|
723 |
+
"loss": 0.2179,
|
724 |
+
"step": 9700
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 4.46,
|
728 |
+
"grad_norm": 5.801839351654053,
|
729 |
+
"learning_rate": 1.7539009978973312e-05,
|
730 |
+
"loss": 0.2142,
|
731 |
+
"step": 9800
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 4.5,
|
735 |
+
"grad_norm": 5.123954772949219,
|
736 |
+
"learning_rate": 1.7327457102721887e-05,
|
737 |
+
"loss": 0.1686,
|
738 |
+
"step": 9900
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 4.55,
|
742 |
+
"grad_norm": 4.904812812805176,
|
743 |
+
"learning_rate": 1.711542876135233e-05,
|
744 |
+
"loss": 0.2073,
|
745 |
+
"step": 10000
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 4.6,
|
749 |
+
"grad_norm": 15.447718620300293,
|
750 |
+
"learning_rate": 1.6902968269123902e-05,
|
751 |
+
"loss": 0.2276,
|
752 |
+
"step": 10100
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 4.64,
|
756 |
+
"grad_norm": 0.12395219504833221,
|
757 |
+
"learning_rate": 1.669011902857791e-05,
|
758 |
+
"loss": 0.1882,
|
759 |
+
"step": 10200
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 4.69,
|
763 |
+
"grad_norm": 17.49830436706543,
|
764 |
+
"learning_rate": 1.6476924521671194e-05,
|
765 |
+
"loss": 0.2127,
|
766 |
+
"step": 10300
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 4.73,
|
770 |
+
"grad_norm": 10.882052421569824,
|
771 |
+
"learning_rate": 1.6263428300893422e-05,
|
772 |
+
"loss": 0.2202,
|
773 |
+
"step": 10400
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 4.78,
|
777 |
+
"grad_norm": 37.238731384277344,
|
778 |
+
"learning_rate": 1.604967398036996e-05,
|
779 |
+
"loss": 0.1663,
|
780 |
+
"step": 10500
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 4.82,
|
784 |
+
"grad_norm": 9.180378913879395,
|
785 |
+
"learning_rate": 1.5835705226952112e-05,
|
786 |
+
"loss": 0.2547,
|
787 |
+
"step": 10600
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 4.87,
|
791 |
+
"grad_norm": 0.04440607875585556,
|
792 |
+
"learning_rate": 1.5621565751296676e-05,
|
793 |
+
"loss": 0.2186,
|
794 |
+
"step": 10700
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 4.91,
|
798 |
+
"grad_norm": 0.13343572616577148,
|
799 |
+
"learning_rate": 1.540729929893649e-05,
|
800 |
+
"loss": 0.2779,
|
801 |
+
"step": 10800
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 4.96,
|
805 |
+
"grad_norm": 1.3157250881195068,
|
806 |
+
"learning_rate": 1.5192949641343834e-05,
|
807 |
+
"loss": 0.1696,
|
808 |
+
"step": 10900
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 5.0,
|
812 |
+
"eval_accuracy": 0.9292246520874752,
|
813 |
+
"eval_loss": 0.34775686264038086,
|
814 |
+
"eval_runtime": 111.4119,
|
815 |
+
"eval_samples_per_second": 22.574,
|
816 |
+
"eval_steps_per_second": 2.827,
|
817 |
+
"step": 10990
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 5.0,
|
821 |
+
"grad_norm": 0.44680455327033997,
|
822 |
+
"learning_rate": 1.4978560566988603e-05,
|
823 |
+
"loss": 0.23,
|
824 |
+
"step": 11000
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 5.05,
|
828 |
+
"grad_norm": 0.041424062103033066,
|
829 |
+
"learning_rate": 1.4764175872392958e-05,
|
830 |
+
"loss": 0.1913,
|
831 |
+
"step": 11100
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 5.1,
|
835 |
+
"grad_norm": 2.6414008140563965,
|
836 |
+
"learning_rate": 1.454983935318433e-05,
|
837 |
+
"loss": 0.1374,
|
838 |
+
"step": 11200
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 5.14,
