jalaneunos
commited on
Commit
•
ad44ebe
1
Parent(s):
509c27e
End of training
Browse files- README.md +3 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Jan24_07-31-05_e814a5b30138/events.out.tfevents.1706084902.e814a5b30138.1747.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1332 -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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) 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: 0.8683385579937304
|
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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.3321
|
36 |
+
- Accuracy: 0.8683
|
37 |
|
38 |
## Model description
|
39 |
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.8683385579937304,
|
4 |
+
"eval_loss": 0.3320719301700592,
|
5 |
+
"eval_runtime": 19.3598,
|
6 |
+
"eval_samples_per_second": 148.297,
|
7 |
+
"eval_steps_per_second": 4.649,
|
8 |
+
"total_flos": 2.0021605356722135e+19,
|
9 |
+
"train_loss": 0.3826778081384036,
|
10 |
+
"train_runtime": 3330.0466,
|
11 |
+
"train_samples_per_second": 77.588,
|
12 |
+
"train_steps_per_second": 0.607
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.8683385579937304,
|
4 |
+
"eval_loss": 0.3320719301700592,
|
5 |
+
"eval_runtime": 19.3598,
|
6 |
+
"eval_samples_per_second": 148.297,
|
7 |
+
"eval_steps_per_second": 4.649
|
8 |
+
}
|
runs/Jan24_07-31-05_e814a5b30138/events.out.tfevents.1706084902.e814a5b30138.1747.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ea7569ced746c4808c302cf828eaa751a86767d9bf47ada2d6c6260b3b540ea
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"total_flos": 2.0021605356722135e+19,
|
4 |
+
"train_loss": 0.3826778081384036,
|
5 |
+
"train_runtime": 3330.0466,
|
6 |
+
"train_samples_per_second": 77.588,
|
7 |
+
"train_steps_per_second": 0.607
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1332 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8683385579937304,
|
3 |
+
"best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-FER2013/checkpoint-1616",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2020,
|
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 |
+
"learning_rate": 2.4752475247524753e-06,
|
14 |
+
"loss": 0.7062,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.1,
|
19 |
+
"learning_rate": 4.950495049504951e-06,
|
20 |
+
"loss": 0.6984,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.15,
|
25 |
+
"learning_rate": 7.4257425742574256e-06,
|
26 |
+
"loss": 0.6891,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.2,
|
31 |
+
"learning_rate": 9.900990099009901e-06,
|
32 |
+
"loss": 0.6814,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.25,
|
37 |
+
"learning_rate": 1.2376237623762377e-05,
|
38 |
+
"loss": 0.6688,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.3,
|
43 |
+
"learning_rate": 1.4851485148514851e-05,
|
44 |
+
"loss": 0.6468,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.35,
|
49 |
+
"learning_rate": 1.7326732673267325e-05,
|
50 |
+
"loss": 0.6276,
|
51 |
+
"step": 70
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.4,
|
55 |
+
"learning_rate": 1.9801980198019803e-05,
|
56 |
+
"loss": 0.6003,
|
57 |
+
"step": 80
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.45,
|
61 |
+
"learning_rate": 2.227722772277228e-05,
|
62 |
+
"loss": 0.5689,
|
63 |
+
"step": 90
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.5,
|
67 |
+
"learning_rate": 2.4752475247524754e-05,
|
68 |
+
"loss": 0.5499,
|
69 |
+
"step": 100
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.54,
|
73 |
+
"learning_rate": 2.722772277227723e-05,
|
74 |
+
"loss": 0.5432,
|
75 |
+
"step": 110
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.59,
|
79 |
+
"learning_rate": 2.9702970297029702e-05,
|
80 |
+
"loss": 0.5408,
|
81 |
+
"step": 120
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.64,
|
85 |
+
"learning_rate": 3.217821782178218e-05,
|
86 |
+
"loss": 0.535,
|
87 |
+
"step": 130
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.69,
|
91 |
+
"learning_rate": 3.465346534653465e-05,
|
92 |
+
"loss": 0.5331,
|
93 |
+
"step": 140
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.74,
|
97 |
+
"learning_rate": 3.712871287128713e-05,
|
98 |
+
"loss": 0.4929,
|
99 |
+
"step": 150
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.79,
|
103 |
+
"learning_rate": 3.9603960396039605e-05,
|
104 |
+
"loss": 0.5054,
|
105 |
+
"step": 160
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.84,
|
109 |
+
"learning_rate": 4.207920792079208e-05,
|
110 |
+
"loss": 0.4882,
|
111 |
+
"step": 170
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.89,
|
115 |
+
"learning_rate": 4.455445544554456e-05,
|
116 |
+
"loss": 0.4844,
|
117 |
+
"step": 180
