balaramas commited on
Commit
ec521fa
1 Parent(s): e45f909

Model save

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: facebook/mbart-large-50-many-to-many-mmt
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: mbart-sahitrans_new_data
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # mbart-sahitrans_new_data
14
+
15
+ This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 5e-05
35
+ - train_batch_size: 4
36
+ - eval_batch_size: 4
37
+ - seed: 42
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: linear
40
+ - num_epochs: 3.0
41
+
42
+ ### Training results
43
+
44
+
45
+
46
+ ### Framework versions
47
+
48
+ - Transformers 4.37.2
49
+ - Pytorch 2.1.2+cu121
50
+ - Datasets 2.16.1
51
+ - Tokenizers 0.15.1
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.0,
3
+ "predict_bleu": 46.7681,
4
+ "predict_gen_len": 12.5226,
5
+ "predict_loss": 1.1072814464569092,
6
+ "predict_runtime": 32.3808,
7
+ "predict_samples": 1263,
8
+ "predict_samples_per_second": 39.005,
9
+ "predict_steps_per_second": 9.759,
10
+ "train_loss": 0.024883948061263487,
11
+ "train_runtime": 1768.5377,
12
+ "train_samples": 53559,
13
+ "train_samples_per_second": 211.99,
14
+ "train_steps_per_second": 52.999
15
+ }
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_length": 200,
43
+ "max_position_embeddings": 1024,
44
+ "model_type": "mbart",
45
+ "normalize_before": true,
46
+ "normalize_embedding": true,
47
+ "num_beams": 5,
48
+ "num_hidden_layers": 12,
49
+ "output_past": true,
50
+ "pad_token_id": 1,
51
+ "scale_embedding": true,
52
+ "static_position_embeddings": false,
53
+ "tokenizer_class": "MBart50Tokenizer",
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.37.2",
56
+ "use_cache": true,
57
+ "vocab_size": 250054
58
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.37.2"
12
+ }
mbart_generated_predictions.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 sha256:267aa3c6ede55e3ce5387e8cf3a33b920d351547908c529bf859c698a4675387
3
+ size 2444578688
predict_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu": 46.7681,
3
+ "predict_gen_len": 12.5226,
4
+ "predict_loss": 1.1072814464569092,
5
+ "predict_runtime": 32.3808,
6
+ "predict_samples": 1263,
7
+ "predict_samples_per_second": 39.005,
8
+ "predict_steps_per_second": 9.759
9
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "unk_token": "<unk>"
69
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:201552f7c207f9a4bea038b8ae995e4908ba34accaf5c791bc520dbac640cc54
3
+ size 17109938
tokenizer_config.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": true,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "language_codes": "ML50",
519
+ "mask_token": "<mask>",
520
+ "model_max_length": 1000000000000000019884624838656,
521
+ "pad_token": "<pad>",
522
+ "sep_token": "</s>",
523
+ "sp_model_kwargs": {},
524
+ "src_lang": "sa_XX",
525
+ "tgt_lang": "hi_IN",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.0,
3
+ "train_loss": 0.024883948061263487,
4
+ "train_runtime": 1768.5377,
5
+ "train_samples": 53559,
6
+ "train_samples_per_second": 211.99,
7
+ "train_steps_per_second": 52.999
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 93730,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "learning_rate": 4.813293502613891e-05,
14
+ "loss": 3.4729,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.07,
19
+ "learning_rate": 4.626587005227782e-05,
20
+ "loss": 3.0263,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.11,
