Model save
Browse files- README.md +72 -0
- all_results.json +8 -0
- config.json +48 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Nov06_15-28-47_dfb0c3665f64/events.out.tfevents.1699284576.dfb0c3665f64.13158.0 +3 -0
- runs/Nov06_15-48-14_dfb0c3665f64/events.out.tfevents.1699285717.dfb0c3665f64.18450.0 +3 -0
- train_results.json +8 -0
- trainer_state.json +880 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224-in21k
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: Action_all_10_class
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# Action_all_10_class
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.3598
|
21 |
+
- Accuracy: 0.9017
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0002
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 5
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
+
| 1.1524 | 0.4 | 100 | 1.0612 | 0.6952 |
|
54 |
+
| 0.9818 | 0.8 | 200 | 0.7399 | 0.7877 |
|
55 |
+
| 0.844 | 1.2 | 300 | 0.7196 | 0.7692 |
|
56 |
+
| 0.7992 | 1.61 | 400 | 0.5383 | 0.8376 |
|
57 |
+
| 0.7203 | 2.01 | 500 | 0.5222 | 0.8390 |
|
58 |
+
| 0.5527 | 2.41 | 600 | 0.5394 | 0.8376 |
|
59 |
+
| 0.5682 | 2.81 | 700 | 0.4943 | 0.8462 |
|
60 |
+
| 0.4238 | 3.21 | 800 | 0.4441 | 0.8675 |
|
61 |
+
| 0.4684 | 3.61 | 900 | 0.4113 | 0.8846 |
|
62 |
+
| 0.4239 | 4.02 | 1000 | 0.3587 | 0.8946 |
|
63 |
+
| 0.4083 | 4.42 | 1100 | 0.3768 | 0.8832 |
|
64 |
+
| 0.3541 | 4.82 | 1200 | 0.3598 | 0.9017 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.35.0
|
70 |
+
- Pytorch 2.1.0+cu118
|
71 |
+
- Datasets 2.14.6
|
72 |
+
- Tokenizers 0.14.1
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"total_flos": 1.539101261655982e+18,
|
4 |
+
"train_loss": 0.6643937945844658,
|
5 |
+
"train_runtime": 748.7697,
|
6 |
+
"train_samples_per_second": 26.524,
|
7 |
+
"train_steps_per_second": 1.663
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
3 |
+
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"encoder_stride": 16,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "\u0995\u09a5\u09be_\u09ac\u09b2\u09be",
|
13 |
+
"1": "\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be",
|
14 |
+
"2": "\u0996\u09be\u0993\u09af\u09bc\u09be",
|
15 |
+
"3": "\u0996\u09c7\u09b2\u09be_\u0995\u09b0\u09be",
|
16 |
+
"4": "\u0998\u09c1\u09ae\u09be\u09a8\u09c7\u09be",
|
17 |
+
"5": "\u09aa\u09a1\u09bc\u09be",
|
18 |
+
"6": "\u09aa\u09be\u09a8_\u0995\u09b0\u09be",
|
19 |
+
"7": "\u09b0\u09be\u09a8\u09cd\u09a8\u09be_\u0995\u09b0\u09be",
|
20 |
+
"8": "\u09b2\u09c7\u0996\u09be",
|
21 |
+
"9": "\u09b9\u09be\u0981\u099f\u09be"
|
22 |
+
},
|
23 |
+
"image_size": 224,
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"\u0995\u09a5\u09be_\u09ac\u09b2\u09be": "0",
|
28 |
+
"\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be": "1",
|
29 |
+
"\u0996\u09be\u0993\u09af\u09bc\u09be": "2",
|
30 |
+
"\u0996\u09c7\u09b2\u09be_\u0995\u09b0\u09be": "3",
|
31 |
+
"\u0998\u09c1\u09ae\u09be\u09a8\u09c7\u09be": "4",
|
32 |
+
"\u09aa\u09a1\u09bc\u09be": "5",
|
33 |
+
"\u09aa\u09be\u09a8_\u0995\u09b0\u09be": "6",
|
34 |
+
"\u09b0\u09be\u09a8\u09cd\u09a8\u09be_\u0995\u09b0\u09be": "7",
|
35 |
+
"\u09b2\u09c7\u0996\u09be": "8",
|
36 |
+
"\u09b9\u09be\u0981\u099f\u09be": "9"
|
37 |
+
},
|
38 |
+
"layer_norm_eps": 1e-12,
|
39 |
+
"model_type": "vit",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_channels": 3,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"patch_size": 16,
|
44 |
+
"problem_type": "single_label_classification",
|
45 |
+
"qkv_bias": true,
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.35.0"
