Hugging Face's logo

bansilp
/
xyz

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
bansilp commited on
Commit
d356df9
•
1 Parent(s): 86225eb

Model save

Browse files
Files changed (9) hide show
  1. README.md +13 -8
  2. all_results.json +8 -8
  3. eval_results.json +4 -4
  4. model.safetensors +1 -1
  5. runs/Dec15_03-35-22_d2a76fcee09b/events.out.tfevents.1702611805.d2a76fcee09b.2614.17 +3 -0
  6. runs/Dec15_03-46-10_d2a76fcee09b/events.out.tfevents.1702611985.d2a76fcee09b.36815.0 +3 -0
  7. train_results.json +4 -4
  8. trainer_state.json +113 -113
  9. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9083333333333333
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: 0.5528
36
- - Accuracy: 0.9083
37
 
38
  ## Model description
39
 
@@ -58,17 +58,22 @@ 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: 5
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.0009 | 1.11 | 100 | 0.7068 | 0.8713 |
69
- | 0.0039 | 2.22 | 200 | 0.6391 | 0.8991 |
70
- | 0.0014 | 3.33 | 300 | 0.5536 | 0.9056 |
71
- | 0.0018 | 4.44 | 400 | 0.5528 | 0.9083 |
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9175925925925926
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: 0.3201
36
+ - Accuracy: 0.9176
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: 10
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.6539 | 1.11 | 100 | 0.8063 | 0.75 |
69
+ | 0.2553 | 2.22 | 200 | 0.5555 | 0.8352 |
70
+ | 0.1909 | 3.33 | 300 | 0.5217 | 0.8454 |
71
+ | 0.0999 | 4.44 | 400 | 0.5075 | 0.8722 |
72
+ | 0.0666 | 5.56 | 500 | 0.4633 | 0.8769 |
73
+ | 0.0392 | 6.67 | 600 | 0.4614 | 0.8741 |
74
+ | 0.0111 | 7.78 | 700 | 0.3574 | 0.9102 |
75
+ | 0.0122 | 8.89 | 800 | 0.3159 | 0.9167 |
76
+ | 0.0112 | 10.0 | 900 | 0.3201 | 0.9176 |
77
 
78
 
79
  ### Framework versions
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 5.0,
3
  "eval_accuracy": 0.9083333333333333,
4
- "eval_loss": 0.5385243892669678,
5
- "eval_runtime": 15.071,
6
- "eval_samples_per_second": 71.661,
7
- "eval_steps_per_second": 8.958,
8
  "total_flos": 1.6739319895474176e+18,
9
- "train_loss": 0.0525758553068671,
10
- "train_runtime": 438.9135,
11
- "train_samples_per_second": 49.212,
12
- "train_steps_per_second": 1.025
13
  }
 
1
  {
2
  "epoch": 5.0,
3
  "eval_accuracy": 0.9083333333333333,
4
+ "eval_loss": 0.5533814430236816,
5
+ "eval_runtime": 13.9693,
6
+ "eval_samples_per_second": 77.312,
7
+ "eval_steps_per_second": 9.664,
8
  "total_flos": 1.6739319895474176e+18,
9
+ "train_loss": 0.015028678889438096,
10
+ "train_runtime": 430.7019,
11
+ "train_samples_per_second": 50.151,
12
+ "train_steps_per_second": 1.045
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.0,
3
  "eval_accuracy": 0.9083333333333333,
4
- "eval_loss": 0.5385243892669678,
5
- "eval_runtime": 15.071,
6
- "eval_samples_per_second": 71.661,
7
- "eval_steps_per_second": 8.958
8
  }
 
