Model save
Browse files- README.md +21 -10
- all_results.json +10 -10
- eval_results.json +5 -6
- model.safetensors +1 -1
- runs/Dec01_13-41-24_610b2a9400b8/events.out.tfevents.1701438092.610b2a9400b8.3653.8 +3 -0
- train_results.json +5 -5
- trainer_state.json +111 -111
- 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 [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) 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 |
|
@@ -58,19 +58,30 @@ The following hyperparameters were used during training:
|
|
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 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
|
75 |
|
76 |
### Framework versions
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.9887218045112782
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.0732
|
36 |
+
- Accuracy: 0.9887
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 50
|
62 |
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 0.2908 | 2.94 | 100 | 0.1524 | 0.9511 |
|
69 |
+
| 0.1806 | 5.88 | 200 | 0.1269 | 0.9586 |
|
70 |
+
| 0.1135 | 8.82 | 300 | 0.0720 | 0.9774 |
|
71 |
+
| 0.1061 | 11.76 | 400 | 0.1519 | 0.9624 |
|
72 |
+
| 0.0816 | 14.71 | 500 | 0.1845 | 0.9398 |
|
73 |
+
| 0.0815 | 17.65 | 600 | 0.0966 | 0.9737 |
|
74 |
+
| 0.0741 | 20.59 | 700 | 0.1029 | 0.9812 |
|
75 |
+
| 0.0423 | 23.53 | 800 | 0.1519 | 0.9699 |
|
76 |
+
| 0.0468 | 26.47 | 900 | 0.0757 | 0.9850 |
|
77 |
+
| 0.0249 | 29.41 | 1000 | 0.0859 | 0.9850 |
|
78 |
+
| 0.0443 | 32.35 | 1100 | 0.0878 | 0.9774 |
|
79 |
+
| 0.0291 | 35.29 | 1200 | 0.0487 | 0.9887 |
|
80 |
+
| 0.0263 | 38.24 | 1300 | 0.0643 | 0.9887 |
|
81 |
+
| 0.0239 | 41.18 | 1400 | 0.1042 | 0.9774 |
|
82 |
+
| 0.0331 | 44.12 | 1500 | 0.0679 | 0.9887 |
|
83 |
+
| 0.0103 | 47.06 | 1600 | 0.0723 | 0.9887 |
|
84 |
+
| 0.0131 | 50.0 | 1700 | 0.0732 | 0.9887 |
|
85 |
|
86 |
|
87 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
-
"total_flos":
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second":
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.015037593984962405,
|
4 |
+
"eval_loss": 2.07399845123291,
|
5 |
+
"eval_runtime": 3.7505,
|
6 |
+
"eval_samples_per_second": 70.923,
|
7 |
+
"eval_steps_per_second": 9.065,
|
8 |
+
"total_flos": 5.337848001643315e+17,
|
9 |
+
"train_loss": 0.17142059330773704,
|
10 |
+
"train_runtime": 289.6781,
|
11 |
+
"train_samples_per_second": 73.323,
|
12 |
+
"train_steps_per_second": 2.347
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"eval_steps_per_second": 12.913
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"eval_accuracy": 0.015037593984962405,
|
3 |
+
"eval_loss": 2.07399845123291,
|
4 |
+
"eval_runtime": 3.7505,
|
5 |
+
"eval_samples_per_second": 70.923,
|
6 |
+
"eval_steps_per_second": 9.065
|
|
|
7 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 111323316
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a925714ef2935d8483bd6ac2cc822604c804a1a4e0e9f6c1009b76d6af332472
|
3 |
size 111323316
|
runs/Dec01_13-41-24_610b2a9400b8/events.out.tfevents.1701438092.610b2a9400b8.3653.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44278824c45c5f66cfc1d834fe8aa9456abef81f190b89f154cc7d318c6c92ec
|
3 |
+
size 37403
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"total_flos": 5.337848001643315e+17,
|
4 |
+
"train_loss": 0.17142059330773704,
|
5 |
+
"train_runtime": 289.6781,
|
6 |
+
"train_samples_per_second": 73.323,
|
7 |
+
"train_steps_per_second": 2.347
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "finetuned-Leukemia-cell/checkpoint-600",
|
4 |
"epoch": 20.0,
|
5 |
"eval_steps": 100,
|
@@ -10,481 +10,481 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.29,
|
13 |
-
"learning_rate": 0.
|
14 |
-
"loss": 1.
|
15 |
"step": 10
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.59,
|
19 |
-
"learning_rate": 0.
|
20 |
-
"loss": 1.
|
21 |
"step": 20
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.88,
|
25 |
-
"learning_rate": 0.
|
26 |
-
"loss":
|
27 |
"step": 30
|
28 |
},
|
29 |
{
|
30 |
"epoch": 1.18,
|
31 |
-
"learning_rate": 0.
|
32 |
-
"loss":
|
33 |
"step": 40
|
34 |
},
|
35 |
{
|
36 |
"epoch": 1.47,
|
37 |
-
"learning_rate": 0.
