Hugging Face's logo

Augusto777
/
swiftformer-xs-DMAE

TensorBoard
Safetensors
swiftformer
Generated from Trainer
Eval Results
Model card Files Metrics Community
Augusto777 commited on
Commit
d3987ef
·
verified ·
1 Parent(s): 2beece7

End of training

Browse files
Files changed (9) hide show
  1. README.md +36 -36
  2. all_results.json +8 -8
  3. eval_results.json +4 -4
  4. model.safetensors +1 -1
  5. runs/Dec02_10-27-56_DESKTOP-SKBE9FB/events.out.tfevents.1733156877.DESKTOP-SKBE9FB.17416.0 +3 -0
  6. runs/Dec02_10-27-56_DESKTOP-SKBE9FB/events.out.tfevents.1733157009.DESKTOP-SKBE9FB.17416.1 +3 -0
  7. train_results.json +4 -4
  8. trainer_state.json +156 -156
  9. training_args.bin +1 -1
README.md CHANGED
@@ -31,7 +31,7 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 113.8883
35
  - Accuracy: 0.1087
36
 
37
  ## Model description
@@ -65,41 +65,41 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | No log | 0.86 | 3 | 113.8883 | 0.1087 |
69
- | No log | 2.0 | 7 | 113.8868 | 0.1087 |
70
- | 114.1606 | 2.86 | 10 | 113.8851 | 0.1087 |
71
- | 114.1606 | 4.0 | 14 | 113.8846 | 0.1087 |
72
- | 114.1606 | 4.86 | 17 | 113.8832 | 0.1087 |
73
- | 113.5172 | 6.0 | 21 | 113.8808 | 0.1087 |
74
- | 113.5172 | 6.86 | 24 | 113.8795 | 0.1087 |
75
- | 113.5172 | 8.0 | 28 | 113.8794 | 0.1087 |
76
- | 111.7557 | 8.86 | 31 | 113.8766 | 0.1087 |
77
- | 111.7557 | 10.0 | 35 | 113.8747 | 0.1087 |
78
- | 111.7557 | 10.86 | 38 | 113.8735 | 0.1087 |
79
- | 115.9434 | 12.0 | 42 | 113.8712 | 0.1087 |
80
- | 115.9434 | 12.86 | 45 | 113.8699 | 0.1087 |
81
- | 115.9434 | 14.0 | 49 | 113.8671 | 0.1087 |
82
- | 112.3427 | 14.86 | 52 | 113.8607 | 0.1087 |
83
- | 112.3427 | 16.0 | 56 | 113.8567 | 0.1087 |
84
- | 112.3427 | 16.86 | 59 | 113.8570 | 0.1087 |
85
- | 113.2123 | 18.0 | 63 | 113.8532 | 0.1087 |
86
- | 113.2123 | 18.86 | 66 | 113.8511 | 0.1087 |
87
- | 114.0835 | 20.0 | 70 | 113.8500 | 0.1087 |
88
- | 114.0835 | 20.86 | 73 | 113.8469 | 0.1087 |
89
- | 114.0835 | 22.0 | 77 | 113.8450 | 0.1087 |
90
- | 114.5528 | 22.86 | 80 | 113.8422 | 0.1087 |
91
- | 114.5528 | 24.0 | 84 | 113.8341 | 0.1087 |
92
- | 114.5528 | 24.86 | 87 | 113.8315 | 0.1087 |
93
- | 114.5432 | 26.0 | 91 | 113.8268 | 0.1087 |
94
- | 114.5432 | 26.86 | 94 | 113.8247 | 0.1087 |
95
- | 114.5432 | 28.0 | 98 | 113.8250 | 0.1087 |
96
- | 112.7825 | 28.86 | 101 | 113.8207 | 0.1087 |
97
- | 112.7825 | 30.0 | 105 | 113.8155 | 0.1087 |
98
- | 112.7825 | 30.86 | 108 | 113.8183 | 0.1087 |
99
- | 114.2965 | 32.0 | 112 | 113.8187 | 0.1087 |
100
- | 114.2965 | 32.86 | 115 | 113.8187 | 0.1087 |
101
- | 114.2965 | 34.0 | 119 | 113.8124 | 0.1087 |
102
- | 114.0925 | 34.29 | 120 | 113.8146 | 0.1087 |
103
 
