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
115ecdc
•
1 Parent(s): 8a5e943

Model save

Browse files
Files changed (8) hide show
  1. README.md +8 -8
  2. all_results.json +9 -9
  3. eval_results.json +5 -6
  4. model.safetensors +1 -1
  5. runs/Dec15_03-02-53_d2a76fcee09b/events.out.tfevents.1702609398.d2a76fcee09b.2614.14 +3 -0
  6. train_results.json +4 -4
  7. trainer_state.json +104 -104
  8. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9046296296296297
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: 0.6721
36
- - Accuracy: 0.9046
37
 
38
  ## Model description
39
 
@@ -52,7 +52,7 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 0.00015
56
  - train_batch_size: 48
57
  - eval_batch_size: 8
58
  - seed: 42
@@ -65,10 +65,10 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.0011 | 1.11 | 100 | 0.8056 | 0.8843 |
69
- | 0.0063 | 2.22 | 200 | 0.7672 | 0.8926 |
70
- | 0.0016 | 3.33 | 300 | 0.6812 | 0.9037 |
71
- | 0.0017 | 4.44 | 400 | 0.6721 | 0.9046 |
72
 
73
 
74
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9064814814814814
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: 0.5586
36
+ - Accuracy: 0.9065
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.0004
56
  - train_batch_size: 48
57
  - eval_batch_size: 8
58
  - seed: 42
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.1059 | 1.11 | 100 | 0.6933 | 0.8546 |
69
+ | 0.02 | 2.22 | 200 | 0.6565 | 0.875 |
70
+ | 0.001 | 3.33 | 300 | 0.5975 | 0.8889 |
71
+ | 0.0027 | 4.44 | 400 | 0.5586 | 0.9065 |
72
 
73
 
74
  ### Framework versions
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 5.0,
3
- "eval_accuracy": 0.9111111111111111,
4
- "eval_loss": 0.5808002948760986,
5
- "eval_runtime": 14.2587,
6
- "eval_samples_per_second": 75.743,
7
- "eval_steps_per_second": 9.468,
8
  "total_flos": 1.6739319895474176e+18,
9
- "train_loss": 0.005469957473170427,
10
- "train_runtime": 432.0933,
11
- "train_samples_per_second": 49.989,
12
- "train_steps_per_second": 1.041
13
  }
 
1
  {
2
  "epoch": 5.0,
3
+ "eval_accuracy": 0.9027777777777778,
4
+ "eval_loss": 0.6732606887817383,
5
+ "eval_runtime": 14.1816,
6
+ "eval_samples_per_second": 76.155,
7
+ "eval_steps_per_second": 9.519,
8
  "total_flos": 1.6739319895474176e+18,
9
+ "train_loss": 0.010621037363954302,
10
+ "train_runtime": 432.9698,
11
+ "train_samples_per_second": 49.888,
12
+ "train_steps_per_second": 1.039
13
  }
eval_results.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "epoch": 5.0,
3
- "eval_accuracy": 0.9111111111111111,
4
- "eval_loss": 0.5808002948760986,
5
- "eval_runtime": 14.2587,
6
- "eval_samples_per_second": 75.743,
7
- "eval_steps_per_second": 9.468
8
  }
 
1
  {
2
+ "eval_accuracy": 0.9027777777777778,
3
+ "eval_loss": 0.6732606887817383,
4
+ "eval_runtime": 14.1816,
5
+ "eval_samples_per_second": 76.155,
6
+ "eval_steps_per_second": 9.519
 
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cb2e8a6393dd918d5d20b651b75dbe1fc04d504db8d7c50fb5a9092f7d5cd1c
3
  size 343245508
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:021f71eca530feb146cad3a37b54e808b8a1bbc86397fc15b6ea6aec6b507761
3
  size 343245508
runs/Dec15_03-02-53_d2a76fcee09b/events.out.tfevents.1702609398.d2a76fcee09b.2614.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d4af415515c0f9b0dde40a771b12daa643d62f9955e41da5c55a7f1d3c6787
3
+ size 13447
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.0,
3
  "total_flos": 1.6739319895474176e+18,
4
- "train_loss": 0.005469957473170427,
5
- "train_runtime": 432.0933,
6
- "train_samples_per_second": 49.989,
7
- "train_steps_per_second": 1.041
8
  }
 