|
38 |
-
"loss":
|
39 |
"step": 50
|
40 |
},
|
41 |
{
|
42 |
"epoch": 1.76,
|
43 |
-
"learning_rate": 0.
|
44 |
-
"loss":
|
45 |
"step": 60
|
46 |
},
|
47 |
{
|
48 |
"epoch": 2.06,
|
49 |
"learning_rate": 0.00018029411764705885,
|
50 |
-
"loss":
|
51 |
"step": 70
|
52 |
},
|
53 |
{
|
54 |
"epoch": 2.35,
|
55 |
"learning_rate": 0.00017735294117647059,
|
56 |
-
"loss":
|
57 |
"step": 80
|
58 |
},
|
59 |
{
|
60 |
"epoch": 2.65,
|
61 |
"learning_rate": 0.00017441176470588235,
|
62 |
-
"loss":
|
63 |
"step": 90
|
64 |
},
|
65 |
{
|
66 |
"epoch": 2.94,
|
67 |
"learning_rate": 0.00017147058823529412,
|
68 |
-
"loss": 0.
|
69 |
"step": 100
|
70 |
},
|
71 |
{
|
72 |
"epoch": 2.94,
|
73 |
-
"eval_accuracy": 0.
|
74 |
-
"eval_loss": 0.
|
75 |
-
"eval_runtime":
|
76 |
-
"eval_samples_per_second":
|
77 |
-
"eval_steps_per_second":
|
78 |
"step": 100
|
79 |
},
|
80 |
{
|
81 |
"epoch": 3.24,
|
82 |
"learning_rate": 0.00016852941176470588,
|
83 |
-
"loss": 0.
|
84 |
"step": 110
|
85 |
},
|
86 |
{
|
87 |
"epoch": 3.53,
|
88 |
"learning_rate": 0.00016558823529411765,
|
89 |
-
"loss": 0.
|
90 |
"step": 120
|
91 |
},
|
92 |
{
|
93 |
"epoch": 3.82,
|
94 |
"learning_rate": 0.0001626470588235294,
|
95 |
-
"loss": 0.
|
96 |
"step": 130
|
97 |
},
|
98 |
{
|
99 |
"epoch": 4.12,
|
100 |
"learning_rate": 0.0001597058823529412,
|
101 |
-
"loss": 0.
|
102 |
"step": 140
|
103 |
},
|
104 |
{
|
105 |
"epoch": 4.41,
|
106 |
"learning_rate": 0.00015676470588235294,
|
107 |
-
"loss": 0.
|
108 |
"step": 150
|
109 |
},
|
110 |
{
|
111 |
"epoch": 4.71,
|
112 |
"learning_rate": 0.00015382352941176473,
|
113 |
-
"loss": 0.
|
114 |
"step": 160
|
115 |
},
|
116 |
{
|
117 |
"epoch": 5.0,
|
118 |
"learning_rate": 0.00015088235294117647,
|
119 |
-
"loss": 0.
|
120 |
"step": 170
|
121 |
},
|
122 |
{
|
123 |
"epoch": 5.29,
|
124 |
"learning_rate": 0.00014794117647058826,
|
125 |
-
"loss": 0.
|
126 |
"step": 180
|
127 |
},
|
128 |
{
|
129 |
"epoch": 5.59,
|
130 |
"learning_rate": 0.000145,
|
131 |
-
"loss": 0.
|
132 |
"step": 190
|
133 |
},
|
134 |
{
|
135 |
"epoch": 5.88,
|
136 |
"learning_rate": 0.00014205882352941177,
|
137 |
-
"loss": 0.
|
138 |
"step": 200
|
139 |
},
|
140 |
{
|
141 |
"epoch": 5.88,
|
142 |
-
"eval_accuracy": 0.
|
143 |
-
"eval_loss": 0.
|
144 |
-
"eval_runtime": 2.
|
145 |
-
"eval_samples_per_second":
|
146 |
-
"eval_steps_per_second":
|
147 |
"step": 200
|
148 |
},
|
149 |
{
|
150 |
"epoch": 6.18,
|
151 |
"learning_rate": 0.00013911764705882353,
|
152 |
-
"loss": 0.
|
153 |
"step": 210
|
154 |
},
|
155 |
{
|
156 |
"epoch": 6.47,
|
157 |
"learning_rate": 0.0001361764705882353,
|
158 |
-
"loss": 0.
|
159 |
"step": 220
|
160 |
},
|
161 |
{
|
162 |
"epoch": 6.76,
|
163 |
"learning_rate": 0.00013323529411764706,
|
164 |
-
"loss": 0.
|
165 |
"step": 230
|
166 |
},
|
167 |
{
|
168 |
"epoch": 7.06,
|
169 |
"learning_rate": 0.00013029411764705883,
|
170 |
-
"loss": 0.
|
171 |
"step": 240
|
172 |
},
|
173 |
{
|
174 |
"epoch": 7.35,
|
175 |
"learning_rate": 0.0001273529411764706,
|
176 |
-
"loss": 0.