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.94,
|
121 |
+
"learning_rate": 4.702970297029703e-05,
|
122 |
+
"loss": 0.5134,
|
123 |
+
"step": 190
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.99,
|
127 |
+
"learning_rate": 4.950495049504951e-05,
|
128 |
+
"loss": 0.495,
|
129 |
+
"step": 200
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 1.0,
|
133 |
+
"eval_accuracy": 0.7739463601532567,
|
134 |
+
"eval_loss": 0.46603715419769287,
|
135 |
+
"eval_runtime": 15.7268,
|
136 |
+
"eval_samples_per_second": 182.555,
|
137 |
+
"eval_steps_per_second": 5.723,
|
138 |
+
"step": 202
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 1.04,
|
142 |
+
"learning_rate": 4.977997799779978e-05,
|
143 |
+
"loss": 0.5214,
|
144 |
+
"step": 210
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 1.09,
|
148 |
+
"learning_rate": 4.950495049504951e-05,
|
149 |
+
"loss": 0.5009,
|
150 |
+
"step": 220
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 1.14,
|
154 |
+
"learning_rate": 4.9229922992299234e-05,
|
155 |
+
"loss": 0.4632,
|
156 |
+
"step": 230
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.19,
|
160 |
+
"learning_rate": 4.895489548954896e-05,
|
161 |
+
"loss": 0.4585,
|
162 |
+
"step": 240
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 1.24,
|
166 |
+
"learning_rate": 4.867986798679868e-05,
|
167 |
+
"loss": 0.4339,
|
168 |
+
"step": 250
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 1.29,
|
172 |
+
"learning_rate": 4.8404840484048406e-05,
|
173 |
+
"loss": 0.4703,
|
174 |
+
"step": 260
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 1.34,
|
178 |
+
"learning_rate": 4.812981298129813e-05,
|
179 |
+
"loss": 0.4748,
|
180 |
+
"step": 270
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 1.39,
|
184 |
+
"learning_rate": 4.785478547854786e-05,
|
185 |
+
"loss": 0.4688,
|
186 |
+
"step": 280
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 1.44,
|
190 |
+
"learning_rate": 4.7579757975797585e-05,
|
191 |
+
"loss": 0.4613,
|
192 |
+
"step": 290
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 1.49,
|
196 |
+
"learning_rate": 4.730473047304731e-05,
|
197 |
+
"loss": 0.4633,
|
198 |
+
"step": 300
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.53,
|
202 |
+
"learning_rate": 4.702970297029703e-05,
|
203 |
+
"loss": 0.4661,
|
204 |
+
"step": 310
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 1.58,
|
208 |
+
"learning_rate": 4.675467546754676e-05,
|
209 |
+
"loss": 0.4476,
|
210 |
+
"step": 320
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 1.63,
|
214 |
+
"learning_rate": 4.647964796479648e-05,
|
215 |
+
"loss": 0.458,
|
216 |
+
"step": 330
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 1.68,
|
220 |
+
"learning_rate": 4.62046204620462e-05,
|
221 |
+
"loss": 0.4606,
|
222 |
+
"step": 340
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 1.73,
|
226 |
+
"learning_rate": 4.592959295929593e-05,
|
227 |
+
"loss": 0.4433,
|
228 |
+
"step": 350
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 1.78,
|
232 |
+
"learning_rate": 4.5654565456545655e-05,
|
233 |
+
"loss": 0.4568,
|
234 |
+
"step": 360
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 1.83,
|
238 |
+
"learning_rate": 4.537953795379538e-05,
|
239 |
+
"loss": 0.4395,
|
240 |
+
"step": 370
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.88,
|
244 |
+
"learning_rate": 4.510451045104511e-05,
|
245 |
+
"loss": 0.448,
|
246 |
+
"step": 380
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 1.93,
|
250 |
+
"learning_rate": 4.4829482948294834e-05,
|
251 |
+
"loss": 0.4722,
|
252 |
+
"step": 390
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 1.98,
|
256 |
+
"learning_rate": 4.455445544554456e-05,
|
257 |
+
"loss": 0.4632,
|
258 |
+
"step": 400
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 2.0,
|
262 |
+
"eval_accuracy": 0.8286311389759665,
|
263 |
+
"eval_loss": 0.3819791376590729,
|
264 |
+
"eval_runtime": 15.8456,
|
265 |
+
"eval_samples_per_second": 181.185,
|
266 |
+
"eval_steps_per_second": 5.68,
|
267 |
+
"step": 404
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 2.03,
|
271 |
+
"learning_rate": 4.427942794279428e-05,
|
272 |
+
"loss": 0.4614,
|
273 |
+
"step": 410
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 2.08,
|
277 |
+
"learning_rate": 4.4004400440044006e-05,
|
278 |
+
"loss": 0.4644,
|
279 |
+
"step": 420
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 2.13,
|
283 |
+
"learning_rate": 4.372937293729373e-05,
|
284 |
+
"loss": 0.4325,
|
285 |
+
"step": 430
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 2.18,
|
289 |
+
"learning_rate": 4.345434543454346e-05,
|
290 |
+
"loss": 0.4297,
|
291 |
+
"step": 440
