Hugging Face's logo

mabrouk
/
amazon-review-summarizer-bart

Text2Text Generation
Transformers
PyTorch
bart
Inference Endpoints
Model card Files Community
3
mabrouk commited on
Commit
69943bd
•
1 Parent(s): 0250f16

new commit

Browse files
Files changed (13) hide show
  1. checkpoint-25000/config.json +70 -0
  2. checkpoint-25000/merges.txt +0 -0
  3. checkpoint-25000/optimizer.pt +3 -0
  4. checkpoint-25000/pytorch_model.bin +3 -0
  5. checkpoint-25000/rng_state.pth +3 -0
  6. checkpoint-25000/scaler.pt +3 -0
  7. checkpoint-25000/scheduler.pt +3 -0
  8. checkpoint-25000/special_tokens_map.json +15 -0
  9. checkpoint-25000/tokenizer.json +0 -0
  10. checkpoint-25000/tokenizer_config.json +16 -0
  11. checkpoint-25000/trainer_state.json +316 -0
  12. checkpoint-25000/training_args.bin +3 -0
  13. checkpoint-25000/vocab.json +0 -0
checkpoint-25000/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large-cnn",
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
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "force_bos_token_to_be_generated": true,
28
+ "forced_bos_token_id": 0,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "length_penalty": 2.0,
44
+ "max_length": 142,
45
+ "max_position_embeddings": 1024,
46
+ "min_length": 56,
47
+ "model_type": "bart",
48
+ "no_repeat_ngram_size": 3,
49
+ "normalize_before": false,
50
+ "num_beams": 4,
51
+ "num_hidden_layers": 12,
52
+ "output_past": true,
53
+ "pad_token_id": 1,
54
+ "prefix": " ",
55
+ "scale_embedding": false,
56
+ "task_specific_params": {
57
+ "summarization": {
58
+ "early_stopping": true,
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "no_repeat_ngram_size": 3,
63
+ "num_beams": 4
64
+ }
65
+ },
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.24.0",
68
+ "use_cache": true,
69
+ "vocab_size": 50264
70
+ }
checkpoint-25000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-25000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c572101639a2de78ca010beb01178040d1408240d8c9d9e615b7bc3ab8b01727
3
+ size 3250621339
checkpoint-25000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ba79fe0c5506fda83f041e8c456e7f62d858d962306139ab05e2e5dd19dc68
3
+ size 1625533697
checkpoint-25000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c73eda020ad908e93abbf5dfc9899fac861b60e9796c8cca76f762709a02579
3
+ size 14439
checkpoint-25000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79fac2d1984fc379a974d710161389cd01010650efcd5b2e486956c015179dad
3
+ size 559
checkpoint-25000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48773cd00ce44ac6a5517bcbced978bbb4bc6ba7c7d43789feaad5a4c43d71b8
3
+ size 623
checkpoint-25000/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-25000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-25000/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 1024,
9
+ "name_or_path": "facebook/bart-large-cnn",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "BartTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
checkpoint-25000/trainer_state.json ADDED
@@ -0,0 +1,316 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 25000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 1.9604e-05,
13
+ "loss": 2.46,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 1.9204e-05,
19
+ "loss": 2.2671,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 1.8804e-05,
25
+ "loss": 2.2099,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.08,
30
+ "learning_rate": 1.8404000000000002e-05,
31
+ "loss": 2.1318,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.1,
36
+ "learning_rate": 1.80048e-05,
37
+ "loss": 2.1846,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.12,
42
+ "learning_rate": 1.76048e-05,
43
+ "loss": 2.1693,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.14,
48
+ "learning_rate": 1.7204800000000002e-05,
49
+ "loss": 2.1344,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.16,
54
+ "learning_rate": 1.6804800000000002e-05,
55
+ "loss": 2.0914,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.18,
60
+ "learning_rate": 1.64048e-05,
61
+ "loss": 2.0775,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.2,
66
+ "learning_rate": 1.60056e-05,
67
+ "loss": 2.0589,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.22,
72
+ "learning_rate": 1.5605600000000002e-05,
73
+ "loss": 2.1024,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.24,
78
+ "learning_rate": 1.52056e-05,
79
+ "loss": 2.0772,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.26,
84
+ "learning_rate": 1.4806400000000001e-05,
85
+ "loss": 2.0638,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.28,
90
+ "learning_rate": 1.44064e-05,
91
+ "loss": 2.0966,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.3,
96