|
177 |
"step": 250
|
178 |
},
|
179 |
{
|
180 |
"epoch": 7.65,
|
181 |
"learning_rate": 0.00012441176470588236,
|
182 |
-
"loss": 0.
|
183 |
"step": 260
|
184 |
},
|
185 |
{
|
186 |
"epoch": 7.94,
|
187 |
"learning_rate": 0.00012147058823529412,
|
188 |
-
"loss": 0.
|
189 |
"step": 270
|
190 |
},
|
191 |
{
|
192 |
"epoch": 8.24,
|
193 |
"learning_rate": 0.00011852941176470589,
|
194 |
-
"loss": 0.
|
195 |
"step": 280
|
196 |
},
|
197 |
{
|
198 |
"epoch": 8.53,
|
199 |
"learning_rate": 0.00011558823529411764,
|
200 |
-
"loss": 0.
|
201 |
"step": 290
|
202 |
},
|
203 |
{
|
204 |
"epoch": 8.82,
|
205 |
"learning_rate": 0.00011264705882352942,
|
206 |
-
"loss": 0.
|
207 |
"step": 300
|
208 |
},
|
209 |
{
|
210 |
"epoch": 8.82,
|
211 |
-
"eval_accuracy": 0.
|
212 |
-
"eval_loss": 0.
|
213 |
-
"eval_runtime":
|
214 |
-
"eval_samples_per_second":
|
215 |
-
"eval_steps_per_second":
|
216 |
"step": 300
|
217 |
},
|
218 |
{
|
219 |
"epoch": 9.12,
|
220 |
"learning_rate": 0.0001097058823529412,
|
221 |
-
"loss": 0.
|
222 |
"step": 310
|
223 |
},
|
224 |
{
|
225 |
"epoch": 9.41,
|
226 |
"learning_rate": 0.00010676470588235295,
|
227 |
-
"loss": 0.
|
228 |
"step": 320
|
229 |
},
|
230 |
{
|
231 |
"epoch": 9.71,
|
232 |
"learning_rate": 0.00010382352941176472,
|
233 |
-
"loss": 0.
|
234 |
"step": 330
|
235 |
},
|
236 |
{
|
237 |
"epoch": 10.0,
|
238 |
"learning_rate": 0.00010088235294117648,
|
239 |
-
"loss": 0.
|
240 |
"step": 340
|
241 |
},
|
242 |
{
|
243 |
"epoch": 10.29,
|
244 |
"learning_rate": 9.794117647058824e-05,
|
245 |
-
"loss": 0.
|
246 |
"step": 350
|
247 |
},
|
248 |
{
|
249 |
"epoch": 10.59,
|
250 |
"learning_rate": 9.5e-05,
|
251 |
-
"loss": 0.
|
252 |
"step": 360
|
253 |
},
|
254 |
{
|
255 |
"epoch": 10.88,
|
256 |
"learning_rate": 9.205882352941177e-05,
|
257 |
-
"loss": 0.
|
258 |
"step": 370
|
259 |
},
|
260 |
{
|
261 |
"epoch": 11.18,
|
262 |
"learning_rate": 8.911764705882354e-05,
|
263 |
-
"loss": 0.
|
264 |
"step": 380
|
265 |
},
|
266 |
{
|
267 |
"epoch": 11.47,
|
268 |
"learning_rate": 8.61764705882353e-05,
|
269 |
-
"loss": 0.
|
270 |
"step": 390
|
271 |
},
|
272 |
{
|
273 |
"epoch": 11.76,
|
274 |
"learning_rate": 8.323529411764707e-05,
|
275 |
-
"loss": 0.
|
276 |
"step": 400
|
277 |
},
|
278 |
{
|
279 |
"epoch": 11.76,
|
280 |
-
"eval_accuracy": 0.
|
281 |
-
"eval_loss": 0.
|
282 |
-
"eval_runtime": 2.
|
283 |
-
"eval_samples_per_second":
|
284 |
-
"eval_steps_per_second":
|
285 |
"step": 400
|
286 |
},
|
287 |
{
|
288 |
"epoch": 12.06,
|
289 |
"learning_rate": 8.029411764705883e-05,
|
290 |
-
"loss": 0.
|
291 |
"step": 410
|
292 |
},
|
293 |
{
|
294 |
"epoch": 12.35,
|
295 |
"learning_rate": 7.73529411764706e-05,
|
296 |
-
"loss": 0.
|
297 |
"step": 420
|
298 |
},
|
299 |
{
|
300 |
"epoch": 12.65,
|
301 |
"learning_rate": 7.441176470588236e-05,
|
302 |
-
"loss": 0.
|
303 |
"step": 430
|
304 |
},
|
305 |
{
|
306 |
"epoch": 12.94,
|
307 |
"learning_rate": 7.147058823529412e-05,
|
308 |
-
"loss": 0.
|
309 |
"step": 440
|
310 |
},
|
311 |
{
|
312 |
"epoch": 13.24,
|
313 |
"learning_rate": 6.852941176470589e-05,
|
314 |
-
"loss": 0.