|
842 |
+
"grad_norm": 0.396395206451416,
|
843 |
+
"learning_rate": 1.433559479514864e-05,
|
844 |
+
"loss": 0.1807,
|
845 |
+
"step": 11300
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 5.19,
|
849 |
+
"grad_norm": 8.14771842956543,
|
850 |
+
"learning_rate": 1.4121485965285485e-05,
|
851 |
+
"loss": 0.1888,
|
852 |
+
"step": 11400
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 5.23,
|
856 |
+
"grad_norm": 0.3801160454750061,
|
857 |
+
"learning_rate": 1.3907556602867213e-05,
|
858 |
+
"loss": 0.1838,
|
859 |
+
"step": 11500
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 5.28,
|
863 |
+
"grad_norm": 1.0655605792999268,
|
864 |
+
"learning_rate": 1.3693850410503614e-05,
|
865 |
+
"loss": 0.1483,
|
866 |
+
"step": 11600
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 5.32,
|
870 |
+
"grad_norm": 0.37717050313949585,
|
871 |
+
"learning_rate": 1.3480411045214147e-05,
|
872 |
+
"loss": 0.1635,
|
873 |
+
"step": 11700
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 5.37,
|
877 |
+
"grad_norm": 0.017707068473100662,
|
878 |
+
"learning_rate": 1.326728210950942e-05,
|
879 |
+
"loss": 0.1871,
|
880 |
+
"step": 11800
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 5.41,
|
884 |
+
"grad_norm": 0.01935901865363121,
|
885 |
+
"learning_rate": 1.3054507142483875e-05,
|
886 |
+
"loss": 0.1479,
|
887 |
+
"step": 11900
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 5.46,
|
891 |
+
"grad_norm": 0.2556498050689697,
|
892 |
+
"learning_rate": 1.2842129610921378e-05,
|
893 |
+
"loss": 0.1754,
|
894 |
+
"step": 12000
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 5.51,
|
898 |
+
"grad_norm": 1.742725133895874,
|
899 |
+
"learning_rate": 1.2630192900415582e-05,
|
900 |
+
"loss": 0.2713,
|
901 |
+
"step": 12100
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 5.55,
|
905 |
+
"grad_norm": 40.924644470214844,
|
906 |
+
"learning_rate": 1.2418740306506923e-05,
|
907 |
+
"loss": 0.1909,
|
908 |
+
"step": 12200
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 5.6,
|
912 |
+
"grad_norm": 49.58342361450195,
|
913 |
+
"learning_rate": 1.2207815025837977e-05,
|
914 |
+
"loss": 0.159,
|
915 |
+
"step": 12300
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 5.64,
|
919 |
+
"grad_norm": 0.03460393100976944,
|
920 |
+
"learning_rate": 1.1997460147328984e-05,
|
921 |
+
"loss": 0.1559,
|
922 |
+
"step": 12400
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 5.69,
|
926 |
+
"grad_norm": 0.0873652920126915,
|
927 |
+
"learning_rate": 1.178771864337546e-05,
|
928 |
+
"loss": 0.1713,
|
929 |
+
"step": 12500
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 5.73,
|
933 |
+
"grad_norm": 0.1891886442899704,
|
934 |
+
"learning_rate": 1.1578633361069559e-05,
|
935 |
+
"loss": 0.2004,
|
936 |
+
"step": 12600
|
937 |
+
},
|
938 |
+
{
|
939 |
+
"epoch": 5.78,
|
940 |
+
"grad_norm": 0.3393521010875702,
|
941 |
+
"learning_rate": 1.1370247013447035e-05,
|
942 |
+
"loss": 0.1993,
|
943 |
+
"step": 12700
|
944 |
+
},
|
945 |
+
{
|
946 |
+
"epoch": 5.82,
|
947 |
+
"grad_norm": 3.934659719467163,
|
948 |
+
"learning_rate": 1.1162602170761611e-05,
|
949 |
+
"loss": 0.1507,
|
950 |
+
"step": 12800
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 5.87,
|
954 |
+
"grad_norm": 1.6851441860198975,
|
955 |
+
"learning_rate": 1.095574125178849e-05,
|
956 |
+
"loss": 0.1649,
|
957 |
+
"step": 12900
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 5.91,