104
 
105
  ### Framework versions
 
31
 
32
  This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 113.8668
35
  - Accuracy: 0.1087
36
 
37
  ## Model description
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | No log | 0.86 | 3 | 113.8668 | 0.1087 |
69
+ | No log | 2.0 | 7 | 113.8652 | 0.1087 |
70
+ | 114.139 | 2.86 | 10 | 113.8636 | 0.1087 |
71
+ | 114.139 | 4.0 | 14 | 113.8630 | 0.1087 |
72
+ | 114.139 | 4.86 | 17 | 113.8617 | 0.1087 |
73
+ | 113.4957 | 6.0 | 21 | 113.8592 | 0.1087 |
74
+ | 113.4957 | 6.86 | 24 | 113.8579 | 0.1087 |
75
+ | 113.4957 | 8.0 | 28 | 113.8578 | 0.1087 |
76
+ | 111.7345 | 8.86 | 31 | 113.8550 | 0.1087 |
77
+ | 111.7345 | 10.0 | 35 | 113.8531 | 0.1087 |
78
+ | 111.7345 | 10.86 | 38 | 113.8520 | 0.1087 |
79
+ | 115.9214 | 12.0 | 42 | 113.8497 | 0.1087 |
80
+ | 115.9214 | 12.86 | 45 | 113.8484 | 0.1087 |
81
+ | 115.9214 | 14.0 | 49 | 113.8455 | 0.1087 |
82
+ | 112.3215 | 14.86 | 52 | 113.8392 | 0.1087 |
83
+ | 112.3215 | 16.0 | 56 | 113.8351 | 0.1087 |
84
+ | 112.3215 | 16.86 | 59 | 113.8354 | 0.1087 |
85
+ | 113.1908 | 18.0 | 63 | 113.8316 | 0.1087 |
86
+ | 113.1908 | 18.86 | 66 | 113.8295 | 0.1087 |
87
+ | 114.062 | 20.0 | 70 | 113.8284 | 0.1087 |
88
+ | 114.062 | 20.86 | 73 | 113.8253 | 0.1087 |
89
+ | 114.062 | 22.0 | 77 | 113.8235 | 0.1087 |
90
+ | 114.5312 | 22.86 | 80 | 113.8207 | 0.1087 |
91
+ | 114.5312 | 24.0 | 84 | 113.8126 | 0.1087 |
92
+ | 114.5312 | 24.86 | 87 | 113.8100 | 0.1087 |
93
+ | 114.5216 | 26.0 | 91 | 113.8053 | 0.1087 |
94
+ | 114.5216 | 26.86 | 94 | 113.8032 | 0.1087 |
95
+ | 114.5216 | 28.0 | 98 | 113.8035 | 0.1087 |
96
+ | 112.7612 | 28.86 | 101 | 113.7992 | 0.1087 |
97
+ | 112.7612 | 30.0 | 105 | 113.7939 | 0.1087 |
98
+ | 112.7612 | 30.86 | 108 | 113.7967 | 0.1087 |
99
+ | 114.2748 | 32.0 | 112 | 113.7973 | 0.1087 |
100
+ | 114.2748 | 32.86 | 115 | 113.7971 | 0.1087 |
101
+ | 114.2748 | 34.0 | 119 | 113.7908 | 0.1087 |
102
+ | 114.0708 | 34.29 | 120 | 113.7932 | 0.1087 |
103
 
104
 
105
  ### Framework versions
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
- "eval_loss": 113.88832092285156,
5
- "eval_runtime": 0.6376,
6
- "eval_samples_per_second": 72.14,
7
- "eval_steps_per_second": 4.705,
8
- "train_loss": 113.7735809326172,
9
- "train_runtime": 129.8431,
10
- "train_samples_per_second": 65.618,
11
- "train_steps_per_second": 0.924
12
  }
 
1
  {
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
+ "eval_loss": 113.86678314208984,
5
+ "eval_runtime": 0.6487,
6
+ "eval_samples_per_second": 70.916,
7
+ "eval_steps_per_second": 4.625,
8
+ "train_loss": 113.75203348795573,
9
+ "train_runtime": 131.4365,
10
+ "train_samples_per_second": 64.822,
11
+ "train_steps_per_second": 0.913
12
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
- "eval_loss": 113.88832092285156,
5
- "eval_runtime": 0.6376,
6
- "eval_samples_per_second": 72.14,
7
- "eval_steps_per_second": 4.705
8
  }
 
1
  {
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
+ "eval_loss": 113.86678314208984,
5
+ "eval_runtime": 0.6487,
6
+ "eval_samples_per_second": 70.916,
7
+ "eval_steps_per_second": 4.625
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd253f136dfe3348ed3c408b8e3c4cb2dc70ebcd178addaee7cca00fdd69500d
3
  size 12203648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:debfd6b2b6d15236fd33ba40707563aedea5995b0c33019829328fa5b74fb0e2
3
  size 12203648
runs/Dec02_10-27-56_DESKTOP-SKBE9FB/events.out.tfevents.1733156877.DESKTOP-SKBE9FB.17416.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5bec58eafeab5462a775aee30c3d5e092925777aa1b87321c5fff154560a56
3
+ size 17833
runs/Dec02_10-27-56_DESKTOP-SKBE9FB/events.out.tfevents.1733157009.DESKTOP-SKBE9FB.17416.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea8a75fef7d5f00aa9aee28e11870af2a7fe86513eb5223bc770ee24c0492fa
3
+ size 405
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 34.29,
3
- "train_loss": 113.7735809326172,
4
- "train_runtime": 129.8431,
5
- "train_samples_per_second": 65.618,
6
- "train_steps_per_second": 0.924
7
  }
 