|
315 |
"step": 450
|
316 |
},
|
317 |
{
|
318 |
"epoch": 13.53,
|
319 |
"learning_rate": 6.558823529411765e-05,
|
320 |
-
"loss": 0.
|
321 |
"step": 460
|
322 |
},
|
323 |
{
|
324 |
"epoch": 13.82,
|
325 |
"learning_rate": 6.264705882352942e-05,
|
326 |
-
"loss": 0.
|
327 |
"step": 470
|
328 |
},
|
329 |
{
|
330 |
"epoch": 14.12,
|
331 |
"learning_rate": 5.970588235294118e-05,
|
332 |
-
"loss": 0.
|
333 |
"step": 480
|
334 |
},
|
335 |
{
|
336 |
"epoch": 14.41,
|
337 |
"learning_rate": 5.676470588235294e-05,
|
338 |
-
"loss": 0.
|
339 |
"step": 490
|
340 |
},
|
341 |
{
|
342 |
"epoch": 14.71,
|
343 |
"learning_rate": 5.382352941176471e-05,
|
344 |
-
"loss": 0.
|
345 |
"step": 500
|
346 |
},
|
347 |
{
|
348 |
"epoch": 14.71,
|
349 |
-
"eval_accuracy": 0.
|
350 |
-
"eval_loss": 0.
|
351 |
-
"eval_runtime":
|
352 |
-
"eval_samples_per_second":
|
353 |
-
"eval_steps_per_second":
|
354 |
"step": 500
|
355 |
},
|
356 |
{
|
357 |
"epoch": 15.0,
|
358 |
"learning_rate": 5.088235294117647e-05,
|
359 |
-
"loss": 0.
|
360 |
"step": 510
|
361 |
},
|
362 |
{
|
363 |
"epoch": 15.29,
|
364 |
"learning_rate": 4.794117647058824e-05,
|
365 |
-
"loss": 0.
|
366 |
"step": 520
|
367 |
},
|
368 |
{
|
369 |
"epoch": 15.59,
|
370 |
"learning_rate": 4.5e-05,
|
371 |
-
"loss": 0.
|
372 |
"step": 530
|
373 |
},
|
374 |
{
|
375 |
"epoch": 15.88,
|
376 |
"learning_rate": 4.205882352941177e-05,
|
377 |
-
"loss": 0.
|
378 |
"step": 540
|
379 |
},
|
380 |
{
|
381 |
"epoch": 16.18,
|
382 |
"learning_rate": 3.911764705882353e-05,
|
383 |
-
"loss": 0.
|
384 |
"step": 550
|
385 |
},
|
386 |
{
|
387 |
"epoch": 16.47,
|
388 |
"learning_rate": 3.61764705882353e-05,
|
389 |
-
"loss": 0.
|
390 |
"step": 560
|
391 |
},
|
392 |
{
|
393 |
"epoch": 16.76,
|
394 |
"learning_rate": 3.3235294117647056e-05,
|
395 |
-
"loss": 0.
|
396 |
"step": 570
|
397 |
},
|
398 |
{
|
399 |
"epoch": 17.06,
|
400 |
"learning_rate": 3.0294117647058824e-05,
|
401 |
-
"loss": 0.
|
402 |
"step": 580
|
403 |
},
|
404 |
{
|
405 |
"epoch": 17.35,
|
406 |
"learning_rate": 2.7352941176470593e-05,
|
407 |
-
"loss": 0.
|
408 |
"step": 590
|
409 |
},
|
410 |
{
|
411 |
"epoch": 17.65,
|
412 |
"learning_rate": 2.4411764705882354e-05,
|
413 |
-
"loss": 0.
|
414 |
"step": 600
|
415 |
},
|
416 |
{
|
417 |
"epoch": 17.65,
|
418 |
-
"eval_accuracy": 0.
|
419 |
-
"eval_loss": 0.
|
420 |
-
"eval_runtime":
|
421 |
-
"eval_samples_per_second":
|
422 |
-
"eval_steps_per_second":
|
423 |
"step": 600
|
424 |
},
|
425 |
{
|
426 |
"epoch": 17.94,
|
427 |
"learning_rate": 2.1470588235294116e-05,
|
428 |
-
"loss": 0.
|
429 |
"step": 610
|
430 |
},
|
431 |
{
|
432 |
"epoch": 18.24,
|
433 |
"learning_rate": 1.8529411764705884e-05,
|
434 |
-
"loss": 0.
|
435 |
"step": 620
|
436 |
},
|
437 |
{
|
438 |
"epoch": 18.53,
|
439 |
"learning_rate": 1.558823529411765e-05,
|
440 |
-
"loss": 0.
|
441 |
"step": 630
|
442 |
},
|
443 |
{
|
444 |
"epoch": 18.82,
|
445 |
"learning_rate": 1.2647058823529412e-05,
|
446 |
-
"loss": 0.
|
447 |
"step": 640
|
448 |
},
|
449 |
{
|
450 |
"epoch": 19.12,
|
451 |
"learning_rate": 9.705882352941177e-06,
|
452 |
-
"loss": 0.