|
961 |
+
"grad_norm": 74.29869079589844,
|
962 |
+
"learning_rate": 1.0749706515158863e-05,
|
963 |
+
"loss": 0.2056,
|
964 |
+
"step": 13000
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 5.96,
|
968 |
+
"grad_norm": 23.88290786743164,
|
969 |
+
"learning_rate": 1.0544540050727048e-05,
|
970 |
+
"loss": 0.1658,
|
971 |
+
"step": 13100
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 6.0,
|
975 |
+
"eval_accuracy": 0.9427435387673956,
|
976 |
+
"eval_loss": 0.3084171712398529,
|
977 |
+
"eval_runtime": 111.2598,
|
978 |
+
"eval_samples_per_second": 22.605,
|
979 |
+
"eval_steps_per_second": 2.831,
|
980 |
+
"step": 13188
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 6.01,
|
984 |
+
"grad_norm": 15.39907169342041,
|
985 |
+
"learning_rate": 1.0340283770972167e-05,
|
986 |
+
"loss": 0.2241,
|
987 |
+
"step": 13200
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 6.05,
|
991 |
+
"grad_norm": 0.004868438933044672,
|
992 |
+
"learning_rate": 1.0136979402436069e-05,
|
993 |
+
"loss": 0.1529,
|
994 |
+
"step": 13300
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 6.1,
|
998 |
+
"grad_norm": 45.70091247558594,
|
999 |
+
"learning_rate": 9.93466847719919e-06,
|
1000 |
+
"loss": 0.1543,
|
1001 |
+
"step": 13400
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 6.14,
|
1005 |
+
"grad_norm": 0.8413438200950623,
|
1006 |
+
"learning_rate": 9.733392324396167e-06,
|
1007 |
+
"loss": 0.1236,
|
1008 |
+
"step": 13500
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 6.19,
|
1012 |
+
"grad_norm": 13.94447135925293,
|
1013 |
+
"learning_rate": 9.533192061772919e-06,
|
1014 |
+
"loss": 0.1151,
|
1015 |
+
"step": 13600
|
1016 |
+
},
|
1017 |
+
{
|
1018 |
+
"epoch": 6.23,
|
1019 |
+
"grad_norm": 0.031886328011751175,
|
1020 |
+
"learning_rate": 9.334108587286877e-06,
|
1021 |
+
"loss": 0.1213,
|
1022 |
+
"step": 13700
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 6.28,
|
1026 |
+
"grad_norm": 1.3224759101867676,
|
1027 |
+
"learning_rate": 9.136182570752153e-06,
|
1028 |
+
"loss": 0.1151,
|
1029 |
+
"step": 13800
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 6.32,
|
1033 |
+
"grad_norm": 0.02312690019607544,
|
1034 |
+
"learning_rate": 8.93945444553128e-06,
|
1035 |
+
"loss": 0.1601,
|
1036 |
+
"step": 13900
|
1037 |
+
},
|
1038 |
+
{
|
1039 |
+
"epoch": 6.37,
|
1040 |
+
"grad_norm": 0.02013530395925045,
|
1041 |
+
"learning_rate": 8.743964400275304e-06,
|
1042 |
+
"loss": 0.133,
|
1043 |
+
"step": 14000
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 6.41,
|
1047 |
+
"grad_norm": 0.02437993884086609,
|
1048 |
+
"learning_rate": 8.549752370713798e-06,
|
1049 |
+
"loss": 0.1754,
|
1050 |
+
"step": 14100
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 6.46,
|
1054 |
+
"grad_norm": 0.005770612042397261,
|
1055 |
+
"learning_rate": 8.356858031496596e-06,
|
1056 |
+
"loss": 0.1421,
|
1057 |
+
"step": 14200
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"epoch": 6.51,
|
1061 |
+
"grad_norm": 0.008364029228687286,
|
1062 |
+
"learning_rate": 8.165320788088888e-06,
|
1063 |
+
"loss": 0.1988,
|
1064 |
+
"step": 14300
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 6.55,
|
1068 |
+
"grad_norm": 0.06003904342651367,
|
1069 |
+
"learning_rate": 7.975179768721187e-06,
|
1070 |
+
"loss": 0.073,
|
1071 |
+
"step": 14400
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 6.6,
|
1075 |
+
"grad_norm": 13.212935447692871,
|