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 2.23,
|
295 |
+
"learning_rate": 4.3179317931793185e-05,
|
296 |
+
"loss": 0.456,
|
297 |
+
"step": 450
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 2.28,
|
301 |
+
"learning_rate": 4.2904290429042904e-05,
|
302 |
+
"loss": 0.4119,
|
303 |
+
"step": 460
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 2.33,
|
307 |
+
"learning_rate": 4.262926292629263e-05,
|
308 |
+
"loss": 0.4101,
|
309 |
+
"step": 470
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 2.38,
|
313 |
+
"learning_rate": 4.2354235423542356e-05,
|
314 |
+
"loss": 0.3827,
|
315 |
+
"step": 480
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 2.43,
|
319 |
+
"learning_rate": 4.207920792079208e-05,
|
320 |
+
"loss": 0.4177,
|
321 |
+
"step": 490
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 2.48,
|
325 |
+
"learning_rate": 4.18041804180418e-05,
|
326 |
+
"loss": 0.4286,
|
327 |
+
"step": 500
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 2.52,
|
331 |
+
"learning_rate": 4.152915291529153e-05,
|
332 |
+
"loss": 0.4471,
|
333 |
+
"step": 510
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 2.57,
|
337 |
+
"learning_rate": 4.1254125412541255e-05,
|
338 |
+
"loss": 0.4304,
|
339 |
+
"step": 520
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 2.62,
|
343 |
+
"learning_rate": 4.097909790979098e-05,
|
344 |
+
"loss": 0.4043,
|
345 |
+
"step": 530
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 2.67,
|
349 |
+
"learning_rate": 4.070407040704071e-05,
|
350 |
+
"loss": 0.4277,
|
351 |
+
"step": 540
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 2.72,
|
355 |
+
"learning_rate": 4.042904290429043e-05,
|
356 |
+
"loss": 0.403,
|
357 |
+
"step": 550
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 2.77,
|
361 |
+
"learning_rate": 4.015401540154016e-05,
|
362 |
+
"loss": 0.4138,
|
363 |
+
"step": 560
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 2.82,
|
367 |
+
"learning_rate": 3.987898789878988e-05,
|
368 |
+
"loss": 0.4005,
|
369 |
+
"step": 570
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 2.87,
|
373 |
+
"learning_rate": 3.9603960396039605e-05,
|
374 |
+
"loss": 0.407,
|
375 |
+
"step": 580
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 2.92,
|
379 |
+
"learning_rate": 3.932893289328933e-05,
|
380 |
+
"loss": 0.4124,
|
381 |
+
"step": 590
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 2.97,
|
385 |
+
"learning_rate": 3.905390539053906e-05,
|
386 |
+
"loss": 0.4013,
|
387 |
+
"step": 600
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 3.0,
|
391 |
+
"eval_accuracy": 0.8446534308603274,
|
392 |
+
"eval_loss": 0.35617050528526306,
|
393 |
+
"eval_runtime": 16.2713,
|
394 |
+
"eval_samples_per_second": 176.445,
|
395 |
+
"eval_steps_per_second": 5.531,
|
396 |
+
"step": 606
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 3.02,
|
400 |
+
"learning_rate": 3.877887788778878e-05,
|
401 |
+
"loss": 0.3881,
|
402 |
+
"step": 610
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 3.07,
|
406 |
+
"learning_rate": 3.8503850385038503e-05,
|
407 |
+
"loss": 0.3761,
|
408 |
+
"step": 620
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 3.12,
|
412 |
+
"learning_rate": 3.822882288228823e-05,
|
413 |
+
"loss": 0.4161,
|
414 |
+
"step": 630
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 3.17,
|
418 |
+
"learning_rate": 3.7953795379537956e-05,
|
419 |
+
"loss": 0.3975,
|
420 |
+
"step": 640
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 3.22,
|
424 |
+
"learning_rate": 3.767876787678768e-05,
|
425 |
+
"loss": 0.4224,
|
426 |
+
"step": 650
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 3.27,
|
430 |
+
"learning_rate": 3.74037403740374e-05,
|
431 |
+
"loss": 0.3849,
|
432 |
+
"step": 660
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 3.32,
|
436 |
+
"learning_rate": 3.712871287128713e-05,
|
437 |
+
"loss": 0.4178,
|
438 |
+
"step": 670
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 3.37,
|
442 |
+
"learning_rate": 3.6853685368536854e-05,
|
443 |
+
"loss": 0.3966,
|
444 |
+
"step": 680
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 3.42,
|
448 |
+
"learning_rate": 3.657865786578658e-05,
|
449 |
+
"loss": 0.3886,
|
450 |
+
"step": 690
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 3.47,
|
454 |
+
"learning_rate": 3.6303630363036307e-05,
|
455 |
+
"loss": 0.4021,
|
456 |
+
"step": 700
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 3.51,
|
460 |
+
"learning_rate": 3.602860286028603e-05,
|
461 |
+
"loss": 0.3913,
|
462 |
+
"step": 710
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 3.56,
|
466 |
+
"learning_rate": 3.575357535753576e-05,
|
467 |
+
"loss": 0.3886,
|
468 |
+
"step": 720
