mikhail-panzo commited on
Commit
0ba1133
1 Parent(s): b2dfdc0

Training in progress, step 2500, checkpoint

Browse files
checkpoint-2500/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<ctc_blank>": 80,
3
+ "<mask>": 79
4
+ }
checkpoint-2500/config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/speecht5_tts",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "SpeechT5ForTextToSpeech"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "conv_bias": false,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "decoder_attention_heads": 12,
39
+ "decoder_ffn_dim": 3072,
40
+ "decoder_layerdrop": 0.1,
41
+ "decoder_layers": 6,
42
+ "decoder_start_token_id": 2,
43
+ "encoder_attention_heads": 12,
44
+ "encoder_ffn_dim": 3072,
45
+ "encoder_layerdrop": 0.1,
46
+ "encoder_layers": 12,
47
+ "encoder_max_relative_position": 160,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.0,
52
+ "guided_attention_loss_num_heads": 2,
53
+ "guided_attention_loss_scale": 10.0,
54
+ "guided_attention_loss_sigma": 0.4,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "initializer_range": 0.02,
59
+ "is_encoder_decoder": true,
60
+ "layer_norm_eps": 1e-05,
61
+ "mask_feature_length": 10,
62
+ "mask_feature_min_masks": 0,
63
+ "mask_feature_prob": 0.0,
64
+ "mask_time_length": 10,
65
+ "mask_time_min_masks": 2,
66
+ "mask_time_prob": 0.05,
67
+ "max_length": 1876,
68
+ "max_speech_positions": 1876,
69
+ "max_text_positions": 600,
70
+ "model_type": "speecht5",
71
+ "num_conv_pos_embedding_groups": 16,
72
+ "num_conv_pos_embeddings": 128,
73
+ "num_feat_extract_layers": 7,
74
+ "num_mel_bins": 80,
75
+ "pad_token_id": 1,
76
+ "positional_dropout": 0.1,
77
+ "reduction_factor": 2,
78
+ "scale_embedding": false,
79
+ "speaker_embedding_dim": 512,
80
+ "speech_decoder_postnet_dropout": 0.5,
81
+ "speech_decoder_postnet_kernel": 5,
82
+ "speech_decoder_postnet_layers": 5,
83
+ "speech_decoder_postnet_units": 256,
84
+ "speech_decoder_prenet_dropout": 0.5,
85
+ "speech_decoder_prenet_layers": 2,
86
+ "speech_decoder_prenet_units": 256,
87
+ "torch_dtype": "float32",
88
+ "transformers_version": "4.41.0.dev0",
89
+ "use_cache": false,
90
+ "use_guided_attention_loss": true,
91
+ "vocab_size": 81
92
+ }
checkpoint-2500/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "max_length": 1876,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.41.0.dev0"
9
+ }
checkpoint-2500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd25c4a678a142e010a1233c672298e1aa32802dbed8d136c972ad48896617e0
3
+ size 577789320
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b41227192f008d109d28f21170ccf6967db5365c7af965d57debd6e1ca4a3f
3
+ size 1155772233
checkpoint-2500/preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "SpeechT5FeatureExtractor",
4
+ "feature_size": 1,
5
+ "fmax": 7600,
6
+ "fmin": 80,
7
+ "frame_signal_scale": 1.0,
8
+ "hop_length": 16,
9
+ "mel_floor": 1e-10,
10
+ "num_mel_bins": 80,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "processor_class": "SpeechT5Processor",
14
+ "reduction_factor": 2,
15
+ "return_attention_mask": true,
16
+ "sampling_rate": 16000,
17
+ "win_function": "hann_window",
18
+ "win_length": 64
19
+ }
checkpoint-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f14e9d535fd9691df47a3a0d93c42788e2d768b645ebaf1d926bea8c08e8ee
3
+ size 14244
checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b382f91d6a62c99969921e0d8014a3b1f89a198a6a81ab888e1194bc144c13d5
3
+ size 1064
checkpoint-2500/special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "mask_token": {
5
+ "content": "<mask>",
6
+ "lstrip": true,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "pad_token": "<pad>",
12
+ "unk_token": "<unk>"
13
+ }
checkpoint-2500/spm_char.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
3
+ size 238473
checkpoint-2500/tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "79": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "80": {
44
+ "content": "<ctc_blank>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": true,