1
  {
2
  "epoch": 34.29,
3
+ "train_loss": 113.75203348795573,
4
+ "train_runtime": 131.4365,
5
+ "train_samples_per_second": 64.822,
6
+ "train_steps_per_second": 0.913
7
  }
trainer_state.json CHANGED
@@ -11,398 +11,398 @@
11
  {
12
  "epoch": 0.86,
13
  "eval_accuracy": 0.10869565217391304,
14
- "eval_loss": 113.88832092285156,
15
- "eval_runtime": 0.6507,
16
- "eval_samples_per_second": 70.697,
17
- "eval_steps_per_second": 4.611,
18
  "step": 3
19
  },
20
  {
21
  "epoch": 2.0,
22
  "eval_accuracy": 0.10869565217391304,
23
- "eval_loss": 113.88676452636719,
24
- "eval_runtime": 0.5971,
25
- "eval_samples_per_second": 77.035,
26
- "eval_steps_per_second": 5.024,
27
  "step": 7
28
  },
29
  {
30
  "epoch": 2.86,
31
  "learning_rate": 2.2916666666666667e-05,
32
- "loss": 114.1606,
33
  "step": 10
34
  },
35
  {
36
  "epoch": 2.86,
37
  "eval_accuracy": 0.10869565217391304,
38
- "eval_loss": 113.88513946533203,
39
- "eval_runtime": 0.6292,
40
- "eval_samples_per_second": 73.113,
41
- "eval_steps_per_second": 4.768,
42
  "step": 10
43
  },
44
  {
45
  "epoch": 4.0,
46
  "eval_accuracy": 0.10869565217391304,
47
- "eval_loss": 113.8846206665039,
48
- "eval_runtime": 0.6036,
49
- "eval_samples_per_second": 76.204,
50
- "eval_steps_per_second": 4.97,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 4.86,
55
  "eval_accuracy": 0.10869565217391304,
56
- "eval_loss": 113.88324737548828,
57
- "eval_runtime": 0.6196,
58
- "eval_samples_per_second": 74.236,
59
- "eval_steps_per_second": 4.841,
60
  "step": 17
61
  },
62
  {
63
  "epoch": 5.71,
64
  "learning_rate": 2.0833333333333336e-05,
65
- "loss": 113.5172,
66
  "step": 20
67
  },
68
  {
69
  "epoch": 6.0,
70
  "eval_accuracy": 0.10869565217391304,
71
- "eval_loss": 113.8808364868164,
72
- "eval_runtime": 0.6092,
73
- "eval_samples_per_second": 75.515,
74
- "eval_steps_per_second": 4.925,
75
  "step": 21
76
  },
77
  {
78
  "epoch": 6.86,
79
  "eval_accuracy": 0.10869565217391304,
80
- "eval_loss": 113.87947082519531,
81
- "eval_runtime": 0.6912,
82
- "eval_samples_per_second": 66.555,
83
- "eval_steps_per_second": 4.341,
84
  "step": 24
85
  },
86
  {
87
  "epoch": 8.0,
88
  "eval_accuracy": 0.10869565217391304,
89
- "eval_loss": 113.87939453125,
90
- "eval_runtime": 0.6041,
91
- "eval_samples_per_second": 76.14,
92
- "eval_steps_per_second": 4.966,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 8.57,
97
  "learning_rate": 1.8750000000000002e-05,
98
- "loss": 111.7557,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 8.86,
103
  "eval_accuracy": 0.10869565217391304,
104
- "eval_loss": 113.87659454345703,
105
- "eval_runtime": 0.6201,
106
- "eval_samples_per_second": 74.177,
107
- "eval_steps_per_second": 4.838,
108
  "step": 31
109
  },
110
  {
111
  "epoch": 10.0,
112
  "eval_accuracy": 0.10869565217391304,
113
- "eval_loss": 113.87474822998047,
114
- "eval_runtime": 0.6842,
115
- "eval_samples_per_second": 67.234,
116
- "eval_steps_per_second": 4.385,
117
  "step": 35
118
  },
119
  {
120
  "epoch": 10.86,
121
  "eval_accuracy": 0.10869565217391304,
122
- "eval_loss": 113.87353515625,
123
- "eval_runtime": 0.6136,
124
- "eval_samples_per_second": 74.962,
125
- "eval_steps_per_second": 4.889,
126
  "step": 38
127
  },
128
  {
129
  "epoch": 11.43,
130
  "learning_rate": 1.6666666666666667e-05,
131
- "loss": 115.9434,
132
  "step": 40
133
  },
134
  {
135
  "epoch": 12.0,
136
  "eval_accuracy": 0.10869565217391304,
137
- "eval_loss": 113.8711929321289,
138
- "eval_runtime": 0.5921,
139