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 3.61,
|
472 |
+
"learning_rate": 3.5478547854785485e-05,
|
473 |
+
"loss": 0.4066,
|
474 |
+
"step": 730
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 3.66,
|
478 |
+
"learning_rate": 3.5203520352035205e-05,
|
479 |
+
"loss": 0.401,
|
480 |
+
"step": 740
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 3.71,
|
484 |
+
"learning_rate": 3.492849284928493e-05,
|
485 |
+
"loss": 0.4002,
|
486 |
+
"step": 750
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 3.76,
|
490 |
+
"learning_rate": 3.465346534653465e-05,
|
491 |
+
"loss": 0.3738,
|
492 |
+
"step": 760
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 3.81,
|
496 |
+
"learning_rate": 3.4378437843784377e-05,
|
497 |
+
"loss": 0.4218,
|
498 |
+
"step": 770
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 3.86,
|
502 |
+
"learning_rate": 3.41034103410341e-05,
|
503 |
+
"loss": 0.368,
|
504 |
+
"step": 780
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 3.91,
|
508 |
+
"learning_rate": 3.382838283828383e-05,
|
509 |
+
"loss": 0.3969,
|
510 |
+
"step": 790
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 3.96,
|
514 |
+
"learning_rate": 3.3553355335533555e-05,
|
515 |
+
"loss": 0.3883,
|
516 |
+
"step": 800
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 4.0,
|
520 |
+
"eval_accuracy": 0.851619644723093,
|
521 |
+
"eval_loss": 0.3426118791103363,
|
522 |
+
"eval_runtime": 15.7929,
|
523 |
+
"eval_samples_per_second": 181.79,
|
524 |
+
"eval_steps_per_second": 5.699,
|
525 |
+
"step": 808
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 4.01,
|
529 |
+
"learning_rate": 3.327832783278328e-05,
|
530 |
+
"loss": 0.3605,
|
531 |
+
"step": 810
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 4.06,
|
535 |
+
"learning_rate": 3.300330033003301e-05,
|
536 |
+
"loss": 0.3797,
|
537 |
+
"step": 820
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 4.11,
|
541 |
+
"learning_rate": 3.272827282728273e-05,
|
542 |
+
"loss": 0.3701,
|
543 |
+
"step": 830
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 4.16,
|
547 |
+
"learning_rate": 3.2453245324532453e-05,
|
548 |
+
"loss": 0.3968,
|
549 |
+
"step": 840
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 4.21,
|
553 |
+
"learning_rate": 3.217821782178218e-05,
|
554 |
+
"loss": 0.3754,
|
555 |
+
"step": 850
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 4.26,
|
559 |
+
"learning_rate": 3.1903190319031906e-05,
|
560 |
+
"loss": 0.3962,
|
561 |
+
"step": 860
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 4.31,
|
565 |
+
"learning_rate": 3.162816281628163e-05,
|
566 |
+
"loss": 0.3723,
|
567 |
+
"step": 870
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 4.36,
|
571 |
+
"learning_rate": 3.135313531353136e-05,
|
572 |
+
"loss": 0.3743,
|
573 |
+
"step": 880
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 4.41,
|
577 |
+
"learning_rate": 3.1078107810781085e-05,
|
578 |
+
"loss": 0.4,
|
579 |
+
"step": 890
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 4.46,
|
583 |
+
"learning_rate": 3.0803080308030804e-05,
|
584 |
+
"loss": 0.3827,
|
585 |
+
"step": 900
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 4.5,
|
589 |
+
"learning_rate": 3.052805280528053e-05,
|
590 |
+
"loss": 0.3488,
|
591 |
+
"step": 910
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 4.55,
|
595 |
+
"learning_rate": 3.0253025302530253e-05,
|
596 |
+
"loss": 0.3755,
|
597 |
+
"step": 920
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 4.6,
|
601 |
+
"learning_rate": 2.9977997799779976e-05,
|
602 |
+
"loss": 0.3695,
|
603 |
+
"step": 930
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 4.65,
|
607 |
+
"learning_rate": 2.9702970297029702e-05,
|
608 |
+
"loss": 0.3803,
|
609 |
+
"step": 940
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 4.7,
|
613 |
+
"learning_rate": 2.942794279427943e-05,
|
614 |
+
"loss": 0.404,
|
615 |
+
"step": 950
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 4.75,
|
619 |
+
"learning_rate": 2.9152915291529155e-05,
|
620 |
+
"loss": 0.3711,
|
621 |
+
"step": 960
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 4.8,
|
625 |
+
"learning_rate": 2.8877887788778878e-05,
|
626 |
+
"loss": 0.3495,
|
627 |
+
"step": 970
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 4.85,
|
631 |
+
"learning_rate": 2.8602860286028604e-05,
|
632 |
+
"loss": 0.3644,
|
633 |
+
"step": 980
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 4.9,
|
637 |
+
"learning_rate": 2.832783278327833e-05,
|
638 |
+
"loss": 0.3673,
|
639 |
+
"step": 990
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 4.95,
|
643 |
+
"learning_rate": 2.8052805280528056e-05,
|
644 |
+
"loss": 0.3597,
|
645 |
