Hugging Face's logo

jayanta
/
test

Image Classification
Transformers
PyTorch
TensorBoard
vit
Model card Files
xet
Metrics Community
1
jayanta commited on
Commit
d581226
·
1 Parent(s): a478be1

Training in progress, epoch 0

Browse files
Files changed (10) hide show
  1. all_results.json +5 -5
  2. config.json +58 -11
  3. preprocessor_config.json +9 -8
  4. pytorch_model.bin +2 -2
  5. runs/Jul10_17-16-51_teesta/events.out.tfevents.1688989619.teesta.40693.0 +2 -2
  6. runs/Jul10_18-44-31_teesta/1688994879.355163/events.out.tfevents.1688994879.teesta.6977.1 +3 -0
  7. runs/Jul10_18-44-31_teesta/events.out.tfevents.1688994879.teesta.6977.0 +3 -0
  8. train_results.json +5 -5
  9. trainer_state.json +172 -172
  10. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 19.73,
3
- "total_flos": 2.8684782950326272e+17,
4
- "train_loss": 0.7429648399353027,
5
- "train_runtime": 749.9349,
6
- "train_samples_per_second": 18.242,
7
- "train_steps_per_second": 0.053
8
  }
 
1
  {
2
  "epoch": 19.73,
3
+ "total_flos": 1.0467617957139087e+18,
4
+ "train_loss": 0.13025596663355826,
5
+ "train_runtime": 778.539,
6
+ "train_samples_per_second": 17.571,
7
+ "train_steps_per_second": 0.051
8
  }
config.json CHANGED
@@ -1,32 +1,79 @@
1
  {
2
- "_name_or_path": "google/vit-base-patch16-224",
3
  "architectures": [
4
- "ViTForImageClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.0,
7
- "encoder_stride": 16,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.0,
10
- "hidden_size": 768,
 
 
 
 
 
11
  "id2label": {
12
  "0": "0",
13
  "1": "1"
14
  },
15
  "image_size": 224,
16
  "initializer_range": 0.02,
17
- "intermediate_size": 3072,
18
  "label2id": {
19
  "0": "0",
20
  "1": "1"
21
  },
22
- "layer_norm_eps": 1e-12,
23
- "model_type": "vit",
24
- "num_attention_heads": 12,
 
 
 
 
 
 
 
 
 
 
 
25
  "num_channels": 3,
26
- "num_hidden_layers": 12,
27
- "patch_size": 16,
 
 
 
 
 
28
  "problem_type": "single_label_classification",
29
- "qkv_bias": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.24.0"
32
  }
 
1
  {
2
+ "_name_or_path": "nvidia/mit-b0",
3
  "architectures": [
4
+ "SegformerForImageClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.0,
7
+ "classifier_dropout_prob": 0.1,
8
+ "decoder_hidden_size": 256,
9
+ "depths": [
10
+ 2,
11
+ 2,
12
+ 2,
13
+ 2
14
+ ],
15
+ "downsampling_rates": [
16
+ 1,
17
+ 4,
18
+ 8,
19
+ 16
20
+ ],
21
+ "drop_path_rate": 0.1,
22
  "hidden_act": "gelu",
23
  "hidden_dropout_prob": 0.0,
24
+ "hidden_sizes": [
25
+ 32,
26
+ 64,
27
+ 160,
28
+ 256
29
+ ],
30
  "id2label": {
31
  "0": "0",
32
  "1": "1"
33
  },
34
  "image_size": 224,
35
  "initializer_range": 0.02,
 
36
  "label2id": {
37
  "0": "0",
38
  "1": "1"
39
  },
40
+ "layer_norm_eps": 1e-06,
41
+ "mlp_ratios": [
42
+ 4,
43
+ 4,
44
+ 4,
45
+ 4
46
+ ],
47
+ "model_type": "segformer",
48
+ "num_attention_heads": [
49
+ 1,
50
+ 2,
51
+ 5,
52
+ 8
53
+ ],
54
  "num_channels": 3,
55
+ "num_encoder_blocks": 4,
56
+ "patch_sizes": [
57
+ 7,
58
+ 3,
59
+ 3,
60
+ 3
61
+ ],
62
  "problem_type": "single_label_classification",
63
+ "reshape_last_stage": true,
64
+ "semantic_loss_ignore_index": 255,
65
+ "sr_ratios": [
66
+ 8,
67
+ 4,
68
+ 2,
69
+ 1
70
+ ],
71
+ "strides": [
72
+ 4,
73
+ 2,
74
+ 2,
75
+ 2
76
+ ],
77
  "torch_dtype": "float32",
78
  "transformers_version": "4.24.0"
79
  }
preprocessor_config.json CHANGED
@@ -1,17 +1,18 @@
1
  {
2
  "do_normalize": true,
3
  "do_resize": true,
4
- "feature_extractor_type": "ViTFeatureExtractor",
5
  "image_mean": [
6
- 0.5,
7
- 0.5,
8
- 0.5
9
  ],
10
  "image_std": [
11
- 0.5,
12
- 0.5,
13
- 0.5
14
  ],
 
