kritigupta commited on
Commit
66bbc66
·
verified ·
1 Parent(s): 653edae

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/triplet_wo_lora_5_epochs",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.46.3",
35
+ "type_vocab_size": 1,
36
+ "use_cache": true,
37
+ "vocab_size": 50265
38
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a11e5e1f2a94307d0f5c21d5634d0f56fdddabbeed9b5cc3da4d754dd2fbbb0
3
+ size 498615900
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d80283671125a4da280748a56aec9c727c8bc6feb205c3cde427775ed66e5ac8
3
+ size 997351674
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6610e4ec4736e3da5d3325c751580c50b9d60ce540c357f4f58f756165c21214
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b47c5cef5da81dd2fe6b6113b88e70bb401f3165f877b619420c539527d22732
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_length": 512,
52
+ "model_max_length": 512,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "</s>",
58
+ "stride": 0,
59
+ "tokenizer_class": "RobertaTokenizer",
60
+ "trim_offsets": true,
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "<unk>"
64
+ }
trainer_state.json ADDED
@@ -0,0 +1,293 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3498,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05717552887364208,
13
+ "grad_norm": 16.45256233215332,
14
+ "learning_rate": 1.942824471126358e-05,
15
+ "loss": 0.9394,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.11435105774728416,
20
+ "grad_norm": 10.084893226623535,
21
+ "learning_rate": 1.885648942252716e-05,
22
+ "loss": 0.7282,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.17152658662092624,
27
+ "grad_norm": 18.495607376098633,
28
+ "learning_rate": 1.828473413379074e-05,
29
+ "loss": 0.6681,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.22870211549456831,
34
+ "grad_norm": 14.434144973754883,
35
+ "learning_rate": 1.7712978845054317e-05,
36
+ "loss": 0.6399,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.2858776443682104,
41
+ "grad_norm": 14.602225303649902,
42
+ "learning_rate": 1.7141223556317898e-05,
43
+ "loss": 0.562,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.34305317324185247,
48
+ "grad_norm": 24.44898796081543,
49
+ "learning_rate": 1.6569468267581476e-05,
50
+ "loss": 0.5233,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.40022870211549455,
55
+ "grad_norm": 23.65103530883789,
56
+ "learning_rate": 1.5997712978845054e-05,
57
+ "loss": 0.503,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.45740423098913663,
62
+ "grad_norm": 17.67190933227539,
63
+ "learning_rate": 1.5425957690108635e-05,
64
+ "loss": 0.5239,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.5145797598627787,
69
+ "grad_norm": 19.96052360534668,
70
+ "learning_rate": 1.4854202401372213e-05,
71
+ "loss": 0.4922,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.5717552887364208,
76
+ "grad_norm": 33.05682373046875,
77
+ "learning_rate": 1.4282447112635793e-05,
78
+ "loss": 0.4561,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.6289308176100629,
83
+ "grad_norm": 23.63544464111328,
84
+ "learning_rate": 1.371069182389937e-05,
85
+ "loss": 0.4756,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.6861063464837049,
90
+ "grad_norm": 24.539167404174805,
91
+ "learning_rate": 1.3138936535162952e-05,
92
+ "loss": 0.4296,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.743281875357347,
97
+ "grad_norm": 21.494192123413086,
98
+ "learning_rate": 1.256718124642653e-05,
99
+ "loss": 0.4298,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.8004574042309891,
104
+ "grad_norm": 19.144065856933594,
105
+ "learning_rate": 1.199542595769011e-05,
106
+ "loss": 0.4316,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.8576329331046312,
111
+ "grad_norm": 17.06574058532715,
112
+ "learning_rate": 1.1423670668953687e-05,
113
+ "loss": 0.4279,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.9148084619782733,
118
+ "grad_norm": 20.61432456970215,
119
+ "learning_rate": 1.0851915380217269e-05,
120
+ "loss": 0.3745,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.9719839908519153,
125
+ "grad_norm": 22.866825103759766,
126
+ "learning_rate": 1.0280160091480847e-05,
127
+ "loss": 0.4147,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 1.0,
132
+ "eval_accuracy": 0.8479130864143372,
133
+ "eval_loss": 0.41266146302223206,
