omar22allam
commited on
Commit
•
a9f0965
1
Parent(s):
5d49b58
Training Completed!
Browse files- README.md +77 -0
- all_results.json +13 -0
- config.json +34 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/May08_09-52-48_cb9d71a650ba/events.out.tfevents.1715161973.cb9d71a650ba.2946.0 +3 -0
- runs/May08_09-56-27_cb9d71a650ba/events.out.tfevents.1715162188.cb9d71a650ba.10808.0 +3 -0
- runs/May08_09-57-09_cb9d71a650ba/events.out.tfevents.1715162240.cb9d71a650ba.10808.1 +3 -0
- runs/May08_10-55-55_bdf2d2ff2ea6/events.out.tfevents.1715165761.bdf2d2ff2ea6.3845.0 +3 -0
- runs/May08_10-55-55_bdf2d2ff2ea6/events.out.tfevents.1715169529.bdf2d2ff2ea6.3845.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +309 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: MRI_vit
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Image Classification
|
15 |
+
type: image-classification
|
16 |
+
dataset:
|
17 |
+
name: imagefolder
|
18 |
+
type: imagefolder
|
19 |
+
config: default
|
20 |
+
split: test
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.9058823529411765
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# MRI_vit
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.4389
|
36 |
+
- Accuracy: 0.9059
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 0.0002
|
56 |
+
- train_batch_size: 16
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 20
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
67 |
+
| 0.0101 | 5.5556 | 100 | 0.4389 | 0.9059 |
|
68 |
+
| 0.0001 | 11.1111 | 200 | 0.6572 | 0.8941 |
|
69 |
+
| 0.0001 | 16.6667 | 300 | 0.6680 | 0.9059 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.40.1
|
75 |
+
- Pytorch 2.3.0+cu121
|
76 |
+
- Datasets 2.19.1
|
77 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.9058823529411765,
|
4 |
+
"eval_loss": 0.43892163038253784,
|
5 |
+
"eval_runtime": 1.8997,
|
6 |
+
"eval_samples_per_second": 44.744,
|
7 |
+
"eval_steps_per_second": 5.79,
|
8 |
+
"total_flos": 4.417082996594688e+17,
|
9 |
+
"train_loss": 0.08463575366784223,
|
10 |
+
"train_runtime": 382.9626,
|
11 |
+
"train_samples_per_second": 14.884,
|
12 |
+
"train_steps_per_second": 0.94
|
13 |
+
}
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
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": "normal",
|
13 |
+
"1": "bengin",
|
14 |
+
"2": "cancer"
|
15 |
+
},
|
16 |
+
"image_size": 224,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"bengin": 1,
|
21 |
+
"cancer": 2,
|
22 |
+
"normal": 0
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"model_type": "vit",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_channels": 3,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"patch_size": 16,
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"qkv_bias": true,
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.40.1"
|
34 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.9058823529411765,
|
4 |
+
"eval_loss": 0.43892163038253784,
|
5 |
+
"eval_runtime": 1.8997,
|
6 |
+
"eval_samples_per_second": 44.744,
|
7 |
+
"eval_steps_per_second": 5.79
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3c8ed14d2b63d5e9d77534be4a4b5c191d05ea1e5d42fa14887dd7255e26e6b
|
3 |
+
size 343227052
|
preprocessor_config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"return_tensors",
|
13 |
+
"data_format",
|
14 |
+
"input_data_format"
|
15 |
+
],
|
16 |
+
"do_normalize": true,
|
17 |
+
"do_rescale": true,
|
18 |
+
"do_resize": true,
|
19 |
+
"image_mean": [
|
20 |
+
0.5,
|
21 |
+
0.5,
|
22 |
+
0.5
|
23 |
+
],
|
24 |
+
"image_processor_type": "ViTImageProcessor",
|
25 |
+
"image_std": [
|
26 |
+
0.5,
|
27 |
+
0.5,
|
28 |
+