15
  "resample": 2,
16
- "size": 224
17
  }
 
1
  {
2
  "do_normalize": true,
3
  "do_resize": true,
4
+ "feature_extractor_type": "SegformerFeatureExtractor",
5
  "image_mean": [
6
+ 0.485,
7
+ 0.456,
8
+ 0.406
9
  ],
10
  "image_std": [
11
+ 0.229,
12
+ 0.224,
13
+ 0.225
14
  ],
15
+ "reduce_labels": false,
16
  "resample": 2,
17
+ "size": 512
18
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:224dbd38a59daef862ff8fa079d716ec204db588af8e4fec55ac30f4cbcea941
3
- size 343268717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c025b0f5f2d4657ee30064a00ccb79687a000bec30ee8c7d9598e4c133589d0
3
+ size 13346069
runs/Jul10_17-16-51_teesta/events.out.tfevents.1688989619.teesta.40693.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb5e3920b732a5c13696b02fc8cc666c6d5c950c08707b4489efaa68067ceef1
3
- size 11981
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56520f237cd1741d0c2646cdfe5ce70c168ac03c523e7b5c1ab6e09f0016ad7d
3
+ size 13872
runs/Jul10_18-44-31_teesta/1688994879.355163/events.out.tfevents.1688994879.teesta.6977.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928f72464bf9a1d8b64a66ec6db0a226ce672259395c94cdaf10ca74a730a8c3
3
+ size 5427
runs/Jul10_18-44-31_teesta/events.out.tfevents.1688994879.teesta.6977.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b375bfef68a0ff2197730553438ae480eb207020337ca4dda51b979cd775ad
3
+ size 4568
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 19.73,
3
- "total_flos": 2.8684782950326272e+17,
4
- "train_loss": 0.7429648399353027,
5
- "train_runtime": 749.9349,
6
- "train_samples_per_second": 18.242,
7
- "train_steps_per_second": 0.053
8
  }
 