1
  {
2
  "epoch": 5.0,
3
  "total_flos": 1.6739319895474176e+18,
4
+ "train_loss": 0.010621037363954302,
5
+ "train_runtime": 432.9698,
6
+ "train_samples_per_second": 49.888,
7
+ "train_steps_per_second": 1.039
8
  }
trainer_state.json CHANGED
@@ -10,301 +10,301 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.11,
13
- "learning_rate": 9.777777777777778e-05,
14
- "loss": 0.0016,
15
  "step": 10
16
  },
17
  {
18
  "epoch": 0.22,
19
- "learning_rate": 9.555555555555557e-05,
20
- "loss": 0.0002,
21
  "step": 20
22
  },
23
  {
24
  "epoch": 0.33,
25
- "learning_rate": 9.333333333333334e-05,
26
- "loss": 0.0176,
27
  "step": 30
28
  },
29
  {
30
  "epoch": 0.44,
31
- "learning_rate": 9.111111111111112e-05,
32
- "loss": 0.0183,
33
  "step": 40
34
  },
35
  {
36
  "epoch": 0.56,
37
- "learning_rate": 8.888888888888889e-05,
38
- "loss": 0.0073,
39
  "step": 50
40
  },
41
  {
42
  "epoch": 0.67,
43
- "learning_rate": 8.666666666666667e-05,
44
- "loss": 0.0016,
45
  "step": 60
46
  },
47
  {
48
  "epoch": 0.78,
49
- "learning_rate": 8.444444444444444e-05,
50
- "loss": 0.0278,
51
  "step": 70
52
  },
53
  {
54
  "epoch": 0.89,
55
- "learning_rate": 8.222222222222222e-05,
56
- "loss": 0.0308,
57
  "step": 80
58
  },
59
  {
60
  "epoch": 1.0,
61
- "learning_rate": 8e-05,
62
- "loss": 0.0035,
63
  "step": 90
64
  },
65
  {
66
  "epoch": 1.11,
67
- "learning_rate": 7.777777777777778e-05,
68
- "loss": 0.0006,
69
  "step": 100
70
  },
71
  {
72
  "epoch": 1.11,
73
- "eval_accuracy": 0.9,
74
- "eval_loss": 0.6743502020835876,
75
- "eval_runtime": 12.9158,
76
- "eval_samples_per_second": 83.618,
77
- "eval_steps_per_second": 10.452,
78
  "step": 100
79
  },
80
  {
81
  "epoch": 1.22,
82
- "learning_rate": 7.555555555555556e-05,
83
- "loss": 0.0023,
84
  "step": 110
85
  },
86
  {
87
  "epoch": 1.33,
88
- "learning_rate": 7.333333333333333e-05,
89
- "loss": 0.0131,
90
  "step": 120
91
  },
92
  {
93
  "epoch": 1.44,
94
- "learning_rate": 7.111111111111112e-05,
95
- "loss": 0.0032,
96
  "step": 130
97
  },
98
  {
99
  "epoch": 1.56,
100
- "learning_rate": 6.88888888888889e-05,
101
- "loss": 0.0019,
102
  "step": 140
103
  },
104
  {
105
  "epoch": 1.67,
106
- "learning_rate": 6.666666666666667e-05,
107
- "loss": 0.0017,
108
  "step": 150
109
  },
110
  {
111
  "epoch": 1.78,
112
- "learning_rate": 6.444444444444446e-05,
113
- "loss": 0.0151,
114
  "step": 160
115
  },
116
  {
117
  "epoch": 1.89,
118
- "learning_rate": 6.222222222222222e-05,
119
- "loss": 0.0088,
120
  "step": 170
121
  },
122
  {
123
  "epoch": 2.0,
124
- "learning_rate": 6e-05,
125
- "loss": 0.005,
126
  "step": 180
127
  },
128
  {
129
  "epoch": 2.11,
130
- "learning_rate": 5.7777777777777776e-05,
131
- "loss": 0.0012,
132
  "step": 190