0.5
|
29 |
+
],
|
30 |
+
"resample": 2,
|
31 |
+
"rescale_factor": 0.00392156862745098,
|
32 |
+
"size": {
|
33 |
+
"height": 224,
|
34 |
+
"width": 224
|
35 |
+
}
|
36 |
+
}
|
runs/May08_09-52-48_cb9d71a650ba/events.out.tfevents.1715161973.cb9d71a650ba.2946.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cea54b6e5289c4562ed201fd3a69b5726da61b6f7bda4ee8031bb94405bd3de
|
3 |
+
size 88
|
runs/May08_09-56-27_cb9d71a650ba/events.out.tfevents.1715162188.cb9d71a650ba.10808.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c631483ef4846639ecc67d617fbebb97042957835cdb593328f2b277a2f06de3
|
3 |
+
size 4685
|
runs/May08_09-57-09_cb9d71a650ba/events.out.tfevents.1715162240.cb9d71a650ba.10808.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2a2a5b9d3b0e43d08fbfe8e682d3e69baa2d096d28111498bcb519a60d6a1d5
|
3 |
+
size 6134
|
runs/May08_10-55-55_bdf2d2ff2ea6/events.out.tfevents.1715165761.bdf2d2ff2ea6.3845.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c793b1e749ea08199c4b35af69abae7e14559164dda6f9cc0cf4d6d07f561cec
|
3 |
+
size 13550
|
runs/May08_10-55-55_bdf2d2ff2ea6/events.out.tfevents.1715169529.bdf2d2ff2ea6.3845.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1376141463191becbd9c23e751550ef21c43d8547ad59d0f926790bd1fc25d73
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"total_flos": 4.417082996594688e+17,
|
4 |
+
"train_loss": 0.08463575366784223,
|
5 |
+
"train_runtime": 382.9626,
|
6 |
+
"train_samples_per_second": 14.884,
|
7 |
+
"train_steps_per_second": 0.94
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,309 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.43892163038253784,
|
3 |
+
"best_model_checkpoint": "./MRI_vit/checkpoint-100",
|
4 |
+
"epoch": 20.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 360,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.5555555555555556,
|
13 |
+
"grad_norm": 5.236236095428467,
|
14 |
+
"learning_rate": 0.00019444444444444446,
|
15 |
+
"loss": 1.0736,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.1111111111111112,
|
20 |
+
"grad_norm": 3.906468629837036,
|
21 |
+
"learning_rate": 0.00018888888888888888,
|
22 |
+
"loss": 0.5346,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.6666666666666665,
|
27 |
+
"grad_norm": 14.102361679077148,
|
28 |
+
"learning_rate": 0.00018333333333333334,
|
29 |
+
"loss": 0.4717,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.2222222222222223,
|
34 |
+
"grad_norm": 7.264150142669678,
|
35 |
+
"learning_rate": 0.00017777777777777779,
|
36 |
+
"loss": 0.3995,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 2.7777777777777777,
|
41 |
+
"grad_norm": 3.351327419281006,
|
42 |
+
"learning_rate": 0.00017222222222222224,
|
43 |
+
"loss": 0.1877,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.3333333333333335,
|
48 |
+
"grad_norm": 7.443002223968506,
|
49 |
+
"learning_rate": 0.0001666666666666667,
|
50 |
+
"loss": 0.148,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 3.888888888888889,
|
55 |
+
"grad_norm": 0.747875452041626,
|
56 |
+
"learning_rate": 0.0001611111111111111,
|
57 |
+
"loss": 0.0747,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 4.444444444444445,
|
62 |
+
"grad_norm": 0.011842708103358746,
|
63 |
+
"learning_rate": 0.00015555555555555556,
|
64 |
+
"loss": 0.0513,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 5.0,
|
69 |
+
"grad_norm": 2.2265398502349854,
|
70 |
+
"learning_rate": 0.00015000000000000001,
|
71 |
+
"loss": 0.0756,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 5.555555555555555,
|
76 |
+
"grad_norm": 0.008857272565364838,
|
77 |
+
"learning_rate": 0.00014444444444444444,
|
78 |