1
  {
2
  "epoch": 19.73,
3
+ "total_flos": 1.0467617957139087e+18,
4
+ "train_loss": 0.13025596663355826,
5
+ "train_runtime": 778.539,
6
+ "train_samples_per_second": 17.571,
7
+ "train_steps_per_second": 0.051
8
  }
trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.8333333333333334,
3
- "best_model_checkpoint": "test/checkpoint-34",
4
  "epoch": 19.727272727272727,
5
  "global_step": 40,
6
  "is_hyper_param_search": false,
@@ -9,281 +9,281 @@
9
  "log_history": [
10
  {
11
  "epoch": 0.73,
12
- "eval_accuracy": 0.7777777777777778,
13
- "eval_f1": 0.770940170940171,
14
- "eval_loss": 0.6720435619354248,
15
- "eval_precision": 0.7695473251028806,
16
- "eval_recall": 0.7777777777777778,
17
- "eval_runtime": 7.169,
18
- "eval_samples_per_second": 5.022,
19
- "eval_steps_per_second": 0.139,
20
  "step": 2
21
  },
22
  {
23
  "epoch": 1.73,
24
- "eval_accuracy": 0.7777777777777778,
25
- "eval_f1": 0.7613168724279835,
26
- "eval_loss": 0.6651345491409302,
27
- "eval_precision": 0.7690202517788725,
28
- "eval_recall": 0.7777777777777778,
29
- "eval_runtime": 5.928,
30
- "eval_samples_per_second": 6.073,
31
- "eval_steps_per_second": 0.169,
32
  "step": 4
33
  },
34
  {
35
  "epoch": 2.73,
36
- "eval_accuracy": 0.6944444444444444,
37
- "eval_f1": 0.6119802984209763,
38
- "eval_loss": 0.6359639763832092,
39
- "eval_precision": 0.6429738562091504,
40
- "eval_recall": 0.6944444444444444,
41
- "eval_runtime": 4.9898,
42
- "eval_samples_per_second": 7.215,
43
- "eval_steps_per_second": 0.2,
44
  "step": 6
45
  },
46
  {
47
  "epoch": 3.73,
48
- "eval_accuracy": 0.6666666666666666,
49
- "eval_f1": 0.5555555555555556,
50
- "eval_loss": 0.6130982041358948,
51
- "eval_precision": 0.47619047619047616,
52
- "eval_recall": 0.6666666666666666,
53
- "eval_runtime": 5.5773,
54
- "eval_samples_per_second": 6.455,
55
- "eval_steps_per_second": 0.179,
56
  "step": 8
57
  },
58
  {
59
  "epoch": 4.73,
60
  "learning_rate": 0.0001,
61
- "loss": 0.85,
62
  "step": 10
63
  },
64
  {
65
  "epoch": 4.73,
66
- "eval_accuracy": 0.6944444444444444,
67
- "eval_f1": 0.569216757741348,
68
- "eval_loss": 0.5958656668663025,
69
- "eval_precision": 0.48225308641975306,
70
- "eval_recall": 0.6944444444444444,
71
- "eval_runtime": 5.3816,
72
- "eval_samples_per_second": 6.689,
73
- "eval_steps_per_second": 0.186,
74
  "step": 10
75
  },
76
  {
77
  "epoch": 5.73,
78
- "eval_accuracy": 0.6944444444444444,
79
- "eval_f1": 0.569216757741348,
80
- "eval_loss": 0.5696195960044861,
81
- "eval_precision": 0.48225308641975306,
82
- "eval_recall": 0.6944444444444444,
83
- "eval_runtime": 5.4307,
84
- "eval_samples_per_second": 6.629,
85
- "eval_steps_per_second": 0.184,
86
  "step": 12
87
  },
88
  {
89
  "epoch": 6.73,
90
- "eval_accuracy": 0.6944444444444444,
91
- "eval_f1": 0.569216757741348,
92
- "eval_loss": 0.5393776297569275,
93
- "eval_precision": 0.48225308641975306,
94
- "eval_recall": 0.6944444444444444,
95
- "eval_runtime": 5.3348,
96
- "eval_samples_per_second": 6.748,
97
- "eval_steps_per_second": 0.187,
98
  "step": 14
99
  },
100
  {
101
  "epoch": 7.73,
102
- "eval_accuracy": 0.6944444444444444,
103
- "eval_f1": 0.569216757741348,
104
- "eval_loss": 0.525506317615509,
105
- "eval_precision": 0.48225308641975306,
106
- "eval_recall": 0.6944444444444444,
107
- "eval_runtime": 4.9234,
108
- "eval_samples_per_second": 7.312,
109
- "eval_steps_per_second": 0.203,
110
  "step": 16
111
  },
112
  {
113
  "epoch": 8.73,
114
- "eval_accuracy": 0.7222222222222222,
115
- "eval_f1": 0.6296296296296295,
116
- "eval_loss": 0.5029427409172058,
117
- "eval_precision": 0.8015873015873016,
118
- "eval_recall": 0.7222222222222222,
119
- "eval_runtime": 4.9254,
120
- "eval_samples_per_second": 7.309,
121
- "eval_steps_per_second": 0.203,
122
  "step": 18
123
  },
124
  {
125
  "epoch": 9.73,
126
  "learning_rate": 6.666666666666667e-05,
127
- "loss": 0.7809,
128
  "step": 20
129
  },
130
  {
131
  "epoch": 9.73,
132
- "eval_accuracy": 0.7222222222222222,
133
- "eval_f1": 0.6296296296296295,
134
- "eval_loss": 0.49091774225234985,
135
- "eval_precision": 0.8015873015873016,
136
- "eval_recall": 0.7222222222222222,
137
- "eval_runtime": 5.0878,
138
- "eval_samples_per_second": 7.076,
139
- "eval_steps_per_second": 0.197,
140
  "step": 20
141
  },
142
  {
143