25
+ "learning_rate": 4.439880507841673e-05,
26
+ "loss": 2.8813,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.15,
31
+ "learning_rate": 4.253174010455564e-05,
32
+ "loss": 2.7034,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.19,
37
+ "learning_rate": 4.066467513069455e-05,
38
+ "loss": 2.7308,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.22,
43
+ "learning_rate": 3.879761015683346e-05,
44
+ "loss": 2.6246,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.26,
49
+ "learning_rate": 3.693054518297237e-05,
50
+ "loss": 2.5404,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.3,
55
+ "learning_rate": 3.506348020911128e-05,
56
+ "loss": 2.543,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.34,
61
+ "learning_rate": 3.319641523525019e-05,
62
+ "loss": 2.4337,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.37,
67
+ "learning_rate": 3.13293502613891e-05,
68
+ "loss": 2.5003,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.41,
73
+ "learning_rate": 2.9462285287528007e-05,
74
+ "loss": 2.4064,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.45,
79
+ "learning_rate": 2.759522031366692e-05,
80
+ "loss": 2.3045,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.49,
85
+ "learning_rate": 2.5728155339805826e-05,
86
+ "loss": 2.3047,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.52,
91
+ "learning_rate": 2.3861090365944735e-05,
92
+ "loss": 2.2855,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.56,
97
+ "learning_rate": 2.1994025392083645e-05,
98
+ "loss": 2.3088,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.6,
103
+ "learning_rate": 2.0126960418222554e-05,
104
+ "loss": 2.2434,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.63,
109
+ "learning_rate": 1.8259895444361464e-05,
110
+ "loss": 2.215,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.67,
115
+ "learning_rate": 1.6392830470500377e-05,
116
+ "loss": 2.2731,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.71,
121
+ "learning_rate": 1.4525765496639285e-05,
122
+ "loss": 2.1623,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.75,
127
+ "learning_rate": 1.2658700522778194e-05,
128
+ "loss": 2.1395,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.78,
133
+ "learning_rate": 1.0791635548917104e-05,
134
+ "loss": 2.2036,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.82,
139
+ "learning_rate": 8.924570575056013e-06,
140
+ "loss": 2.1406,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 0.86,
145
+ "learning_rate": 7.057505601194922e-06,
146
+ "loss": 2.0425,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 0.9,
151
+ "learning_rate": 5.190440627333831e-06,
152
+ "loss": 2.0832,
153
+ "step": 12000
154
+ },
155
+ {
156
+ "epoch": 0.93,
157
+ "learning_rate": 3.3233756534727413e-06,
158
+ "loss": 2.0409,
159
+ "step": 12500
160
+ },
161
+ {
162
+ "epoch": 0.97,
163
+ "learning_rate": 1.4563106796116506e-06,
164
+ "loss": 2.0602,
165
+ "step": 13000
166
+ },
167
+ {
168
+ "epoch": 1.01,
169
+ "learning_rate": 3.991784914115011e-05,
170
+ "loss": 2.1169,
171
+ "step": 13500
172
+ },
173
+ {
174
+ "epoch": 1.05,
175
+ "learning_rate": 3.95444361463779e-05,
176
+ "loss": 1.9384,
177
+ "step": 14000
178
+ },
179
+ {
180
+ "epoch": 1.08,
181
+ "learning_rate": 3.917102315160568e-05,
182
+ "loss": 1.9064,
183
+ "step": 14500
184
+ },
185
+ {
186
+ "epoch": 1.12,
187
+ "learning_rate": 3.879761015683346e-05,
188