|
453 |
"step": 650
|
454 |
},
|
455 |
{
|
456 |
"epoch": 19.41,
|
457 |
"learning_rate": 6.7647058823529414e-06,
|
458 |
-
"loss": 0.
|
459 |
"step": 660
|
460 |
},
|
461 |
{
|
462 |
"epoch": 19.71,
|
463 |
"learning_rate": 3.823529411764706e-06,
|
464 |
-
"loss": 0.
|
465 |
"step": 670
|
466 |
},
|
467 |
{
|
468 |
"epoch": 20.0,
|
469 |
"learning_rate": 8.823529411764706e-07,
|
470 |
-
"loss": 0.
|
471 |
"step": 680
|
472 |
},
|
473 |
{
|
474 |
"epoch": 20.0,
|
475 |
"step": 680,
|
476 |
-
"total_flos":
|
477 |
-
"train_loss": 0.
|
478 |
-
"train_runtime":
|
479 |
-
"train_samples_per_second":
|
480 |
-
"train_steps_per_second":
|
481 |
}
|
482 |
],
|
483 |
"logging_steps": 10,
|
484 |
"max_steps": 680,
|
485 |
"num_train_epochs": 20,
|
486 |
"save_steps": 100,
|
487 |
-
"total_flos":
|
488 |
"trial_name": null,
|
489 |
"trial_params": null
|
490 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.05951835587620735,
|
3 |
"best_model_checkpoint": "finetuned-Leukemia-cell/checkpoint-600",
|
4 |
"epoch": 20.0,
|
5 |
"eval_steps": 100,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.29,
|
13 |
+
"learning_rate": 0.00019705882352941177,
|
14 |
+
"loss": 1.5799,
|
15 |
"step": 10
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.59,
|
19 |
+
"learning_rate": 0.00019441176470588235,
|
20 |
+
"loss": 1.1614,
|
21 |
"step": 20
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.88,
|
25 |
+
"learning_rate": 0.00019147058823529414,
|
26 |
+
"loss": 0.8677,
|
27 |
"step": 30
|
28 |
},
|
29 |
{
|
30 |
"epoch": 1.18,
|
31 |
+
"learning_rate": 0.00018882352941176472,
|
32 |
+
"loss": 0.7303,
|
33 |
"step": 40
|
34 |
},
|
35 |
{
|
36 |
"epoch": 1.47,
|
37 |
+
"learning_rate": 0.00018588235294117648,
|
38 |
+
"loss": 0.4837,
|
39 |
"step": 50
|
40 |
},
|
41 |
{
|
42 |
"epoch": 1.76,
|
43 |
+
"learning_rate": 0.00018294117647058825,
|
44 |
+
"loss": 0.4625,
|
45 |
"step": 60
|
46 |
},
|
47 |
{
|
48 |
"epoch": 2.06,
|
49 |
"learning_rate": 0.00018029411764705885,
|
50 |
+
"loss": 0.3693,
|
51 |
"step": 70
|
52 |
},
|
53 |
{
|
54 |
"epoch": 2.35,
|
55 |
"learning_rate": 0.00017735294117647059,
|
56 |
+
"loss": 0.331,
|
57 |
"step": 80
|
58 |
},
|
59 |
{
|
60 |
"epoch": 2.65,
|
61 |
"learning_rate": 0.00017441176470588235,
|
62 |
+
"loss": 0.2914,
|
63 |
"step": 90
|
64 |
},
|
65 |
{
|
66 |
"epoch": 2.94,
|
67 |
"learning_rate": 0.00017147058823529412,
|
68 |
+
"loss": 0.2926,
|
69 |
"step": 100
|
70 |
},
|
71 |
{
|
72 |
"epoch": 2.94,
|
73 |
+
"eval_accuracy": 0.943609022556391,
|
74 |
+
"eval_loss": 0.15237735211849213,
|
75 |
+
"eval_runtime": 1.9186,
|
76 |
+
"eval_samples_per_second": 138.643,
|
77 |
+
"eval_steps_per_second": 17.721,
|
78 |
"step": 100
|
79 |
},
|
80 |
{
|
81 |
"epoch": 3.24,
|
82 |
"learning_rate": 0.00016852941176470588,
|
83 |
+
"loss": 0.2343,
|
84 |
"step": 110
|
85 |
},
|
86 |
{
|
87 |
"epoch": 3.53,
|
88 |
"learning_rate": 0.00016558823529411765,
|
89 |
+
"loss": 0.2078,
|
90 |
"step": 120
|
91 |
},
|
92 |
{
|
93 |
"epoch": 3.82,
|
94 |
"learning_rate": 0.0001626470588235294,
|
95 |
+
"loss": 0.2448,
|
96 |
"step": 130
|
97 |
},
|
98 |
{
|
99 |
"epoch": 4.12,
|
100 |
"learning_rate": 0.0001597058823529412,