133
  },
134
  {
135
  "epoch": 2.22,
136
- "learning_rate": 5.555555555555556e-05,
137
- "loss": 0.0048,
138
  "step": 200
139
  },
140
  {
141
  "epoch": 2.22,
142
- "eval_accuracy": 0.899074074074074,
143
- "eval_loss": 0.660332202911377,
144
- "eval_runtime": 12.4492,
145
- "eval_samples_per_second": 86.753,
146
- "eval_steps_per_second": 10.844,
147
  "step": 200
148
  },
149
  {
150
  "epoch": 2.33,
151
- "learning_rate": 5.333333333333333e-05,
152
- "loss": 0.0008,
153
  "step": 210
154
  },
155
  {
156
  "epoch": 2.44,
157
- "learning_rate": 5.111111111111111e-05,
158
- "loss": 0.0017,
159
  "step": 220
160
  },
161
  {
162
  "epoch": 2.56,
163
- "learning_rate": 4.888888888888889e-05,
164
- "loss": 0.0031,
165
  "step": 230
166
  },
167
  {
168
  "epoch": 2.67,
169
- "learning_rate": 4.666666666666667e-05,
170
- "loss": 0.0044,
171
  "step": 240
172
  },
173
  {
174
  "epoch": 2.78,
175
- "learning_rate": 4.4444444444444447e-05,
176
- "loss": 0.0041,
177
  "step": 250
178
  },
179
  {
180
  "epoch": 2.89,
181
- "learning_rate": 4.222222222222222e-05,
182
  "loss": 0.0015,
183
  "step": 260
184
  },
185
  {
186
  "epoch": 3.0,
187
- "learning_rate": 4e-05,
188
- "loss": 0.0256,
189
  "step": 270
190
  },
191
  {
192
  "epoch": 3.11,
193
- "learning_rate": 3.777777777777778e-05,
194
  "loss": 0.0002,
195
  "step": 280
196
  },
197
  {
198
  "epoch": 3.22,
199
- "learning_rate": 3.555555555555556e-05,
200
  "loss": 0.0002,
201
  "step": 290
202
  },
203
  {
204
  "epoch": 3.33,
205
- "learning_rate": 3.3333333333333335e-05,
206
- "loss": 0.0015,
207
  "step": 300
208
  },
209
  {
210
  "epoch": 3.33,
211
- "eval_accuracy": 0.9,
212
- "eval_loss": 0.6311585307121277,
213
- "eval_runtime": 13.0559,
214
- "eval_samples_per_second": 82.722,
215
- "eval_steps_per_second": 10.34,
216
  "step": 300
217
  },
218
  {
219
  "epoch": 3.44,
220
- "learning_rate": 3.111111111111111e-05,
221
- "loss": 0.0036,
222
  "step": 310
223
  },
224
  {
225
  "epoch": 3.56,
226
- "learning_rate": 2.8888888888888888e-05,
227
- "loss": 0.0012,
228
  "step": 320
229
  },
230
  {
231
  "epoch": 3.67,
232
- "learning_rate": 2.6666666666666667e-05,
233
- "loss": 0.0136,
234
  "step": 330
235
  },
236
  {
237
  "epoch": 3.78,
238
- "learning_rate": 2.4444444444444445e-05,
239
  "loss": 0.0002,
240
  "step": 340
241
  },
242
  {
243
  "epoch": 3.89,
244
- "learning_rate": 2.2222222222222223e-05,
245
- "loss": 0.0045,
246
  "step": 350
247
  },
248
  {
249
  "epoch": 4.0,
250
- "learning_rate": 2e-05,
251
  "loss": 0.0002,
252
  "step": 360
253
  },
254
  {
255
  "epoch": 4.11,
256
- "learning_rate": 1.777777777777778e-05,
257
- "loss": 0.0002,
258
  "step": 370
259
  },
260
  {
261
  "epoch": 4.22,
262
