malmarjeh commited on
Commit
e4b5fa5
1 Parent(s): ac09fd7

add model files

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./drive/MyDrive/mbert2mbert/checkpoint-15000",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "bert-base-multilingual-cased",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "BertForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "decoder_start_token_id": null,
17
+ "directionality": "bidi",
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "gradient_checkpointing": false,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 0,
47
+ "model_type": "bert",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "pooler_fc_size": 768,
59
+ "pooler_num_attention_heads": 12,
60
+ "pooler_num_fc_layers": 3,
61
+ "pooler_size_per_head": 128,
62
+ "pooler_type": "first_token_transform",
63
+ "position_embedding_type": "absolute",
64
+ "prefix": null,
65
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "repetition_penalty": 1.0,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "sep_token_id": null,
71
+ "task_specific_params": null,
72
+ "temperature": 1.0,
73
+ "tie_encoder_decoder": false,
74
+ "tie_word_embeddings": true,
75
+ "tokenizer_class": null,
76
+ "top_k": 50,
77
+ "top_p": 1.0,
78
+ "torchscript": false,
79
+ "transformers_version": "4.5.1",
80
+ "type_vocab_size": 2,
81
+ "use_bfloat16": false,
82
+ "use_cache": true,
83
+ "vocab_size": 119547
84
+ },
85
+ "decoder_start_token_id": 101,
86
+ "encoder": {
87
+ "_name_or_path": "bert-base-multilingual-cased",
88
+ "add_cross_attention": false,
89
+ "architectures": [
90
+ "BertForMaskedLM"
91
+ ],
92
+ "attention_probs_dropout_prob": 0.1,
93
+ "bad_words_ids": null,
94
+ "bos_token_id": null,
95
+ "chunk_size_feed_forward": 0,
96
+ "decoder_start_token_id": null,
97
+ "directionality": "bidi",
98
+ "diversity_penalty": 0.0,
99
+ "do_sample": false,
100
+ "early_stopping": false,
101
+ "encoder_no_repeat_ngram_size": 0,
102
+ "eos_token_id": null,
103
+ "finetuning_task": null,
104
+ "forced_bos_token_id": null,
105
+ "forced_eos_token_id": null,
106
+ "gradient_checkpointing": false,
107
+ "hidden_act": "gelu",
108
+ "hidden_dropout_prob": 0.1,
109
+ "hidden_size": 768,
110
+ "id2label": {
111
+ "0": "LABEL_0",
112
+ "1": "LABEL_1"
113
+ },
114
+ "initializer_range": 0.02,
115
+ "intermediate_size": 3072,
116
+ "is_decoder": false,
117
+ "is_encoder_decoder": false,
118
+ "label2id": {
119
+ "LABEL_0": 0,
120
+ "LABEL_1": 1
121
+ },
122
+ "layer_norm_eps": 1e-12,
123
+ "length_penalty": 1.0,
124
+ "max_length": 20,
125
+ "max_position_embeddings": 512,
126
+ "min_length": 0,
127
+ "model_type": "bert",
128
+ "no_repeat_ngram_size": 0,
129
+ "num_attention_heads": 12,
130
+ "num_beam_groups": 1,
131
+ "num_beams": 1,
132
+ "num_hidden_layers": 12,
133
+ "num_return_sequences": 1,
134