|
48 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6363d9138987ea57aac64eafb945b3ac0b14d984633e1fb7767c771d2c14ce60
|
3 |
+
size 343248584
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTFeatureExtractor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
runs/Nov06_15-28-47_dfb0c3665f64/events.out.tfevents.1699284576.dfb0c3665f64.13158.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d107ba01bc126303e3030ec6601d7fd8529baef4d485825e1c3bb5a1d42913e4
|
3 |
+
size 28930
|
runs/Nov06_15-48-14_dfb0c3665f64/events.out.tfevents.1699285717.dfb0c3665f64.18450.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ef7591ced63d1eb31098d3cf612684c3e577dfaea1ff781856b4c86a6805e7c
|
3 |
+
size 28930
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"total_flos": 1.539101261655982e+18,
|
4 |
+
"train_loss": 0.6643937945844658,
|
5 |
+
"train_runtime": 748.7697,
|
6 |
+
"train_samples_per_second": 26.524,
|
7 |
+
"train_steps_per_second": 1.663
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,880 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.39916983246803284,
|
3 |
+
"best_model_checkpoint": "Action_all_10_class/checkpoint-1200",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 1245,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04,
|
13 |
+
"learning_rate": 0.00019839357429718877,
|
14 |
+
"loss": 2.2294,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.08,
|
19 |
+
"learning_rate": 0.00019678714859437752,
|
20 |
+
"loss": 2.1036,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.12,
|
25 |
+
"learning_rate": 0.00019518072289156628,
|
26 |
+
"loss": 1.9019,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.16,
|
31 |
+
"learning_rate": 0.00019357429718875504,
|
32 |
+
"loss": 1.6396,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.2,
|
37 |
+
"learning_rate": 0.00019196787148594377,
|
38 |
+
"loss": 1.5942,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.24,
|
43 |
+
"learning_rate": 0.00019036144578313252,
|
44 |
+
"loss": 1.3722,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.28,
|
49 |
+
"learning_rate": 0.00018875502008032128,
|
50 |
+
"loss": 1.2927,
|
51 |
+
"step": 70
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.32,
|
55 |
+
"learning_rate": 0.00018714859437751004,
|
56 |
+
"loss": 1.2947,
|
57 |
+
"step": 80
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.36,
|
61 |
+
"learning_rate": 0.0001855421686746988,
|
62 |
+
"loss": 1.2353,
|
63 |
+
"step": 90
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.4,
|
67 |
+
"learning_rate": 0.00018393574297188755,
|
68 |
+
"loss": 1.1348,
|
69 |
+
"step": 100
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.4,
|
73 |
+
"eval_accuracy": 0.698005698005698,
|
74 |
+
"eval_loss": 1.0964313745498657,
|
75 |
+
"eval_runtime": 13.3411,
|
76 |
+
"eval_samples_per_second": 52.619,
|
77 |
+
"eval_steps_per_second": 6.596,
|
78 |
+
"step": 100
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 0.44,
|
82 |
+
"learning_rate": 0.0001823293172690763,
|
83 |
+
"loss": 1.0305,
|
84 |
+
"step": 110
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.48,
|
88 |
+
"learning_rate": 0.00018072289156626507,
|
89 |
+
"loss": 1.0352,
|
90 |
+
"step": 120
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.52,
|
94 |
+
"learning_rate": 0.00017911646586345382,
|
95 |
+
"loss": 1.0957,
|
96 |
+
"step": 130
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.56,
|
100 |
+
"learning_rate": 0.00017751004016064258,
|
101 |
+
"loss": 1.1747,
|
102 |
+
"step": 140