- "eval_samples_per_second": 77.685,
140
- "eval_steps_per_second": 5.066,
141
  "step": 42
142
  },
143
  {
144
  "epoch": 12.86,
145
  "eval_accuracy": 0.10869565217391304,
146
- "eval_loss": 113.86994934082031,
147
- "eval_runtime": 0.6321,
148
- "eval_samples_per_second": 72.768,
149
- "eval_steps_per_second": 4.746,
150
  "step": 45
151
  },
152
  {
153
  "epoch": 14.0,
154
  "eval_accuracy": 0.10869565217391304,
155
- "eval_loss": 113.86713409423828,
156
- "eval_runtime": 0.6061,
157
- "eval_samples_per_second": 75.891,
158
- "eval_steps_per_second": 4.949,
159
  "step": 49
160
  },
161
  {
162
  "epoch": 14.29,
163
  "learning_rate": 1.4583333333333335e-05,
164
- "loss": 112.3427,
165
  "step": 50
166
  },
167
  {
168
  "epoch": 14.86,
169
  "eval_accuracy": 0.10869565217391304,
170
- "eval_loss": 113.8606948852539,
171
- "eval_runtime": 0.6062,
172
- "eval_samples_per_second": 75.889,
173
- "eval_steps_per_second": 4.949,
174
  "step": 52
175
  },
176
  {
177
  "epoch": 16.0,
178
  "eval_accuracy": 0.10869565217391304,
179
- "eval_loss": 113.8567123413086,
180
- "eval_runtime": 0.5916,
181
- "eval_samples_per_second": 77.75,
182
- "eval_steps_per_second": 5.071,
183
  "step": 56
184
  },
185
  {
186
  "epoch": 16.86,
187
  "eval_accuracy": 0.10869565217391304,
188
- "eval_loss": 113.85698699951172,
189
- "eval_runtime": 0.6427,
190
- "eval_samples_per_second": 71.578,
191
- "eval_steps_per_second": 4.668,
192
  "step": 59
193
  },
194
  {
195
  "epoch": 17.14,
196
  "learning_rate": 1.25e-05,
197
- "loss": 113.2123,
198
  "step": 60
199
  },
200
  {
201
  "epoch": 18.0,
202
  "eval_accuracy": 0.10869565217391304,
203
- "eval_loss": 113.85321807861328,
204
- "eval_runtime": 0.6122,
205
- "eval_samples_per_second": 75.144,
206
- "eval_steps_per_second": 4.901,
207
  "step": 63
208
  },
209
  {
210
  "epoch": 18.86,
211
  "eval_accuracy": 0.10869565217391304,
212
- "eval_loss": 113.85108184814453,
213
- "eval_runtime": 0.6031,
214
- "eval_samples_per_second": 76.268,
215
- "eval_steps_per_second": 4.974,
216
  "step": 66
217
  },
218
  {
219
  "epoch": 20.0,
220
  "learning_rate": 1.0416666666666668e-05,
221
- "loss": 114.0835,
222
  "step": 70
223
  },
224
  {
225
  "epoch": 20.0,
226
  "eval_accuracy": 0.10869565217391304,
227
- "eval_loss": 113.85003662109375,
228
- "eval_runtime": 0.6361,
229
- "eval_samples_per_second": 72.311,
230
- "eval_steps_per_second": 4.716,
231
  "step": 70
232
  },
233
  {
234
  "epoch": 20.86,
235
  "eval_accuracy": 0.10869565217391304,
236
- "eval_loss": 113.84687805175781,
237
- "eval_runtime": 0.6076,
238
- "eval_samples_per_second": 75.702,
239
- "eval_steps_per_second": 4.937,
240
  "step": 73
241
  },
242
  {
243
  "epoch": 22.0,
244
  "eval_accuracy": 0.10869565217391304,
245
- "eval_loss": 113.84497833251953,
246
- "eval_runtime": 0.5921,
247
- "eval_samples_per_second": 77.683,
248
- "eval_steps_per_second": 5.066,
249
  "step": 77
250
  },
251
  {
252
  "epoch": 22.86,
253
  "learning_rate": 8.333333333333334e-06,
254
- "loss": 114.5528,
255
  "step": 80
256
  },
257
  {
258
  "epoch": 22.86,
259
  "eval_accuracy": 0.10869565217391304,
260
- "eval_loss": 113.84217834472656,
261
- "eval_runtime": 0.6551,
262
- "eval_samples_per_second": 70.213,
263
- "eval_steps_per_second": 4.579,
264
  "step": 80
265
  },
266
  {
267
  "epoch": 24.0,
268
  "eval_accuracy": 0.10869565217391304,
269
- "eval_loss": 113.83406829833984,
270
- "eval_runtime": 0.5936,
271
- "eval_samples_per_second": 77.488,
272
- "eval_steps_per_second": 5.054,