+ "learning_rate": 1.4006400000000002e-05,
97
+ "loss": 1.9985,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.32,
102
+ "learning_rate": 1.3606400000000002e-05,
103
+ "loss": 2.0813,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.34,
108
+ "learning_rate": 1.3206400000000001e-05,
109
+ "loss": 2.0429,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.36,
114
+ "learning_rate": 1.2806400000000002e-05,
115
+ "loss": 2.0296,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.38,
120
+ "learning_rate": 1.24064e-05,
121
+ "loss": 2.0589,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.4,
126
+ "learning_rate": 1.20064e-05,
127
+ "loss": 1.9988,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.42,
132
+ "learning_rate": 1.16064e-05,
133
+ "loss": 2.0147,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.44,
138
+ "learning_rate": 1.1206400000000002e-05,
139
+ "loss": 2.0093,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.46,
144
+ "learning_rate": 1.0806400000000002e-05,
145
+ "loss": 2.0379,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.48,
150
+ "learning_rate": 1.0407200000000001e-05,
151
+ "loss": 2.0037,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.5,
156
+ "learning_rate": 1.0007200000000001e-05,
157
+ "loss": 1.9776,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.52,
162
+ "learning_rate": 9.607200000000002e-06,
163
+ "loss": 1.9606,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.54,
168
+ "learning_rate": 9.2072e-06,
169
+ "loss": 2.028,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.56,
174
+ "learning_rate": 8.808000000000001e-06,
175
+ "loss": 1.9674,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.58,
180
+ "learning_rate": 8.408e-06,
181
+ "loss": 1.9895,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.6,
186
+ "learning_rate": 8.008e-06,
187
+ "loss": 1.9596,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.62,
192
+ "learning_rate": 7.608000000000001e-06,
193
+ "loss": 2.0047,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.64,
198
+ "learning_rate": 7.208e-06,
199
+ "loss": 1.9908,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.66,
204
+ "learning_rate": 6.808800000000001e-06,
205
+ "loss": 1.9246,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.68,
210
+ "learning_rate": 6.4088e-06,
211
+ "loss": 1.9711,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.7,
216
+ "learning_rate": 6.0088e-06,
217
+ "loss": 1.9285,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.72,
222
+ "learning_rate": 5.608800000000001e-06,
223
+ "loss": 1.9388,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.74,
228
+ "learning_rate": 5.2096e-06,
229
+ "loss": 1.9361,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.76,
234
+ "learning_rate": 4.8096000000000005e-06,
235
+ "loss": 1.9566,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.78,
240
+ "learning_rate": 4.4104e-06,
241
+ "loss": 1.9158,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.8,
246
+ "learning_rate": 4.010400000000001e-06,
247
+ "loss": 1.927,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.82,
252
+ "learning_rate": 3.6104000000000006e-06,
253
+ "loss": 1.9152,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.84,
258
+ "learning_rate": 3.2104000000000002e-06,
259
+ "loss": 1.906,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.86,
264
+ "learning_rate": 2.8104000000000002e-06,
265
+ "loss": 1.9252,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.88,
270
+ "learning_rate": 2.4104000000000002e-06,
271
+ "loss": 1.9316,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.9,
276
+ "learning_rate": 2.0112e-06,
277
+ "loss": 1.8907,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.92,
282
+ "learning_rate": 1.6112000000000003e-06,
283
+ "loss": 1.8786,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 0.94,
288
+ "learning_rate": 1.2112000000000002e-06,
289
+ "loss": 1.9196,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 0.96,
294
+ "learning_rate": 8.112000000000001e-07,
295
+ "loss": 1.9025,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 0.98,
300
+ "learning_rate": 4.112e-07,
301
+ "loss": 1.9201,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 1.0,
306
+ "learning_rate": 1.12e-08,
307
+ "loss": 1.8927,
308
+ "step": 25000
309
+ }
310
+ ],
311
+ "max_steps": 25000,
312
+ "num_train_epochs": 1,
313
+ "total_flos": 4.818482588575334e+16,
314
+ "trial_name": null,
315
+ "trial_params": null
316
+ }
checkpoint-25000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3876b5b0271b198b566ccebca92a8be4e9bf4273409e1be640b71fd89811f517
3
+ size 3503
checkpoint-25000/vocab.json ADDED
The diff for this file is too large to render. See raw diff