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 0.6,
|
106 |
+
"learning_rate": 0.00017590361445783134,
|
107 |
+
"loss": 1.0863,
|
108 |
+
"step": 150
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.64,
|
112 |
+
"learning_rate": 0.0001742971887550201,
|
113 |
+
"loss": 1.0802,
|
114 |
+
"step": 160
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.68,
|
118 |
+
"learning_rate": 0.00017269076305220885,
|
119 |
+
"loss": 1.0912,
|
120 |
+
"step": 170
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 0.72,
|
124 |
+
"learning_rate": 0.0001710843373493976,
|
125 |
+
"loss": 1.0056,
|
126 |
+
"step": 180
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 0.76,
|
130 |
+
"learning_rate": 0.00016947791164658636,
|
131 |
+
"loss": 0.9641,
|
132 |
+
"step": 190
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 0.8,
|
136 |
+
"learning_rate": 0.00016787148594377512,
|
137 |
+
"loss": 0.9992,
|
138 |
+
"step": 200
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 0.8,
|
142 |
+
"eval_accuracy": 0.7948717948717948,
|
143 |
+
"eval_loss": 0.7362096309661865,
|
144 |
+
"eval_runtime": 13.2093,
|
145 |
+
"eval_samples_per_second": 53.145,
|
146 |
+
"eval_steps_per_second": 6.662,
|
147 |
+
"step": 200
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.84,
|
151 |
+
"learning_rate": 0.00016626506024096388,
|
152 |
+
"loss": 0.9851,
|
153 |
+
"step": 210
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.88,
|
157 |
+
"learning_rate": 0.00016465863453815263,
|
158 |
+
"loss": 0.886,
|
159 |
+
"step": 220
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.92,
|
163 |
+
"learning_rate": 0.0001630522088353414,
|
164 |
+
"loss": 0.9604,
|
165 |
+
"step": 230
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.96,
|
169 |
+
"learning_rate": 0.00016144578313253015,
|
170 |
+
"loss": 0.7707,
|
171 |
+
"step": 240
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 1.0,
|
175 |
+
"learning_rate": 0.00016,
|
176 |
+
"loss": 0.9153,
|
177 |
+
"step": 250
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.04,
|
181 |
+
"learning_rate": 0.00015839357429718874,
|
182 |
+
"loss": 0.7581,
|
183 |
+
"step": 260
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 1.08,
|
187 |
+
"learning_rate": 0.0001567871485943775,
|
188 |
+
"loss": 0.6622,
|
189 |
+
"step": 270
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 1.12,
|
193 |
+
"learning_rate": 0.00015518072289156626,
|
194 |
+
"loss": 0.7251,
|
195 |
+
"step": 280
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 1.16,
|
199 |
+
"learning_rate": 0.00015357429718875501,
|
200 |
+
"loss": 0.7955,
|
201 |
+
"step": 290
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 1.2,
|
205 |
+
"learning_rate": 0.00015196787148594377,
|
206 |
+
"loss": 0.8314,
|
207 |
+
"step": 300
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 1.2,
|
211 |
+
"eval_accuracy": 0.8205128205128205,
|
212 |
+
"eval_loss": 0.6410418748855591,
|
213 |
+
"eval_runtime": 12.6655,
|
214 |
+
"eval_samples_per_second": 55.426,
|
215 |
+
"eval_steps_per_second": 6.948,
|
216 |
+
"step": 300
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 1.24,
|
220 |
+
"learning_rate": 0.00015036144578313253,
|
221 |
+
"loss": 0.845,
|
222 |
+
"step": 310
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 1.29,
|
226 |
+
"learning_rate": 0.00014875502008032128,
|
227 |
+
"loss": 0.7132,
|
228 |
+
"step": 320
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 1.33,
|
232 |
+
"learning_rate": 0.00014714859437751004,
|
233 |
+
"loss": 0.7161,
|
234 |
+