273
  "step": 84
274
  },
275
  {
276
  "epoch": 24.86,
277
  "eval_accuracy": 0.10869565217391304,
278
- "eval_loss": 113.83149719238281,
279
- "eval_runtime": 0.6102,
280
- "eval_samples_per_second": 75.391,
281
- "eval_steps_per_second": 4.917,
282
  "step": 87
283
  },
284
  {
285
  "epoch": 25.71,
286
  "learning_rate": 6.25e-06,
287
- "loss": 114.5432,
288
  "step": 90
289
  },
290
  {
291
  "epoch": 26.0,
292
  "eval_accuracy": 0.10869565217391304,
293
- "eval_loss": 113.82682037353516,
294
- "eval_runtime": 0.6111,
295
- "eval_samples_per_second": 75.27,
296
- "eval_steps_per_second": 4.909,
297
  "step": 91
298
  },
299
  {
300
  "epoch": 26.86,
301
  "eval_accuracy": 0.10869565217391304,
302
- "eval_loss": 113.82469940185547,
303
- "eval_runtime": 0.6141,
304
- "eval_samples_per_second": 74.902,
305
- "eval_steps_per_second": 4.885,
306
  "step": 94
307
  },
308
  {
309
  "epoch": 28.0,
310
  "eval_accuracy": 0.10869565217391304,
311
- "eval_loss": 113.82501220703125,
312
- "eval_runtime": 0.6132,
313
- "eval_samples_per_second": 75.022,
314
- "eval_steps_per_second": 4.893,
315
  "step": 98
316
  },
317
  {
318
  "epoch": 28.57,
319
  "learning_rate": 4.166666666666667e-06,
320
- "loss": 112.7825,
321
  "step": 100
322
  },
323
  {
324
  "epoch": 28.86,
325
  "eval_accuracy": 0.10869565217391304,
326
- "eval_loss": 113.8207015991211,
327
- "eval_runtime": 0.6082,
328
- "eval_samples_per_second": 75.639,
329
- "eval_steps_per_second": 4.933,
330
  "step": 101
331
  },
332
  {
333
  "epoch": 30.0,
334
  "eval_accuracy": 0.10869565217391304,
335
- "eval_loss": 113.8154525756836,
336
- "eval_runtime": 0.6136,
337
- "eval_samples_per_second": 74.962,
338
- "eval_steps_per_second": 4.889,
339
  "step": 105
340
  },
341
  {
342
  "epoch": 30.86,
343
  "eval_accuracy": 0.10869565217391304,
344
- "eval_loss": 113.81825256347656,
345
- "eval_runtime": 0.6111,
346
- "eval_samples_per_second": 75.27,
347
- "eval_steps_per_second": 4.909,
348
  "step": 108
349
  },
350
  {
351
  "epoch": 31.43,
352
  "learning_rate": 2.0833333333333334e-06,
353
- "loss": 114.2965,
354
  "step": 110
355
  },
356
  {
357
  "epoch": 32.0,
358
  "eval_accuracy": 0.10869565217391304,
359
- "eval_loss": 113.8187484741211,
360
- "eval_runtime": 0.6492,
361
- "eval_samples_per_second": 70.86,
362
- "eval_steps_per_second": 4.621,
363
  "step": 112
364
  },
365
  {
366
  "epoch": 32.86,
367
  "eval_accuracy": 0.10869565217391304,
368
- "eval_loss": 113.81865692138672,
369
- "eval_runtime": 0.6381,
370
- "eval_samples_per_second": 72.084,
371
- "eval_steps_per_second": 4.701,
372
  "step": 115
373
  },
374
  {
375
  "epoch": 34.0,
376
  "eval_accuracy": 0.10869565217391304,
377
- "eval_loss": 113.81236267089844,
378
- "eval_runtime": 0.6046,
379
- "eval_samples_per_second": 76.078,
380
- "eval_steps_per_second": 4.962,
381
  "step": 119
382
  },
383
  {
384
  "epoch": 34.29,
385
  "learning_rate": 0.0,
386
- "loss": 114.0925,
387
  "step": 120
388
  },
389
  {
390
  "epoch": 34.29,
391
  "eval_accuracy": 0.10869565217391304,
392
- "eval_loss": 113.81463623046875,
393
- "eval_runtime": 0.6637,
394
- "eval_samples_per_second": 69.313,
395
- "eval_steps_per_second": 4.52,
396
  "step": 120
397
  },
398
  {
399
  "epoch": 34.29,
400
  "step": 120,
401
  "total_flos": 2.0027429927092224e+16,
402
- "train_loss": 113.7735809326172,
403
- "train_runtime": 129.8431,
404
- "train_samples_per_second": 65.618,
405
- "train_steps_per_second": 0.924
406
  }
407
  ],
408
  "logging_steps": 10,
 