1076 |
+
"learning_rate": 7.78647381639607e-06,
|
1077 |
+
"loss": 0.1858,
|
1078 |
+
"step": 14500
|
1079 |
+
},
|
1080 |
+
{
|
1081 |
+
"epoch": 6.64,
|
1082 |
+
"grad_norm": 0.03764009103178978,
|
1083 |
+
"learning_rate": 7.599241480953112e-06,
|
1084 |
+
"loss": 0.1373,
|
1085 |
+
"step": 14600
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"epoch": 6.69,
|
1089 |
+
"grad_norm": 0.01994572952389717,
|
1090 |
+
"learning_rate": 7.413521011193705e-06,
|
1091 |
+
"loss": 0.1165,
|
1092 |
+
"step": 14700
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 6.73,
|
1096 |
+
"grad_norm": 36.3884162902832,
|
1097 |
+
"learning_rate": 7.229350347067426e-06,
|
1098 |
+
"loss": 0.1989,
|
1099 |
+
"step": 14800
|
1100 |
+
},
|
1101 |
+
{
|
1102 |
+
"epoch": 6.78,
|
1103 |
+
"grad_norm": 0.005731828045099974,
|
1104 |
+
"learning_rate": 7.046767111921425e-06,
|
1105 |
+
"loss": 0.0917,
|
1106 |
+
"step": 14900
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 6.82,
|
1110 |
+
"grad_norm": 48.87177658081055,
|
1111 |
+
"learning_rate": 6.865808604814564e-06,
|
1112 |
+
"loss": 0.1263,
|
1113 |
+
"step": 15000
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 6.87,
|
1117 |
+
"grad_norm": 29.0344295501709,
|
1118 |
+
"learning_rate": 6.686511792897767e-06,
|
1119 |
+
"loss": 0.1724,
|
1120 |
+
"step": 15100
|
1121 |
+
},
|
1122 |
+
{
|
1123 |
+
"epoch": 6.92,
|
1124 |
+
"grad_norm": 0.013815321959555149,
|
1125 |
+
"learning_rate": 6.508913303862144e-06,
|
1126 |
+
"loss": 0.1795,
|
1127 |
+
"step": 15200
|
1128 |
+
},
|
1129 |
+
{
|
1130 |
+
"epoch": 6.96,
|
1131 |
+
"grad_norm": 29.06551742553711,
|
1132 |
+
"learning_rate": 6.333049418456533e-06,
|
1133 |
+
"loss": 0.1383,
|
1134 |
+
"step": 15300
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 7.0,
|
1138 |
+
"eval_accuracy": 0.9391650099403579,
|
1139 |
+
"eval_loss": 0.3318726718425751,
|
1140 |
+
"eval_runtime": 111.0425,
|
1141 |
+
"eval_samples_per_second": 22.649,
|
1142 |
+
"eval_steps_per_second": 2.837,
|
1143 |
+
"step": 15386
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 7.01,
|
1147 |
+
"grad_norm": 54.77537536621094,
|
1148 |
+
"learning_rate": 6.1589560630758656e-06,
|
1149 |
+
"loss": 0.102,
|
1150 |
+
"step": 15400
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 7.05,
|
1154 |
+
"grad_norm": 1.445946455001831,
|
1155 |
+
"learning_rate": 5.986668802421924e-06,
|
1156 |
+
"loss": 0.1061,
|
1157 |
+
"step": 15500
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 7.1,
|
1161 |
+
"grad_norm": 30.50276756286621,
|
1162 |
+
"learning_rate": 5.8162228322380155e-06,
|
1163 |
+
"loss": 0.1004,
|
1164 |
+
"step": 15600
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 7.14,
|
1168 |
+
"grad_norm": 0.28580981492996216,
|
1169 |
+
"learning_rate": 5.647652972118998e-06,
|
1170 |
+
"loss": 0.095,
|
1171 |
+
"step": 15700
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 7.19,
|
1175 |
+
"grad_norm": 8.433425903320312,
|
1176 |
+
"learning_rate": 5.480993658398129e-06,
|
1177 |
+
"loss": 0.2191,
|
1178 |
+
"step": 15800
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 7.23,
|
1182 |
+
"grad_norm": 23.46518898010254,
|
1183 |
+
"learning_rate": 5.316278937112267e-06,
|
1184 |
+
"loss": 0.1039,
|
1185 |
+
"step": 15900
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 7.28,
|
1189 |
+
"grad_norm": 0.1998785138130188,
|
1190 |
+
"learning_rate": 5.153542457046737e-06,
|
1191 |