"step": 330
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 1.37,
|
238 |
+
"learning_rate": 0.0001455421686746988,
|
239 |
+
"loss": 0.7773,
|
240 |
+
"step": 340
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.41,
|
244 |
+
"learning_rate": 0.00014393574297188756,
|
245 |
+
"loss": 0.7676,
|
246 |
+
"step": 350
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 1.45,
|
250 |
+
"learning_rate": 0.0001423293172690763,
|
251 |
+
"loss": 0.8516,
|
252 |
+
"step": 360
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 1.49,
|
256 |
+
"learning_rate": 0.00014072289156626507,
|
257 |
+
"loss": 0.6597,
|
258 |
+
"step": 370
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 1.53,
|
262 |
+
"learning_rate": 0.00013911646586345383,
|
263 |
+
"loss": 0.6998,
|
264 |
+
"step": 380
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 1.57,
|
268 |
+
"learning_rate": 0.00013751004016064258,
|
269 |
+
"loss": 0.8191,
|
270 |
+
"step": 390
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 1.61,
|
274 |
+
"learning_rate": 0.00013590361445783134,
|
275 |
+
"loss": 0.7359,
|
276 |
+
"step": 400
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 1.61,
|
280 |
+
"eval_accuracy": 0.8247863247863247,
|
281 |
+
"eval_loss": 0.5803518891334534,
|
282 |
+
"eval_runtime": 12.2034,
|
283 |
+
"eval_samples_per_second": 57.525,
|
284 |
+
"eval_steps_per_second": 7.211,
|
285 |
+
"step": 400
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 1.65,
|
289 |
+
"learning_rate": 0.0001342971887550201,
|
290 |
+
"loss": 0.7354,
|
291 |
+
"step": 410
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 1.69,
|
295 |
+
"learning_rate": 0.00013269076305220885,
|
296 |
+
"loss": 0.7507,
|
297 |
+
"step": 420
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 1.73,
|
301 |
+
"learning_rate": 0.0001310843373493976,
|
302 |
+
"loss": 0.8088,
|
303 |
+
"step": 430
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.77,
|
307 |
+
"learning_rate": 0.00012947791164658637,
|
308 |
+
"loss": 0.7279,
|
309 |
+
"step": 440
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.81,
|
313 |
+
"learning_rate": 0.00012787148594377512,
|
314 |
+
"loss": 0.7254,
|
315 |
+
"step": 450
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 1.85,
|
319 |
+
"learning_rate": 0.00012626506024096385,
|
320 |
+
"loss": 0.6707,
|
321 |
+
"step": 460
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.89,
|
325 |
+
"learning_rate": 0.0001246586345381526,
|
326 |
+
"loss": 0.6482,
|
327 |
+
"step": 470
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 1.93,
|
331 |
+
"learning_rate": 0.00012305220883534137,
|
332 |
+
"loss": 0.7238,
|
333 |
+
"step": 480
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 1.97,
|
337 |
+
"learning_rate": 0.00012144578313253012,
|
338 |
+
"loss": 0.6626,
|
339 |
+
"step": 490
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 2.01,
|
343 |
+
"learning_rate": 0.00011983935742971888,
|
344 |
+
"loss": 0.776,
|
345 |
+
"step": 500
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 2.01,
|
349 |
+
"eval_accuracy": 0.8376068376068376,
|
350 |
+
"eval_loss": 0.5489934086799622,
|
351 |
+
"eval_runtime": 12.4349,
|
352 |
+
"eval_samples_per_second": 56.454,
|
353 |
+
"eval_steps_per_second": 7.077,
|
354 |
+
"step": 500
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 2.05,
|
358 |
+
"learning_rate": 0.00011823293172690764,
|
359 |
+
"loss": 0.8069,
|
360 |
+
"step": 510
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 2.09,
|
364 |
+
"learning_rate": 0.0001166265060240964,