1
  {
2
  "epoch": 5.0,
3
  "eval_accuracy": 0.9083333333333333,
4
+ "eval_loss": 0.5533814430236816,
5
+ "eval_runtime": 13.9693,
6
+ "eval_samples_per_second": 77.312,
7
+ "eval_steps_per_second": 9.664
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ffdef6ed6dcc0e0387cfae75079af794dfdaa5c63cfb4f5f306726b6a1fae6
3
  size 343245508
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b06ae38c0b51f1466eb373ce6ecf98bcd0f7492b3e486f681a11a79fadb6687
3
  size 343245508
runs/Dec15_03-35-22_d2a76fcee09b/events.out.tfevents.1702611805.d2a76fcee09b.2614.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef5a4d9e5c80a1ec0df54a951c33e6b5eaf4a17c8a44f225ab9519d182b88296
3
+ size 411
runs/Dec15_03-46-10_d2a76fcee09b/events.out.tfevents.1702611985.d2a76fcee09b.36815.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51bea51287a39b0211a5910e37918c77b30a676645f539f5198555ed6af89233
3
+ size 21776
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.0,
3
  "total_flos": 1.6739319895474176e+18,
4
- "train_loss": 0.0525758553068671,
5
- "train_runtime": 438.9135,
6
- "train_samples_per_second": 49.212,
7
- "train_steps_per_second": 1.025
8
  }
 