+
"step": 1000
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 5.0,
|
649 |
+
"learning_rate": 2.777777777777778e-05,
|
650 |
+
"loss": 0.3801,
|
651 |
+
"step": 1010
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 5.0,
|
655 |
+
"eval_accuracy": 0.8561476837338906,
|
656 |
+
"eval_loss": 0.33033424615859985,
|
657 |
+
"eval_runtime": 16.0262,
|
658 |
+
"eval_samples_per_second": 179.144,
|
659 |
+
"eval_steps_per_second": 5.616,
|
660 |
+
"step": 1010
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 5.05,
|
664 |
+
"learning_rate": 2.7502750275027505e-05,
|
665 |
+
"loss": 0.3717,
|
666 |
+
"step": 1020
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 5.1,
|
670 |
+
"learning_rate": 2.722772277227723e-05,
|
671 |
+
"loss": 0.3409,
|
672 |
+
"step": 1030
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 5.15,
|
676 |
+
"learning_rate": 2.6952695269526958e-05,
|
677 |
+
"loss": 0.3647,
|
678 |
+
"step": 1040
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 5.2,
|
682 |
+
"learning_rate": 2.667766776677668e-05,
|
683 |
+
"loss": 0.3454,
|
684 |
+
"step": 1050
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 5.25,
|
688 |
+
"learning_rate": 2.64026402640264e-05,
|
689 |
+
"loss": 0.3592,
|
690 |
+
"step": 1060
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 5.3,
|
694 |
+
"learning_rate": 2.6127612761276126e-05,
|
695 |
+
"loss": 0.3529,
|
696 |
+
"step": 1070
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 5.35,
|
700 |
+
"learning_rate": 2.5852585258525853e-05,
|
701 |
+
"loss": 0.3598,
|
702 |
+
"step": 1080
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 5.4,
|
706 |
+
"learning_rate": 2.557755775577558e-05,
|
707 |
+
"loss": 0.3922,
|
708 |
+
"step": 1090
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 5.45,
|
712 |
+
"learning_rate": 2.53025302530253e-05,
|
713 |
+
"loss": 0.3547,
|
714 |
+
"step": 1100
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 5.5,
|
718 |
+
"learning_rate": 2.5027502750275028e-05,
|
719 |
+
"loss": 0.3432,
|
720 |
+
"step": 1110
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 5.54,
|
724 |
+
"learning_rate": 2.4752475247524754e-05,
|
725 |
+
"loss": 0.3542,
|
726 |
+
"step": 1120
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 5.59,
|
730 |
+
"learning_rate": 2.447744774477448e-05,
|
731 |
+
"loss": 0.3541,
|
732 |
+
"step": 1130
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 5.64,
|
736 |
+
"learning_rate": 2.4202420242024203e-05,
|
737 |
+
"loss": 0.3475,
|
738 |
+
"step": 1140
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 5.69,
|
742 |
+
"learning_rate": 2.392739273927393e-05,
|
743 |
+
"loss": 0.3528,
|
744 |
+
"step": 1150
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 5.74,
|
748 |
+
"learning_rate": 2.3652365236523656e-05,
|
749 |
+
"loss": 0.3446,
|
750 |
+
"step": 1160
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 5.79,
|
754 |
+
"learning_rate": 2.337733773377338e-05,
|
755 |
+
"loss": 0.3264,
|
756 |
+
"step": 1170
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 5.84,
|
760 |
+
"learning_rate": 2.31023102310231e-05,
|
761 |
+
"loss": 0.3327,
|
762 |
+
"step": 1180
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 5.89,
|
766 |
+
"learning_rate": 2.2827282728272828e-05,
|
767 |
+
"loss": 0.3529,
|
768 |
+
"step": 1190
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 5.94,
|
772 |
+
"learning_rate": 2.2552255225522554e-05,
|
773 |
+
"loss": 0.3473,
|
774 |
+
"step": 1200
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 5.99,
|
778 |
+
"learning_rate": 2.227722772277228e-05,
|
779 |
+
"loss": 0.3612,
|
780 |
+
"step": 1210
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 6.0,
|
784 |
+
"eval_accuracy": 0.8557993730407524,
|
785 |
+
"eval_loss": 0.3362487852573395,
|
786 |
+
"eval_runtime": 15.9082,
|
787 |
+
"eval_samples_per_second": 180.474,
|
788 |
+
"eval_steps_per_second": 5.657,
|
789 |
+
"step": 1212
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 6.04,
|
793 |
+
"learning_rate": 2.2002200220022003e-05,
|
794 |
+
"loss": 0.3324,
|
795 |
+
"step": 1220
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 6.09,
|
799 |
+
"learning_rate": 2.172717271727173e-05,
|
800 |
+
"loss": 0.3365,
|
801 |
+
"step": 1230
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 6.14,
|
805 |
+
"learning_rate": 2.1452145214521452e-05,
|
806 |
+
"loss": 0.3212,
|
807 |
+
"step": 1240
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 6.19,
|
811 |
+
"learning_rate": 2.1177117711771178e-05,
|
812 |
+
"loss": 0.33,
|
813 |
+
"step": 1250
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 6.24,
|
817 |
+
"learning_rate": 2.09020902090209e-05,
|
818 |
+
