NguyenTan commited on
Commit
acaa48c
·
verified ·
1 Parent(s): 473e584

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.15,
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "MBartForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.15,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.0,
10
+ "d_model": 1024,
11
+ "decoder_attention_heads": 16,
12
+ "decoder_ffn_dim": 4096,
13
+ "decoder_layerdrop": 0.0,
14
+ "decoder_layers": 12,
15
+ "decoder_start_token_id": 0,
16
+ "dropout": 0.15,
17
+ "dtype": "float32",
18
+ "encoder_attention_heads": 16,
19
+ "encoder_ffn_dim": 4096,
20
+ "encoder_layerdrop": 0.0,
21
+ "encoder_layers": 12,
22
+ "eos_token_id": 2,
23
+ "forced_eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "init_std": 0.02,
26
+ "is_encoder_decoder": true,
27
+ "max_position_embeddings": 1024,
28
+ "model_type": "mbart",
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "scale_embedding": false,
32
+ "tokenizer_class": "BartphoTokenizer",
33
+ "transformers_version": "4.57.3",
34
+ "use_cache": true,
35
+ "vocab_size": 40030
36
+ }
last-checkpoint/dict.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "eos_token_id": [
5
+ 2
6
+ ],
7
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "max_length": 512,
10
+ "max_new_tokens": 512,
11
+ "pad_token_id": 1,
12
+ "transformers_version": "4.57.3"
13
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fa7e8dc76a1ad80fea8451376493e842c4a3fb713cc61e3730ffb7943836e26
3
+ size 1583480280
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f61d9e38597f7e1097962bfa578b78425fe844a9ec6398e8bccb06d0d3be805e
3
+ size 3166958572
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172c6e9da1198fecb1104ae5588ac154055d22275bb62749b67f1d60379ff0a7
3
+ size 14645
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27712306309eef7ef52a4de0e2e9c9c3c61f74c51a1439a49e7192d4f554d614
3
+ size 1383
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68aec417c91400a5fbe9c98d7447dabd74ed3b0812272a5f21d640985e919bad
3
+ size 1465
last-checkpoint/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "40029": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 1024,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "sp_model_kwargs": {},
54
+ "tokenizer_class": "BartphoTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,759 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1000,
3
+ "best_metric": 1.7293134927749634,
4
+ "best_model_checkpoint": "hieptt/vietnamese-correction-ft/checkpoint-1000",
5
+ "epoch": 0.024186136506554445,
6
+ "eval_steps": 1000,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 2.4186136506554445e-05,
14
+ "grad_norm": 6.7611775398254395,
15
+ "learning_rate": 0.0,
16
+ "loss": 4.8761,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.00024186136506554442,
21
+ "grad_norm": 7.387487888336182,
22
+ "learning_rate": 4.5e-07,
23
+ "loss": 4.9048,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.00048372273013108885,
28
+ "grad_norm": 9.89797592163086,
29
+ "learning_rate": 9.5e-07,
30
+ "loss": 4.7162,
31
+ "step": 20
32
+ },
33
+ {
34
+ "epoch": 0.0007255840951966333,
35
+ "grad_norm": 12.0128755569458,
36
+ "learning_rate": 1.45e-06,
37
+ "loss": 4.3937,
38
+ "step": 30
39
+ },
40
+ {
41
+ "epoch": 0.0009674454602621777,
42
+ "grad_norm": 13.892581939697266,
43
+ "learning_rate": 1.95e-06,
44
+ "loss": 4.0291,
45
+ "step": 40
46
+ },
47
+ {
48
+ "epoch": 0.0012093068253277222,
49
+ "grad_norm": 14.026715278625488,
50
+ "learning_rate": 2.4500000000000003e-06,
51
+ "loss": 3.5469,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 0.0014511681903932665,
56
+ "grad_norm": 4.720450401306152,
57
+ "learning_rate": 2.95e-06,
58
+ "loss": 2.8797,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 0.001693029555458811,
63
+ "grad_norm": 2.526860237121582,
64
+ "learning_rate": 3.4500000000000004e-06,
65
+ "loss": 2.3633,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 0.0019348909205243554,
70
+ "grad_norm": 1.6215327978134155,
71
+ "learning_rate": 3.95e-06,
72
+ "loss": 2.0775,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 0.0021767522855899,
77
+ "grad_norm": 0.8917969465255737,
78
+ "learning_rate": 4.45e-06,
79