+ "output_attentions": false,
135
+ "output_hidden_states": false,
136
+ "output_scores": false,
137
+ "pad_token_id": 0,
138
+ "pooler_fc_size": 768,
139
+ "pooler_num_attention_heads": 12,
140
+ "pooler_num_fc_layers": 3,
141
+ "pooler_size_per_head": 128,
142
+ "pooler_type": "first_token_transform",
143
+ "position_embedding_type": "absolute",
144
+ "prefix": null,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "sep_token_id": null,
151
+ "task_specific_params": null,
152
+ "temperature": 1.0,
153
+ "tie_encoder_decoder": false,
154
+ "tie_word_embeddings": true,
155
+ "tokenizer_class": null,
156
+ "top_k": 50,
157
+ "top_p": 1.0,
158
+ "torchscript": false,
159
+ "transformers_version": "4.5.1",
160
+ "type_vocab_size": 2,
161
+ "use_bfloat16": false,
162
+ "use_cache": true,
163
+ "vocab_size": 119547
164
+ },
165
+ "eos_token_id": 102,
166
+ "is_encoder_decoder": true,
167
+ "max_length": 42,
168
+ "min_length": 5,
169
+ "model_type": "encoder-decoder",
170
+ "pad_token_id": 0,
171
+ "tie_encoder_decoder": true,
172
+ "vocab_size": 119547
173
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6ff7ec04d79d8d46be651dbf957afccf1d7e7870b3cbd1f9f05c68763258edc
3
+ size 827914229
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a43880977f4f83b4040c24bb11b6e5795e817a17a1668080851028cedc7b6fa
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/46880f3b0081fda494a4e15b05787692aa4c1e21e0ff2428ba8b14d4eda0784d.b33e51591f94f17c238ee9b1fac75b96ff2678cbaed6e108feadb3449d18dc24", "name_or_path": "bert-base-multilingual-cased"}
trainer_state.json ADDED
@@ -0,0 +1,288 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.175986495041148,
5
+ "global_step": 17000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.42,
12
+ "learning_rate": 3.3333333333333335e-05,
13
+ "loss": 4.4431,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "epoch": 0.42,
18
+ "eval_loss": 3.1658337116241455,
19
+ "eval_rouge-1": 0.1104,
20
+ "eval_rouge-2": 0.0147,
21
+ "eval_rouge-l": 0.1071,
22
+ "eval_runtime": 938.5942,
23
+ "eval_samples_per_second": 4.447,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.84,
28
+ "learning_rate": 4.8873366381252815e-05,
29
+ "loss": 3.0017,
30
+ "step": 2000
31
+ },
32
+ {
33
+ "epoch": 0.84,
34
+ "eval_loss": 2.450249195098877,
35
+ "eval_rouge-1": 0.2256,
36
+ "eval_rouge-2": 0.0714,
37
+ "eval_rouge-l": 0.2134,
38
+ "eval_runtime": 828.0492,
39
+ "eval_samples_per_second": 5.041,
40
+ "step": 2000
41
+ },
42
+ {
43
+ "epoch": 1.27,
44
+ "learning_rate": 4.662009914375845e-05,
45
+ "loss": 2.258,
46
+ "step": 3000
47
+ },
48
+ {
49
+ "epoch": 1.27,
50
+ "eval_loss": 1.915558099746704,
51
+ "eval_rouge-1": 0.3442,
52
+ "eval_rouge-2": 0.1597,
53
+ "eval_rouge-l": 0.3284,
54
+ "eval_runtime": 854.823,
55
+ "eval_samples_per_second": 4.883,
56
+ "step": 3000
57
+ },
58
+ {
59