"loss": 0.3627,
|
819 |
+
"step": 1260
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 6.29,
|
823 |
+
"learning_rate": 2.0627062706270627e-05,
|
824 |
+
"loss": 0.3322,
|
825 |
+
"step": 1270
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 6.34,
|
829 |
+
"learning_rate": 2.0352035203520354e-05,
|
830 |
+
"loss": 0.3236,
|
831 |
+
"step": 1280
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 6.39,
|
835 |
+
"learning_rate": 2.007700770077008e-05,
|
836 |
+
"loss": 0.3398,
|
837 |
+
"step": 1290
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 6.44,
|
841 |
+
"learning_rate": 1.9801980198019803e-05,
|
842 |
+
"loss": 0.3481,
|
843 |
+
"step": 1300
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 6.49,
|
847 |
+
"learning_rate": 1.952695269526953e-05,
|
848 |
+
"loss": 0.3421,
|
849 |
+
"step": 1310
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 6.53,
|
853 |
+
"learning_rate": 1.9251925192519252e-05,
|
854 |
+
"loss": 0.3136,
|
855 |
+
"step": 1320
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 6.58,
|
859 |
+
"learning_rate": 1.8976897689768978e-05,
|
860 |
+
"loss": 0.3432,
|
861 |
+
"step": 1330
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 6.63,
|
865 |
+
"learning_rate": 1.87018701870187e-05,
|
866 |
+
"loss": 0.3277,
|
867 |
+
"step": 1340
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 6.68,
|
871 |
+
"learning_rate": 1.8426842684268427e-05,
|
872 |
+
"loss": 0.3285,
|
873 |
+
"step": 1350
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 6.73,
|
877 |
+
"learning_rate": 1.8151815181518153e-05,
|
878 |
+
"loss": 0.3449,
|
879 |
+
"step": 1360
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 6.78,
|
883 |
+
"learning_rate": 1.787678767876788e-05,
|
884 |
+
"loss": 0.3433,
|
885 |
+
"step": 1370
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 6.83,
|
889 |
+
"learning_rate": 1.7601760176017602e-05,
|
890 |
+
"loss": 0.3275,
|
891 |
+
"step": 1380
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 6.88,
|
895 |
+
"learning_rate": 1.7326732673267325e-05,
|
896 |
+
"loss": 0.3351,
|
897 |
+
"step": 1390
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 6.93,
|
901 |
+
"learning_rate": 1.705170517051705e-05,
|
902 |
+
"loss": 0.2946,
|
903 |
+
"step": 1400
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 6.98,
|
907 |
+
"learning_rate": 1.6776677667766778e-05,
|
908 |
+
"loss": 0.3504,
|
909 |
+
"step": 1410
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 7.0,
|
913 |
+
"eval_accuracy": 0.8652037617554859,
|
914 |
+
"eval_loss": 0.330201655626297,
|
915 |
+
"eval_runtime": 15.6907,
|
916 |
+
"eval_samples_per_second": 182.974,
|
917 |
+
"eval_steps_per_second": 5.736,
|
918 |
+
"step": 1414
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 7.03,
|
922 |
+
"learning_rate": 1.6501650165016504e-05,
|
923 |
+
"loss": 0.3424,
|
924 |
+
"step": 1420
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 7.08,
|
928 |
+
"learning_rate": 1.6226622662266227e-05,
|
929 |
+
"loss": 0.3244,
|
930 |
+
"step": 1430
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 7.13,
|
934 |
+
"learning_rate": 1.5951595159515953e-05,
|
935 |
+
"loss": 0.3208,
|
936 |
+
"step": 1440
|
937 |
+
},
|
938 |
+
{
|
939 |
+
"epoch": 7.18,
|
940 |
+
"learning_rate": 1.567656765676568e-05,
|
941 |
+
"loss": 0.3002,
|
942 |
+
"step": 1450
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 7.23,
|
946 |
+
"learning_rate": 1.5401540154015402e-05,
|
947 |
+
"loss": 0.3007,
|
948 |
+
"step": 1460
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 7.28,
|
952 |
+
"learning_rate": 1.5126512651265127e-05,
|
953 |
+
"loss": 0.3443,
|
954 |
+
"step": 1470
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 7.33,
|
958 |
+
"learning_rate": 1.4851485148514851e-05,
|
959 |
+
"loss": 0.3192,
|
960 |
+
"step": 1480
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 7.38,
|
964 |
+
"learning_rate": 1.4576457645764577e-05,
|
965 |
+
"loss": 0.3146,
|
966 |
+
"step": 1490
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 7.43,
|
970 |
+
"learning_rate": 1.4301430143014302e-05,
|
971 |
+
"loss": 0.3147,
|
972 |
+
"step": 1500
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 7.48,
|
976 |
+
"learning_rate": 1.4026402640264028e-05,
|
977 |
+
"loss": 0.3041,
|
978 |
+
"step": 1510
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 7.52,
|
982 |
+
"learning_rate": 1.3751375137513753e-05,
|
983 |
+
"loss": 0.2958,
|
984 |
+
"step": 1520
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 7.57,
|
988 |
+
"learning_rate": 1.3476347634763479e-05,
|
989 |
+
"loss": 0.3235,
|
990 |
+
"step": 1530
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 7.62,
|
994 |