+ "loss": 1.9263,
189
+ "step": 15000
190
+ },
191
+ {
192
+ "epoch": 1.16,
193
+ "learning_rate": 3.8424197162061244e-05,
194
+ "loss": 1.984,
195
+ "step": 15500
196
+ },
197
+ {
198
+ "epoch": 1.19,
199
+ "learning_rate": 3.805078416728902e-05,
200
+ "loss": 1.9026,
201
+ "step": 16000
202
+ },
203
+ {
204
+ "epoch": 1.23,
205
+ "learning_rate": 3.7677371172516806e-05,
206
+ "loss": 1.9688,
207
+ "step": 16500
208
+ },
209
+ {
210
+ "epoch": 1.27,
211
+ "learning_rate": 3.7303958177744584e-05,
212
+ "loss": 1.9084,
213
+ "step": 17000
214
+ },
215
+ {
216
+ "epoch": 1.31,
217
+ "learning_rate": 3.693054518297237e-05,
218
+ "loss": 1.9521,
219
+ "step": 17500
220
+ },
221
+ {
222
+ "epoch": 1.34,
223
+ "learning_rate": 3.655713218820015e-05,
224
+ "loss": 1.9084,
225
+ "step": 18000
226
+ },
227
+ {
228
+ "epoch": 1.38,
229
+ "learning_rate": 3.618371919342793e-05,
230
+ "loss": 1.957,
231
+ "step": 18500
232
+ },
233
+ {
234
+ "epoch": 1.42,
235
+ "learning_rate": 3.5810306198655716e-05,
236
+ "loss": 1.9216,
237
+ "step": 19000
238
+ },
239
+ {
240
+ "epoch": 1.46,
241
+ "learning_rate": 3.54368932038835e-05,
242
+ "loss": 1.9009,
243
+ "step": 19500
244
+ },
245
+ {
246
+ "epoch": 1.49,
247
+ "learning_rate": 3.506348020911128e-05,
248
+ "loss": 1.9264,
249
+ "step": 20000
250
+ },
251
+ {
252
+ "epoch": 1.53,
253
+ "learning_rate": 3.469006721433906e-05,
254
+ "loss": 1.9279,
255
+ "step": 20500
256
+ },
257
+ {
258
+ "epoch": 1.57,
259
+ "learning_rate": 3.431665421956684e-05,
260
+ "loss": 1.8553,
261
+ "step": 21000
262
+ },
263
+ {
264
+ "epoch": 1.61,
265
+ "learning_rate": 3.3943241224794625e-05,
266
+ "loss": 1.9544,
267
+ "step": 21500
268
+ },
269
+ {
270
+ "epoch": 1.64,
271
+ "learning_rate": 3.35698282300224e-05,
272
+ "loss": 1.8713,
273
+ "step": 22000
274
+ },
275
+ {
276
+ "epoch": 1.68,
277
+ "learning_rate": 3.319641523525019e-05,
278
+ "loss": 1.877,
279
+ "step": 22500
280
+ },
281
+ {
282
+ "epoch": 1.72,
283
+ "learning_rate": 3.2823002240477966e-05,
284
+ "loss": 1.8483,
285
+ "step": 23000
286
+ },
287
+ {
288
+ "epoch": 1.76,
289
+ "learning_rate": 3.244958924570575e-05,
290
+ "loss": 1.8154,
291
+ "step": 23500
292
+ },
293
+ {
294
+ "epoch": 1.79,
295
+ "learning_rate": 3.2076176250933535e-05,
296
+ "loss": 1.897,
297
+ "step": 24000
298
+ },
299
+ {
300
+ "epoch": 1.83,
301
+ "learning_rate": 3.170276325616132e-05,
302
+ "loss": 1.8807,
303
+ "step": 24500
304
+ },
305
+ {
306
+ "epoch": 1.87,
307
+ "learning_rate": 3.13293502613891e-05,
308
+ "loss": 1.8696,
309
+ "step": 25000
310
+ },
311
+ {
312
+ "epoch": 1.9,
313
+ "learning_rate": 3.095593726661688e-05,
314
+ "loss": 1.8949,
315
+ "step": 25500
316
+ },
317
+ {
318
+ "epoch": 1.94,
319
+ "learning_rate": 3.058252427184466e-05,
320
+ "loss": 1.8808,
321
+ "step": 26000
322
+ },
323
+ {
324
+ "epoch": 1.98,
325
+ "learning_rate": 3.0209111277072444e-05,
326
+ "loss": 1.8257,
327
+ "step": 26500
328
+ },
329
+ {
330
+ "epoch": 2.02,
331
+ "learning_rate": 2.9835698282300222e-05,
332
+ "loss": 1.6733,
333
+ "step": 27000
334
+ },
335
+ {
336
+ "epoch": 2.05,
337
+ "learning_rate": 2.9462285287528007e-05,
338
+ "loss": 1.3824,
339
+ "step": 27500
340
+ },
341
+ {
342
+ "epoch": 2.09,
343
+ "learning_rate": 2.9088872292755788e-05,
344
+ "loss": 1.4268,
345
+ "step": 28000
346
+ },
347
+ {
348
+ "epoch": 2.13,
349
+ "learning_rate": 2.8715459297983573e-05,
350
+ "loss": 1.3661,
351
+ "step": 28500
352
+ },