+
"loss": 0.0101,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 5.555555555555555,
|
83 |
+
"eval_accuracy": 0.9058823529411765,
|
84 |
+
"eval_loss": 0.43892163038253784,
|
85 |
+
"eval_runtime": 27.2539,
|
86 |
+
"eval_samples_per_second": 3.119,
|
87 |
+
"eval_steps_per_second": 0.404,
|
88 |
+
"step": 100
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 6.111111111111111,
|
92 |
+
"grad_norm": 0.0082765007391572,
|
93 |
+
"learning_rate": 0.0001388888888888889,
|
94 |
+
"loss": 0.0143,
|
95 |
+
"step": 110
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 6.666666666666667,
|
99 |
+
"grad_norm": 0.22718505561351776,
|
100 |
+
"learning_rate": 0.00013333333333333334,
|
101 |
+
"loss": 0.0033,
|
102 |
+
"step": 120
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 7.222222222222222,
|
106 |
+
"grad_norm": 0.004425971303135157,
|
107 |
+
"learning_rate": 0.00012777777777777776,
|
108 |
+
"loss": 0.0003,
|
109 |
+
"step": 130
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 7.777777777777778,
|
113 |
+
"grad_norm": 0.16841186583042145,
|
114 |
+
"learning_rate": 0.00012222222222222224,
|
115 |
+
"loss": 0.0004,
|
116 |
+
"step": 140
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 8.333333333333334,
|
120 |
+
"grad_norm": 0.0038613828364759684,
|
121 |
+
"learning_rate": 0.00011666666666666668,
|
122 |
+
"loss": 0.0003,
|
123 |
+
"step": 150
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 8.88888888888889,
|
127 |
+
"grad_norm": 0.002841161098331213,
|
128 |
+
"learning_rate": 0.00011111111111111112,
|
129 |
+
"loss": 0.0002,
|
130 |
+
"step": 160
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 9.444444444444445,
|
134 |
+
"grad_norm": 0.004673393908888102,
|
135 |
+
"learning_rate": 0.00010555555555555557,
|
136 |
+
"loss": 0.0001,
|
137 |
+
"step": 170
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 10.0,
|
141 |
+
"grad_norm": 0.002209365600720048,
|
142 |
+
"learning_rate": 0.0001,
|
143 |
+
"loss": 0.0001,
|
144 |
+
"step": 180
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 10.555555555555555,
|
148 |
+
"grad_norm": 0.0015867718029767275,
|
149 |
+
"learning_rate": 9.444444444444444e-05,
|
150 |
+
"loss": 0.0001,
|
151 |
+
"step": 190
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 11.11111111111111,
|
155 |
+
"grad_norm": 0.0017831118311733007,
|
156 |
+
"learning_rate": 8.888888888888889e-05,
|
157 |
+
"loss": 0.0001,
|
158 |
+
"step": 200
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 11.11111111111111,
|
162 |
+
"eval_accuracy": 0.8941176470588236,
|
163 |
+
"eval_loss": 0.6572446227073669,
|
164 |
+
"eval_runtime": 2.0264,
|
165 |
+
"eval_samples_per_second": 41.947,
|
166 |
+
"eval_steps_per_second": 5.428,
|
167 |
+
"step": 200
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 11.666666666666666,
|
171 |
+
"grad_norm": 0.0011566176544874907,
|
172 |
+
"learning_rate": 8.333333333333334e-05,
|
173 |
+
"loss": 0.0001,
|
174 |
+
"step": 210
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 12.222222222222221,
|
178 |
+
"grad_norm": 0.0012466717744246125,
|
179 |
+
"learning_rate": 7.777777777777778e-05,
|
180 |
+
"loss": 0.0001,
|
181 |
+
"step": 220
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 12.777777777777779,
|
185 |
+
"grad_norm": 0.001513423747383058,
|
186 |
+
"learning_rate": 7.222222222222222e-05,
|
187 |
+
"loss": 0.0001,
|
188 |
+
"step": 230
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 13.333333333333334,
|
192 |
+
"grad_norm": 0.002179619623348117,
|
193 |
+
"learning_rate": 6.666666666666667e-05,
|
194 |
+
"loss": 0.0001,
|
195 |
+
"step": 240