+
"learning_rate": 1.32013201320132e-05,
|
995 |
+
"loss": 0.3137,
|
996 |
+
"step": 1540
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 7.67,
|
1000 |
+
"learning_rate": 1.2926292629262926e-05,
|
1001 |
+
"loss": 0.3222,
|
1002 |
+
"step": 1550
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 7.72,
|
1006 |
+
"learning_rate": 1.265126512651265e-05,
|
1007 |
+
"loss": 0.3087,
|
1008 |
+
"step": 1560
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 7.77,
|
1012 |
+
"learning_rate": 1.2376237623762377e-05,
|
1013 |
+
"loss": 0.2969,
|
1014 |
+
"step": 1570
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 7.82,
|
1018 |
+
"learning_rate": 1.2101210121012102e-05,
|
1019 |
+
"loss": 0.3091,
|
1020 |
+
"step": 1580
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 7.87,
|
1024 |
+
"learning_rate": 1.1826182618261828e-05,
|
1025 |
+
"loss": 0.3356,
|
1026 |
+
"step": 1590
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 7.92,
|
1030 |
+
"learning_rate": 1.155115511551155e-05,
|
1031 |
+
"loss": 0.2903,
|
1032 |
+
"step": 1600
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 7.97,
|
1036 |
+
"learning_rate": 1.1276127612761277e-05,
|
1037 |
+
"loss": 0.3366,
|
1038 |
+
"step": 1610
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 8.0,
|
1042 |
+
"eval_accuracy": 0.8683385579937304,
|
1043 |
+
"eval_loss": 0.3320719301700592,
|
1044 |
+
"eval_runtime": 15.9857,
|
1045 |
+
"eval_samples_per_second": 179.598,
|
1046 |
+
"eval_steps_per_second": 5.63,
|
1047 |
+
"step": 1616
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 8.02,
|
1051 |
+
"learning_rate": 1.1001100110011001e-05,
|
1052 |
+
"loss": 0.2956,
|
1053 |
+
"step": 1620
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 8.07,
|
1057 |
+
"learning_rate": 1.0726072607260726e-05,
|
1058 |
+
"loss": 0.2987,
|
1059 |
+
"step": 1630
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 8.12,
|
1063 |
+
"learning_rate": 1.045104510451045e-05,
|
1064 |
+
"loss": 0.2965,
|
1065 |
+
"step": 1640
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 8.17,
|
1069 |
+
"learning_rate": 1.0176017601760177e-05,
|
1070 |
+
"loss": 0.3014,
|
1071 |
+
"step": 1650
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 8.22,
|
1075 |
+
"learning_rate": 9.900990099009901e-06,
|
1076 |
+
"loss": 0.3267,
|
1077 |
+
"step": 1660
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 8.27,
|
1081 |
+
"learning_rate": 9.625962596259626e-06,
|
1082 |
+
"loss": 0.3243,
|
1083 |
+
"step": 1670
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 8.32,
|
1087 |
+
"learning_rate": 9.35093509350935e-06,
|
1088 |
+
"loss": 0.2841,
|
1089 |
+
"step": 1680
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 8.37,
|
1093 |
+
"learning_rate": 9.075907590759077e-06,
|
1094 |
+
"loss": 0.2949,
|
1095 |
+
"step": 1690
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 8.42,
|
1099 |
+
"learning_rate": 8.800880088008801e-06,
|
1100 |
+
"loss": 0.2944,
|
1101 |
+
"step": 1700
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 8.47,
|
1105 |
+
"learning_rate": 8.525852585258526e-06,
|
1106 |
+
"loss": 0.3137,
|
1107 |
+
"step": 1710
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 8.51,
|
1111 |
+
"learning_rate": 8.250825082508252e-06,
|
1112 |
+
"loss": 0.2825,
|
1113 |
+
"step": 1720
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 8.56,
|
1117 |
+
"learning_rate": 7.975797579757976e-06,
|
1118 |
+
"loss": 0.3012,
|
1119 |
+
"step": 1730
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 8.61,
|
1123 |
+
"learning_rate": 7.700770077007701e-06,
|
1124 |
+
"loss": 0.3221,
|
1125 |
+
"step": 1740
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 8.66,
|
1129 |
+
"learning_rate": 7.4257425742574256e-06,
|
1130 |
+
"loss": 0.2977,
|
1131 |
+
"step": 1750
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 8.71,
|
1135 |
+
"learning_rate": 7.150715071507151e-06,
|
1136 |
+
"loss": 0.316,
|
1137 |
+
"step": 1760
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 8.76,
|
1141 |
+
"learning_rate": 6.875687568756876e-06,
|
1142 |
+
"loss": 0.3023,
|
1143 |
+
"step": 1770
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 8.81,
|
1147 |
+
"learning_rate": 6.6006600660066e-06,
|
1148 |
+
"loss": 0.2937,
|
1149 |
+
"step": 1780
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 8.86,
|
1153 |
+
"learning_rate": 6.325632563256325e-06,
|
1154 |
+
"loss": 0.2825,
|
1155 |
+
"step": 1790
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 8.91,
|
1159 |
+
"learning_rate": 6.050605060506051e-06,
|
1160 |
+
"loss": 0.2907,
|
1161 |
+
"step": 1800
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 8.96,
|
1165 |
+
"learning_rate": 5.775577557755775e-06,