353
+ {
354
+ "epoch": 2.17,
355
+ "learning_rate": 2.834204630321135e-05,
356
+ "loss": 1.3921,
357
+ "step": 29000
358
+ },
359
+ {
360
+ "epoch": 2.2,
361
+ "learning_rate": 2.7968633308439135e-05,
362
+ "loss": 1.381,
363
+ "step": 29500
364
+ },
365
+ {
366
+ "epoch": 2.24,
367
+ "learning_rate": 2.759522031366692e-05,
368
+ "loss": 1.4431,
369
+ "step": 30000
370
+ },
371
+ {
372
+ "epoch": 2.28,
373
+ "learning_rate": 2.7221807318894698e-05,
374
+ "loss": 1.4092,
375
+ "step": 30500
376
+ },
377
+ {
378
+ "epoch": 2.32,
379
+ "learning_rate": 2.6848394324122482e-05,
380
+ "loss": 1.3834,
381
+ "step": 31000
382
+ },
383
+ {
384
+ "epoch": 2.35,
385
+ "learning_rate": 2.6474981329350264e-05,
386
+ "loss": 1.3976,
387
+ "step": 31500
388
+ },
389
+ {
390
+ "epoch": 2.39,
391
+ "learning_rate": 2.6101568334578048e-05,
392
+ "loss": 1.4163,
393
+ "step": 32000
394
+ },
395
+ {
396
+ "epoch": 2.43,
397
+ "learning_rate": 2.5728155339805826e-05,
398
+ "loss": 1.463,
399
+ "step": 32500
400
+ },
401
+ {
402
+ "epoch": 2.46,
403
+ "learning_rate": 2.535474234503361e-05,
404
+ "loss": 1.3829,
405
+ "step": 33000
406
+ },
407
+ {
408
+ "epoch": 2.5,
409
+ "learning_rate": 2.498132935026139e-05,
410
+ "loss": 1.4267,
411
+ "step": 33500
412
+ },
413
+ {
414
+ "epoch": 2.54,
415
+ "learning_rate": 2.4607916355489173e-05,
416
+ "loss": 1.4251,
417
+ "step": 34000
418
+ },
419
+ {
420
+ "epoch": 2.58,
421
+ "learning_rate": 2.4234503360716954e-05,
422
+ "loss": 1.3971,
423
+ "step": 34500
424
+ },
425
+ {
426
+ "epoch": 2.61,
427
+ "learning_rate": 2.3861090365944735e-05,
428
+ "loss": 1.4307,
429
+ "step": 35000
430
+ },
431
+ {
432
+ "epoch": 2.65,
433
+ "learning_rate": 2.3487677371172517e-05,
434
+ "loss": 1.3797,
435
+ "step": 35500
436
+ },
437
+ {
438
+ "epoch": 2.69,
439
+ "learning_rate": 2.3114264376400298e-05,
440
+ "loss": 1.4136,
441
+ "step": 36000
442
+ },
443
+ {
444
+ "epoch": 2.73,
445
+ "learning_rate": 2.2740851381628083e-05,
446
+ "loss": 1.3923,
447
+ "step": 36500
448
+ },
449
+ {
450
+ "epoch": 2.76,
451
+ "learning_rate": 2.2367438386855864e-05,
452
+ "loss": 1.4402,
453
+ "step": 37000
454
+ },
455
+ {
456
+ "epoch": 2.8,
457
+ "learning_rate": 2.1994025392083645e-05,
458
+ "loss": 1.4485,
459
+ "step": 37500
460
+ },
461
+ {
462
+ "epoch": 2.84,
463
+ "learning_rate": 2.1620612397311426e-05,
464
+ "loss": 1.3766,
465
+ "step": 38000
466
+ },
467
+ {
468
+ "epoch": 2.88,
469
+ "learning_rate": 2.1247199402539207e-05,
470
+ "loss": 1.3877,
471
+ "step": 38500
472
+ },
473
+ {
474
+ "epoch": 2.91,
475
+ "learning_rate": 2.0873786407766992e-05,
476
+ "loss": 1.4218,
477
+ "step": 39000
478
+ },
479
+ {
480
+ "epoch": 2.95,
481
+ "learning_rate": 2.0500373412994773e-05,
482
+ "loss": 1.4167,
483
+ "step": 39500
484
+ },
485
+ {
486
+ "epoch": 2.99,
487
+ "learning_rate": 2.0126960418222554e-05,
488
+ "loss": 1.3621,
489
+ "step": 40000
490
+ },
491
+ {
492
+ "epoch": 3.02,
493
+ "learning_rate": 1.9753547423450336e-05,
494
+ "loss": 1.0586,
495
+ "step": 40500
496
+ },
497
+ {
498
+ "epoch": 3.06,
499
+ "learning_rate": 1.9380134428678117e-05,
500
+ "loss": 0.9882,
501
+ "step": 41000
502
+ },
503
+ {
504
+ "epoch": 3.1,
505
+ "learning_rate": 1.9006721433905898e-05,
506
+ "loss": 0.9795,
507
+ "step": 41500
508
+ },
509
+ {
510
+ "epoch": 3.14,
511
+ "learning_rate": 1.8633308439133683e-05,
512
+ "loss": 0.9992,
513
+ "step": 42000
514
+ },
515
+ {
516
+ "epoch": 3.17,