+ "loss": 1.9554,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 0.0024186136506554445,
84
+ "grad_norm": 0.8278113603591919,
85
+ "learning_rate": 4.950000000000001e-06,
86
+ "loss": 1.887,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 0.0026604750157209886,
91
+ "grad_norm": 0.8582026362419128,
92
+ "learning_rate": 5.45e-06,
93
+ "loss": 1.8405,
94
+ "step": 110
95
+ },
96
+ {
97
+ "epoch": 0.002902336380786533,
98
+ "grad_norm": 0.7158175110816956,
99
+ "learning_rate": 5.95e-06,
100
+ "loss": 1.8095,
101
+ "step": 120
102
+ },
103
+ {
104
+ "epoch": 0.0031441977458520776,
105
+ "grad_norm": 0.6908526420593262,
106
+ "learning_rate": 6.45e-06,
107
+ "loss": 1.7881,
108
+ "step": 130
109
+ },
110
+ {
111
+ "epoch": 0.003386059110917622,
112
+ "grad_norm": 0.746881902217865,
113
+ "learning_rate": 6.950000000000001e-06,
114
+ "loss": 1.7647,
115
+ "step": 140
116
+ },
117
+ {
118
+ "epoch": 0.0036279204759831663,
119
+ "grad_norm": 0.6858472228050232,
120
+ "learning_rate": 7.45e-06,
121
+ "loss": 1.7577,
122
+ "step": 150
123
+ },
124
+ {
125
+ "epoch": 0.003869781841048711,
126
+ "grad_norm": 0.7207092642784119,
127
+ "learning_rate": 7.95e-06,
128
+ "loss": 1.7499,
129
+ "step": 160
130
+ },
131
+ {
132
+ "epoch": 0.004111643206114255,
133
+ "grad_norm": 0.6050883531570435,
134
+ "learning_rate": 8.45e-06,
135
+ "loss": 1.741,
136
+ "step": 170
137
+ },
138
+ {
139
+ "epoch": 0.0043535045711798,
140
+ "grad_norm": 0.7387958765029907,
141
+ "learning_rate": 8.95e-06,
142
+ "loss": 1.7283,
143
+ "step": 180
144
+ },
145
+ {
146
+ "epoch": 0.004595365936245344,
147
+ "grad_norm": 0.7111212015151978,
148
+ "learning_rate": 9.450000000000001e-06,
149
+ "loss": 1.707,
150
+ "step": 190
151
+ },
152
+ {
153
+ "epoch": 0.004837227301310889,
154
+ "grad_norm": 0.6965436935424805,
155
+ "learning_rate": 9.950000000000001e-06,
156
+ "loss": 1.706,
157
+ "step": 200
158
+ },
159
+ {
160
+ "epoch": 0.005079088666376433,
161
+ "grad_norm": 0.6116521954536438,
162
+ "learning_rate": 1.045e-05,
163
+ "loss": 1.7065,
164
+ "step": 210
165
+ },
166
+ {
167
+ "epoch": 0.005320950031441977,
168
+ "grad_norm": 0.5820265412330627,
169
+ "learning_rate": 1.095e-05,
170
+ "loss": 1.6962,
171
+ "step": 220
172
+ },
173
+ {
174
+ "epoch": 0.005562811396507522,
175
+ "grad_norm": 0.6360993981361389,
176
+ "learning_rate": 1.145e-05,
177
+ "loss": 1.6822,
178
+ "step": 230
179
+ },
180
+ {
181
+ "epoch": 0.005804672761573066,
182
+ "grad_norm": 0.5463513731956482,
183
+ "learning_rate": 1.195e-05,
184
+ "loss": 1.6794,
185
+ "step": 240
186
+ },
187
+ {
188
+ "epoch": 0.006046534126638611,
189
+ "grad_norm": 0.5612601041793823,
190
+ "learning_rate": 1.2450000000000001e-05,
191
+ "loss": 1.6587,
192
+ "step": 250
193
+ },
194
+ {
195
+ "epoch": 0.006288395491704155,
196
+ "grad_norm": 0.657686173915863,
197
+ "learning_rate": 1.2950000000000001e-05,
198
+ "loss": 1.6756,
199
+ "step": 260
200
+ },
201
+ {
202
+ "epoch": 0.006530256856769699,
203
+ "grad_norm": 0.6136758327484131,
204
+ "learning_rate": 1.3450000000000002e-05,
205
+ "loss": 1.6723,
206
+ "step": 270
207
+ },
208
+ {
209
+ "epoch": 0.006772118221835244,
210
+ "grad_norm": 0.6555290818214417,
211
+ "learning_rate": 1.3950000000000002e-05,
212
+ "loss": 1.6605,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 0.007013979586900788,
217
+ "grad_norm": 0.5237599611282349,
218
+ "learning_rate": 1.4449999999999999e-05,
219
+ "loss": 1.6497,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 0.0072558409519663325,
224
+ "grad_norm": 0.617452085018158,
225
+ "learning_rate": 1.4950000000000001e-05,
226
+ "loss": 1.6441,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 0.0074977023170318775,
231
+ "grad_norm": 0.5212193727493286,
232
+ "learning_rate": 1.545e-05,
233
+ "loss": 1.6478,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 0.007739563682097422,
238
+ "grad_norm": 0.41100624203681946,
239
+ "learning_rate": 1.595e-05,
240
+ "loss": 1.6405,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 0.007981425047162967,
245
+ "grad_norm": 0.5392923355102539,
246
+ "learning_rate": 1.645e-05,
247
+ "loss": 1.6441,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 0.00822328641222851,
252
+ "grad_norm": 0.5176446437835693,
253