1
  {
2
  "epoch": 5.0,
3
  "total_flos": 1.6739319895474176e+18,
4
+ "train_loss": 0.015028678889438096,
5
+ "train_runtime": 430.7019,
6
+ "train_samples_per_second": 50.151,
7
+ "train_steps_per_second": 1.045
8
  }
trainer_state.json CHANGED
@@ -10,318 +10,318 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.11,
13
- "learning_rate": 0.0003911111111111111,
14
- "loss": 0.0127,
15
  "step": 10
16
  },
17
  {
18
  "epoch": 0.22,
19
- "learning_rate": 0.0003822222222222223,
20
- "loss": 0.1644,
21
  "step": 20
22
  },
23
  {
24
  "epoch": 0.33,
25
- "learning_rate": 0.0003733333333333334,
26
- "loss": 0.2691,
27
  "step": 30
28
  },
29
  {
30
  "epoch": 0.44,
31
- "learning_rate": 0.00036444444444444447,
32
- "loss": 0.2196,
33
  "step": 40
34
  },
35
  {
36
  "epoch": 0.56,
37
- "learning_rate": 0.00035555555555555557,
38
- "loss": 0.1119,
39
  "step": 50
40
  },
41
  {
42
  "epoch": 0.67,
43
- "learning_rate": 0.00034666666666666667,
44
- "loss": 0.1708,
45
  "step": 60
46
  },
47
  {
48
  "epoch": 0.78,
49
- "learning_rate": 0.00033777777777777777,
50
- "loss": 0.2104,
51
  "step": 70
52
  },
53
  {
54
  "epoch": 0.89,
55
- "learning_rate": 0.00032888888888888887,
56
- "loss": 0.1343,
57
  "step": 80
58
  },
59
  {
60
  "epoch": 1.0,
61
- "learning_rate": 0.00032,
62
- "loss": 0.1185,
63
  "step": 90
64
  },
65
  {
66
  "epoch": 1.11,
67
- "learning_rate": 0.0003111111111111111,
68
- "loss": 0.1059,
69
  "step": 100
70
  },
71
  {
72
  "epoch": 1.11,
73
- "eval_accuracy": 0.8546296296296296,
74
- "eval_loss": 0.693325936794281,
75
- "eval_runtime": 12.9043,
76
- "eval_samples_per_second": 83.693,
77
- "eval_steps_per_second": 10.462,
78
  "step": 100
79
  },
80
  {
81
  "epoch": 1.22,
82
- "learning_rate": 0.0003022222222222222,
83
- "loss": 0.0944,
84
  "step": 110
85
  },
86
  {
87
  "epoch": 1.33,
88
- "learning_rate": 0.0002933333333333333,
89
- "loss": 0.1009,
90
  "step": 120
91
  },
92
  {
93
  "epoch": 1.44,
94
- "learning_rate": 0.0002844444444444445,
95
- "loss": 0.0579,
96
  "step": 130
97
  },
98
  {
99
  "epoch": 1.56,
100
- "learning_rate": 0.0002755555555555556,
101
- "loss": 0.093,
102
  "step": 140
103
  },
104
  {
105
  "epoch": 1.67,
106
- "learning_rate": 0.0002666666666666667,
107
- "loss": 0.054,
108
  "step": 150
109
  },
110
  {
111
  "epoch": 1.78,
112
- "learning_rate": 0.00025777777777777783,
113
- "loss": 0.0366,
114
  "step": 160
115
  },
116
  {
117
  "epoch": 1.89,
118
- "learning_rate": 0.0002488888888888889,
119
- "loss": 0.027,
120
  "step": 170
121
  },
122
  {
123
  "epoch": 2.0,
124
- "learning_rate": 0.00024,
125
- "loss": 0.0369,
126
  "step": 180
127
  },
128
  {
129
  "epoch": 2.11,
130
- "learning_rate": 0.0002311111111111111,
131
- "loss": 0.0354,
132
  "step": 190
133
  },
134
  {
135
  "epoch": 2.22,
136
- "learning_rate": 0.00022222222222222223,
137
- "loss": 0.02,
138
  "step": 200
139
  },
140
  {
141
  "epoch": 2.22,
142
- "eval_accuracy": 0.875,
143
- "eval_loss": 0.656458854675293,
144
- "eval_runtime": 12.7588,
145
- "eval_samples_per_second": 84.647,
146
- "eval_steps_per_second": 10.581,
147
  "step": 200
148
  },
149
  {
150
  "epoch": 2.33,
151
- "learning_rate": 0.00021333333333333333,
152
- "loss": 0.0236,
153
  "step": 210
154
  },
155
  {
156
  "epoch": 2.44,
157
- "learning_rate": 0.00020444444444444443,
158
- "loss": 0.032,
159
  "step": 220
160
  },
161
  {
162
  "epoch": 2.56,
163
- "learning_rate": 0.00019555555555555556,
164
- "loss": 0.0369,