|
101 |
+
"loss": 0.2146,
|
102 |
"step": 140
|
103 |
},
|
104 |
{
|
105 |
"epoch": 4.41,
|
106 |
"learning_rate": 0.00015676470588235294,
|
107 |
+
"loss": 0.2086,
|
108 |
"step": 150
|
109 |
},
|
110 |
{
|
111 |
"epoch": 4.71,
|
112 |
"learning_rate": 0.00015382352941176473,
|
113 |
+
"loss": 0.1924,
|
114 |
"step": 160
|
115 |
},
|
116 |
{
|
117 |
"epoch": 5.0,
|
118 |
"learning_rate": 0.00015088235294117647,
|
119 |
+
"loss": 0.0882,
|
120 |
"step": 170
|
121 |
},
|
122 |
{
|
123 |
"epoch": 5.29,
|
124 |
"learning_rate": 0.00014794117647058826,
|
125 |
+
"loss": 0.1726,
|
126 |
"step": 180
|
127 |
},
|
128 |
{
|
129 |
"epoch": 5.59,
|
130 |
"learning_rate": 0.000145,
|
131 |
+
"loss": 0.1193,
|
132 |
"step": 190
|
133 |
},
|
134 |
{
|
135 |
"epoch": 5.88,
|
136 |
"learning_rate": 0.00014205882352941177,
|
137 |
+
"loss": 0.1844,
|
138 |
"step": 200
|
139 |
},
|
140 |
{
|
141 |
"epoch": 5.88,
|
142 |
+
"eval_accuracy": 0.943609022556391,
|
143 |
+
"eval_loss": 0.1717682033777237,
|
144 |
+
"eval_runtime": 2.2294,
|
145 |
+
"eval_samples_per_second": 119.314,
|
146 |
+
"eval_steps_per_second": 15.251,
|
147 |
"step": 200
|
148 |
},
|
149 |
{
|
150 |
"epoch": 6.18,
|
151 |
"learning_rate": 0.00013911764705882353,
|
152 |
+
"loss": 0.31,
|
153 |
"step": 210
|
154 |
},
|
155 |
{
|
156 |
"epoch": 6.47,
|
157 |
"learning_rate": 0.0001361764705882353,
|
158 |
+
"loss": 0.1387,
|
159 |
"step": 220
|
160 |
},
|
161 |
{
|
162 |
"epoch": 6.76,
|
163 |
"learning_rate": 0.00013323529411764706,
|
164 |
+
"loss": 0.2172,
|
165 |
"step": 230
|
166 |
},
|
167 |
{
|
168 |
"epoch": 7.06,
|
169 |
"learning_rate": 0.00013029411764705883,
|
170 |
+
"loss": 0.1062,
|
171 |
"step": 240
|
172 |
},
|
173 |
{
|
174 |
"epoch": 7.35,
|
175 |
"learning_rate": 0.0001273529411764706,
|
176 |
+
"loss": 0.1055,
|
177 |
"step": 250
|
178 |
},
|
179 |
{
|
180 |
"epoch": 7.65,
|
181 |
"learning_rate": 0.00012441176470588236,
|
182 |
+
"loss": 0.087,
|
183 |
"step": 260
|
184 |
},
|
185 |
{
|
186 |
"epoch": 7.94,
|
187 |
"learning_rate": 0.00012147058823529412,
|
188 |
+
"loss": 0.0817,
|
189 |
"step": 270
|
190 |
},
|
191 |
{
|
192 |
"epoch": 8.24,
|
193 |
"learning_rate": 0.00011852941176470589,
|
194 |
+
"loss": 0.0727,
|
195 |
"step": 280
|
196 |
},
|
197 |
{
|
198 |
"epoch": 8.53,
|
199 |
"learning_rate": 0.00011558823529411764,
|
200 |
+
"loss": 0.0561,
|
201 |
"step": 290
|
202 |
},
|
203 |
{
|
204 |
"epoch": 8.82,
|
205 |
"learning_rate": 0.00011264705882352942,
|
206 |
+
"loss": 0.1189,
|
207 |
"step": 300
|
208 |
},
|
209 |
{
|
210 |
"epoch": 8.82,
|
211 |
+
"eval_accuracy": 0.9661654135338346,
|
212 |
+
"eval_loss": 0.08863785862922668,
|
213 |
+
"eval_runtime": 1.8695,
|
214 |
+
"eval_samples_per_second": 142.285,
|
215 |
+
"eval_steps_per_second": 18.187,
|
216 |
"step": 300
|
217 |
},
|
218 |
{
|
219 |
"epoch": 9.12,
|
220 |
"learning_rate": 0.0001097058823529412,
|
221 |
+
"loss": 0.0705,
|
222 |
"step": 310
|
223 |
},
|
224 |
{
|
225 |
"epoch": 9.41,
|
226 |
"learning_rate": 0.00010676470588235295,
|
227 |
+
"loss": 0.147,
|
228 |
"step": 320
|
229 |
},
|
230 |
{
|
231 |
"epoch": 9.71,
|
232 |
"learning_rate": 0.00010382352941176472,
|
233 |
+