  "epoch": 10.73,
144
- "eval_accuracy": 0.6944444444444444,
145
- "eval_f1": 0.569216757741348,
146
- "eval_loss": 0.47324174642562866,
147
- "eval_precision": 0.48225308641975306,
148
- "eval_recall": 0.6944444444444444,
149
- "eval_runtime": 6.264,
150
- "eval_samples_per_second": 5.747,
151
- "eval_steps_per_second": 0.16,
152
  "step": 22
153
  },
154
  {
155
  "epoch": 11.73,
156
- "eval_accuracy": 0.7222222222222222,
157
- "eval_f1": 0.6296296296296295,
158
- "eval_loss": 0.47097042202949524,
159
- "eval_precision": 0.8015873015873016,
160
- "eval_recall": 0.7222222222222222,
161
- "eval_runtime": 4.8001,
162
- "eval_samples_per_second": 7.5,
163
- "eval_steps_per_second": 0.208,
164
  "step": 24
165
  },
166
  {
167
  "epoch": 12.73,
168
- "eval_accuracy": 0.7222222222222222,
169
- "eval_f1": 0.6296296296296295,
170
- "eval_loss": 0.4540965259075165,
171
- "eval_precision": 0.8015873015873016,
172
- "eval_recall": 0.7222222222222222,
173
- "eval_runtime": 4.7617,
174
- "eval_samples_per_second": 7.56,
175
- "eval_steps_per_second": 0.21,
176
  "step": 26
177
  },
178
  {
179
  "epoch": 13.73,
180
- "eval_accuracy": 0.7777777777777778,
181
- "eval_f1": 0.7296113847837985,
182
- "eval_loss": 0.44506168365478516,
183
- "eval_precision": 0.8316498316498316,
184
- "eval_recall": 0.7777777777777778,
185
- "eval_runtime": 4.873,
186
- "eval_samples_per_second": 7.388,
187
- "eval_steps_per_second": 0.205,
188
  "step": 28
189
  },
190
  {
191
  "epoch": 14.73,
192
  "learning_rate": 3.3333333333333335e-05,
193
- "loss": 0.6976,
194
  "step": 30
195
  },
196
  {
197
  "epoch": 14.73,
198
- "eval_accuracy": 0.7777777777777778,
199
- "eval_f1": 0.7296113847837985,
200
- "eval_loss": 0.44511425495147705,
201
- "eval_precision": 0.8316498316498316,
202
- "eval_recall": 0.7777777777777778,
203
- "eval_runtime": 5.299,
204
- "eval_samples_per_second": 6.794,
205
- "eval_steps_per_second": 0.189,
206
  "step": 30
207
  },
208
  {
209
  "epoch": 15.73,
210
- "eval_accuracy": 0.8055555555555556,
211
- "eval_f1": 0.7721247563352827,
212
- "eval_loss": 0.4380625784397125,
213
- "eval_precision": 0.8480902777777778,
214
- "eval_recall": 0.8055555555555556,
215
- "eval_runtime": 5.0388,
216
- "eval_samples_per_second": 7.145,
217
- "eval_steps_per_second": 0.198,
218
  "step": 32
219
  },
220
  {
221
  "epoch": 16.73,
222
- "eval_accuracy": 0.8333333333333334,
223
- "eval_f1": 0.8110119047619047,
224
- "eval_loss": 0.4326169788837433,
225
- "eval_precision": 0.8655913978494624,
226
- "eval_recall": 0.8333333333333334,
227
- "eval_runtime": 5.6799,
228
- "eval_samples_per_second": 6.338,
229
- "eval_steps_per_second": 0.176,
230
  "step": 34
231
  },
232
  {
233
  "epoch": 17.73,
234
- "eval_accuracy": 0.7777777777777778,
235
- "eval_f1": 0.7296113847837985,
236
- "eval_loss": 0.4337227940559387,
237
- "eval_precision": 0.8316498316498316,
238
- "eval_recall": 0.7777777777777778,
239
- "eval_runtime": 4.7411,
240
- "eval_samples_per_second": 7.593,
241
- "eval_steps_per_second": 0.211,
242
  "step": 36
243
  },
244
  {
245
  "epoch": 18.73,
246
- "eval_accuracy": 0.8055555555555556,
247
- "eval_f1": 0.7721247563352827,
248
- "eval_loss": 0.4260648787021637,
249
- "eval_precision": 0.8480902777777778,
250
- "eval_recall": 0.8055555555555556,
251
- "eval_runtime": 5.2317,
252
- "eval_samples_per_second": 6.881,
253
- "eval_steps_per_second": 0.191,
254
  "step": 38
255
  },
256
  {
257
  "epoch": 19.73,
258
  "learning_rate": 0.0,
259
- "loss": 0.6433,
260
  "step": 40
261
  },
262
  {
263
  "epoch": 19.73,
264
- "eval_accuracy": 0.75,
265
- "eval_f1": 0.6825293350717081,
266
- "eval_loss": 0.42079275846481323,
267
- "eval_precision": 0.8161764705882353,
268
- "eval_recall": 0.75,
269
- "eval_runtime": 6.4007,
270
- "eval_samples_per_second": 5.624,
271
- "eval_steps_per_second": 0.156,
272
  "step": 40
273
  },
274
  {
275
  "epoch": 19.73,
276
  "step": 40,
277
- "total_flos": 2.8684782950326272e+17,
278
- "train_loss": 0.7429648399353027,
279
- "train_runtime": 749.9349,
280
- "train_samples_per_second": 18.242,
281
- "train_steps_per_second": 0.053
282
  }
283
  ],
284
  "max_steps": 40,
285
  "num_train_epochs": 20,
286
- "total_flos": 2.8684782950326272e+17,
287
  "trial_name": null,
288
  "trial_params": null
289
  }
 