+
"loss": 0.1161,
|
1192 |
+
"step": 16000
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 7.32,
|
1196 |
+
"grad_norm": 0.5174553990364075,
|
1197 |
+
"learning_rate": 4.992817462861397e-06,
|
1198 |
+
"loss": 0.1093,
|
1199 |
+
"step": 16100
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 7.37,
|
1203 |
+
"grad_norm": 10.745183944702148,
|
1204 |
+
"learning_rate": 4.834136788299248e-06,
|
1205 |
+
"loss": 0.152,
|
1206 |
+
"step": 16200
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 7.42,
|
1210 |
+
"grad_norm": 0.035963889211416245,
|
1211 |
+
"learning_rate": 4.67753284947898e-06,
|
1212 |
+
"loss": 0.0887,
|
1213 |
+
"step": 16300
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 7.46,
|
1217 |
+
"grad_norm": 0.02713492140173912,
|
1218 |
+
"learning_rate": 4.523037638272822e-06,
|
1219 |
+
"loss": 0.0964,
|
1220 |
+
"step": 16400
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 7.51,
|
1224 |
+
"grad_norm": 0.04027700796723366,
|
1225 |
+
"learning_rate": 4.370682715771108e-06,
|
1226 |
+
"loss": 0.0898,
|
1227 |
+
"step": 16500
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 7.55,
|
1231 |
+
"grad_norm": 32.831809997558594,
|
1232 |
+
"learning_rate": 4.220499205834783e-06,
|
1233 |
+
"loss": 0.1376,
|
1234 |
+
"step": 16600
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 7.6,
|
1238 |
+
"grad_norm": 1.195786952972412,
|
1239 |
+
"learning_rate": 4.072517788737264e-06,
|
1240 |
+
"loss": 0.1386,
|
1241 |
+
"step": 16700
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 7.64,
|
1245 |
+
"grad_norm": 0.0985260009765625,
|
1246 |
+
"learning_rate": 3.926768694896931e-06,
|
1247 |
+
"loss": 0.1031,
|
1248 |
+
"step": 16800
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 7.69,
|
1252 |
+
"grad_norm": 66.71458435058594,
|
1253 |
+
"learning_rate": 3.783281698701482e-06,
|
1254 |
+
"loss": 0.1584,
|
1255 |
+
"step": 16900
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 7.73,
|
1259 |
+
"grad_norm": 0.06048920005559921,
|
1260 |
+
"learning_rate": 3.6420861124254607e-06,
|
1261 |
+
"loss": 0.1557,
|
1262 |
+
"step": 17000
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 7.78,
|
1266 |
+
"grad_norm": 35.74193572998047,
|
1267 |
+
"learning_rate": 3.5032107802422107e-06,
|
1268 |
+
"loss": 0.1509,
|
1269 |
+
"step": 17100
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 7.83,
|
1273 |
+
"grad_norm": 0.14910955727100372,
|
1274 |
+
"learning_rate": 3.3666840723314145e-06,
|
1275 |
+
"loss": 0.1421,
|
1276 |
+
"step": 17200
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 7.87,
|
1280 |
+
"grad_norm": 44.823760986328125,
|
1281 |
+
"learning_rate": 3.232533879083511e-06,
|
1282 |
+
"loss": 0.1181,
|
1283 |
+
"step": 17300
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 7.92,
|
1287 |
+
"grad_norm": 7.532151699066162,
|
1288 |
+
"learning_rate": 3.1007876054020724e-06,
|
1289 |
+
"loss": 0.1385,
|
1290 |
+
"step": 17400
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 7.96,
|
1294 |
+
"grad_norm": 28.50664520263672,
|
1295 |
+
"learning_rate": 2.9714721651054e-06,
|
1296 |
+
"loss": 0.1222,
|
1297 |
+
"step": 17500
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 8.0,
|
1301 |
+
"eval_accuracy": 0.9479125248508946,
|
1302 |
+
"eval_loss": 0.3132196068763733,
|
1303 |
+
"eval_runtime": 111.2173,
|
1304 |
+
"eval_samples_per_second": 22.613,
|
1305 |
+
"eval_steps_per_second": 2.832,
|
1306 |
+