165
  "step": 230
166
  },
167
  {
168
  "epoch": 2.67,
169
- "learning_rate": 0.0001866666666666667,
170
- "loss": 0.0339,
171
  "step": 240
172
  },
173
  {
174
  "epoch": 2.78,
175
- "learning_rate": 0.00017777777777777779,
176
- "loss": 0.0207,
177
  "step": 250
178
  },
179
  {
180
  "epoch": 2.89,
181
- "learning_rate": 0.00016888888888888889,
182
- "loss": 0.0291,
183
  "step": 260
184
  },
185
  {
186
  "epoch": 3.0,
187
- "learning_rate": 0.00016,
188
- "loss": 0.0237,
189
  "step": 270
190
  },
191
  {
192
  "epoch": 3.11,
193
- "learning_rate": 0.0001511111111111111,
194
- "loss": 0.0023,
195
  "step": 280
196
  },
197
  {
198
  "epoch": 3.22,
199
- "learning_rate": 0.00014222222222222224,
200
- "loss": 0.0072,
201
  "step": 290
202
  },
203
  {
204
  "epoch": 3.33,
205
- "learning_rate": 0.00013333333333333334,
206
- "loss": 0.001,
207
  "step": 300
208
  },
209
  {
210
  "epoch": 3.33,
211
- "eval_accuracy": 0.8888888888888888,
212
- "eval_loss": 0.5975281000137329,
213
- "eval_runtime": 12.7539,
214
- "eval_samples_per_second": 84.68,
215
- "eval_steps_per_second": 10.585,
216
  "step": 300
217
  },
218
  {
219
  "epoch": 3.44,
220
- "learning_rate": 0.00012444444444444444,
221
- "loss": 0.0209,
222
  "step": 310
223
  },
224
  {
225
  "epoch": 3.56,
226
- "learning_rate": 0.00011555555555555555,
227
- "loss": 0.0208,
228
  "step": 320
229
  },
230
  {
231
  "epoch": 3.67,
232
- "learning_rate": 0.00010666666666666667,
233
- "loss": 0.0064,
234
  "step": 330
235
  },
236
  {
237
  "epoch": 3.78,
238
- "learning_rate": 9.777777777777778e-05,
239
- "loss": 0.0011,
240
  "step": 340
241
  },
242
  {
243
  "epoch": 3.89,
244
- "learning_rate": 8.888888888888889e-05,
245
- "loss": 0.004,
246
  "step": 350
247
  },
248
  {
249
  "epoch": 4.0,
250
- "learning_rate": 8e-05,
251
- "loss": 0.0097,
252
  "step": 360
253
  },
254
  {
255
  "epoch": 4.11,
256
- "learning_rate": 7.111111111111112e-05,
257
- "loss": 0.0004,
258
  "step": 370
259
  },
260
  {
261
  "epoch": 4.22,
262
- "learning_rate": 6.222222222222222e-05,
263
- "loss": 0.0015,
264
  "step": 380
265
  },
266
  {
267
  "epoch": 4.33,
268
- "learning_rate": 5.333333333333333e-05,
269
- "loss": 0.0004,
270
  "step": 390
271
  },
272
  {
273
  "epoch": 4.44,
274
- "learning_rate": 4.4444444444444447e-05,
275
- "loss": 0.0027,
276
  "step": 400
277
  },
278
  {
279
  "epoch": 4.44,
280
- "eval_accuracy": 0.9064814814814814,
281
- "eval_loss": 0.5585721731185913,
282
- "eval_runtime": 13.4691,
283
- "eval_samples_per_second": 80.184,
284
- "eval_steps_per_second": 10.023,
285
  "step": 400
286
  },
287
  {
288
  "epoch": 4.56,
289
- "learning_rate": 3.555555555555556e-05,
290
- "loss": 0.0003,
291
  "step": 410
292
  },
293
  {
294
  "epoch": 4.67,
295
- "learning_rate": 2.6666666666666667e-05,
296
- "loss": 0.0018,
297
  "step": 420
298
  },
299
  {
300
  "epoch": 4.78,
301
- "learning_rate": 1.777777777777778e-05,
302
- "loss": 0.0054,
303
  "step": 430
304
  },
305
  {
306
  "epoch": 4.89,
307
- "learning_rate": 8.88888888888889e-06,
308
- "loss": 0.0057,
309
  "step": 440
310
  },
311
  {
312
  "epoch": 5.0,
313
  "learning_rate": 0.0,
314
- "loss": 0.0004,
315
  "step": 450
316
  },
317
  {
318
  "epoch": 5.0,
319
  "step": 450,
320
  "total_flos": 1.6739319895474176e+18,
321
- "train_loss": 0.0525758553068671,
322
- "train_runtime": 438.9135,
323
- "train_samples_per_second": 49.212,
324
- "train_steps_per_second": 1.025
325
  }
326
  ],
327