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 13.88888888888889,
|
199 |
+
"grad_norm": 0.0014120868872851133,
|
200 |
+
"learning_rate": 6.111111111111112e-05,
|
201 |
+
"loss": 0.0001,
|
202 |
+
"step": 250
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 14.444444444444445,
|
206 |
+
"grad_norm": 0.001132520497776568,
|
207 |
+
"learning_rate": 5.555555555555556e-05,
|
208 |
+
"loss": 0.0001,
|
209 |
+
"step": 260
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 15.0,
|
213 |
+
"grad_norm": 0.0012154107680544257,
|
214 |
+
"learning_rate": 5e-05,
|
215 |
+
"loss": 0.0001,
|
216 |
+
"step": 270
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 15.555555555555555,
|
220 |
+
"grad_norm": 0.002115760464221239,
|
221 |
+
"learning_rate": 4.4444444444444447e-05,
|
222 |
+
"loss": 0.0001,
|
223 |
+
"step": 280
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 16.11111111111111,
|
227 |
+
"grad_norm": 0.0015289848670363426,
|
228 |
+
"learning_rate": 3.888888888888889e-05,
|
229 |
+
"loss": 0.0001,
|
230 |
+
"step": 290
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 16.666666666666668,
|
234 |
+
"grad_norm": 0.0009787428425624967,
|
235 |
+
"learning_rate": 3.3333333333333335e-05,
|
236 |
+
"loss": 0.0001,
|
237 |
+
"step": 300
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 16.666666666666668,
|
241 |
+
"eval_accuracy": 0.9058823529411765,
|
242 |
+
"eval_loss": 0.6680212616920471,
|
243 |
+
"eval_runtime": 1.8187,
|
244 |
+
"eval_samples_per_second": 46.736,
|
245 |
+
"eval_steps_per_second": 6.048,
|
246 |
+
"step": 300
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 17.22222222222222,
|
250 |
+
"grad_norm": 0.001420836430042982,
|
251 |
+
"learning_rate": 2.777777777777778e-05,
|
252 |
+
"loss": 0.0001,
|
253 |
+
"step": 310
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 17.77777777777778,
|
257 |
+
"grad_norm": 0.0010666553862392902,
|
258 |
+
"learning_rate": 2.2222222222222223e-05,
|
259 |
+
"loss": 0.0001,
|
260 |
+
"step": 320
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 18.333333333333332,
|
264 |
+
"grad_norm": 0.0015172103885561228,
|
265 |
+
"learning_rate": 1.6666666666666667e-05,
|
266 |
+
"loss": 0.0001,
|
267 |
+
"step": 330
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 18.88888888888889,
|
271 |
+
"grad_norm": 0.0011879707453772426,
|
272 |
+
"learning_rate": 1.1111111111111112e-05,
|
273 |
+
"loss": 0.0001,
|
274 |
+
"step": 340
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 19.444444444444443,
|
278 |
+
"grad_norm": 0.0010126435663551092,
|
279 |
+
"learning_rate": 5.555555555555556e-06,
|
280 |
+
"loss": 0.0001,
|
281 |
+
"step": 350
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 20.0,
|
285 |
+
"grad_norm": 0.0008644484914839268,
|
286 |
+
"learning_rate": 0.0,
|
287 |
+
"loss": 0.0001,
|
288 |
+
"step": 360
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 20.0,
|
292 |
+
"step": 360,
|
293 |
+
"total_flos": 4.417082996594688e+17,
|
294 |
+
"train_loss": 0.08463575366784223,
|
295 |
+
"train_runtime": 382.9626,
|
296 |
+
"train_samples_per_second": 14.884,
|
297 |
+
"train_steps_per_second": 0.94
|
298 |
+
}
|
299 |
+
],
|
300 |
+
"logging_steps": 10,
|
301 |
+
"max_steps": 360,
|
302 |
+
"num_input_tokens_seen": 0,
|
303 |
+
"num_train_epochs": 20,
|
304 |
+
"save_steps": 100,
|
305 |
+
"total_flos": 4.417082996594688e+17,
|
306 |
+
"train_batch_size": 16,
|
307 |
+
"trial_name": null,
|
308 |
+
"trial_params": null
|
309 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:457a4f6a155fba095bde6d77ebdfb0d9648139ed63be3da9aca8aeb714c1c11b
|
3 |
+
size 4984
|