|
1166 |
+
"loss": 0.3007,
|
1167 |
+
"step": 1810
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 9.0,
|
1171 |
+
"eval_accuracy": 0.866597004528039,
|
1172 |
+
"eval_loss": 0.33304381370544434,
|
1173 |
+
"eval_runtime": 16.241,
|
1174 |
+
"eval_samples_per_second": 176.775,
|
1175 |
+
"eval_steps_per_second": 5.542,
|
1176 |
+
"step": 1818
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 9.01,
|
1180 |
+
"learning_rate": 5.500550055005501e-06,
|
1181 |
+
"loss": 0.297,
|
1182 |
+
"step": 1820
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 9.06,
|
1186 |
+
"learning_rate": 5.225522552255225e-06,
|
1187 |
+
"loss": 0.2894,
|
1188 |
+
"step": 1830
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 9.11,
|
1192 |
+
"learning_rate": 4.950495049504951e-06,
|
1193 |
+
"loss": 0.2927,
|
1194 |
+
"step": 1840
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 9.16,
|
1198 |
+
"learning_rate": 4.675467546754675e-06,
|
1199 |
+
"loss": 0.2884,
|
1200 |
+
"step": 1850
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 9.21,
|
1204 |
+
"learning_rate": 4.400440044004401e-06,
|
1205 |
+
"loss": 0.3217,
|
1206 |
+
"step": 1860
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 9.26,
|
1210 |
+
"learning_rate": 4.125412541254126e-06,
|
1211 |
+
"loss": 0.3278,
|
1212 |
+
"step": 1870
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"epoch": 9.31,
|
1216 |
+
"learning_rate": 3.8503850385038505e-06,
|
1217 |
+
"loss": 0.3126,
|
1218 |
+
"step": 1880
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"epoch": 9.36,
|
1222 |
+
"learning_rate": 3.5753575357535755e-06,
|
1223 |
+
"loss": 0.2997,
|
1224 |
+
"step": 1890
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 9.41,
|
1228 |
+
"learning_rate": 3.3003300330033e-06,
|
1229 |
+
"loss": 0.279,
|
1230 |
+
"step": 1900
|
1231 |
+
},
|
1232 |
+
{
|
1233 |
+
"epoch": 9.46,
|
1234 |
+
"learning_rate": 3.0253025302530254e-06,
|
1235 |
+
"loss": 0.2686,
|
1236 |
+
"step": 1910
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"epoch": 9.5,
|
1240 |
+
"learning_rate": 2.7502750275027504e-06,
|
1241 |
+
"loss": 0.2811,
|
1242 |
+
"step": 1920
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 9.55,
|
1246 |
+
"learning_rate": 2.4752475247524753e-06,
|
1247 |
+
"loss": 0.2866,
|
1248 |
+
"step": 1930
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 9.6,
|
1252 |
+
"learning_rate": 2.2002200220022003e-06,
|
1253 |
+
"loss": 0.2746,
|
1254 |
+
"step": 1940
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 9.65,
|
1258 |
+
"learning_rate": 1.9251925192519253e-06,
|
1259 |
+
"loss": 0.2565,
|
1260 |
+
"step": 1950
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"epoch": 9.7,
|
1264 |
+
"learning_rate": 1.65016501650165e-06,
|
1265 |
+
"loss": 0.3004,
|
1266 |
+
"step": 1960
|
1267 |
+
},
|
1268 |
+
{
|
1269 |
+
"epoch": 9.75,
|
1270 |
+
"learning_rate": 1.3751375137513752e-06,
|
1271 |
+
"loss": 0.3053,
|
1272 |
+
"step": 1970
|
1273 |
+
},
|
1274 |
+
{
|
1275 |
+
"epoch": 9.8,
|
1276 |
+
"learning_rate": 1.1001100110011001e-06,
|
1277 |
+
"loss": 0.2805,
|
1278 |
+
"step": 1980
|
1279 |
+
},
|
1280 |
+
{
|
1281 |
+
"epoch": 9.85,
|
1282 |
+
"learning_rate": 8.25082508250825e-07,
|
1283 |
+
"loss": 0.2817,
|
1284 |
+
"step": 1990
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 9.9,
|
1288 |
+
"learning_rate": 5.500550055005501e-07,
|
1289 |
+
"loss": 0.3138,
|
1290 |
+
"step": 2000
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 9.95,
|
1294 |
+
"learning_rate": 2.7502750275027504e-07,
|
1295 |
+
"loss": 0.2733,
|
1296 |
+
"step": 2010
|
1297 |
+
},
|
1298 |
+
{
|
1299 |
+
"epoch": 10.0,
|
1300 |
+
"learning_rate": 0.0,
|
1301 |
+
"loss": 0.3089,
|
1302 |
+
"step": 2020
|
1303 |
+
},
|
1304 |
+
{
|
1305 |
+
"epoch": 10.0,
|
1306 |
+
"eval_accuracy": 0.8655520724486242,
|
1307 |
+
"eval_loss": 0.3326851427555084,
|
1308 |
+
"eval_runtime": 15.8375,
|
1309 |
+
"eval_samples_per_second": 181.279,
|
1310 |
+
"eval_steps_per_second": 5.683,
|
1311 |
+
"step": 2020
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 10.0,
|
1315 |
+
"step": 2020,
|
1316 |
+
"total_flos": 2.0021605356722135e+19,
|
1317 |
+
"train_loss": 0.3826778081384036,
|
1318 |
+
"train_runtime": 3330.0466,
|
1319 |
+
"train_samples_per_second": 77.588,
|
1320 |
+
"train_steps_per_second": 0.607
|
1321 |
+
}
|
1322 |
+
],
|
1323 |
+
"logging_steps": 10,
|
1324 |
+
"max_steps": 2020,
|
1325 |
+
"num_input_tokens_seen": 0,
|
1326 |
+
"num_train_epochs": 10,
|
1327 |
+
"save_steps": 500,
|
1328 |
+
"total_flos": 2.0021605356722135e+19,
|
1329 |
+
"train_batch_size": 32,
|
1330 |
+
"trial_name": null,
|
1331 |
+
"trial_params": null
|
1332 |
+
}
|