1
  {
2
+ "best_metric": 0.9444444444444444,
3
+ "best_model_checkpoint": "test/checkpoint-18",
4
  "epoch": 19.727272727272727,
5
  "global_step": 40,
6
  "is_hyper_param_search": false,
 
9
  "log_history": [
10
  {
11
  "epoch": 0.73,
12
+ "eval_accuracy": 0.6388888888888888,
13
+ "eval_f1": 0.6513851917578626,
14
+ "eval_loss": 0.6436764597892761,
15
+ "eval_precision": 0.6720549981419547,
16
+ "eval_recall": 0.6388888888888888,
17
+ "eval_runtime": 6.0758,
18
+ "eval_samples_per_second": 5.925,
19
+ "eval_steps_per_second": 0.165,
20
  "step": 2
21
  },
22
  {
23
  "epoch": 1.73,
24
+ "eval_accuracy": 0.8055555555555556,
25
+ "eval_f1": 0.7647399681297986,
26
+ "eval_loss": 0.3604269325733185,
27
+ "eval_precision": 0.8468013468013468,
28
+ "eval_recall": 0.8055555555555556,
29
+ "eval_runtime": 5.7608,
30
+ "eval_samples_per_second": 6.249,
31
+ "eval_steps_per_second": 0.174,
32
  "step": 4
33
  },
34
  {
35
  "epoch": 2.73,
36
+ "eval_accuracy": 0.8888888888888888,
37
+ "eval_f1": 0.8888888888888888,
38
+ "eval_loss": 0.22702129185199738,
39
+ "eval_precision": 0.8888888888888888,
40
+ "eval_recall": 0.8888888888888888,
41
+ "eval_runtime": 4.8725,
42
+ "eval_samples_per_second": 7.388,
43
+ "eval_steps_per_second": 0.205,
44
  "step": 6
45
  },
46
  {
47
  "epoch": 3.73,
48
+ "eval_accuracy": 0.8888888888888888,
49
+ "eval_f1": 0.8888888888888888,
50
+ "eval_loss": 0.16791754961013794,
51
+ "eval_precision": 0.8888888888888888,
52
+ "eval_recall": 0.8888888888888888,
53
+ "eval_runtime": 6.131,
54
+ "eval_samples_per_second": 5.872,
55
+ "eval_steps_per_second": 0.163,
56
  "step": 8
57
  },
58
  {
59
  "epoch": 4.73,
60
  "learning_rate": 0.0001,
61
+ "loss": 0.4939,
62
  "step": 10
63
  },
64
  {
65
  "epoch": 4.73,
66
+ "eval_accuracy": 0.8888888888888888,
67
+ "eval_f1": 0.8888888888888888,
68
+ "eval_loss": 0.15902230143547058,
69
+ "eval_precision": 0.8888888888888888,
70
+ "eval_recall": 0.8888888888888888,
71
+ "eval_runtime": 4.9896,
72
+ "eval_samples_per_second": 7.215,
73
+ "eval_steps_per_second": 0.2,
74
  "step": 10
75
  },
76
  {
77
  "epoch": 5.73,
78
+ "eval_accuracy": 0.9166666666666666,
79
+ "eval_f1": 0.9152598477325389,
80
+ "eval_loss": 0.15024107694625854,
81
+ "eval_precision": 0.9156378600823045,
82
+ "eval_recall": 0.9166666666666666,
83
+ "eval_runtime": 4.9812,
84
+ "eval_samples_per_second": 7.227,
85
+ "eval_steps_per_second": 0.201,
86
  "step": 12
87
  },
88
  {
89
  "epoch": 6.73,
90
+ "eval_accuracy": 0.9166666666666666,
91
+ "eval_f1": 0.9152598477325389,
92
+ "eval_loss": 0.13303342461585999,
93
+ "eval_precision": 0.9156378600823045,
94
+ "eval_recall": 0.9166666666666666,
95
+ "eval_runtime": 4.8591,
96
+ "eval_samples_per_second": 7.409,
97
+ "eval_steps_per_second": 0.206,
98
  "step": 14
99
  },
100
  {
101
  "epoch": 7.73,
102
+ "eval_accuracy": 0.8888888888888888,
103