|
365 |
+
"loss": 0.5448,
|
366 |
+
"step": 520
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 2.13,
|
370 |
+
"learning_rate": 0.00011502008032128515,
|
371 |
+
"loss": 0.7318,
|
372 |
+
"step": 530
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 2.17,
|
376 |
+
"learning_rate": 0.00011341365461847391,
|
377 |
+
"loss": 0.5083,
|
378 |
+
"step": 540
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 2.21,
|
382 |
+
"learning_rate": 0.00011180722891566267,
|
383 |
+
"loss": 0.6493,
|
384 |
+
"step": 550
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 2.25,
|
388 |
+
"learning_rate": 0.0001102008032128514,
|
389 |
+
"loss": 0.4928,
|
390 |
+
"step": 560
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 2.29,
|
394 |
+
"learning_rate": 0.00010859437751004015,
|
395 |
+
"loss": 0.5395,
|
396 |
+
"step": 570
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 2.33,
|
400 |
+
"learning_rate": 0.00010698795180722891,
|
401 |
+
"loss": 0.5588,
|
402 |
+
"step": 580
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 2.37,
|
406 |
+
"learning_rate": 0.00010538152610441767,
|
407 |
+
"loss": 0.5892,
|
408 |
+
"step": 590
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 2.41,
|
412 |
+
"learning_rate": 0.00010377510040160642,
|
413 |
+
"loss": 0.614,
|
414 |
+
"step": 600
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 2.41,
|
418 |
+
"eval_accuracy": 0.8504273504273504,
|
419 |
+
"eval_loss": 0.5006864070892334,
|
420 |
+
"eval_runtime": 12.2103,
|
421 |
+
"eval_samples_per_second": 57.493,
|
422 |
+
"eval_steps_per_second": 7.207,
|
423 |
+
"step": 600
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 2.45,
|
427 |
+
"learning_rate": 0.00010216867469879518,
|
428 |
+
"loss": 0.7658,
|
429 |
+
"step": 610
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 2.49,
|
433 |
+
"learning_rate": 0.00010056224899598394,
|
434 |
+
"loss": 0.5152,
|
435 |
+
"step": 620
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 2.53,
|
439 |
+
"learning_rate": 9.89558232931727e-05,
|
440 |
+
"loss": 0.4941,
|
441 |
+
"step": 630
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 2.57,
|
445 |
+
"learning_rate": 9.734939759036145e-05,
|
446 |
+
"loss": 0.6831,
|
447 |
+
"step": 640
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 2.61,
|
451 |
+
"learning_rate": 9.574297188755021e-05,
|
452 |
+
"loss": 0.5971,
|
453 |
+
"step": 650
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 2.65,
|
457 |
+
"learning_rate": 9.413654618473896e-05,
|
458 |
+
"loss": 0.5842,
|
459 |
+
"step": 660
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 2.69,
|
463 |
+
"learning_rate": 9.253012048192772e-05,
|
464 |
+
"loss": 0.5976,
|
465 |
+
"step": 670
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 2.73,
|
469 |
+
"learning_rate": 9.092369477911648e-05,
|
470 |
+
"loss": 0.5051,
|
471 |
+
"step": 680
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.77,
|
475 |
+
"learning_rate": 8.931726907630522e-05,
|
476 |
+
"loss": 0.4737,
|
477 |
+
"step": 690
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 2.81,
|
481 |
+
"learning_rate": 8.771084337349398e-05,
|
482 |
+
"loss": 0.5484,
|
483 |
+
"step": 700
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 2.81,
|
487 |
+
"eval_accuracy": 0.8333333333333334,
|
488 |
+
"eval_loss": 0.5322346091270447,
|
489 |
+
"eval_runtime": 12.3228,
|
490 |
+
"eval_samples_per_second": 56.968,
|
491 |
+
"eval_steps_per_second": 7.141,
|
492 |
+
"step": 700
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 2.85,
|
496 |