+ "learning_rate": 1.6950000000000002e-05,
254
+ "loss": 1.6401,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 0.008465147777294055,
259
+ "grad_norm": 0.4990129768848419,
260
+ "learning_rate": 1.745e-05,
261
+ "loss": 1.6385,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 0.0087070091423596,
266
+ "grad_norm": 0.6200714111328125,
267
+ "learning_rate": 1.795e-05,
268
+ "loss": 1.6222,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 0.008948870507425145,
273
+ "grad_norm": 0.4544118046760559,
274
+ "learning_rate": 1.845e-05,
275
+ "loss": 1.6267,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 0.009190731872490688,
280
+ "grad_norm": 0.4579808712005615,
281
+ "learning_rate": 1.895e-05,
282
+ "loss": 1.6265,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 0.009432593237556233,
287
+ "grad_norm": 0.5392481088638306,
288
+ "learning_rate": 1.9450000000000002e-05,
289
+ "loss": 1.6208,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 0.009674454602621778,
294
+ "grad_norm": 0.4114883840084076,
295
+ "learning_rate": 1.995e-05,
296
+ "loss": 1.6137,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 0.009916315967687321,
301
+ "grad_norm": 0.4515584409236908,
302
+ "learning_rate": 2.045e-05,
303
+ "loss": 1.6196,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 0.010158177332752866,
308
+ "grad_norm": 0.585402250289917,
309
+ "learning_rate": 2.095e-05,
310
+ "loss": 1.6049,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 0.010400038697818411,
315
+ "grad_norm": 0.6052455902099609,
316
+ "learning_rate": 2.145e-05,
317
+ "loss": 1.6083,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 0.010641900062883954,
322
+ "grad_norm": 0.5212528109550476,
323
+ "learning_rate": 2.195e-05,
324
+ "loss": 1.6074,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 0.0108837614279495,
329
+ "grad_norm": 0.5251073837280273,
330
+ "learning_rate": 2.245e-05,
331
+ "loss": 1.6033,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 0.011125622793015044,
336
+ "grad_norm": 0.5946005582809448,
337
+ "learning_rate": 2.2950000000000002e-05,
338
+ "loss": 1.5976,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 0.011367484158080587,
343
+ "grad_norm": 0.5436714887619019,
344
+ "learning_rate": 2.345e-05,
345
+ "loss": 1.5982,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 0.011609345523146132,
350
+ "grad_norm": 0.4346768260002136,
351
+ "learning_rate": 2.395e-05,
352
+ "loss": 1.5983,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 0.011851206888211677,
357
+ "grad_norm": 0.4886501729488373,
358
+ "learning_rate": 2.445e-05,
359
+ "loss": 1.5915,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 0.012093068253277222,
364
+ "grad_norm": 0.41521257162094116,
365
+ "learning_rate": 2.495e-05,
366
+ "loss": 1.5944,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 0.012334929618342766,
371
+ "grad_norm": 0.42215368151664734,
372
+ "learning_rate": 2.5450000000000002e-05,
373
+ "loss": 1.5959,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 0.01257679098340831,
378
+ "grad_norm": 0.5773257613182068,
379
+ "learning_rate": 2.595e-05,
380
+ "loss": 1.5945,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 0.012818652348473855,
385
+ "grad_norm": 0.4475298225879669,
386
+ "learning_rate": 2.6450000000000003e-05,
387
+ "loss": 1.5976,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 0.013060513713539399,
392
+ "grad_norm": 0.44435611367225647,
393
+ "learning_rate": 2.6950000000000005e-05,
394
+ "loss": 1.586,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 0.013302375078604944,
399
+ "grad_norm": 0.3894321620464325,
400
+ "learning_rate": 2.7450000000000003e-05,
401
+ "loss": 1.591,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 0.013544236443670489,
406
+ "grad_norm": 0.5355809926986694,
407
+ "learning_rate": 2.7950000000000005e-05,
408
+ "loss": 1.5951,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 0.013786097808736032,
413
+ "grad_norm": 0.42732134461402893,
414
+ "learning_rate": 2.845e-05,
415
+ "loss": 1.5921,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 0.014027959173801577,
420
+ "grad_norm": 0.4931578040122986,
421
+ "learning_rate": 2.895e-05,
422
