Model save
Browse files- README.md +8 -7
- all_results.json +13 -0
- eval_results.json +8 -0
- model.safetensors +1 -1
- runs/Nov30_22-57-39_6c26dad0aabb/events.out.tfevents.1701386629.6c26dad0aabb.7066.2 +3 -0
- runs/Nov30_23-24-53_6c26dad0aabb/events.out.tfevents.1701386704.6c26dad0aabb.7066.3 +3 -0
- train_results.json +8 -0
- trainer_state.json +202 -0
- training_args.bin +1 -1
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 |
|
@@ -53,20 +53,21 @@ More information needed
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 0.0002
|
56 |
-
- train_batch_size:
|
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:
|
62 |
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
-
| 0.
|
69 |
-
| 0.
|
|
|
70 |
|
71 |
|
72 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.9774436090225563
|
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: 0.0870
|
36 |
+
- Accuracy: 0.9774
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 0.0002
|
56 |
+
- train_batch_size: 32
|
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: 10
|
62 |
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 0.1606 | 2.94 | 100 | 0.1829 | 0.9511 |
|
69 |
+
| 0.1895 | 5.88 | 200 | 0.1441 | 0.9662 |
|
70 |
+
| 0.0423 | 8.82 | 300 | 0.0870 | 0.9774 |
|
71 |
|
72 |
|
73 |
### Framework versions
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.9548872180451128,
|
4 |
+
"eval_loss": 0.18233025074005127,
|
5 |
+
"eval_runtime": 2.6375,
|
6 |
+
"eval_samples_per_second": 100.853,
|
7 |
+
"eval_steps_per_second": 12.891,
|
8 |
+
"total_flos": 3.292007238315049e+17,
|
9 |
+
"train_loss": 0.5091555158593761,
|
10 |
+
"train_runtime": 958.3438,
|
11 |
+
"train_samples_per_second": 4.433,
|
12 |
+
"train_steps_per_second": 0.28
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.9548872180451128,
|
4 |
+
"eval_loss": 0.18233025074005127,
|
5 |
+
"eval_runtime": 2.6375,
|
6 |
+
"eval_samples_per_second": 100.853,
|
7 |
+
"eval_steps_per_second": 12.891
|
8 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343239356
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86d8fbbe5587bcb92891682aa722012947d3377ee2016b310819dd2600bc17ef
|
3 |
size 343239356
|
runs/Nov30_22-57-39_6c26dad0aabb/events.out.tfevents.1701386629.6c26dad0aabb.7066.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bea73d0d4adbbe9129f6586d6751a267009f6fa8865d7c9a5b0cc9cb9ad6dd30
|
3 |
+
size 411
|
runs/Nov30_23-24-53_6c26dad0aabb/events.out.tfevents.1701386704.6c26dad0aabb.7066.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:602b22072b791babf9ea719e668e129769682f42f6f62da6b1287ad798a2aa10
|
3 |
+
size 11146
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"total_flos": 3.292007238315049e+17,
|
4 |
+
"train_loss": 0.5091555158593761,
|
5 |
+
"train_runtime": 958.3438,
|
6 |
+
"train_samples_per_second": 4.433,
|
7 |
+
"train_steps_per_second": 0.28
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.18233025074005127,
|
3 |
+
"best_model_checkpoint": "finetuned-Leukemia-cell/checkpoint-200",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 268,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.15,
|
13 |
+
"learning_rate": 0.00019253731343283584,
|
14 |
+
"loss": 1.7951,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.3,
|
19 |
+
"learning_rate": 0.00018507462686567165,
|
20 |
+
"loss": 1.3572,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.45,
|
25 |
+
"learning_rate": 0.00017761194029850748,
|
26 |
+
"loss": 0.98,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.6,
|
31 |
+
"learning_rate": 0.00017014925373134328,
|
32 |
+
"loss": 0.9394,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.75,
|
37 |
+
"learning_rate": 0.00016268656716417911,
|
38 |
+
"loss": 0.7973,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.9,
|
43 |
+
"learning_rate": 0.00015522388059701495,
|
44 |
+
"loss": 0.8591,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.04,
|
49 |
+
"learning_rate": 0.00014776119402985075,
|
50 |
+
"loss": 0.6357,
|
51 |
+
"step": 70
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.19,
|
55 |
+
"learning_rate": 0.00014029850746268658,
|
56 |
+