- "learning_rate": 1.5555555555555555e-05,
263
- "loss": 0.0018,
264
  "step": 380
265
  },
266
  {
267
  "epoch": 4.33,
268
- "learning_rate": 1.3333333333333333e-05,
269
  "loss": 0.0002,
270
  "step": 390
271
  },
272
  {
273
  "epoch": 4.44,
274
- "learning_rate": 1.1111111111111112e-05,
275
- "loss": 0.0015,
276
  "step": 400
277
  },
278
  {
279
  "epoch": 4.44,
280
- "eval_accuracy": 0.9111111111111111,
281
- "eval_loss": 0.582186758518219,
282
- "eval_runtime": 12.1335,
283
- "eval_samples_per_second": 89.01,
284
- "eval_steps_per_second": 11.126,
285
  "step": 400
286
  },
287
  {
288
  "epoch": 4.56,
289
- "learning_rate": 8.88888888888889e-06,
290
  "loss": 0.0002,
291
  "step": 410
292
  },
293
  {
294
  "epoch": 4.67,
295
- "learning_rate": 6.666666666666667e-06,
296
- "loss": 0.0023,
297
  "step": 420
298
  },
299
  {
300
  "epoch": 4.78,
301
- "learning_rate": 4.444444444444445e-06,
302
- "loss": 0.0042,
303
  "step": 430
304
  },
305
  {
306
  "epoch": 4.89,
307
- "learning_rate": 2.2222222222222225e-06,
308
  "loss": 0.0031,
309
  "step": 440
310
  },
@@ -318,10 +318,10 @@
318
  "epoch": 5.0,
319
  "step": 450,
320
  "total_flos": 1.6739319895474176e+18,
321
- "train_loss": 0.005469957473170427,
322
- "train_runtime": 432.0933,
323
- "train_samples_per_second": 49.989,
324
- "train_steps_per_second": 1.041
325
  }
326
  ],
327
  "logging_steps": 10,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.11,
13
+ "learning_rate": 0.00014666666666666664,
14
+ "loss": 0.0009,
15
  "step": 10
16
  },
17
  {
18
  "epoch": 0.22,
19
+ "learning_rate": 0.00014333333333333334,
20
+ "loss": 0.0419,
21
  "step": 20
22
  },
23
  {
24
  "epoch": 0.33,
25
+ "learning_rate": 0.00014,
26
+ "loss": 0.0832,
27
  "step": 30
28
  },
29
  {
30
  "epoch": 0.44,
31
+ "learning_rate": 0.00013666666666666666,
32
+ "loss": 0.0619,
33
  "step": 40
34
  },
35
  {
36
  "epoch": 0.56,
37
+ "learning_rate": 0.0001333333333333333,
38
+ "loss": 0.0023,
39
  "step": 50
40
  },
41
  {
42
  "epoch": 0.67,
43
+ "learning_rate": 0.00013,
44
+ "loss": 0.0057,
45
  "step": 60
46
  },
47
  {
48
  "epoch": 0.78,
49
+ "learning_rate": 0.00012666666666666666,
50
+ "loss": 0.0184,
51
  "step": 70
52
  },
53
  {
54
  "epoch": 0.89,
55
+ "learning_rate": 0.0001233333333333333,
56
+ "loss": 0.0331,
57
  "step": 80
58
  },
59
  {
60
  "epoch": 1.0,
61
+ "learning_rate": 0.00011999999999999999,
62
+ "loss": 0.0038,
63
  "step": 90
64
  },
65
  {
66
  "epoch": 1.11,
67
+ "learning_rate": 0.00011666666666666665,
68
+ "loss": 0.0011,
69
  "step": 100
70
  },
71
  {
72
  "epoch": 1.11,
73
+ "eval_accuracy": 0.8842592592592593,
74
+ "eval_loss": 0.8055844306945801,
75
+ "eval_runtime": 12.7548,
76
+ "eval_samples_per_second": 84.674,
77