+ "loss": 1.5833,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 0.014269820538867122,
427
+ "grad_norm": 0.4680155813694,
428
+ "learning_rate": 2.945e-05,
429
+ "loss": 1.5854,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 0.014511681903932665,
434
+ "grad_norm": 0.4610539674758911,
435
+ "learning_rate": 2.995e-05,
436
+ "loss": 1.5796,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 0.01475354326899821,
441
+ "grad_norm": 0.5503636002540588,
442
+ "learning_rate": 3.045e-05,
443
+ "loss": 1.5765,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 0.014995404634063755,
448
+ "grad_norm": 0.5213884711265564,
449
+ "learning_rate": 3.095e-05,
450
+ "loss": 1.5788,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 0.015237265999129298,
455
+ "grad_norm": 0.44397738575935364,
456
+ "learning_rate": 3.145e-05,
457
+ "loss": 1.5799,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 0.015479127364194843,
462
+ "grad_norm": 0.4421987235546112,
463
+ "learning_rate": 3.1950000000000004e-05,
464
+ "loss": 1.5818,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 0.015720988729260386,
469
+ "grad_norm": 0.48444682359695435,
470
+ "learning_rate": 3.245e-05,
471
+ "loss": 1.5672,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 0.015962850094325933,
476
+ "grad_norm": 0.3913522958755493,
477
+ "learning_rate": 3.295e-05,
478
+ "loss": 1.5795,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 0.016204711459391476,
483
+ "grad_norm": 0.5272910594940186,
484
+ "learning_rate": 3.345000000000001e-05,
485
+ "loss": 1.5814,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 0.01644657282445702,
490
+ "grad_norm": 0.6935471296310425,
491
+ "learning_rate": 3.3950000000000005e-05,
492
+ "loss": 1.5796,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 0.016688434189522566,
497
+ "grad_norm": 0.45269250869750977,
498
+ "learning_rate": 3.445e-05,
499
+ "loss": 1.5775,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 0.01693029555458811,
504
+ "grad_norm": 0.5092645883560181,
505
+ "learning_rate": 3.495e-05,
506
+ "loss": 1.5734,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 0.017172156919653656,
511
+ "grad_norm": 0.45498231053352356,
512
+ "learning_rate": 3.545e-05,
513
+ "loss": 1.5763,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 0.0174140182847192,
518
+ "grad_norm": 0.7897817492485046,
519
+ "learning_rate": 3.595e-05,
520
+ "loss": 1.5702,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 0.017655879649784743,
525
+ "grad_norm": 0.5634914040565491,
526
+ "learning_rate": 3.645e-05,
527
+ "loss": 1.5794,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 0.01789774101485029,
532
+ "grad_norm": 0.47791045904159546,
533
+ "learning_rate": 3.6950000000000004e-05,
534
+ "loss": 1.5667,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 0.018139602379915833,
539
+ "grad_norm": 0.5094493627548218,
540
+ "learning_rate": 3.745e-05,
541
+ "loss": 1.5741,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 0.018381463744981376,
546
+ "grad_norm": 0.8162134289741516,
547
+ "learning_rate": 3.795e-05,
548
+ "loss": 1.5617,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 0.018623325110046923,
553
+ "grad_norm": 0.5486655235290527,
554
+ "learning_rate": 3.845e-05,
555
+ "loss": 1.567,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 0.018865186475112466,
560
+ "grad_norm": 0.5235345959663391,
561
+ "learning_rate": 3.8950000000000005e-05,
562
+ "loss": 1.5721,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 0.01910704784017801,
567
+ "grad_norm": 0.5451304316520691,
568
+ "learning_rate": 3.9450000000000003e-05,
569
+ "loss": 1.5636,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 0.019348909205243556,
574
+ "grad_norm": 0.9819433093070984,
575
+ "learning_rate": 3.995e-05,
576
+ "loss": 1.5763,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 0.0195907705703091,
581
+ "grad_norm": 0.5126760601997375,
582
+ "learning_rate": 4.045000000000001e-05,
583
+ "loss": 1.5624,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 0.019832631935374642,
588
+ "grad_norm": 0.4358855187892914,
589
+ "learning_rate": 4.095e-05,
590
+ "loss": 1.5598,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 0.02007449330044019,
595
