Earlan Josh Sabillano commited on
Commit
be620c4
·
verified ·
1 Parent(s): 0461369

Add files using upload-large-folder tool

Browse files
checkpoint-372/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large-mnli",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "encoder_attention_heads": 16,
22
+ "encoder_ffn_dim": 4096,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 12,
25
+ "eos_token_id": 2,
26
+ "forced_eos_token_id": 2,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "contradiction",
30
+ "1": "neutral",
31
+ "2": "entailment"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_encoder_decoder": true,
35
+ "label2id": {
36
+ "contradiction": 0,
37
+ "entailment": 2,
38
+ "neutral": 1
39
+ },
40
+ "max_position_embeddings": 1024,
41
+ "model_type": "bart",
42
+ "normalize_before": false,
43
+ "num_hidden_layers": 12,
44
+ "output_past": false,
45
+ "pad_token_id": 1,
46
+ "scale_embedding": false,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.48.3",
49
+ "use_cache": true,
50
+ "vocab_size": 50265
51
+ }
checkpoint-372/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.48.3"
9
+ }
checkpoint-372/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f70cacbe02f71d7fc7c7aeb2eca84d54f4ba2622d459d4c3f69c85e0ba572715
3
+ size 1625426996
checkpoint-372/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb90e921d85a51f310351d5f6f9c254c166631639742aa0f8e8c969ac96003a
3
+ size 3250759951
checkpoint-372/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3570a2905f26560fcccb4d2a2943795e881f47503488f0a90de8a71f2b6818a6
3
+ size 14244
checkpoint-372/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b5e6fdd4ac8947f62724067566ca74b82cd474980a3e5c15c66de64bd39e98
3
+ size 1064
checkpoint-372/trainer_state.json ADDED
@@ -0,0 +1,308 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9809045226130655,
5
+ "eval_steps": 500,
6
+ "global_step": 372,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08040201005025126,
13
+ "grad_norm": 29.01942253112793,
14
+ "learning_rate": 4.865591397849463e-05,
15
+ "loss": 2.798,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.16080402010050251,
20
+ "grad_norm": 2.744927406311035,
21
+ "learning_rate": 4.731182795698925e-05,
22
+ "loss": 0.7463,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.24120603015075376,
27
+ "grad_norm": 23.628087997436523,
28
+ "learning_rate": 4.596774193548387e-05,
29
+ "loss": 0.6532,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.32160804020100503,
34
+ "grad_norm": 7.0060715675354,
35
+ "learning_rate": 4.4623655913978496e-05,
36
+ "loss": 0.6,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.4020100502512563,
41
+ "grad_norm": 4.830014228820801,
42
+ "learning_rate": 4.327956989247312e-05,
43
+ "loss": 0.4285,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.4824120603015075,
48
+ "grad_norm": 3.5819506645202637,
49
+ "learning_rate": 4.1935483870967746e-05,
50
+ "loss": 0.4012,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.5628140703517588,
55
+ "grad_norm": 11.144820213317871,
56
+ "learning_rate": 4.0591397849462364e-05,
57
+ "loss": 0.319,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.6432160804020101,