"step": 17584
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 8.01,
|
1310 |
+
"grad_norm": 0.00245882966555655,
|
1311 |
+
"learning_rate": 2.8446139754284486e-06,
|
1312 |
+
"loss": 0.0782,
|
1313 |
+
"step": 17600
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 8.05,
|
1317 |
+
"grad_norm": 0.3096585273742676,
|
1318 |
+
"learning_rate": 2.7202389516261346e-06,
|
1319 |
+
"loss": 0.1482,
|
1320 |
+
"step": 17700
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 8.1,
|
1324 |
+
"grad_norm": 38.84019088745117,
|
1325 |
+
"learning_rate": 2.5983725016792574e-06,
|
1326 |
+
"loss": 0.1191,
|
1327 |
+
"step": 17800
|
1328 |
+
},
|
1329 |
+
{
|
1330 |
+
"epoch": 8.14,
|
1331 |
+
"grad_norm": 0.24393437802791595,
|
1332 |
+
"learning_rate": 2.4790395211040296e-06,
|
1333 |
+
"loss": 0.1095,
|
1334 |
+
"step": 17900
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 8.19,
|
1338 |
+
"grad_norm": 0.32781603932380676,
|
1339 |
+
"learning_rate": 2.36226438786627e-06,
|
1340 |
+
"loss": 0.121,
|
1341 |
+
"step": 18000
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 8.23,
|
1345 |
+
"grad_norm": 8.179335594177246,
|
1346 |
+
"learning_rate": 2.2480709574013637e-06,
|
1347 |
+
"loss": 0.0564,
|
1348 |
+
"step": 18100
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 8.28,
|
1352 |
+
"grad_norm": 0.03705134242773056,
|
1353 |
+
"learning_rate": 2.1364825577409424e-06,
|
1354 |
+
"loss": 0.1466,
|
1355 |
+
"step": 18200
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 8.33,
|
1359 |
+
"grad_norm": 0.8985774517059326,
|
1360 |
+
"learning_rate": 2.0275219847473026e-06,
|
1361 |
+
"loss": 0.1097,
|
1362 |
+
"step": 18300
|
1363 |
+
},
|
1364 |
+
{
|
1365 |
+
"epoch": 8.37,
|
1366 |
+
"grad_norm": 7.916272163391113,
|
1367 |
+
"learning_rate": 1.9212114974565664e-06,
|
1368 |
+
"loss": 0.1213,
|
1369 |
+
"step": 18400
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"epoch": 8.42,
|
1373 |
+
"grad_norm": 0.16036684811115265,
|
1374 |
+
"learning_rate": 1.8175728135314707e-06,
|
1375 |
+
"loss": 0.0848,
|
1376 |
+
"step": 18500
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 8.46,
|
1380 |
+
"grad_norm": 0.01501951552927494,
|
1381 |
+
"learning_rate": 1.7166271048247796e-06,
|
1382 |
+
"loss": 0.089,
|
1383 |
+
"step": 18600
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 8.51,
|
1387 |
+
"grad_norm": 80.24330139160156,
|
1388 |
+
"learning_rate": 1.6183949930541898e-06,
|
1389 |
+
"loss": 0.1014,
|
1390 |
+
"step": 18700
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 8.55,
|
1394 |
+
"grad_norm": 0.014790402725338936,
|
1395 |
+
"learning_rate": 1.5228965455896054e-06,
|
1396 |
+
"loss": 0.1042,
|
1397 |
+
"step": 18800
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 8.6,
|
1401 |
+
"grad_norm": 0.005228283815085888,
|
1402 |
+
"learning_rate": 1.4301512713536873e-06,
|
1403 |
+
"loss": 0.1056,
|
1404 |
+
"step": 18900
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 8.64,
|
1408 |
+
"grad_norm": 0.0038773128762841225,
|
1409 |
+
"learning_rate": 1.3401781168364591e-06,
|
1410 |
+
"loss": 0.0963,
|
1411 |
+
"step": 19000
|
1412 |
+
},
|
1413 |
+
{
|
1414 |
+
"epoch": 8.69,
|
1415 |
+
"grad_norm": 0.009148034267127514,
|
1416 |
+
"learning_rate": 1.2529954622248114e-06,
|
1417 |
+
"loss": 0.109,
|
1418 |
+
"step": 19100
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 8.74,
|
1422 |
+
"grad_norm": 0.10844717919826508,
|
1423 |