+ "grad_norm": 0.46795687079429626,
596
+ "learning_rate": 4.145e-05,
597
+ "loss": 1.5662,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 0.020316354665505732,
602
+ "grad_norm": 0.7062624096870422,
603
+ "learning_rate": 4.195e-05,
604
+ "loss": 1.5606,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 0.020558216030571275,
609
+ "grad_norm": 0.4150901734828949,
610
+ "learning_rate": 4.245e-05,
611
+ "loss": 1.5537,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 0.020800077395636822,
616
+ "grad_norm": 0.43676918745040894,
617
+ "learning_rate": 4.295e-05,
618
+ "loss": 1.559,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 0.021041938760702365,
623
+ "grad_norm": 0.43422532081604004,
624
+ "learning_rate": 4.345e-05,
625
+ "loss": 1.5578,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 0.02128380012576791,
630
+ "grad_norm": 0.5572603940963745,
631
+ "learning_rate": 4.3950000000000004e-05,
632
+ "loss": 1.56,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 0.021525661490833455,
637
+ "grad_norm": 0.5086297392845154,
638
+ "learning_rate": 4.445e-05,
639
+ "loss": 1.5552,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 0.021767522855899,
644
+ "grad_norm": 0.4402131736278534,
645
+ "learning_rate": 4.495e-05,
646
+ "loss": 1.5529,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 0.02200938422096454,
651
+ "grad_norm": 0.48463812470436096,
652
+ "learning_rate": 4.545000000000001e-05,
653
+ "loss": 1.5545,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 0.02225124558603009,
658
+ "grad_norm": 0.43822240829467773,
659
+ "learning_rate": 4.5950000000000006e-05,
660
+ "loss": 1.5478,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 0.02249310695109563,
665
+ "grad_norm": 0.4400993883609772,
666
+ "learning_rate": 4.6450000000000004e-05,
667
+ "loss": 1.5394,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 0.022734968316161175,
672
+ "grad_norm": 0.5330896377563477,
673
+ "learning_rate": 4.695e-05,
674
+ "loss": 1.5495,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 0.02297682968122672,
679
+ "grad_norm": 0.48620447516441345,
680
+ "learning_rate": 4.745e-05,
681
+ "loss": 1.5498,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 0.023218691046292265,
686
+ "grad_norm": 0.587838351726532,
687
+ "learning_rate": 4.795e-05,
688
+ "loss": 1.5612,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 0.023460552411357808,
693
+ "grad_norm": 0.7441233396530151,
694
+ "learning_rate": 4.845e-05,
695
+ "loss": 1.5732,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 0.023702413776423355,
700
+ "grad_norm": 1.0196274518966675,
701
+ "learning_rate": 4.8950000000000004e-05,
702
+ "loss": 1.7309,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 0.023944275141488898,
707
+ "grad_norm": 2.096895217895508,
708
+ "learning_rate": 4.945e-05,
709
+ "loss": 1.9244,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 0.024186136506554445,
714
+ "grad_norm": 0.6858440637588501,
715
+ "learning_rate": 4.995e-05,
716
+ "loss": 1.7569,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 0.024186136506554445,
721
+ "eval_loss": 1.7293134927749634,
722
+ "eval_runtime": 1146.3923,
723
+ "eval_sacrebleu": 88.63943237810263,
724
+ "eval_samples_per_second": 88.143,
725
+ "eval_steps_per_second": 0.689,
726
+ "step": 1000
727
+ }
728
+ ],
729
+ "logging_steps": 10,
730
+ "max_steps": 50000,
731
+ "num_input_tokens_seen": 0,
732
+ "num_train_epochs": 2,
733
+ "save_steps": 1000,
734
+ "stateful_callbacks": {
735
+ "EarlyStoppingCallback": {
736
+ "args": {
737
+ "early_stopping_patience": 5,
738
+ "early_stopping_threshold": 0.0001
739
+ },
740
+ "attributes": {
741
+ "early_stopping_patience_counter": 0
742
+ }
743
+ },
744
+ "TrainerControl": {
745
+ "args": {
746
+ "should_epoch_stop": false,
747
+ "should_evaluate": false,
748
+ "should_log": false,
749
+ "should_save": true,
750
+ "should_training_stop": false
751
+ },
752
+ "attributes": {}
753
+ }
754
+ },
755
+ "total_flos": 2.054005594049741e+16,
756
+ "train_batch_size": 64,
757
+ "trial_name": null,
758
+ "trial_params": null
759
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ac17f5232af6c5d50e0e4fa5343f65e47cffc82fe93621b234d0fdfe916e7e
3
+ size 6033