  "logging_steps": 10,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.11,
13
+ "learning_rate": 0.00019555555555555556,
14
+ "loss": 0.0098,
15
  "step": 10
16
  },
17
  {
18
  "epoch": 0.22,
19
+ "learning_rate": 0.00019111111111111114,
20
+ "loss": 0.0428,
21
  "step": 20
22
  },
23
  {
24
  "epoch": 0.33,
25
+ "learning_rate": 0.0001866666666666667,
26
+ "loss": 0.0188,
27
  "step": 30
28
  },
29
  {
30
  "epoch": 0.44,
31
+ "learning_rate": 0.00018222222222222224,
32
+ "loss": 0.0763,
33
  "step": 40
34
  },
35
  {
36
  "epoch": 0.56,
37
+ "learning_rate": 0.00017777777777777779,
38
+ "loss": 0.0098,
39
  "step": 50
40
  },
41
  {
42
  "epoch": 0.67,
43
+ "learning_rate": 0.00017333333333333334,
44
+ "loss": 0.0312,
45
  "step": 60
46
  },
47
  {
48
  "epoch": 0.78,
49
+ "learning_rate": 0.00016888888888888889,
50
+ "loss": 0.0579,
51
  "step": 70
52
  },
53
  {
54
  "epoch": 0.89,
55
+ "learning_rate": 0.00016444444444444444,
56
+ "loss": 0.024,
57
  "step": 80
58
  },
59
  {
60
  "epoch": 1.0,
61
+ "learning_rate": 0.00016,
62
+ "loss": 0.086,
63
  "step": 90
64
  },
65
  {
66
  "epoch": 1.11,
67
+ "learning_rate": 0.00015555555555555556,
68
+ "loss": 0.0009,
69
  "step": 100
70
  },
71
  {
72
  "epoch": 1.11,
73
+ "eval_accuracy": 0.8712962962962963,
74
+ "eval_loss": 0.7067815661430359,
75
+ "eval_runtime": 13.5776,
76
+ "eval_samples_per_second": 79.543,
77
+ "eval_steps_per_second": 9.943,
78
  "step": 100
79
  },
80
  {
81
  "epoch": 1.22,
82
+ "learning_rate": 0.0001511111111111111,
83
+ "loss": 0.0317,
84
  "step": 110
85
  },
86
  {
87
  "epoch": 1.33,
88
+ "learning_rate": 0.00014666666666666666,
89
+ "loss": 0.0388,
90
  "step": 120
91
  },
92
  {
93
  "epoch": 1.44,
94
+ "learning_rate": 0.00014222222222222224,
95
+ "loss": 0.0213,
96
  "step": 130
97
  },
98
  {
99
  "epoch": 1.56,
100
+ "learning_rate": 0.0001377777777777778,
101
+ "loss": 0.0258,
102
  "step": 140
103
  },
104
  {
105
  "epoch": 1.67,
106
+ "learning_rate": 0.00013333333333333334,
107
+ "loss": 0.0206,
108
  "step": 150
109
  },
110
  {
111
  "epoch": 1.78,
112
+ "learning_rate": 0.00012888888888888892,
113
+ "loss": 0.0481,
114
  "step": 160
115
  },
116
  {
117
  "epoch": 1.89,
118
+ "learning_rate": 0.00012444444444444444,
119
+ "loss": 0.0115,
120
  "step": 170
121
  },
122
  {
123
  "epoch": 2.0,
124
+ "learning_rate": 0.00012,
125
+ "loss": 0.015,
126
  "step": 180
127
  },
128
  {
129
  "epoch": 2.11,
130
+ "learning_rate": 0.00011555555555555555,
131
+ "loss": 0.0517,
132
  "step": 190
133
  },
134
  {
135
  "epoch": 2.22,
136
+ "learning_rate": 0.00011111111111111112,
137
+ "loss": 0.0039,
138
  "step": 200
139
  },
140
  {
141
  "epoch": 2.22,
142
+ "eval_accuracy": 0.899074074074074,
143
+ "eval_loss": 0.6390542387962341,
144
+ "eval_runtime": 12.7742,
145
+ "eval_samples_per_second": 84.545,
146
+ "eval_steps_per_second": 10.568,
147
  "step": 200
148
  },
149
  {
150
  "epoch": 2.33,
151
+ "learning_rate": 0.00010666666666666667,
152
+ "loss": 0.0066,
153
  "step": 210
154
  },
155
  {
156
  "epoch": 2.44,
157
+ "learning_rate": 0.00010222222222222222,
158
+ "loss": 0.002,
159
  "step": 220
160
  },
161
  {
162
  "epoch": 2.56,
163
+ "learning_rate": 9.777777777777778e-05,
164
+ "loss": 0.001,
165
  "step": 230
166
  },
167
  {
168
  "epoch": 2.67,
169
+ "learning_rate": 9.333333333333334e-05,
170
+ "loss": 0.0042,
171
  "step": 240
172
  },
173
  {
174
  "epoch": 2.78,
175
+ "learning_rate": 8.888888888888889e-05,
176