11
  {
12
  "epoch": 0.86,
13
  "eval_accuracy": 0.10869565217391304,
14
+ "eval_loss": 113.86678314208984,
15
+ "eval_runtime": 0.6737,
16
+ "eval_samples_per_second": 68.283,
17
+ "eval_steps_per_second": 4.453,
18
  "step": 3
19
  },
20
  {
21
  "epoch": 2.0,
22
  "eval_accuracy": 0.10869565217391304,
23
+ "eval_loss": 113.8652114868164,
24
+ "eval_runtime": 0.6176,
25
+ "eval_samples_per_second": 74.476,
26
+ "eval_steps_per_second": 4.857,
27
  "step": 7
28
  },
29
  {
30
  "epoch": 2.86,
31
  "learning_rate": 2.2916666666666667e-05,
32
+ "loss": 114.139,
33
  "step": 10
34
  },
35
  {
36
  "epoch": 2.86,
37
  "eval_accuracy": 0.10869565217391304,
38
+ "eval_loss": 113.86360168457031,
39
+ "eval_runtime": 0.6252,
40
+ "eval_samples_per_second": 73.581,
41
+ "eval_steps_per_second": 4.799,
42
  "step": 10
43
  },
44
  {
45
  "epoch": 4.0,
46
  "eval_accuracy": 0.10869565217391304,
47
+ "eval_loss": 113.86296081542969,
48
+ "eval_runtime": 0.6111,
49
+ "eval_samples_per_second": 75.27,
50
+ "eval_steps_per_second": 4.909,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 4.86,
55
  "eval_accuracy": 0.10869565217391304,
56
+ "eval_loss": 113.86167907714844,
57
+ "eval_runtime": 0.6116,
58
+ "eval_samples_per_second": 75.206,
59
+ "eval_steps_per_second": 4.905,
60
  "step": 17
61
  },
62
  {
63
  "epoch": 5.71,
64
  "learning_rate": 2.0833333333333336e-05,
65
+ "loss": 113.4957,
66
  "step": 20
67
  },
68
  {
69
  "epoch": 6.0,
70
  "eval_accuracy": 0.10869565217391304,
71
+ "eval_loss": 113.85923767089844,
72
+ "eval_runtime": 0.6187,
73
+ "eval_samples_per_second": 74.355,
74
+ "eval_steps_per_second": 4.849,
75
  "step": 21
76
  },
77
  {
78
  "epoch": 6.86,
79
  "eval_accuracy": 0.10869565217391304,
80
+ "eval_loss": 113.8578872680664,
81
+ "eval_runtime": 0.6091,
82
+ "eval_samples_per_second": 75.517,
83
+ "eval_steps_per_second": 4.925,
84
  "step": 24
85
  },
86
  {
87
  "epoch": 8.0,
88
  "eval_accuracy": 0.10869565217391304,
89
+ "eval_loss": 113.8578109741211,
90
+ "eval_runtime": 0.6207,
91
+ "eval_samples_per_second": 74.114,
92
+ "eval_steps_per_second": 4.834,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 8.57,
97
  "learning_rate": 1.8750000000000002e-05,
98
+ "loss": 111.7345,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 8.86,
103
  "eval_accuracy": 0.10869565217391304,
104
+ "eval_loss": 113.8550033569336,
105
+ "eval_runtime": 0.6176,
106
+ "eval_samples_per_second": 74.476,
107
+ "eval_steps_per_second": 4.857,
108
  "step": 31
109
  },
110
  {
111
  "epoch": 10.0,
112
  "eval_accuracy": 0.10869565217391304,
113
+ "eval_loss": 113.85313415527344,
114
+ "eval_runtime": 0.5966,
115
+ "eval_samples_per_second": 77.098,
116
+ "eval_steps_per_second": 5.028,
117
  "step": 35
118
  },
119
  {
120
  "epoch": 10.86,
121
  "eval_accuracy": 0.10869565217391304,
122
+ "eval_loss": 113.85196685791016,
123
+ "eval_runtime": 0.6032,
124
+ "eval_samples_per_second": 76.266,
125
+ "eval_steps_per_second": 4.974,
126
  "step": 38
127
  },
128
  {
129
  "epoch": 11.43,
130
  "learning_rate": 1.6666666666666667e-05,
131
+ "loss": 115.9214,
132
  "step": 40
133
  },
134
  {
135
  "epoch": 12.0,
136
  "eval_accuracy": 0.10869565217391304,
137
+ "eval_loss": 113.84968566894531,
138
+ "eval_runtime": 0.5951,
139
+ "eval_samples_per_second": 77.294,
140
+ "eval_steps_per_second": 5.041,
141
  "step": 42
142
  },
143
  {
144
  "epoch": 12.86,
145
  "eval_accuracy": 0.10869565217391304,
146
+ "eval_loss": 113.8483657836914,
147
+ "eval_runtime": 0.6171,