+ "eval_steps_per_second": 10.584,
78
  "step": 100
79
  },
80
  {
81
  "epoch": 1.22,
82
+ "learning_rate": 0.00011333333333333331,
83
+ "loss": 0.0092,
84
  "step": 110
85
  },
86
  {
87
  "epoch": 1.33,
88
+ "learning_rate": 0.00010999999999999998,
89
+ "loss": 0.011,
90
  "step": 120
91
  },
92
  {
93
  "epoch": 1.44,
94
+ "learning_rate": 0.00010666666666666667,
95
+ "loss": 0.0039,
96
  "step": 130
97
  },
98
  {
99
  "epoch": 1.56,
100
+ "learning_rate": 0.00010333333333333333,
101
+ "loss": 0.0289,
102
  "step": 140
103
  },
104
  {
105
  "epoch": 1.67,
106
+ "learning_rate": 9.999999999999999e-05,
107
+ "loss": 0.0204,
108
  "step": 150
109
  },
110
  {
111
  "epoch": 1.78,
112
+ "learning_rate": 9.666666666666667e-05,
113
+ "loss": 0.0024,
114
  "step": 160
115
  },
116
  {
117
  "epoch": 1.89,
118
+ "learning_rate": 9.333333333333333e-05,
119
+ "loss": 0.0471,
120
  "step": 170
121
  },
122
  {
123
  "epoch": 2.0,
124
+ "learning_rate": 8.999999999999999e-05,
125
+ "loss": 0.0247,
126
  "step": 180
127
  },
128
  {
129
  "epoch": 2.11,
130
+ "learning_rate": 8.666666666666665e-05,
131
+ "loss": 0.0016,
132
  "step": 190
133
  },
134
  {
135
  "epoch": 2.22,
136
+ "learning_rate": 8.333333333333333e-05,
137
+ "loss": 0.0063,
138
  "step": 200
139
  },
140
  {
141
  "epoch": 2.22,
142
+ "eval_accuracy": 0.8925925925925926,
143
+ "eval_loss": 0.7672075629234314,
144
+ "eval_runtime": 13.3931,
145
+ "eval_samples_per_second": 80.639,
146
+ "eval_steps_per_second": 10.08,
147
  "step": 200
148
  },
149
  {
150
  "epoch": 2.33,
151
+ "learning_rate": 7.999999999999999e-05,
152
+ "loss": 0.0004,
153
  "step": 210
154
  },
155
  {
156
  "epoch": 2.44,
157
+ "learning_rate": 7.666666666666666e-05,
158
+ "loss": 0.0009,
159
  "step": 220
160
  },
161
  {
162
  "epoch": 2.56,
163
+ "learning_rate": 7.333333333333332e-05,
164
+ "loss": 0.0003,
165
  "step": 230
166
  },
167
  {
168
  "epoch": 2.67,
169
+ "learning_rate": 7e-05,
170
+ "loss": 0.0122,
171
  "step": 240
172
  },
173
  {
174
  "epoch": 2.78,
175
+ "learning_rate": 6.666666666666666e-05,
176
+ "loss": 0.0182,
177
  "step": 250
178
  },
179
  {
180
  "epoch": 2.89,
181
+ "learning_rate": 6.333333333333333e-05,
182
  "loss": 0.0015,
183
  "step": 260
184
  },
185
  {
186
  "epoch": 3.0,
187
+ "learning_rate": 5.9999999999999995e-05,
188
+ "loss": 0.0041,
189
  "step": 270
190
  },
191
  {
192
  "epoch": 3.11,
193
+ "learning_rate": 5.666666666666666e-05,
194
  "loss": 0.0002,
195
  "step": 280
196
  },
197
  {
198
  "epoch": 3.22,
199
+ "learning_rate": 5.333333333333333e-05,
200
  "loss": 0.0002,
201
  "step": 290
202
  },
203
  {
204
  "epoch": 3.33,
205
+ "learning_rate": 4.9999999999999996e-05,
206
+ "loss": 0.0016,
207
  "step": 300
208