"loss": 0.0612,
|
234 |
"step": 330
|
235 |
},
|
236 |
{
|
237 |
"epoch": 10.0,
|
238 |
"learning_rate": 0.00010088235294117648,
|
239 |
+
"loss": 0.0926,
|
240 |
"step": 340
|
241 |
},
|
242 |
{
|
243 |
"epoch": 10.29,
|
244 |
"learning_rate": 9.794117647058824e-05,
|
245 |
+
"loss": 0.0977,
|
246 |
"step": 350
|
247 |
},
|
248 |
{
|
249 |
"epoch": 10.59,
|
250 |
"learning_rate": 9.5e-05,
|
251 |
+
"loss": 0.1104,
|
252 |
"step": 360
|
253 |
},
|
254 |
{
|
255 |
"epoch": 10.88,
|
256 |
"learning_rate": 9.205882352941177e-05,
|
257 |
+
"loss": 0.0834,
|
258 |
"step": 370
|
259 |
},
|
260 |
{
|
261 |
"epoch": 11.18,
|
262 |
"learning_rate": 8.911764705882354e-05,
|
263 |
+
"loss": 0.0831,
|
264 |
"step": 380
|
265 |
},
|
266 |
{
|
267 |
"epoch": 11.47,
|
268 |
"learning_rate": 8.61764705882353e-05,
|
269 |
+
"loss": 0.0464,
|
270 |
"step": 390
|
271 |
},
|
272 |
{
|
273 |
"epoch": 11.76,
|
274 |
"learning_rate": 8.323529411764707e-05,
|
275 |
+
"loss": 0.0682,
|
276 |
"step": 400
|
277 |
},
|
278 |
{
|
279 |
"epoch": 11.76,
|
280 |
+
"eval_accuracy": 0.9699248120300752,
|
281 |
+
"eval_loss": 0.09778111428022385,
|
282 |
+
"eval_runtime": 2.3942,
|
283 |
+
"eval_samples_per_second": 111.103,
|
284 |
+
"eval_steps_per_second": 14.201,
|
285 |
"step": 400
|
286 |
},
|
287 |
{
|
288 |
"epoch": 12.06,
|
289 |
"learning_rate": 8.029411764705883e-05,
|
290 |
+
"loss": 0.0504,
|
291 |
"step": 410
|
292 |
},
|
293 |
{
|
294 |
"epoch": 12.35,
|
295 |
"learning_rate": 7.73529411764706e-05,
|
296 |
+
"loss": 0.0379,
|
297 |
"step": 420
|
298 |
},
|
299 |
{
|
300 |
"epoch": 12.65,
|
301 |
"learning_rate": 7.441176470588236e-05,
|
302 |
+
"loss": 0.0261,
|
303 |
"step": 430
|
304 |
},
|
305 |
{
|
306 |
"epoch": 12.94,
|
307 |
"learning_rate": 7.147058823529412e-05,
|
308 |
+
"loss": 0.0838,
|
309 |
"step": 440
|
310 |
},
|
311 |
{
|
312 |
"epoch": 13.24,
|
313 |
"learning_rate": 6.852941176470589e-05,
|
314 |
+
"loss": 0.0262,
|
315 |
"step": 450
|
316 |
},
|
317 |
{
|
318 |
"epoch": 13.53,
|
319 |
"learning_rate": 6.558823529411765e-05,
|
320 |
+
"loss": 0.0232,
|
321 |
"step": 460
|
322 |
},
|
323 |
{
|
324 |
"epoch": 13.82,
|
325 |
"learning_rate": 6.264705882352942e-05,
|
326 |
+
"loss": 0.0403,
|
327 |
"step": 470
|
328 |
},
|
329 |
{
|
330 |
"epoch": 14.12,
|
331 |
"learning_rate": 5.970588235294118e-05,
|
332 |
+
"loss": 0.049,
|
333 |
"step": 480
|
334 |
},
|
335 |
{
|
336 |
"epoch": 14.41,
|
337 |
"learning_rate": 5.676470588235294e-05,
|
338 |
+
"loss": 0.0606,
|
339 |
"step": 490
|
340 |
},
|
341 |
{
|
342 |
"epoch": 14.71,
|
343 |
"learning_rate": 5.382352941176471e-05,
|
344 |
+
"loss": 0.0439,
|
345 |
"step": 500
|
346 |
},
|
347 |
{
|
348 |
"epoch": 14.71,
|
349 |
+
"eval_accuracy": 0.9736842105263158,
|
350 |
+
"eval_loss": 0.08120405673980713,
|
351 |
+
"eval_runtime": 1.897,
|
352 |
+
"eval_samples_per_second": 140.22,
|
353 |
+
"eval_steps_per_second": 17.923,
|
354 |
"step": 500
|
355 |
},
|
356 |
{
|
357 |
"epoch": 15.0,
|
358 |
"learning_rate": 5.088235294117647e-05,
|
359 |
+
"loss": 0.0495,
|
360 |
"step": 510
|
361 |
},
|
362 |
{
|
363 |
"epoch": 15.29,
|
364 |
"learning_rate": 4.794117647058824e-05,
|
365 |
+
"loss": 0.0337,