+
"learning_rate": 1.1686211176477208e-06,
|
1424 |
+
"loss": 0.1075,
|
1425 |
+
"step": 19200
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 8.78,
|
1429 |
+
"grad_norm": 0.017569424584507942,
|
1430 |
+
"learning_rate": 1.0870723195378852e-06,
|
1431 |
+
"loss": 0.1228,
|
1432 |
+
"step": 19300
|
1433 |
+
},
|
1434 |
+
{
|
1435 |
+
"epoch": 8.83,
|
1436 |
+
"grad_norm": 39.32170104980469,
|
1437 |
+
"learning_rate": 1.00836572711058e-06,
|
1438 |
+
"loss": 0.1414,
|
1439 |
+
"step": 19400
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 8.87,
|
1443 |
+
"grad_norm": 28.396100997924805,
|
1444 |
+
"learning_rate": 9.325174189604346e-07,
|
1445 |
+
"loss": 0.129,
|
1446 |
+
"step": 19500
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 8.92,
|
1450 |
+
"grad_norm": 0.031751640141010284,
|
1451 |
+
"learning_rate": 8.595428897768071e-07,
|
1452 |
+
"loss": 0.1163,
|
1453 |
+
"step": 19600
|
1454 |
+
},
|
1455 |
+
{
|
1456 |
+
"epoch": 8.96,
|
1457 |
+
"grad_norm": 1.8334925174713135,
|
1458 |
+
"learning_rate": 7.894570471784418e-07,
|
1459 |
+
"loss": 0.1196,
|
1460 |
+
"step": 19700
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 9.0,
|
1464 |
+
"eval_accuracy": 0.9467196819085487,
|
1465 |
+
"eval_loss": 0.3136024475097656,
|
1466 |
+
"eval_runtime": 111.3615,
|
1467 |
+
"eval_samples_per_second": 22.584,
|
1468 |
+
"eval_steps_per_second": 2.829,
|
1469 |
+
"step": 19782
|
1470 |
+
},
|
1471 |
+
{
|
1472 |
+
"epoch": 9.01,
|
1473 |
+
"grad_norm": 9.599562644958496,
|
1474 |
+
"learning_rate": 7.222742086680756e-07,
|
1475 |
+
"loss": 0.1225,
|
1476 |
+
"step": 19800
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 9.05,
|
1480 |
+
"grad_norm": 20.813501358032227,
|
1481 |
+
"learning_rate": 6.580080987075721e-07,
|
1482 |
+
"loss": 0.0845,
|
1483 |
+
"step": 19900
|
1484 |
+
},
|
1485 |
+
{
|
1486 |
+
"epoch": 9.1,
|
1487 |
+
"grad_norm": 0.00961952656507492,
|
1488 |
+
"learning_rate": 5.966718459142196e-07,
|
1489 |
+
"loss": 0.107,
|
1490 |
+
"step": 20000
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 9.14,
|
1494 |
+
"grad_norm": 0.0361330471932888,
|
1495 |
+
"learning_rate": 5.382779803787579e-07,
|
1496 |
+
"loss": 0.0993,
|
1497 |
+
"step": 20100
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 9.19,
|
1501 |
+
"grad_norm": 0.8669134378433228,
|
1502 |
+
"learning_rate": 4.82838431105655e-07,
|
1503 |
+
"loss": 0.0874,
|
1504 |
+
"step": 20200
|
1505 |
+
},
|
1506 |
+
{
|
1507 |
+
"epoch": 9.24,
|
1508 |
+
"grad_norm": 0.02739112637937069,
|
1509 |
+
"learning_rate": 4.303645235761866e-07,
|
1510 |
+
"loss": 0.1095,
|
1511 |
+
"step": 20300
|
1512 |
+
},
|
1513 |
+
{
|
1514 |
+
"epoch": 9.28,
|
1515 |
+
"grad_norm": 0.019733713939785957,
|
1516 |
+
"learning_rate": 3.808669774348167e-07,
|
1517 |
+
"loss": 0.1325,
|
1518 |
+
"step": 20400
|
1519 |
+
},
|
1520 |
+
{
|
1521 |
+
"epoch": 9.33,
|
1522 |
+
"grad_norm": 0.0024758102372288704,
|
1523 |
+
"learning_rate": 3.3435590429932493e-07,
|
1524 |
+
"loss": 0.0883,
|
1525 |
+
"step": 20500
|
1526 |
+
},
|
1527 |
+
{
|
1528 |
+
"epoch": 9.37,
|
1529 |
+
"grad_norm": 0.04354145750403404,
|
1530 |
+
"learning_rate": 2.908408056951578e-07,
|
1531 |
+
"loss": 0.0939,
|
1532 |
+
"step": 20600
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 9.42,
|
1536 |
+
"grad_norm": 10.014009475708008,
|
1537 |
+
"learning_rate": 2.5033057111440106e-07,
|
1538 |
+
"loss": 0.0856,
|
1539 |
+