148
+ "eval_samples_per_second": 74.538,
149
+ "eval_steps_per_second": 4.861,
150
  "step": 45
151
  },
152
  {
153
  "epoch": 14.0,
154
  "eval_accuracy": 0.10869565217391304,
155
+ "eval_loss": 113.84552001953125,
156
+ "eval_runtime": 0.6081,
157
+ "eval_samples_per_second": 75.641,
158
+ "eval_steps_per_second": 4.933,
159
  "step": 49
160
  },
161
  {
162
  "epoch": 14.29,
163
  "learning_rate": 1.4583333333333335e-05,
164
+ "loss": 112.3215,
165
  "step": 50
166
  },
167
  {
168
  "epoch": 14.86,
169
  "eval_accuracy": 0.10869565217391304,
170
+ "eval_loss": 113.83916473388672,
171
+ "eval_runtime": 0.7172,
172
+ "eval_samples_per_second": 64.142,
173
+ "eval_steps_per_second": 4.183,
174
  "step": 52
175
  },
176
  {
177
  "epoch": 16.0,
178
  "eval_accuracy": 0.10869565217391304,
179
+ "eval_loss": 113.83506774902344,
180
+ "eval_runtime": 0.6271,
181
+ "eval_samples_per_second": 73.349,
182
+ "eval_steps_per_second": 4.784,
183
  "step": 56
184
  },
185
  {
186
  "epoch": 16.86,
187
  "eval_accuracy": 0.10869565217391304,
188
+ "eval_loss": 113.83540344238281,
189
+ "eval_runtime": 0.6112,
190
+ "eval_samples_per_second": 75.268,
191
+ "eval_steps_per_second": 4.909,
192
  "step": 59
193
  },
194
  {
195
  "epoch": 17.14,
196
  "learning_rate": 1.25e-05,
197
+ "loss": 113.1908,
198
  "step": 60
199
  },
200
  {
201
  "epoch": 18.0,
202
  "eval_accuracy": 0.10869565217391304,
203
+ "eval_loss": 113.83159637451172,
204
+ "eval_runtime": 0.6036,
205
+ "eval_samples_per_second": 76.204,
206
+ "eval_steps_per_second": 4.97,
207
  "step": 63
208
  },
209
  {
210
  "epoch": 18.86,
211
  "eval_accuracy": 0.10869565217391304,
212
+ "eval_loss": 113.82946014404297,
213
+ "eval_runtime": 0.6282,
214
+ "eval_samples_per_second": 73.23,
215
+ "eval_steps_per_second": 4.776,
216
  "step": 66
217
  },
218
  {
219
  "epoch": 20.0,
220
  "learning_rate": 1.0416666666666668e-05,
221
+ "loss": 114.062,
222
  "step": 70
223
  },
224
  {
225
  "epoch": 20.0,
226
  "eval_accuracy": 0.10869565217391304,
227
+ "eval_loss": 113.82839965820312,
228
+ "eval_runtime": 0.5991,
229
+ "eval_samples_per_second": 76.778,
230
+ "eval_steps_per_second": 5.007,
231
  "step": 70
232
  },
233
  {
234
  "epoch": 20.86,
235
  "eval_accuracy": 0.10869565217391304,
236
+ "eval_loss": 113.8253402709961,
237
+ "eval_runtime": 0.5961,
238
+ "eval_samples_per_second": 77.162,
239
+ "eval_steps_per_second": 5.032,
240
  "step": 73
241
  },
242
  {
243
  "epoch": 22.0,
244
  "eval_accuracy": 0.10869565217391304,
245
+ "eval_loss": 113.82349395751953,
246
+ "eval_runtime": 0.7817,
247
+ "eval_samples_per_second": 58.847,
248
+ "eval_steps_per_second": 3.838,
249
  "step": 77
250
  },
251
  {
252
  "epoch": 22.86,
253
  "learning_rate": 8.333333333333334e-06,
254
+ "loss": 114.5312,
255
  "step": 80
256
  },
257
  {
258
  "epoch": 22.86,
259
  "eval_accuracy": 0.10869565217391304,
260
+ "eval_loss": 113.82068634033203,
261
+ "eval_runtime": 0.6071,
262
+ "eval_samples_per_second": 75.766,
263
+ "eval_steps_per_second": 4.941,
264
  "step": 80
265
  },
266
  {
267
  "epoch": 24.0,
268
  "eval_accuracy": 0.10869565217391304,
269
+ "eval_loss": 113.81257629394531,
270
+ "eval_runtime": 0.6061,
271
+ "eval_samples_per_second": 75.891,
272
+ "eval_steps_per_second": 4.949,
273
  "step": 84
274
  },
275
  {
276
  "epoch": 24.86,
277
  "eval_accuracy": 0.10869565217391304,
278
+ "eval_loss": 113.81000518798828,
279
+ "eval_runtime": 0.6011,
280
+ "eval_samples_per_second": 76.522,
281