517
+ "learning_rate": 1.8259895444361464e-05,
518
+ "loss": 0.9474,
519
+ "step": 42500
520
+ },
521
+ {
522
+ "epoch": 3.21,
523
+ "learning_rate": 1.7886482449589245e-05,
524
+ "loss": 0.9975,
525
+ "step": 43000
526
+ },
527
+ {
528
+ "epoch": 3.25,
529
+ "learning_rate": 1.7513069454817026e-05,
530
+ "loss": 0.9606,
531
+ "step": 43500
532
+ },
533
+ {
534
+ "epoch": 3.29,
535
+ "learning_rate": 1.713965646004481e-05,
536
+ "loss": 0.9781,
537
+ "step": 44000
538
+ },
539
+ {
540
+ "epoch": 3.32,
541
+ "learning_rate": 1.6766243465272592e-05,
542
+ "loss": 1.0437,
543
+ "step": 44500
544
+ },
545
+ {
546
+ "epoch": 3.36,
547
+ "learning_rate": 1.6392830470500377e-05,
548
+ "loss": 0.963,
549
+ "step": 45000
550
+ },
551
+ {
552
+ "epoch": 3.4,
553
+ "learning_rate": 1.6019417475728158e-05,
554
+ "loss": 1.0407,
555
+ "step": 45500
556
+ },
557
+ {
558
+ "epoch": 3.44,
559
+ "learning_rate": 1.564600448095594e-05,
560
+ "loss": 1.0054,
561
+ "step": 46000
562
+ },
563
+ {
564
+ "epoch": 3.47,
565
+ "learning_rate": 1.527259148618372e-05,
566
+ "loss": 1.0396,
567
+ "step": 46500
568
+ },
569
+ {
570
+ "epoch": 3.51,
571
+ "learning_rate": 1.4899178491411503e-05,
572
+ "loss": 1.0051,
573
+ "step": 47000
574
+ },
575
+ {
576
+ "epoch": 3.55,
577
+ "learning_rate": 1.4525765496639285e-05,
578
+ "loss": 0.9828,
579
+ "step": 47500
580
+ },
581
+ {
582
+ "epoch": 3.58,
583
+ "learning_rate": 1.4152352501867066e-05,
584
+ "loss": 0.9976,
585
+ "step": 48000
586
+ },
587
+ {
588
+ "epoch": 3.62,
589
+ "learning_rate": 1.3778939507094849e-05,
590
+ "loss": 1.0251,
591
+ "step": 48500
592
+ },
593
+ {
594
+ "epoch": 3.66,
595
+ "learning_rate": 1.340552651232263e-05,
596
+ "loss": 1.0432,
597
+ "step": 49000
598
+ },
599
+ {
600
+ "epoch": 3.7,
601
+ "learning_rate": 1.3032113517550413e-05,
602
+ "loss": 0.9727,
603
+ "step": 49500
604
+ },
605
+ {
606
+ "epoch": 3.73,
607
+ "learning_rate": 1.2658700522778194e-05,
608
+ "loss": 0.9822,
609
+ "step": 50000
610
+ },
611
+ {
612
+ "epoch": 3.77,
613
+ "learning_rate": 1.2285287528005974e-05,
614
+ "loss": 1.0392,
615
+ "step": 50500
616
+ },
617
+ {
618
+ "epoch": 3.81,
619
+ "learning_rate": 1.1911874533233758e-05,
620
+ "loss": 0.9943,
621
+ "step": 51000
622
+ },
623
+ {
624
+ "epoch": 3.85,
625
+ "learning_rate": 1.153846153846154e-05,
626
+ "loss": 1.0256,
627
+ "step": 51500
628
+ },
629
+ {
630
+ "epoch": 3.88,
631
+ "learning_rate": 1.116504854368932e-05,
632
+ "loss": 1.0166,
633
+ "step": 52000
634
+ },
635
+ {
636
+ "epoch": 3.92,
637
+ "learning_rate": 1.0791635548917104e-05,
638
+ "loss": 0.9493,
639
+ "step": 52500
640
+ },
641
+ {
642
+ "epoch": 3.96,
643
+ "learning_rate": 1.0418222554144885e-05,
644
+ "loss": 1.0561,
645
+ "step": 53000
646
+ },
647
+ {
648
+ "epoch": 4.0,
649
+ "learning_rate": 1.0044809559372668e-05,
650
+ "loss": 0.976,
651
+ "step": 53500
652
+ },
653
+ {
654
+ "epoch": 4.03,
655
+ "learning_rate": 9.671396564600449e-06,
656
+ "loss": 0.7222,
657
+ "step": 54000
658
+ },
659
+ {
660
+ "epoch": 4.07,
661
+ "learning_rate": 9.29798356982823e-06,
662
+ "loss": 0.6606,
663
+ "step": 54500
664
+ },
665
+ {
666
+ "epoch": 4.11,
667
+ "learning_rate": 8.924570575056013e-06,
668
+ "loss": 0.6666,
669
+ "step": 55000
670
+ },
671
+ {
672
+ "epoch": 4.14,
673
+ "learning_rate": 8.551157580283794e-06,
674
+ "loss": 0.6524,
675
+ "step": 55500
676
+ },
677
+ {
678
+ "epoch": 4.18,
679
+ "learning_rate": 8.177744585511576e-06,