+
"learning_rate": 8.610441767068274e-05,
|
497 |
+
"loss": 0.4436,
|
498 |
+
"step": 710
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 2.89,
|
502 |
+
"learning_rate": 8.449799196787149e-05,
|
503 |
+
"loss": 0.6452,
|
504 |
+
"step": 720
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 2.93,
|
508 |
+
"learning_rate": 8.289156626506025e-05,
|
509 |
+
"loss": 0.5724,
|
510 |
+
"step": 730
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 2.97,
|
514 |
+
"learning_rate": 8.128514056224899e-05,
|
515 |
+
"loss": 0.3933,
|
516 |
+
"step": 740
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 3.01,
|
520 |
+
"learning_rate": 7.967871485943775e-05,
|
521 |
+
"loss": 0.5753,
|
522 |
+
"step": 750
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 3.05,
|
526 |
+
"learning_rate": 7.80722891566265e-05,
|
527 |
+
"loss": 0.4426,
|
528 |
+
"step": 760
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 3.09,
|
532 |
+
"learning_rate": 7.646586345381526e-05,
|
533 |
+
"loss": 0.5442,
|
534 |
+
"step": 770
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 3.13,
|
538 |
+
"learning_rate": 7.485943775100402e-05,
|
539 |
+
"loss": 0.4839,
|
540 |
+
"step": 780
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 3.17,
|
544 |
+
"learning_rate": 7.325301204819278e-05,
|
545 |
+
"loss": 0.3711,
|
546 |
+
"step": 790
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 3.21,
|
550 |
+
"learning_rate": 7.164658634538153e-05,
|
551 |
+
"loss": 0.3844,
|
552 |
+
"step": 800
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 3.21,
|
556 |
+
"eval_accuracy": 0.8518518518518519,
|
557 |
+
"eval_loss": 0.5012323260307312,
|
558 |
+
"eval_runtime": 12.9006,
|
559 |
+
"eval_samples_per_second": 54.416,
|
560 |
+
"eval_steps_per_second": 6.821,
|
561 |
+
"step": 800
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 3.25,
|
565 |
+
"learning_rate": 7.004016064257029e-05,
|
566 |
+
"loss": 0.513,
|
567 |
+
"step": 810
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 3.29,
|
571 |
+
"learning_rate": 6.843373493975905e-05,
|
572 |
+
"loss": 0.3505,
|
573 |
+
"step": 820
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 3.33,
|
577 |
+
"learning_rate": 6.68273092369478e-05,
|
578 |
+
"loss": 0.4022,
|
579 |
+
"step": 830
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 3.37,
|
583 |
+
"learning_rate": 6.522088353413655e-05,
|
584 |
+
"loss": 0.3574,
|
585 |
+
"step": 840
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 3.41,
|
589 |
+
"learning_rate": 6.36144578313253e-05,
|
590 |
+
"loss": 0.5703,
|
591 |
+
"step": 850
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 3.45,
|
595 |
+
"learning_rate": 6.200803212851406e-05,
|
596 |
+
"loss": 0.4585,
|
597 |
+
"step": 860
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 3.49,
|
601 |
+
"learning_rate": 6.040160642570282e-05,
|
602 |
+
"loss": 0.3114,
|
603 |
+
"step": 870
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 3.53,
|
607 |
+
"learning_rate": 5.8795180722891576e-05,
|
608 |
+
"loss": 0.3508,
|
609 |
+
"step": 880
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 3.57,
|
613 |
+
"learning_rate": 5.718875502008032e-05,
|
614 |
+
"loss": 0.3614,
|
615 |
+
"step": 890
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 3.61,
|
619 |
+
"learning_rate": 5.5582329317269076e-05,
|
620 |
+
"loss": 0.5681,
|
621 |
+
"step": 900
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 3.61,
|
625 |
+
"eval_accuracy": 0.8589743589743589,
|
626 |
+
"eval_loss": 0.49228861927986145,
|
627 |
+