|
366 |
"step": 520
|
367 |
},
|
368 |
{
|
369 |
"epoch": 15.59,
|
370 |
"learning_rate": 4.5e-05,
|
371 |
+
"loss": 0.0987,
|
372 |
"step": 530
|
373 |
},
|
374 |
{
|
375 |
"epoch": 15.88,
|
376 |
"learning_rate": 4.205882352941177e-05,
|
377 |
+
"loss": 0.0218,
|
378 |
"step": 540
|
379 |
},
|
380 |
{
|
381 |
"epoch": 16.18,
|
382 |
"learning_rate": 3.911764705882353e-05,
|
383 |
+
"loss": 0.0324,
|
384 |
"step": 550
|
385 |
},
|
386 |
{
|
387 |
"epoch": 16.47,
|
388 |
"learning_rate": 3.61764705882353e-05,
|
389 |
+
"loss": 0.0364,
|
390 |
"step": 560
|
391 |
},
|
392 |
{
|
393 |
"epoch": 16.76,
|
394 |
"learning_rate": 3.3235294117647056e-05,
|
395 |
+
"loss": 0.0284,
|
396 |
"step": 570
|
397 |
},
|
398 |
{
|
399 |
"epoch": 17.06,
|
400 |
"learning_rate": 3.0294117647058824e-05,
|
401 |
+
"loss": 0.0306,
|
402 |
"step": 580
|
403 |
},
|
404 |
{
|
405 |
"epoch": 17.35,
|
406 |
"learning_rate": 2.7352941176470593e-05,
|
407 |
+
"loss": 0.0535,
|
408 |
"step": 590
|
409 |
},
|
410 |
{
|
411 |
"epoch": 17.65,
|
412 |
"learning_rate": 2.4411764705882354e-05,
|
413 |
+
"loss": 0.0544,
|
414 |
"step": 600
|
415 |
},
|
416 |
{
|
417 |
"epoch": 17.65,
|
418 |
+
"eval_accuracy": 0.981203007518797,
|
419 |
+
"eval_loss": 0.05951835587620735,
|
420 |
+
"eval_runtime": 1.8559,
|
421 |
+
"eval_samples_per_second": 143.327,
|
422 |
+
"eval_steps_per_second": 18.32,
|
423 |
"step": 600
|
424 |
},
|
425 |
{
|
426 |
"epoch": 17.94,
|
427 |
"learning_rate": 2.1470588235294116e-05,
|
428 |
+
"loss": 0.0121,
|
429 |
"step": 610
|
430 |
},
|
431 |
{
|
432 |
"epoch": 18.24,
|
433 |
"learning_rate": 1.8529411764705884e-05,
|
434 |
+
"loss": 0.0049,
|
435 |
"step": 620
|
436 |
},
|
437 |
{
|
438 |
"epoch": 18.53,
|
439 |
"learning_rate": 1.558823529411765e-05,
|
440 |
+
"loss": 0.0086,
|
441 |
"step": 630
|
442 |
},
|
443 |
{
|
444 |
"epoch": 18.82,
|
445 |
"learning_rate": 1.2647058823529412e-05,
|
446 |
+
"loss": 0.0102,
|
447 |
"step": 640
|
448 |
},
|
449 |
{
|
450 |
"epoch": 19.12,
|
451 |
"learning_rate": 9.705882352941177e-06,
|
452 |
+
"loss": 0.0342,
|
453 |
"step": 650
|
454 |
},
|
455 |
{
|
456 |
"epoch": 19.41,
|
457 |
"learning_rate": 6.7647058823529414e-06,
|
458 |
+
"loss": 0.0367,
|
459 |
"step": 660
|
460 |
},
|
461 |
{
|
462 |
"epoch": 19.71,
|
463 |
"learning_rate": 3.823529411764706e-06,
|
464 |
+
"loss": 0.0313,
|
465 |
"step": 670
|
466 |
},
|
467 |
{
|
468 |
"epoch": 20.0,
|
469 |
"learning_rate": 8.823529411764706e-07,
|
470 |
+
"loss": 0.0465,
|
471 |
"step": 680
|
472 |
},
|
473 |
{
|
474 |
"epoch": 20.0,
|
475 |
"step": 680,
|
476 |
+
"total_flos": 5.337848001643315e+17,
|
477 |
+
"train_loss": 0.17142059330773704,
|
478 |
+
"train_runtime": 289.6781,
|
479 |
+
"train_samples_per_second": 73.323,
|
480 |
+
"train_steps_per_second": 2.347
|
481 |
}
|
482 |
],
|
483 |
"logging_steps": 10,
|
484 |
"max_steps": 680,
|
485 |
"num_train_epochs": 20,
|
486 |
"save_steps": 100,
|
487 |
+
"total_flos": 5.337848001643315e+17,
|
488 |
"trial_name": null,
|
489 |
"trial_params": null
|
490 |
}
|
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 sha256:68354e0c5b01561e938df0004ef20ef191e70a1505432fac27a2b4cc3d56354e
|
3 |
size 4600
|