680
+ "loss": 0.6646,
681
+ "step": 56000
682
+ },
683
+ {
684
+ "epoch": 4.22,
685
+ "learning_rate": 7.804331590739359e-06,
686
+ "loss": 0.7429,
687
+ "step": 56500
688
+ },
689
+ {
690
+ "epoch": 4.26,
691
+ "learning_rate": 7.43091859596714e-06,
692
+ "loss": 0.711,
693
+ "step": 57000
694
+ },
695
+ {
696
+ "epoch": 4.29,
697
+ "learning_rate": 7.057505601194922e-06,
698
+ "loss": 0.6983,
699
+ "step": 57500
700
+ },
701
+ {
702
+ "epoch": 4.33,
703
+ "learning_rate": 6.684092606422704e-06,
704
+ "loss": 0.6639,
705
+ "step": 58000
706
+ },
707
+ {
708
+ "epoch": 4.37,
709
+ "learning_rate": 6.310679611650486e-06,
710
+ "loss": 0.7254,
711
+ "step": 58500
712
+ },
713
+ {
714
+ "epoch": 4.41,
715
+ "learning_rate": 5.937266616878267e-06,
716
+ "loss": 0.701,
717
+ "step": 59000
718
+ },
719
+ {
720
+ "epoch": 4.44,
721
+ "learning_rate": 5.563853622106049e-06,
722
+ "loss": 0.7424,
723
+ "step": 59500
724
+ },
725
+ {
726
+ "epoch": 4.48,
727
+ "learning_rate": 5.190440627333831e-06,
728
+ "loss": 0.6679,
729
+ "step": 60000
730
+ },
731
+ {
732
+ "epoch": 4.52,
733
+ "learning_rate": 4.817027632561613e-06,
734
+ "loss": 0.6413,
735
+ "step": 60500
736
+ },
737
+ {
738
+ "epoch": 4.56,
739
+ "learning_rate": 4.443614637789395e-06,
740
+ "loss": 0.7014,
741
+ "step": 61000
742
+ },
743
+ {
744
+ "epoch": 4.59,
745
+ "learning_rate": 4.070201643017177e-06,
746
+ "loss": 0.6786,
747
+ "step": 61500
748
+ },
749
+ {
750
+ "epoch": 4.63,
751
+ "learning_rate": 3.6967886482449596e-06,
752
+ "loss": 0.6792,
753
+ "step": 62000
754
+ },
755
+ {
756
+ "epoch": 4.67,
757
+ "learning_rate": 3.3233756534727413e-06,
758
+ "loss": 0.7148,
759
+ "step": 62500
760
+ },
761
+ {
762
+ "epoch": 4.71,
763
+ "learning_rate": 2.949962658700523e-06,
764
+ "loss": 0.6512,
765
+ "step": 63000
766
+ },
767
+ {
768
+ "epoch": 4.74,
769
+ "learning_rate": 2.5765496639283046e-06,
770
+ "loss": 0.681,
771
+ "step": 63500
772
+ },
773
+ {
774
+ "epoch": 4.78,
775
+ "learning_rate": 2.203136669156087e-06,
776
+ "loss": 0.7019,
777
+ "step": 64000
778
+ },
779
+ {
780
+ "epoch": 4.82,
781
+ "learning_rate": 1.8297236743838687e-06,
782
+ "loss": 0.5755,
783
+ "step": 64500
784
+ },
785
+ {
786
+ "epoch": 4.85,
787
+ "learning_rate": 1.4563106796116506e-06,
788
+ "loss": 0.5506,
789
+ "step": 65000
790
+ },
791
+ {
792
+ "epoch": 4.89,
793
+ "learning_rate": 1.0828976848394324e-06,
794
+ "loss": 0.5695,
795
+ "step": 65500
796
+ },
797
+ {
798
+ "epoch": 4.93,
799
+ "learning_rate": 7.094846900672144e-07,
800
+ "loss": 0.5534,
801
+ "step": 66000
802
+ },
803
+ {
804
+ "epoch": 4.97,
805
+ "learning_rate": 3.360716952949963e-07,
806
+ "loss": 0.5473,
807
+ "step": 66500
808
+ },
809
+ {
810
+ "epoch": 5.0,
811
+ "learning_rate": 1.425904192894484e-05,
812
+ "loss": 0.5644,
813
+ "step": 67000
814
+ },
815
+ {
816
+ "epoch": 5.04,
817
+ "learning_rate": 1.39923183612504e-05,
818
+ "loss": 0.574,
819
+ "step": 67500
820
+ },
821
+ {
822
+ "epoch": 5.08,
823
+ "learning_rate": 1.3725594793555959e-05,
824
+ "loss": 0.5951,
825
+ "step": 68000
826
+ },
827
+ {
828
+ "epoch": 5.12,
829
+ "learning_rate": 1.345887122586152e-05,
830
+ "loss": 0.6167,
831
+ "step": 68500
832
+ },
833
+ {
834
+ "epoch": 5.15,
835
+ "learning_rate": 1.3192147658167076e-05,
836
+ "loss": 0.6116,
837
+ "step": 69000
838
+ },
839
+ {
840
+ "epoch": 5.19,
841
+ "learning_rate": 1.2925424090472635e-05,
842
+ "loss": 0.6739,
843