+ "eval_f1": 0.8888888888888888,
104
+ "eval_loss": 0.12413659691810608,
105
+ "eval_precision": 0.8888888888888888,
106
+ "eval_recall": 0.8888888888888888,
107
+ "eval_runtime": 5.4858,
108
+ "eval_samples_per_second": 6.562,
109
+ "eval_steps_per_second": 0.182,
110
  "step": 16
111
  },
112
  {
113
  "epoch": 8.73,
114
+ "eval_accuracy": 0.9444444444444444,
115
+ "eval_f1": 0.9423868312757201,
116
+ "eval_loss": 0.0989239364862442,
117
+ "eval_precision": 0.9484126984126983,
118
+ "eval_recall": 0.9444444444444444,
119
+ "eval_runtime": 5.6045,
120
+ "eval_samples_per_second": 6.423,
121
+ "eval_steps_per_second": 0.178,
122
  "step": 18
123
  },
124
  {
125
  "epoch": 9.73,
126
  "learning_rate": 6.666666666666667e-05,
127
+ "loss": 0.0234,
128
  "step": 20
129
  },
130
  {
131
  "epoch": 9.73,
132
+ "eval_accuracy": 0.9166666666666666,
133
+ "eval_f1": 0.9152598477325389,
134
+ "eval_loss": 0.10008219629526138,
135
+ "eval_precision": 0.9156378600823045,
136
+ "eval_recall": 0.9166666666666666,
137
+ "eval_runtime": 6.5249,
138
+ "eval_samples_per_second": 5.517,
139
+ "eval_steps_per_second": 0.153,
140
  "step": 20
141
  },
142
  {
143
  "epoch": 10.73,
144
+ "eval_accuracy": 0.9444444444444444,
145
+ "eval_f1": 0.9423868312757201,
146
+ "eval_loss": 0.09186337888240814,
147
+ "eval_precision": 0.9484126984126983,
148
+ "eval_recall": 0.9444444444444444,
149
+ "eval_runtime": 5.01,
150
+ "eval_samples_per_second": 7.186,
151
+ "eval_steps_per_second": 0.2,
152
  "step": 22
153
  },
154
  {
155
  "epoch": 11.73,
156
+ "eval_accuracy": 0.9444444444444444,
157
+ "eval_f1": 0.9423868312757201,
158
+ "eval_loss": 0.09773090481758118,
159
+ "eval_precision": 0.9484126984126983,
160
+ "eval_recall": 0.9444444444444444,
161
+ "eval_runtime": 5.7387,
162
+ "eval_samples_per_second": 6.273,
163
+ "eval_steps_per_second": 0.174,
164
  "step": 24
165
  },
166
  {
167
  "epoch": 12.73,
168
+ "eval_accuracy": 0.9444444444444444,
169
+ "eval_f1": 0.9423868312757201,
170
+ "eval_loss": 0.10761526226997375,
171
+ "eval_precision": 0.9484126984126983,
172
+ "eval_recall": 0.9444444444444444,
173
+ "eval_runtime": 5.1262,
174
+ "eval_samples_per_second": 7.023,
175
+ "eval_steps_per_second": 0.195,
176
  "step": 26
177
  },
178
  {
179
  "epoch": 13.73,
180
+ "eval_accuracy": 0.9444444444444444,
181
+ "eval_f1": 0.9423868312757201,
182
+ "eval_loss": 0.09590016305446625,
183
+ "eval_precision": 0.9484126984126983,
184
+ "eval_recall": 0.9444444444444444,
185
+ "eval_runtime": 5.0649,
186
+ "eval_samples_per_second": 7.108,
187
+ "eval_steps_per_second": 0.197,
188
  "step": 28
189
  },
190
  {
191
  "epoch": 14.73,
192
  "learning_rate": 3.3333333333333335e-05,
193
+ "loss": 0.0024,
194
  "step": 30
195
  },
196
  {
197
  "epoch": 14.73,
198
+ "eval_accuracy": 0.9444444444444444,
199
+ "eval_f1": 0.9423868312757201,
200