+ "epoch": 1.69,
60
+ "learning_rate": 4.4366831906264086e-05,
61
+ "loss": 1.8476,
62
+ "step": 4000
63
+ },
64
+ {
65
+ "epoch": 1.69,
66
+ "eval_loss": 1.7214736938476562,
67
+ "eval_rouge-1": 0.3784,
68
+ "eval_rouge-2": 0.1998,
69
+ "eval_rouge-l": 0.362,
70
+ "eval_runtime": 711.98,
71
+ "eval_samples_per_second": 5.863,
72
+ "step": 4000
73
+ },
74
+ {
75
+ "epoch": 2.11,
76
+ "learning_rate": 4.211356466876972e-05,
77
+ "loss": 1.6932,
78
+ "step": 5000
79
+ },
80
+ {
81
+ "epoch": 2.11,
82
+ "eval_loss": 1.6499994993209839,
83
+ "eval_rouge-1": 0.3992,
84
+ "eval_rouge-2": 0.2227,
85
+ "eval_rouge-l": 0.3822,
86
+ "eval_runtime": 721.767,
87
+ "eval_samples_per_second": 5.783,
88
+ "step": 5000
89
+ },
90
+ {
91
+ "epoch": 2.53,
92
+ "learning_rate": 3.986029743127535e-05,
93
+ "loss": 1.5271,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 2.53,
98
+ "eval_loss": 1.5838263034820557,
99
+ "eval_rouge-1": 0.3999,
100
+ "eval_rouge-2": 0.2255,
101
+ "eval_rouge-l": 0.3825,
102
+ "eval_runtime": 791.7162,
103
+ "eval_samples_per_second": 5.272,
104
+ "step": 6000
105
+ },
106
+ {
107
+ "epoch": 2.95,
108
+ "learning_rate": 3.760703019378098e-05,
109
+ "loss": 1.4984,
110
+ "step": 7000
111
+ },
112
+ {
113
+ "epoch": 2.95,
114
+ "eval_loss": 1.5331367254257202,
115
+ "eval_rouge-1": 0.4063,
116
+ "eval_rouge-2": 0.2319,
117
+ "eval_rouge-l": 0.39,
118
+ "eval_runtime": 787.263,
119
+ "eval_samples_per_second": 5.302,
120
+ "step": 7000
121
+ },
122
+ {
123
+ "epoch": 3.38,
124
+ "learning_rate": 3.535376295628662e-05,
125
+ "loss": 1.3435,
126
+ "step": 8000
127
+ },
128
+ {
129
+ "epoch": 3.38,
130
+ "eval_loss": 1.5344029664993286,
131
+ "eval_rouge-1": 0.419,
132
+ "eval_rouge-2": 0.2391,
133
+ "eval_rouge-l": 0.4009,
134
+ "eval_runtime": 801.0657,
135
+ "eval_samples_per_second": 5.211,
136
+ "step": 8000
137
+ },
138
+ {
139
+ "epoch": 3.8,
140
+ "learning_rate": 3.310049571879225e-05,
141
+ "loss": 1.275,
142
+ "step": 9000
143
+ },
144
+ {
145
+ "epoch": 3.8,
146
+ "eval_loss": 1.5167639255523682,
147
+ "eval_rouge-1": 0.4172,
148
+ "eval_rouge-2": 0.2399,
149
+ "eval_rouge-l": 0.398,
150
+ "eval_runtime": 714.2604,
151
+ "eval_samples_per_second": 5.844,
152
+ "step": 9000
153
+ },
154
+ {
155
+ "epoch": 4.22,
156
+ "learning_rate": 3.0847228481297885e-05,
157
+ "loss": 1.2267,
158
+ "step": 10000
159
+ },
160
+ {
161
+ "epoch": 4.22,
162
+ "eval_loss": 1.5133156776428223,
163
+ "eval_rouge-1": 0.4215,
164
+ "eval_rouge-2": 0.2435,
165
+ "eval_rouge-l": 0.402,
166
+ "eval_runtime": 712.9933,
167
+ "eval_samples_per_second": 5.854,
168
+ "step": 10000
169
+ },
170
+ {
171
+ "epoch": 4.64,
172
+ "learning_rate": 2.859396124380352e-05,
173
+ "loss": 1.1519,
174
+ "step": 11000
175
+ },
176
+ {
177
+ "epoch": 4.64,
178
+ "eval_loss": 1.4870655536651611,
179
+ "eval_rouge-1": 0.4202,