  },
209
  {
210
  "epoch": 3.33,
211
+ "eval_accuracy": 0.9037037037037037,
212
+ "eval_loss": 0.6811866164207458,
213
+ "eval_runtime": 12.8153,
214
+ "eval_samples_per_second": 84.274,
215
+ "eval_steps_per_second": 10.534,
216
  "step": 300
217
  },
218
  {
219
  "epoch": 3.44,
220
+ "learning_rate": 4.6666666666666665e-05,
221
+ "loss": 0.0033,
222
  "step": 310
223
  },
224
  {
225
  "epoch": 3.56,
226
+ "learning_rate": 4.333333333333333e-05,
227
+ "loss": 0.0008,
228
  "step": 320
229
  },
230
  {
231
  "epoch": 3.67,
232
+ "learning_rate": 3.9999999999999996e-05,
233
+ "loss": 0.003,
234
  "step": 330
235
  },
236
  {
237
  "epoch": 3.78,
238
+ "learning_rate": 3.666666666666666e-05,
239
  "loss": 0.0002,
240
  "step": 340
241
  },
242
  {
243
  "epoch": 3.89,
244
+ "learning_rate": 3.333333333333333e-05,
245
+ "loss": 0.0095,
246
  "step": 350
247
  },
248
  {
249
  "epoch": 4.0,
250
+ "learning_rate": 2.9999999999999997e-05,
251
  "loss": 0.0002,
252
  "step": 360
253
  },
254
  {
255
  "epoch": 4.11,
256
+ "learning_rate": 2.6666666666666667e-05,
257
+ "loss": 0.0001,
258
  "step": 370
259
  },
260
  {
261
  "epoch": 4.22,
262
+ "learning_rate": 2.3333333333333332e-05,
263
+ "loss": 0.0016,
264
  "step": 380
265
  },
266
  {
267
  "epoch": 4.33,
268
+ "learning_rate": 1.9999999999999998e-05,
269
  "loss": 0.0002,
270
  "step": 390
271
  },
272
  {
273
  "epoch": 4.44,
274
+ "learning_rate": 1.6666666666666664e-05,
275
+ "loss": 0.0017,
276
  "step": 400
277
  },
278
  {
279
  "epoch": 4.44,
280
+ "eval_accuracy": 0.9046296296296297,
281
+ "eval_loss": 0.6721389293670654,
282
+ "eval_runtime": 12.3755,
283
+ "eval_samples_per_second": 87.269,
284
+ "eval_steps_per_second": 10.909,
285
  "step": 400
286
  },
287
  {
288
  "epoch": 4.56,
289
+ "learning_rate": 1.3333333333333333e-05,
290
  "loss": 0.0002,
291
  "step": 410
292
  },
293
  {
294
  "epoch": 4.67,
295
+ "learning_rate": 9.999999999999999e-06,
296
+ "loss": 0.0025,
297
  "step": 420
298
  },
299
  {
300
  "epoch": 4.78,
301
+ "learning_rate": 6.666666666666667e-06,
302
+ "loss": 0.004,
303
  "step": 430
304
  },
305
  {
306
  "epoch": 4.89,
307
+ "learning_rate": 3.3333333333333333e-06,
308
  "loss": 0.0031,
309
  "step": 440
310
  },
 
318
  "epoch": 5.0,
319
  "step": 450,
320
  "total_flos": 1.6739319895474176e+18,
321
+ "train_loss": 0.010621037363954302,
322
+ "train_runtime": 432.9698,
323
+ "train_samples_per_second": 49.888,
324
+ "train_steps_per_second": 1.039
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 sha256:1079af4ea79686f3693c95cb2212a48af2693b1cbe2f5e43dcf6667043b4efc1
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf957047e4ef28d8cbe1f0f8e02d27ba9ae96d94d13ab6aff2f23772cf24642
3
  size 4536