+ "eval_steps_per_second": 4.991,
282
  "step": 87
283
  },
284
  {
285
  "epoch": 25.71,
286
  "learning_rate": 6.25e-06,
287
+ "loss": 114.5216,
288
  "step": 90
289
  },
290
  {
291
  "epoch": 26.0,
292
  "eval_accuracy": 0.10869565217391304,
293
+ "eval_loss": 113.80531311035156,
294
+ "eval_runtime": 0.5966,
295
+ "eval_samples_per_second": 77.098,
296
+ "eval_steps_per_second": 5.028,
297
  "step": 91
298
  },
299
  {
300
  "epoch": 26.86,
301
  "eval_accuracy": 0.10869565217391304,
302
+ "eval_loss": 113.80321502685547,
303
+ "eval_runtime": 0.6162,
304
+ "eval_samples_per_second": 74.657,
305
+ "eval_steps_per_second": 4.869,
306
  "step": 94
307
  },
308
  {
309
  "epoch": 28.0,
310
  "eval_accuracy": 0.10869565217391304,
311
+ "eval_loss": 113.803466796875,
312
+ "eval_runtime": 0.5991,
313
+ "eval_samples_per_second": 76.777,
314
+ "eval_steps_per_second": 5.007,
315
  "step": 98
316
  },
317
  {
318
  "epoch": 28.57,
319
  "learning_rate": 4.166666666666667e-06,
320
+ "loss": 112.7612,
321
  "step": 100
322
  },
323
  {
324
  "epoch": 28.86,
325
  "eval_accuracy": 0.10869565217391304,
326
+ "eval_loss": 113.7991714477539,
327
+ "eval_runtime": 0.6142,
328
+ "eval_samples_per_second": 74.9,
329
+ "eval_steps_per_second": 4.885,
330
  "step": 101
331
  },
332
  {
333
  "epoch": 30.0,
334
  "eval_accuracy": 0.10869565217391304,
335
+ "eval_loss": 113.7939224243164,
336
+ "eval_runtime": 0.6141,
337
+ "eval_samples_per_second": 74.902,
338
+ "eval_steps_per_second": 4.885,
339
  "step": 105
340
  },
341
  {
342
  "epoch": 30.86,
343
  "eval_accuracy": 0.10869565217391304,
344
+ "eval_loss": 113.79671478271484,
345
+ "eval_runtime": 0.6337,
346
+ "eval_samples_per_second": 72.594,
347
+ "eval_steps_per_second": 4.734,
348
  "step": 108
349
  },
350
  {
351
  "epoch": 31.43,
352
  "learning_rate": 2.0833333333333334e-06,
353
+ "loss": 114.2748,
354
  "step": 110
355
  },
356
  {
357
  "epoch": 32.0,
358
  "eval_accuracy": 0.10869565217391304,
359
+ "eval_loss": 113.79725646972656,
360
+ "eval_runtime": 0.6392,
361
+ "eval_samples_per_second": 71.97,
362
+ "eval_steps_per_second": 4.694,
363
  "step": 112
364
  },
365
  {
366
  "epoch": 32.86,
367
  "eval_accuracy": 0.10869565217391304,
368
+ "eval_loss": 113.79711151123047,
369
+ "eval_runtime": 0.5956,
370
+ "eval_samples_per_second": 77.228,
371
+ "eval_steps_per_second": 5.037,
372
  "step": 115
373
  },
374
  {
375
  "epoch": 34.0,
376
  "eval_accuracy": 0.10869565217391304,
377
+ "eval_loss": 113.7907943725586,
378
+ "eval_runtime": 0.5981,
379
+ "eval_samples_per_second": 76.906,
380
+ "eval_steps_per_second": 5.016,
381
  "step": 119
382
  },
383
  {
384
  "epoch": 34.29,
385
  "learning_rate": 0.0,
386
+ "loss": 114.0708,
387
  "step": 120
388
  },
389
  {
390
  "epoch": 34.29,
391
  "eval_accuracy": 0.10869565217391304,
392
+ "eval_loss": 113.79315948486328,
393
+ "eval_runtime": 0.5946,
394
+ "eval_samples_per_second": 77.358,
395
+ "eval_steps_per_second": 5.045,
396
  "step": 120
397
  },
398
  {
399
  "epoch": 34.29,
400
  "step": 120,
401
  "total_flos": 2.0027429927092224e+16,
402
+ "train_loss": 113.75203348795573,
403
+ "train_runtime": 131.4365,
404
+ "train_samples_per_second": 64.822,
405
+ "train_steps_per_second": 0.913
406
  }
407
  ],
408
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15dffc887f0abc9caee2e18a2b30612e3655124e57b6e83dea493f5517e66aea
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3df9ef77f964a231a079193edbe54fab4c39d9bd25184de47de575af773cd47
3
  size 4728