62
+ "grad_norm": 6.964443206787109,
63
+ "learning_rate": 3.924731182795699e-05,
64
+ "loss": 0.3855,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.7236180904522613,
69
+ "grad_norm": 10.514158248901367,
70
+ "learning_rate": 3.7903225806451614e-05,
71
+ "loss": 0.3164,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.8040201005025126,
76
+ "grad_norm": 2.0289254188537598,
77
+ "learning_rate": 3.655913978494624e-05,
78
+ "loss": 0.2692,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.8844221105527639,
83
+ "grad_norm": 1.9192312955856323,
84
+ "learning_rate": 3.5215053763440864e-05,
85
+ "loss": 0.2635,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.964824120603015,
90
+ "grad_norm": 6.680674076080322,
91
+ "learning_rate": 3.387096774193548e-05,
92
+ "loss": 0.3005,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.0,
97
+ "eval_loss": 0.2973356246948242,
98
+ "eval_runtime": 8.055,
99
+ "eval_samples_per_second": 247.052,
100
+ "eval_steps_per_second": 30.913,
101
+ "step": 125
102
+ },
103
+ {
104
+ "epoch": 1.0402010050251256,
105
+ "grad_norm": 9.173807144165039,
106
+ "learning_rate": 3.252688172043011e-05,
107
+ "loss": 0.3001,
108
+ "step": 130
109
+ },
110
+ {
111
+ "epoch": 1.120603015075377,
112
+ "grad_norm": 3.8994596004486084,
113
+ "learning_rate": 3.118279569892473e-05,
114
+ "loss": 0.2407,
115
+ "step": 140
116
+ },
117
+ {
118
+ "epoch": 1.2010050251256281,
119
+ "grad_norm": 4.364039421081543,
120
+ "learning_rate": 2.9838709677419357e-05,
121
+ "loss": 0.2059,
122
+ "step": 150
123
+ },
124
+ {
125
+ "epoch": 1.2814070351758793,
126
+ "grad_norm": 13.414017677307129,
127
+ "learning_rate": 2.8494623655913982e-05,
128
+ "loss": 0.2356,
129
+ "step": 160
130
+ },
131
+ {
132
+ "epoch": 1.3618090452261307,
133
+ "grad_norm": 11.49068832397461,
134
+ "learning_rate": 2.71505376344086e-05,
135
+ "loss": 0.3452,
136
+ "step": 170
137
+ },
138
+ {
139
+ "epoch": 1.442211055276382,
140
+ "grad_norm": 7.965292453765869,
141
+ "learning_rate": 2.5806451612903226e-05,
142
+ "loss": 0.2722,
143
+ "step": 180
144
+ },
145
+ {
146
+ "epoch": 1.5226130653266332,
147
+ "grad_norm": 2.0057058334350586,
148
+ "learning_rate": 2.446236559139785e-05,
149
+ "loss": 0.1858,
150
+ "step": 190
151
+ },
152
+ {
153
+ "epoch": 1.6030150753768844,
154
+ "grad_norm": 3.195129632949829,
155
+ "learning_rate": 2.3118279569892472e-05,
156
+ "loss": 0.2449,
157
+ "step": 200
158
+ },
159
+ {
160
+ "epoch": 1.6834170854271355,
161
+ "grad_norm": 4.746509075164795,
162
+ "learning_rate": 2.1774193548387097e-05,
163
+ "loss": 0.2339,
164
+ "step": 210
165
+ },
166
+ {
167
+ "epoch": 1.763819095477387,
168
+ "grad_norm": 2.469165086746216,
169
+ "learning_rate": 2.0430107526881722e-05,
170
+ "loss": 0.1992,
171
+ "step": 220
172
+ },
173
+ {
174
+ "epoch": 1.8442211055276383,
175
+ "grad_norm": 3.318335771560669,
176
+ "learning_rate": 1.9086021505376344e-05,
177
+ "loss": 0.2243,
178
+ "step": 230
179
+ },
180
+ {
181
+ "epoch": 1.9246231155778895,
182
+ "grad_norm": 2.4900591373443604,
183
+ "learning_rate": 1.774193548387097e-05,
184
+ "loss": 0.2452,
185
+ "step": 240
186
+ },
187