"step": 20700
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 9.46,
|
1543 |
+
"grad_norm": 0.00877867080271244,
|
1544 |
+
"learning_rate": 2.1283347619979243e-07,
|
1545 |
+
"loss": 0.0977,
|
1546 |
+
"step": 20800
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 9.51,
|
1550 |
+
"grad_norm": 0.0024496885016560555,
|
1551 |
+
"learning_rate": 1.7835718105413235e-07,
|
1552 |
+
"loss": 0.1331,
|
1553 |
+
"step": 20900
|
1554 |
+
},
|
1555 |
+
{
|
1556 |
+
"epoch": 9.55,
|
1557 |
+
"grad_norm": 0.2954551577568054,
|
1558 |
+
"learning_rate": 1.4690872867542892e-07,
|
1559 |
+
"loss": 0.126,
|
1560 |
+
"step": 21000
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 9.6,
|
1564 |
+
"grad_norm": 0.06035974249243736,
|
1565 |
+
"learning_rate": 1.1849454351812394e-07,
|
1566 |
+
"loss": 0.077,
|
1567 |
+
"step": 21100
|
1568 |
+
},
|
1569 |
+
{
|
1570 |
+
"epoch": 9.65,
|
1571 |
+
"grad_norm": 0.7805526852607727,
|
1572 |
+
"learning_rate": 9.312043018067762e-08,
|
1573 |
+
"loss": 0.1167,
|
1574 |
+
"step": 21200
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 9.69,
|
1578 |
+
"grad_norm": 0.09065116941928864,
|
1579 |
+
"learning_rate": 7.079157221975718e-08,
|
1580 |
+
"loss": 0.1658,
|
1581 |
+
"step": 21300
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 9.74,
|
1585 |
+
"grad_norm": 0.00335172307677567,
|
1586 |
+
"learning_rate": 5.1512531091333914e-08,
|
1587 |
+
"loss": 0.126,
|
1588 |
+
"step": 21400
|
1589 |
+
},
|
1590 |
+
{
|
1591 |
+
"epoch": 9.78,
|
1592 |
+
"grad_norm": 1.6308414936065674,
|
1593 |
+
"learning_rate": 3.528724521882687e-08,
|
1594 |
+
"loss": 0.1088,
|
1595 |
+
"step": 21500
|
1596 |
+
},
|
1597 |
+
{
|
1598 |
+
"epoch": 9.83,
|
1599 |
+
"grad_norm": 22.293624877929688,
|
1600 |
+
"learning_rate": 2.211902918855313e-08,
|
1601 |
+
"loss": 0.1201,
|
1602 |
+
"step": 21600
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 9.87,
|
1606 |
+
"grad_norm": 0.030308537185192108,
|
1607 |
+
"learning_rate": 1.2010573072602783e-08,
|
1608 |
+
"loss": 0.0758,
|
1609 |
+
"step": 21700
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 9.92,
|
1613 |
+
"grad_norm": 5.30928897857666,
|
1614 |
+
"learning_rate": 4.963941879295164e-09,
|
1615 |
+
"loss": 0.0952,
|
1616 |
+
"step": 21800
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 9.96,
|
1620 |
+
"grad_norm": 0.04648282751441002,
|
1621 |
+
"learning_rate": 9.805751313296529e-10,
|
1622 |
+
"loss": 0.1257,
|
1623 |
+
"step": 21900
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 10.0,
|
1627 |
+
"eval_accuracy": 0.94831013916501,
|
1628 |
+
"eval_loss": 0.3119918704032898,
|
1629 |
+
"eval_runtime": 111.4853,
|
1630 |
+
"eval_samples_per_second": 22.559,
|
1631 |
+
"eval_steps_per_second": 2.825,
|
1632 |
+
"step": 21980
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 10.0,
|
1636 |
+
"step": 21980,
|
1637 |
+
"total_flos": 4.09349935387607e+19,
|
1638 |
+
"train_loss": 0.2596938943081926,
|
1639 |
+
"train_runtime": 18130.6882,
|
1640 |
+
"train_samples_per_second": 9.697,
|
1641 |
+
"train_steps_per_second": 1.212
|
1642 |
+
}
|
1643 |
+
],
|
1644 |
+
"logging_steps": 100,
|
1645 |
+
"max_steps": 21980,
|
1646 |
+
"num_input_tokens_seen": 0,
|
1647 |
+
"num_train_epochs": 10,
|
1648 |
+
"save_steps": 500,
|
1649 |
+
"total_flos": 4.09349935387607e+19,
|
1650 |
+
"train_batch_size": 8,
|
1651 |
+
"trial_name": null,
|
1652 |
+
"trial_params": null
|
1653 |
+
}
|