134
+ "eval_macro_f1": 0.8474960392826089,
135
+ "eval_mae": 0.21297884505431675,
136
+ "eval_runtime": 71.394,
137
+ "eval_samples_per_second": 97.991,
138
+ "eval_steps_per_second": 6.135,
139
+ "step": 1749
140
+ },
141
+ {
142
+ "epoch": 1.0291595197255574,
143
+ "grad_norm": 26.078060150146484,
144
+ "learning_rate": 9.708404802744426e-06,
145
+ "loss": 0.3367,
146
+ "step": 1800
147
+ },
148
+ {
149
+ "epoch": 1.0863350485991996,
150
+ "grad_norm": 35.28126525878906,
151
+ "learning_rate": 9.136649514008006e-06,
152
+ "loss": 0.3372,
153
+ "step": 1900
154
+ },
155
+ {
156
+ "epoch": 1.1435105774728416,
157
+ "grad_norm": 17.67495346069336,
158
+ "learning_rate": 8.564894225271586e-06,
159
+ "loss": 0.3287,
160
+ "step": 2000
161
+ },
162
+ {
163
+ "epoch": 1.2006861063464838,
164
+ "grad_norm": 15.450718879699707,
165
+ "learning_rate": 7.993138936535163e-06,
166
+ "loss": 0.3343,
167
+ "step": 2100
168
+ },
169
+ {
170
+ "epoch": 1.2578616352201257,
171
+ "grad_norm": 14.494579315185547,
172
+ "learning_rate": 7.421383647798742e-06,
173
+ "loss": 0.3577,
174
+ "step": 2200
175
+ },
176
+ {
177
+ "epoch": 1.315037164093768,
178
+ "grad_norm": 16.795316696166992,
179
+ "learning_rate": 6.849628359062321e-06,
180
+ "loss": 0.3342,
181
+ "step": 2300
182
+ },
183
+ {
184
+ "epoch": 1.3722126929674099,
185
+ "grad_norm": 11.91577434539795,
186
+ "learning_rate": 6.277873070325901e-06,
187
+ "loss": 0.3215,
188
+ "step": 2400
189
+ },
190
+ {
191
+ "epoch": 1.429388221841052,
192
+ "grad_norm": 50.900177001953125,
193
+ "learning_rate": 5.706117781589479e-06,
194
+ "loss": 0.3033,
195
+ "step": 2500
196
+ },
197
+ {
198
+ "epoch": 1.486563750714694,
199
+ "grad_norm": 16.473859786987305,
200
+ "learning_rate": 5.134362492853059e-06,
201
+ "loss": 0.2926,
202
+ "step": 2600
203
+ },
204
+ {
205
+ "epoch": 1.5437392795883362,
206
+ "grad_norm": 20.416208267211914,
207
+ "learning_rate": 4.562607204116639e-06,
208
+ "loss": 0.3158,
209
+ "step": 2700
210
+ },
211
+ {
212
+ "epoch": 1.6009148084619782,
213
+ "grad_norm": 42.29115676879883,
214
+ "learning_rate": 3.990851915380217e-06,
215
+ "loss": 0.2899,
216
+ "step": 2800
217
+ },
218
+ {
219
+ "epoch": 1.6580903373356204,
220
+ "grad_norm": 7.523388385772705,
221
+ "learning_rate": 3.419096626643797e-06,
222
+ "loss": 0.2854,
223
+ "step": 2900
224
+ },
225
+ {
226
+ "epoch": 1.7152658662092626,
227
+ "grad_norm": 20.52057456970215,
228
+ "learning_rate": 2.847341337907376e-06,
229
+ "loss": 0.2671,
230
+ "step": 3000
231
+ },
232
+ {
233
+ "epoch": 1.7724413950829045,
234
+ "grad_norm": 18.777076721191406,
235
+ "learning_rate": 2.275586049170955e-06,
236
+ "loss": 0.3091,
237
+ "step": 3100
238
+ },
239
+ {
240
+ "epoch": 1.8296169239565465,
241
+ "grad_norm": 19.842416763305664,
242
+ "learning_rate": 1.7038307604345341e-06,
243
+ "loss": 0.2826,
244
+ "step": 3200
245
+ },
246
+ {
247
+ "epoch": 1.8867924528301887,
248
+ "grad_norm": 17.401905059814453,
249
+ "learning_rate": 1.1320754716981133e-06,
250
+ "loss": 0.2574,
251
+ "step": 3300
252
+ },
253
+ {
254
+ "epoch": 1.943967981703831,
255
+ "grad_norm": 38.20063018798828,
256
+ "learning_rate": 5.603201829616924e-07,
257
+ "loss": 0.2809,
258
+ "step": 3400
259
+ },
260
+ {
261
+ "epoch": 2.0,
262
+ "eval_accuracy": 0.8733562231063843,
263
+ "eval_loss": 0.3558960258960724,
264
+ "eval_macro_f1": 0.8732167839855643,
265
+ "eval_mae": 0.18010291595197256,
266
+ "eval_runtime": 71.6658,
267
+ "eval_samples_per_second": 97.62,
268
+ "eval_steps_per_second": 6.112,
269
+ "step": 3498
270
+ }
271
+ ],
272
+ "logging_steps": 100,
273
+ "max_steps": 3498,
274
+ "num_input_tokens_seen": 0,
275
+ "num_train_epochs": 2,
276
+ "save_steps": 500,
277
+ "stateful_callbacks": {
278
+ "TrainerControl": {
279
+ "args": {
280
+ "should_epoch_stop": false,
281
+ "should_evaluate": false,
282
+ "should_log": false,
283
+ "should_save": true,
284
+ "should_training_stop": true
285
+ },
286
+ "attributes": {}
287
+ }
288
+ },
289
+ "total_flos": 1.4722774402387968e+16,
290
+ "train_batch_size": 16,
291
+ "trial_name": null,
292
+ "trial_params": null
293
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:967cdbf239080237bba0a07b7d4e02fff6821b5532b3c496ff92921420edbdf9
3
+ size 5240
vocab.json ADDED
The diff for this file is too large to render. See raw diff