+ {
188
+ "epoch": 2.0,
189
+ "grad_norm": 1.6156350374221802,
190
+ "learning_rate": 1.639784946236559e-05,
191
+ "loss": 0.1968,
192
+ "step": 250
193
+ },
194
+ {
195
+ "epoch": 2.0,
196
+ "eval_loss": 0.22428156435489655,
197
+ "eval_runtime": 7.7355,
198
+ "eval_samples_per_second": 257.256,
199
+ "eval_steps_per_second": 32.189,
200
+ "step": 250
201
+ },
202
+ {
203
+ "epoch": 2.080402010050251,
204
+ "grad_norm": 5.255651950836182,
205
+ "learning_rate": 1.5053763440860215e-05,
206
+ "loss": 0.1432,
207
+ "step": 260
208
+ },
209
+ {
210
+ "epoch": 2.1608040201005023,
211
+ "grad_norm": 4.3175578117370605,
212
+ "learning_rate": 1.3709677419354839e-05,
213
+ "loss": 0.1143,
214
+ "step": 270
215
+ },
216
+ {
217
+ "epoch": 2.241206030150754,
218
+ "grad_norm": 2.5253961086273193,
219
+ "learning_rate": 1.2365591397849464e-05,
220
+ "loss": 0.1325,
221
+ "step": 280
222
+ },
223
+ {
224
+ "epoch": 2.321608040201005,
225
+ "grad_norm": 5.174256801605225,
226
+ "learning_rate": 1.1021505376344087e-05,
227
+ "loss": 0.116,
228
+ "step": 290
229
+ },
230
+ {
231
+ "epoch": 2.4020100502512562,
232
+ "grad_norm": 3.690969228744507,
233
+ "learning_rate": 9.67741935483871e-06,
234
+ "loss": 0.0768,
235
+ "step": 300
236
+ },
237
+ {
238
+ "epoch": 2.4824120603015074,
239
+ "grad_norm": 4.675231456756592,
240
+ "learning_rate": 8.333333333333334e-06,
241
+ "loss": 0.1081,
242
+ "step": 310
243
+ },
244
+ {
245
+ "epoch": 2.5628140703517586,
246
+ "grad_norm": 5.262183666229248,
247
+ "learning_rate": 6.989247311827957e-06,
248
+ "loss": 0.1212,
249
+ "step": 320
250
+ },
251
+ {
252
+ "epoch": 2.64321608040201,
253
+ "grad_norm": 3.3453903198242188,
254
+ "learning_rate": 5.64516129032258e-06,
255
+ "loss": 0.1103,
256
+ "step": 330
257
+ },
258
+ {
259
+ "epoch": 2.7236180904522613,
260
+ "grad_norm": 3.3446080684661865,
261
+ "learning_rate": 4.3010752688172045e-06,
262
+ "loss": 0.1406,
263
+ "step": 340
264
+ },
265
+ {
266
+ "epoch": 2.8040201005025125,
267
+ "grad_norm": 3.0553841590881348,
268
+ "learning_rate": 2.9569892473118283e-06,
269
+ "loss": 0.1042,
270
+ "step": 350
271
+ },
272
+ {
273
+ "epoch": 2.884422110552764,
274
+ "grad_norm": 1.7012218236923218,
275
+ "learning_rate": 1.6129032258064516e-06,
276
+ "loss": 0.1145,
277
+ "step": 360
278
+ },
279
+ {
280
+ "epoch": 2.964824120603015,
281
+ "grad_norm": 3.853684425354004,
282
+ "learning_rate": 2.688172043010753e-07,
283
+ "loss": 0.0893,
284
+ "step": 370
285
+ }
286
+ ],
287
+ "logging_steps": 10,
288
+ "max_steps": 372,
289
+ "num_input_tokens_seen": 0,
290
+ "num_train_epochs": 3,
291
+ "save_steps": 100,
292
+ "stateful_callbacks": {
293
+ "TrainerControl": {
294
+ "args": {
295
+ "should_epoch_stop": false,
296
+ "should_evaluate": false,
297
+ "should_log": false,
298
+ "should_save": true,
299
+ "should_training_stop": true
300
+ },
301
+ "attributes": {}
302
+ }
303
+ },
304
+ "total_flos": 2539747126960128.0,
305
+ "train_batch_size": 8,
306
+ "trial_name": null,
307
+ "trial_params": null
308
+ }
checkpoint-372/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8f0e6064381a1811a4f562171b36052a99ad4099d891eec9fcb57aec61a8f2
3
+ size 5368