"eval_runtime": 13.1999,
|
628 |
+
"eval_samples_per_second": 53.182,
|
629 |
+
"eval_steps_per_second": 6.667,
|
630 |
+
"step": 900
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 3.65,
|
634 |
+
"learning_rate": 5.397590361445783e-05,
|
635 |
+
"loss": 0.5074,
|
636 |
+
"step": 910
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 3.69,
|
640 |
+
"learning_rate": 5.236947791164659e-05,
|
641 |
+
"loss": 0.3371,
|
642 |
+
"step": 920
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 3.73,
|
646 |
+
"learning_rate": 5.076305220883535e-05,
|
647 |
+
"loss": 0.5226,
|
648 |
+
"step": 930
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 3.78,
|
652 |
+
"learning_rate": 4.9156626506024104e-05,
|
653 |
+
"loss": 0.4462,
|
654 |
+
"step": 940
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 3.82,
|
658 |
+
"learning_rate": 4.7550200803212854e-05,
|
659 |
+
"loss": 0.4781,
|
660 |
+
"step": 950
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 3.86,
|
664 |
+
"learning_rate": 4.594377510040161e-05,
|
665 |
+
"loss": 0.4001,
|
666 |
+
"step": 960
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 3.9,
|
670 |
+
"learning_rate": 4.433734939759036e-05,
|
671 |
+
"loss": 0.4788,
|
672 |
+
"step": 970
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 3.94,
|
676 |
+
"learning_rate": 4.273092369477912e-05,
|
677 |
+
"loss": 0.4561,
|
678 |
+
"step": 980
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 3.98,
|
682 |
+
"learning_rate": 4.1124497991967875e-05,
|
683 |
+
"loss": 0.2563,
|
684 |
+
"step": 990
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 4.02,
|
688 |
+
"learning_rate": 3.9518072289156625e-05,
|
689 |
+
"loss": 0.4315,
|
690 |
+
"step": 1000
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 4.02,
|
694 |
+
"eval_accuracy": 0.8774928774928775,
|
695 |
+
"eval_loss": 0.42575880885124207,
|
696 |
+
"eval_runtime": 13.0968,
|
697 |
+
"eval_samples_per_second": 53.601,
|
698 |
+
"eval_steps_per_second": 6.719,
|
699 |
+
"step": 1000
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 4.06,
|
703 |
+
"learning_rate": 3.791164658634538e-05,
|
704 |
+
"loss": 0.2898,
|
705 |
+
"step": 1010
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 4.1,
|
709 |
+
"learning_rate": 3.630522088353414e-05,
|
710 |
+
"loss": 0.3803,
|
711 |
+
"step": 1020
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 4.14,
|
715 |
+
"learning_rate": 3.4698795180722896e-05,
|
716 |
+
"loss": 0.2827,
|
717 |
+
"step": 1030
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 4.18,
|
721 |
+
"learning_rate": 3.309236947791165e-05,
|
722 |
+
"loss": 0.3382,
|
723 |
+
"step": 1040
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 4.22,
|
727 |
+
"learning_rate": 3.14859437751004e-05,
|
728 |
+
"loss": 0.3808,
|
729 |
+
"step": 1050
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 4.26,
|
733 |
+
"learning_rate": 2.987951807228916e-05,
|
734 |
+
"loss": 0.2551,
|
735 |
+
"step": 1060
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 4.3,
|
739 |
+
"learning_rate": 2.827309236947791e-05,
|
740 |
+
"loss": 0.3011,
|
741 |
+
"step": 1070
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 4.34,
|
745 |
+
"learning_rate": 2.6666666666666667e-05,
|
746 |
+
"loss": 0.4091,
|
747 |
+
"step": 1080
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 4.38,
|
751 |
+
"learning_rate": 2.5060240963855423e-05,
|
752 |
+
"loss": 0.286,
|
753 |
+
"step": 1090
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 4.42,
|
757 |
+
"learning_rate": 2.345381526104418e-05,
|
758 |
+