"loss": 0.6522,
|
57 |
+
"step": 80
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.34,
|
61 |
+
"learning_rate": 0.0001328358208955224,
|
62 |
+
"loss": 0.495,
|
63 |
+
"step": 90
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 1.49,
|
67 |
+
"learning_rate": 0.00012537313432835822,
|
68 |
+
"loss": 0.4862,
|
69 |
+
"step": 100
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 1.49,
|
73 |
+
"eval_accuracy": 0.9172932330827067,
|
74 |
+
"eval_loss": 0.4092223644256592,
|
75 |
+
"eval_runtime": 173.193,
|
76 |
+
"eval_samples_per_second": 1.536,
|
77 |
+
"eval_steps_per_second": 0.196,
|
78 |
+
"step": 100
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 1.64,
|
82 |
+
"learning_rate": 0.00011791044776119405,
|
83 |
+
"loss": 0.5047,
|
84 |
+
"step": 110
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.79,
|
88 |
+
"learning_rate": 0.00011044776119402987,
|
89 |
+
"loss": 0.3878,
|
90 |
+
"step": 120
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 1.94,
|
94 |
+
"learning_rate": 0.00010298507462686569,
|
95 |
+
"loss": 0.43,
|
96 |
+
"step": 130
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 2.09,
|
100 |
+
"learning_rate": 9.552238805970149e-05,
|
101 |
+
"loss": 0.3441,
|
102 |
+
"step": 140
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 2.24,
|
106 |
+
"learning_rate": 8.805970149253732e-05,
|
107 |
+
"loss": 0.3271,
|
108 |
+
"step": 150
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 2.39,
|
112 |
+
"learning_rate": 8.059701492537314e-05,
|
113 |
+
"loss": 0.3415,
|
114 |
+
"step": 160
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 2.54,
|
118 |
+
"learning_rate": 7.313432835820896e-05,
|
119 |
+
"loss": 0.293,
|
120 |
+
"step": 170
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 2.69,
|
124 |
+
"learning_rate": 6.567164179104478e-05,
|
125 |
+
"loss": 0.2864,
|
126 |
+
"step": 180
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 2.84,
|
130 |
+
"learning_rate": 5.82089552238806e-05,
|
131 |
+
"loss": 0.2873,
|
132 |
+
"step": 190
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 2.99,
|
136 |
+
"learning_rate": 5.074626865671642e-05,
|
137 |
+
"loss": 0.2095,
|
138 |
+
"step": 200
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 2.99,
|
142 |
+
"eval_accuracy": 0.9548872180451128,
|
143 |
+
"eval_loss": 0.18233025074005127,
|
144 |
+
"eval_runtime": 2.578,
|
145 |
+
"eval_samples_per_second": 103.183,
|
146 |
+
"eval_steps_per_second": 13.189,
|
147 |
+
"step": 200
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 3.13,
|
151 |
+
"learning_rate": 4.328358208955224e-05,
|
152 |
+
"loss": 0.1822,
|
153 |
+
"step": 210
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 3.28,
|
157 |
+
"learning_rate": 3.582089552238806e-05,
|
158 |
+
"loss": 0.228,
|
159 |
+
"step": 220
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 3.43,
|
163 |
+
"learning_rate": 2.835820895522388e-05,
|
164 |
+
"loss": 0.1377,
|
165 |
+
"step": 230
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 3.58,
|
169 |
+
"learning_rate": 2.0895522388059702e-05,
|
170 |
+
"loss": 0.2099,
|
171 |
+
"step": 240
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 3.73,
|
175 |
+
"learning_rate": 1.3432835820895523e-05,
|
176 |
+
"loss": 0.1576,
|
177 |
+
"step": 250
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 3.88,
|
181 |
+
"learning_rate": 5.970149253731343e-06,
|
182 |
+
"loss": 0.1394,
|
183 |
+
"step": 260
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 4.0,
|
187 |
+
"step": 268,
|
188 |
+
"total_flos": 3.292007238315049e+17,
|
189 |
+
"train_loss": 0.5091555158593761,
|
190 |
+
"train_runtime": 958.3438,
|
191 |
+
"train_samples_per_second": 4.433,
|
192 |
+
"train_steps_per_second": 0.28
|
193 |
+
}
|
194 |
+
],
|
195 |
+
"logging_steps": 10,
|
196 |
+
"max_steps": 268,
|
197 |
+
"num_train_epochs": 4,
|
198 |
+
"save_steps": 100,
|
199 |
+
"total_flos": 3.292007238315049e+17,
|
200 |
+
"trial_name": null,
|
201 |
+
"trial_params": null
|
202 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:945f141fbeb29ad39b8605b232d98a21f0507a88e5e0eb935c00a2a7f5a4a921
|
3 |
size 4600
|