180
+ "eval_rouge-2": 0.244,
181
+ "eval_rouge-l": 0.4013,
182
+ "eval_runtime": 437.1167,
183
+ "eval_samples_per_second": 9.549,
184
+ "step": 11000
185
+ },
186
+ {
187
+ "epoch": 5.07,
188
+ "learning_rate": 2.6340694006309152e-05,
189
+ "loss": 1.1841,
190
+ "step": 12000
191
+ },
192
+ {
193
+ "epoch": 5.07,
194
+ "eval_loss": 1.5044740438461304,
195
+ "eval_rouge-1": 0.4269,
196
+ "eval_rouge-2": 0.2471,
197
+ "eval_rouge-l": 0.4076,
198
+ "eval_runtime": 446.0452,
199
+ "eval_samples_per_second": 9.358,
200
+ "step": 12000
201
+ },
202
+ {
203
+ "epoch": 5.49,
204
+ "learning_rate": 2.4087426768814784e-05,
205
+ "loss": 1.0586,
206
+ "step": 13000
207
+ },
208
+ {
209
+ "epoch": 5.49,
210
+ "eval_loss": 1.4930425882339478,
211
+ "eval_rouge-1": 0.4285,
212
+ "eval_rouge-2": 0.2518,
213
+ "eval_rouge-l": 0.4109,
214
+ "eval_runtime": 430.9672,
215
+ "eval_samples_per_second": 9.685,
216
+ "step": 13000
217
+ },
218
+ {
219
+ "epoch": 5.91,
220
+ "learning_rate": 2.1834159531320416e-05,
221
+ "loss": 1.0657,
222
+ "step": 14000
223
+ },
224
+ {
225
+ "epoch": 5.91,
226
+ "eval_loss": 1.488339900970459,
227
+ "eval_rouge-1": 0.4273,
228
+ "eval_rouge-2": 0.2514,
229
+ "eval_rouge-l": 0.4084,
230
+ "eval_runtime": 438.2586,
231
+ "eval_samples_per_second": 9.524,
232
+ "step": 14000
233
+ },
234
+ {
235
+ "epoch": 6.33,
236
+ "learning_rate": 1.958089229382605e-05,
237
+ "loss": 0.9725,
238
+ "step": 15000
239
+ },
240
+ {
241
+ "epoch": 6.33,
242
+ "eval_loss": 1.5135878324508667,
243
+ "eval_rouge-1": 0.4312,
244
+ "eval_rouge-2": 0.2537,
245
+ "eval_rouge-l": 0.4116,
246
+ "eval_runtime": 436.2911,
247
+ "eval_samples_per_second": 9.567,
248
+ "step": 15000
249
+ },
250
+ {
251
+ "epoch": 6.75,
252
+ "learning_rate": 1.732762505633168e-05,
253
+ "loss": 0.9176,
254
+ "step": 16000
255
+ },
256
+ {
257
+ "epoch": 6.75,
258
+ "eval_loss": 1.5166784524917603,
259
+ "eval_rouge-1": 0.433,
260
+ "eval_rouge-2": 0.2559,
261
+ "eval_rouge-l": 0.4146,
262
+ "eval_runtime": 820.6736,
263
+ "eval_samples_per_second": 5.086,
264
+ "step": 16000
265
+ },
266
+ {
267
+ "epoch": 7.18,
268
+ "learning_rate": 1.5074357818837314e-05,
269
+ "loss": 0.8982,
270
+ "step": 17000
271
+ },
272
+ {
273
+ "epoch": 7.18,
274
+ "eval_loss": 1.535448431968689,
275
+ "eval_rouge-1": 0.4293,
276
+ "eval_rouge-2": 0.2538,
277
+ "eval_rouge-l": 0.4101,
278
+ "eval_runtime": 828.443,
279
+ "eval_samples_per_second": 5.038,
280
+ "step": 17000
281
+ }
282
+ ],
283
+ "max_steps": 23690,
284
+ "num_train_epochs": 10,
285
+ "total_flos": 1.317233087652327e+17,
286
+ "trial_name": null,
287
+ "trial_params": null
288
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63d31c04276cc71b7fce380bad6f43829c17562ecc7ae01678dcf34351c5526a
3
+ size 2415
vocab.txt ADDED
The diff for this file is too large to render. See raw diff