"loss": 0.3804,
|
759 |
+
"step": 1100
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 4.42,
|
763 |
+
"eval_accuracy": 0.8675213675213675,
|
764 |
+
"eval_loss": 0.4324430227279663,
|
765 |
+
"eval_runtime": 12.1257,
|
766 |
+
"eval_samples_per_second": 57.894,
|
767 |
+
"eval_steps_per_second": 7.257,
|
768 |
+
"step": 1100
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 4.46,
|
772 |
+
"learning_rate": 2.1847389558232934e-05,
|
773 |
+
"loss": 0.2672,
|
774 |
+
"step": 1110
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 4.5,
|
778 |
+
"learning_rate": 2.0240963855421687e-05,
|
779 |
+
"loss": 0.3661,
|
780 |
+
"step": 1120
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 4.54,
|
784 |
+
"learning_rate": 1.863453815261044e-05,
|
785 |
+
"loss": 0.3126,
|
786 |
+
"step": 1130
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 4.58,
|
790 |
+
"learning_rate": 1.7028112449799198e-05,
|
791 |
+
"loss": 0.3455,
|
792 |
+
"step": 1140
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 4.62,
|
796 |
+
"learning_rate": 1.5421686746987955e-05,
|
797 |
+
"loss": 0.3604,
|
798 |
+
"step": 1150
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 4.66,
|
802 |
+
"learning_rate": 1.3815261044176708e-05,
|
803 |
+
"loss": 0.4628,
|
804 |
+
"step": 1160
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 4.7,
|
808 |
+
"learning_rate": 1.2208835341365463e-05,
|
809 |
+
"loss": 0.4074,
|
810 |
+
"step": 1170
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 4.74,
|
814 |
+
"learning_rate": 1.0602409638554217e-05,
|
815 |
+
"loss": 0.2512,
|
816 |
+
"step": 1180
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 4.78,
|
820 |
+
"learning_rate": 8.995983935742972e-06,
|
821 |
+
"loss": 0.2974,
|
822 |
+
"step": 1190
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 4.82,
|
826 |
+
"learning_rate": 7.389558232931727e-06,
|
827 |
+
"loss": 0.2887,
|
828 |
+
"step": 1200
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 4.82,
|
832 |
+
"eval_accuracy": 0.8803418803418803,
|
833 |
+
"eval_loss": 0.39916983246803284,
|
834 |
+
"eval_runtime": 12.2383,
|
835 |
+
"eval_samples_per_second": 57.361,
|
836 |
+
"eval_steps_per_second": 7.191,
|
837 |
+
"step": 1200
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 4.86,
|
841 |
+
"learning_rate": 5.783132530120483e-06,
|
842 |
+
"loss": 0.3073,
|
843 |
+
"step": 1210
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 4.9,
|
847 |
+
"learning_rate": 4.176706827309238e-06,
|
848 |
+
"loss": 0.2825,
|
849 |
+
"step": 1220
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 4.94,
|
853 |
+
"learning_rate": 2.570281124497992e-06,
|
854 |
+
"loss": 0.288,
|
855 |
+
"step": 1230
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 4.98,
|
859 |
+
"learning_rate": 9.638554216867472e-07,
|
860 |
+
"loss": 0.3198,
|
861 |
+
"step": 1240
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 5.0,
|
865 |
+
"step": 1245,
|
866 |
+
"total_flos": 1.539101261655982e+18,
|
867 |
+
"train_loss": 0.6643937945844658,
|
868 |
+
"train_runtime": 748.7697,
|
869 |
+
"train_samples_per_second": 26.524,
|
870 |
+
"train_steps_per_second": 1.663
|
871 |
+
}
|
872 |
+
],
|
873 |
+
"logging_steps": 10,
|
874 |
+
"max_steps": 1245,
|
875 |
+
"num_train_epochs": 5,
|
876 |
+
"save_steps": 100,
|
877 |
+
"total_flos": 1.539101261655982e+18,
|
878 |
+
"trial_name": null,
|
879 |
+
"trial_params": null
|
880 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a86b97c3f3eb410a6524ee6c1322af224937e174f3d53cb28b8020e2c478c35
|
3 |
+
size 4536
|