+ "step": 69500
844
+ },
845
+ {
846
+ "epoch": 5.23,
847
+ "learning_rate": 1.2658700522778194e-05,
848
+ "loss": 0.6638,
849
+ "step": 70000
850
+ },
851
+ {
852
+ "epoch": 5.27,
853
+ "learning_rate": 1.2391976955083752e-05,
854
+ "loss": 0.6339,
855
+ "step": 70500
856
+ },
857
+ {
858
+ "epoch": 5.3,
859
+ "learning_rate": 1.212525338738931e-05,
860
+ "loss": 0.6601,
861
+ "step": 71000
862
+ },
863
+ {
864
+ "epoch": 5.34,
865
+ "learning_rate": 1.1858529819694868e-05,
866
+ "loss": 0.6563,
867
+ "step": 71500
868
+ },
869
+ {
870
+ "epoch": 5.38,
871
+ "learning_rate": 1.1591806252000428e-05,
872
+ "loss": 0.6491,
873
+ "step": 72000
874
+ },
875
+ {
876
+ "epoch": 5.41,
877
+ "learning_rate": 1.1325082684305987e-05,
878
+ "loss": 0.6026,
879
+ "step": 72500
880
+ },
881
+ {
882
+ "epoch": 5.45,
883
+ "learning_rate": 1.1058359116611544e-05,
884
+ "loss": 0.6851,
885
+ "step": 73000
886
+ },
887
+ {
888
+ "epoch": 5.49,
889
+ "learning_rate": 1.0791635548917104e-05,
890
+ "loss": 0.6337,
891
+ "step": 73500
892
+ },
893
+ {
894
+ "epoch": 5.53,
895
+ "learning_rate": 1.0524911981222661e-05,
896
+ "loss": 0.6659,
897
+ "step": 74000
898
+ },
899
+ {
900
+ "epoch": 5.56,
901
+ "learning_rate": 1.025818841352822e-05,
902
+ "loss": 0.6691,
903
+ "step": 74500
904
+ },
905
+ {
906
+ "epoch": 5.6,
907
+ "learning_rate": 9.991464845833778e-06,
908
+ "loss": 0.6611,
909
+ "step": 75000
910
+ },
911
+ {
912
+ "epoch": 5.64,
913
+ "learning_rate": 9.724741278139336e-06,
914
+ "loss": 0.6542,
915
+ "step": 75500
916
+ },
917
+ {
918
+ "epoch": 5.68,
919
+ "learning_rate": 9.458017710444895e-06,
920
+ "loss": 0.6849,
921
+ "step": 76000
922
+ },
923
+ {
924
+ "epoch": 5.71,
925
+ "learning_rate": 9.191294142750454e-06,
926
+ "loss": 0.6552,
927
+ "step": 76500
928
+ },
929
+ {
930
+ "epoch": 5.75,
931
+ "learning_rate": 8.924570575056013e-06,
932
+ "loss": 0.6636,
933
+ "step": 77000
934
+ },
935
+ {
936
+ "epoch": 5.79,
937
+ "learning_rate": 8.65784700736157e-06,
938
+ "loss": 0.6323,
939
+ "step": 77500
940
+ },
941
+ {
942
+ "epoch": 5.83,
943
+ "learning_rate": 8.39112343966713e-06,
944
+ "loss": 0.6581,
945
+ "step": 78000
946
+ },
947
+ {
948
+ "epoch": 5.86,
949
+ "learning_rate": 8.124399871972687e-06,
950
+ "loss": 0.6613,
951
+ "step": 78500
952
+ },
953
+ {
954
+ "epoch": 5.9,
955
+ "learning_rate": 7.857676304278247e-06,
956
+ "loss": 0.6816,
957
+ "step": 79000
958
+ },
959
+ {
960
+ "epoch": 5.94,
961
+ "learning_rate": 7.590952736583805e-06,
962
+ "loss": 0.6908,
963
+ "step": 79500
964
+ },
965
+ {
966
+ "epoch": 5.97,
967
+ "learning_rate": 7.324229168889363e-06,
968
+ "loss": 0.6854,
969
+ "step": 80000
970
+ },
971
+ {
972
+ "epoch": 6.01,
973
+ "learning_rate": 7.057505601194922e-06,
974
+ "loss": 0.5705,
975
+ "step": 80500
976
+ },
977
+ {
978
+ "epoch": 6.05,
979
+ "learning_rate": 6.79078203350048e-06,
980
+ "loss": 0.4532,
981
+ "step": 81000
982
+ },
983
+ {
984
+ "epoch": 6.09,
985
+ "learning_rate": 6.5240584658060394e-06,
986
+ "loss": 0.4785,
987
+ "step": 81500
988
+ },
989
+ {
990
+ "epoch": 6.12,
991
+ "learning_rate": 6.257334898111597e-06,
992
+ "loss": 0.4568,
993
+ "step": 82000
994
+ },
995
+ {
996
+ "epoch": 6.16,
997
+ "learning_rate": 5.990611330417156e-06,
998
+ "loss": 0.4415,
999
+ "step": 82500
1000
+ },
1001
+ {
1002
+ "epoch": 6.2,
1003
+ "learning_rate": 5.723887762722714e-06,
1004
+ "loss": 0.4598,
1005
+ "step": 83000
1006
+ },
1007
+ {
1008