+ "eval_loss": 0.11737969517707825,
201
+ "eval_precision": 0.9484126984126983,
202
+ "eval_recall": 0.9444444444444444,
203
+ "eval_runtime": 10.5713,
204
+ "eval_samples_per_second": 3.405,
205
+ "eval_steps_per_second": 0.095,
206
  "step": 30
207
  },
208
  {
209
  "epoch": 15.73,
210
+ "eval_accuracy": 0.9444444444444444,
211
+ "eval_f1": 0.9423868312757201,
212
+ "eval_loss": 0.10555433481931686,
213
+ "eval_precision": 0.9484126984126983,
214
+ "eval_recall": 0.9444444444444444,
215
+ "eval_runtime": 5.3198,
216
+ "eval_samples_per_second": 6.767,
217
+ "eval_steps_per_second": 0.188,
218
  "step": 32
219
  },
220
  {
221
  "epoch": 16.73,
222
+ "eval_accuracy": 0.9444444444444444,
223
+ "eval_f1": 0.9423868312757201,
224
+ "eval_loss": 0.1085939034819603,
225
+ "eval_precision": 0.9484126984126983,
226
+ "eval_recall": 0.9444444444444444,
227
+ "eval_runtime": 5.2418,
228
+ "eval_samples_per_second": 6.868,
229
+ "eval_steps_per_second": 0.191,
230
  "step": 34
231
  },
232
  {
233
  "epoch": 17.73,
234
+ "eval_accuracy": 0.9444444444444444,
235
+ "eval_f1": 0.9423868312757201,
236
+ "eval_loss": 0.11273058503866196,
237
+ "eval_precision": 0.9484126984126983,
238
+ "eval_recall": 0.9444444444444444,
239
+ "eval_runtime": 6.5423,
240
+ "eval_samples_per_second": 5.503,
241
+ "eval_steps_per_second": 0.153,
242
  "step": 36
243
  },
244
  {
245
  "epoch": 18.73,
246
+ "eval_accuracy": 0.9444444444444444,
247
+ "eval_f1": 0.9423868312757201,
248
+ "eval_loss": 0.1172882616519928,
249
+ "eval_precision": 0.9484126984126983,
250
+ "eval_recall": 0.9444444444444444,
251
+ "eval_runtime": 5.9599,
252
+ "eval_samples_per_second": 6.04,
253
+ "eval_steps_per_second": 0.168,
254
  "step": 38
255
  },
256
  {
257
  "epoch": 19.73,
258
  "learning_rate": 0.0,
259
+ "loss": 0.0013,
260
  "step": 40
261
  },
262
  {
263
  "epoch": 19.73,
264
+ "eval_accuracy": 0.9444444444444444,
265
+ "eval_f1": 0.9423868312757201,
266
+ "eval_loss": 0.11149459332227707,
267
+ "eval_precision": 0.9484126984126983,
268
+ "eval_recall": 0.9444444444444444,
269
+ "eval_runtime": 5.9908,
270
+ "eval_samples_per_second": 6.009,
271
+ "eval_steps_per_second": 0.167,
272
  "step": 40
273
  },
274
  {
275
  "epoch": 19.73,
276
  "step": 40,
277
+ "total_flos": 1.0467617957139087e+18,
278
+ "train_loss": 0.13025596663355826,
279
+ "train_runtime": 778.539,
280
+ "train_samples_per_second": 17.571,
281
+ "train_steps_per_second": 0.051
282
  }
283
  ],
284
  "max_steps": 40,
285
  "num_train_epochs": 20,
286
+ "total_flos": 1.0467617957139087e+18,
287
  "trial_name": null,
288
  "trial_params": null
289
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a24e0b9bc7c80089107c68a211b86b5a64a5036f730fcfc386da6a2e2aef4e1f
3
  size 3387
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49aab5e5341ad6773a4a7b366c080f1cd6f47aa4da51bb4235c3e6f7333bdf36
3
  size 3387