+ "loss": 0.004,
177
  "step": 250
178
  },
179
  {
180
  "epoch": 2.89,
181
+ "learning_rate": 8.444444444444444e-05,
182
+ "loss": 0.0018,
183
  "step": 260
184
  },
185
  {
186
  "epoch": 3.0,
187
+ "learning_rate": 8e-05,
188
+ "loss": 0.0019,
189
  "step": 270
190
  },
191
  {
192
  "epoch": 3.11,
193
+ "learning_rate": 7.555555555555556e-05,
194
+ "loss": 0.0002,
195
  "step": 280
196
  },
197
  {
198
  "epoch": 3.22,
199
+ "learning_rate": 7.111111111111112e-05,
200
+ "loss": 0.0002,
201
  "step": 290
202
  },
203
  {
204
  "epoch": 3.33,
205
+ "learning_rate": 6.666666666666667e-05,
206
+ "loss": 0.0014,
207
  "step": 300
208
  },
209
  {
210
  "epoch": 3.33,
211
+ "eval_accuracy": 0.9055555555555556,
212
+ "eval_loss": 0.5535524487495422,
213
+ "eval_runtime": 12.7035,
214
+ "eval_samples_per_second": 85.016,
215
+ "eval_steps_per_second": 10.627,
216
  "step": 300
217
  },
218
  {
219
  "epoch": 3.44,
220
+ "learning_rate": 6.222222222222222e-05,
221
+ "loss": 0.0037,
222
  "step": 310
223
  },
224
  {
225
  "epoch": 3.56,
226
+ "learning_rate": 5.7777777777777776e-05,
227
+ "loss": 0.0017,
228
  "step": 320
229
  },
230
  {
231
  "epoch": 3.67,
232
+ "learning_rate": 5.333333333333333e-05,
233
+ "loss": 0.0033,
234
  "step": 330
235
  },
236
  {
237
  "epoch": 3.78,
238
+ "learning_rate": 4.888888888888889e-05,
239
+ "loss": 0.0002,
240
  "step": 340
241
  },
242
  {
243
  "epoch": 3.89,
244
+ "learning_rate": 4.4444444444444447e-05,
245
+ "loss": 0.0043,
246
  "step": 350
247
  },
248
  {
249
  "epoch": 4.0,
250
+ "learning_rate": 4e-05,
251
+ "loss": 0.0002,
252
  "step": 360
253
  },
254
  {
255
  "epoch": 4.11,
256
+ "learning_rate": 3.555555555555556e-05,
257
+ "loss": 0.0002,
258
  "step": 370
259
  },
260
  {
261
  "epoch": 4.22,
262
+ "learning_rate": 3.111111111111111e-05,
263
+ "loss": 0.0017,
264
  "step": 380
265
  },
266
  {
267
  "epoch": 4.33,
268
+ "learning_rate": 2.6666666666666667e-05,
269
+ "loss": 0.0002,
270
  "step": 390
271
  },
272
  {
273
  "epoch": 4.44,
274
+ "learning_rate": 2.2222222222222223e-05,
275
+ "loss": 0.0018,
276
  "step": 400
277
  },
278
  {
279
  "epoch": 4.44,
280
+ "eval_accuracy": 0.9083333333333333,
281
+ "eval_loss": 0.5527949333190918,
282
+ "eval_runtime": 12.8229,
283
+ "eval_samples_per_second": 84.224,
284
+ "eval_steps_per_second": 10.528,
285
  "step": 400
286
  },
287
  {
288
  "epoch": 4.56,
289
+ "learning_rate": 1.777777777777778e-05,
290
+ "loss": 0.0002,
291
  "step": 410
292
  },
293
  {
294
  "epoch": 4.67,
295
+ "learning_rate": 1.3333333333333333e-05,
296
+ "loss": 0.002,
297
  "step": 420
298
  },
299
  {
300
  "epoch": 4.78,
301
+ "learning_rate": 8.88888888888889e-06,
302
+ "loss": 0.0044,
303
  "step": 430
304
  },
305
  {
306
  "epoch": 4.89,
307
+ "learning_rate": 4.444444444444445e-06,
308
+ "loss": 0.0032,
309
  "step": 440
310
  },
311
  {
312
  "epoch": 5.0,
313
  "learning_rate": 0.0,
314
+ "loss": 0.0002,
315
  "step": 450
316
  },
317
  {
318
  "epoch": 5.0,
319
  "step": 450,
320
  "total_flos": 1.6739319895474176e+18,
321
+ "train_loss": 0.015028678889438096,
322
+ "train_runtime": 430.7019,
323
+ "train_samples_per_second": 50.151,
324
+ "train_steps_per_second": 1.045
325
  }
326
  ],
327
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90907e3dd7aecdcf75b1b49998b4f34ff366531748788590ec538a0a00479ea7
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f84633d96f461c6cad6bc6d2052b12d6fc4b45d0640428f182e9d3e3a67b5f
3
  size 4536