+ "epoch": 6.24,
1009
+ "learning_rate": 5.457164195028273e-06,
1010
+ "loss": 0.4661,
1011
+ "step": 83500
1012
+ },
1013
+ {
1014
+ "epoch": 6.27,
1015
+ "learning_rate": 5.190440627333831e-06,
1016
+ "loss": 0.437,
1017
+ "step": 84000
1018
+ },
1019
+ {
1020
+ "epoch": 6.31,
1021
+ "learning_rate": 4.92371705963939e-06,
1022
+ "loss": 0.4782,
1023
+ "step": 84500
1024
+ },
1025
+ {
1026
+ "epoch": 6.35,
1027
+ "learning_rate": 4.656993491944948e-06,
1028
+ "loss": 0.465,
1029
+ "step": 85000
1030
+ },
1031
+ {
1032
+ "epoch": 6.39,
1033
+ "learning_rate": 4.390269924250507e-06,
1034
+ "loss": 0.4491,
1035
+ "step": 85500
1036
+ },
1037
+ {
1038
+ "epoch": 6.42,
1039
+ "learning_rate": 4.123546356556066e-06,
1040
+ "loss": 0.4727,
1041
+ "step": 86000
1042
+ },
1043
+ {
1044
+ "epoch": 6.46,
1045
+ "learning_rate": 3.856822788861624e-06,
1046
+ "loss": 0.4576,
1047
+ "step": 86500
1048
+ },
1049
+ {
1050
+ "epoch": 6.5,
1051
+ "learning_rate": 3.590099221167183e-06,
1052
+ "loss": 0.4565,
1053
+ "step": 87000
1054
+ },
1055
+ {
1056
+ "epoch": 6.53,
1057
+ "learning_rate": 3.3233756534727413e-06,
1058
+ "loss": 0.4646,
1059
+ "step": 87500
1060
+ },
1061
+ {
1062
+ "epoch": 6.57,
1063
+ "learning_rate": 3.0566520857782996e-06,
1064
+ "loss": 0.4749,
1065
+ "step": 88000
1066
+ },
1067
+ {
1068
+ "epoch": 6.61,
1069
+ "learning_rate": 2.789928518083858e-06,
1070
+ "loss": 0.3821,
1071
+ "step": 88500
1072
+ },
1073
+ {
1074
+ "epoch": 6.65,
1075
+ "learning_rate": 2.523204950389417e-06,
1076
+ "loss": 0.4083,
1077
+ "step": 89000
1078
+ },
1079
+ {
1080
+ "epoch": 6.68,
1081
+ "learning_rate": 2.2564813826949748e-06,
1082
+ "loss": 0.4041,
1083
+ "step": 89500
1084
+ },
1085
+ {
1086
+ "epoch": 6.72,
1087
+ "learning_rate": 1.9897578150005336e-06,
1088
+ "loss": 0.4081,
1089
+ "step": 90000
1090
+ },
1091
+ {
1092
+ "epoch": 6.76,
1093
+ "learning_rate": 1.723034247306092e-06,
1094
+ "loss": 0.4027,
1095
+ "step": 90500
1096
+ },
1097
+ {
1098
+ "epoch": 6.8,
1099
+ "learning_rate": 1.4563106796116506e-06,
1100
+ "loss": 0.4354,
1101
+ "step": 91000
1102
+ },
1103
+ {
1104
+ "epoch": 6.83,
1105
+ "learning_rate": 1.189587111917209e-06,
1106
+ "loss": 0.4193,
1107
+ "step": 91500
1108
+ },
1109
+ {
1110
+ "epoch": 6.87,
1111
+ "learning_rate": 9.228635442227675e-07,
1112
+ "loss": 0.3877,
1113
+ "step": 92000
1114
+ },
1115
+ {
1116
+ "epoch": 6.91,
1117
+ "learning_rate": 6.56139976528326e-07,
1118
+ "loss": 0.4322,
1119
+ "step": 92500
1120
+ },
1121
+ {
1122
+ "epoch": 6.95,
1123
+ "learning_rate": 3.894164088338846e-07,
1124
+ "loss": 0.4068,
1125
+ "step": 93000
1126
+ },
1127
+ {
1128
+ "epoch": 6.98,
1129
+ "learning_rate": 1.226928411394431e-07,
1130
+ "loss": 0.3968,
1131
+ "step": 93500
1132
+ },
1133
+ {
1134
+ "epoch": 7.0,
1135
+ "step": 93730,
1136
+ "total_flos": 2.490638010831667e+16,
1137
+ "train_loss": 0.024883948061263487,
1138
+ "train_runtime": 1768.5377,
1139
+ "train_samples_per_second": 211.99,
1140
+ "train_steps_per_second": 52.999
1141
+ }
1142
+ ],
1143
+ "logging_steps": 500,
1144
+ "max_steps": 93730,
1145
+ "num_input_tokens_seen": 0,
1146
+ "num_train_epochs": 7,
1147
+ "save_steps": 500,
1148
+ "total_flos": 2.490638010831667e+16,
1149
+ "train_batch_size": 4,
1150
+ "trial_name": null,
1151
+ "trial_params": null
1152
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81764c2f689a4b3fc5fb3c2433c16a2b363d6e376aada1aded503088659c121f
3
+ size 5048