54
+ "eos_token": "</s>",
55
+ "mask_token": "<mask>",
56
+ "model_max_length": 600,
57
+ "normalize": false,
58
+ "pad_token": "<pad>",
59
+ "processor_class": "SpeechT5Processor",
60
+ "sp_model_kwargs": {},
61
+ "tokenizer_class": "SpeechT5Tokenizer",
62
+ "unk_token": "<unk>"
63
+ }
checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,423 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4078540802001953,
3
+ "best_model_checkpoint": "mikhail-panzo/fil_b128_le4_s8000/checkpoint-1000",
4
+ "epoch": 220.99447513812154,
5
+ "eval_steps": 500,
6
+ "global_step": 2500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 4.419889502762431,
13
+ "grad_norm": 2.1200406551361084,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 0.77,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 8.839779005524862,
20
+ "grad_norm": 0.8919622302055359,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.695,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 13.259668508287293,
27
+ "grad_norm": 0.9864558577537537,
28
+ "learning_rate": 7.5e-06,
29
+ "loss": 0.6278,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 17.679558011049725,
34
+ "grad_norm": 0.9195986986160278,
35
+ "learning_rate": 1e-05,
36
+ "loss": 0.5431,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 22.099447513812155,
41
+ "grad_norm": 1.0175281763076782,
42
+ "learning_rate": 1.25e-05,
43
+ "loss": 0.5155,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 26.519337016574585,
48
+ "grad_norm": 1.0303566455841064,
49
+ "learning_rate": 1.5e-05,
50
+ "loss": 0.502,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 30.939226519337016,
55
+ "grad_norm": 1.005897879600525,
56
+ "learning_rate": 1.75e-05,
57
+ "loss": 0.4889,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 35.35911602209945,
62
+ "grad_norm": 1.0381360054016113,
63
+ "learning_rate": 2e-05,
64
+ "loss": 0.477,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 39.77900552486188,
69
+ "grad_norm": 1.2148911952972412,
70
+ "learning_rate": 2.25e-05,
71
+ "loss": 0.4711,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 44.19889502762431,
76
+ "grad_norm": 1.5404785871505737,
77
+ "learning_rate": 2.5e-05,
78
+ "loss": 0.463,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 44.19889502762431,
83
+ "eval_loss": 0.42523157596588135,
84
+ "eval_runtime": 15.6706,
85
+ "eval_samples_per_second": 10.274,
86
+ "eval_steps_per_second": 1.34,
87
+ "step": 500
88
+ },
89
+ {
90
+ "epoch": 48.61878453038674,
91
+ "grad_norm": 1.1097612380981445,
92
+ "learning_rate": 2.7500000000000004e-05,
93
+ "loss": 0.4601,
94
+ "step": 550
95
+ },
96
+ {
97
+ "epoch": 53.03867403314917,
98
+ "grad_norm": 1.2796109914779663,
99
+ "learning_rate": 3e-05,
100
+ "loss": 0.454,
101
+ "step": 600
102
+ },
103
+ {
104
+ "epoch": 57.4585635359116,
105
+ "grad_norm": 1.0656301975250244,
106
+ "learning_rate": 3.2500000000000004e-05,
107
+ "loss": 0.4498,
108
+ "step": 650
109
+ },
110
+ {
111
+ "epoch": 61.87845303867403,
112
+ "grad_norm": 1.3971511125564575,
113
+ "learning_rate": 3.5e-05,
114
+ "loss": 0.4439,
115
+ "step": 700
116
+ },
117
+ {
118
+ "epoch": 66.29834254143647,
119
+ "grad_norm": 1.9344899654388428,
120
+ "learning_rate": 3.7500000000000003e-05,
121
+ "loss": 0.4418,
122
+ "step": 750
123
+ },
124
+ {
125
+ "epoch": 70.7182320441989,
126
+ "grad_norm": 1.080334186553955,
127
+ "learning_rate": 4e-05,
128
+ "loss": 0.4379,
129
+ "step": 800
130
+ },
131
+ {
132
+ "epoch": 75.13812154696133,
133
+ "grad_norm": 1.9891581535339355,
134
+ "learning_rate": 4.25e-05,
135
+ "loss": 0.4334,
136
+ "step": 850
137
+ },
138
+ {
139
+ "epoch": 79.55801104972376,
140
+ "grad_norm": 1.3854402303695679,
141
+ "learning_rate": 4.5e-05,
142
+ "loss": 0.4331,
143
+ "step": 900
144
+ },
145
+ {
146
+ "epoch": 83.97790055248619,
147
+ "grad_norm": 1.5818183422088623,
148
+ "learning_rate": 4.75e-05,
149
+ "loss": 0.428,
150
+ "step": 950
151
+ },
152
+ {
153
+ "epoch": 88.39779005524862,
154
+ "grad_norm": 1.8474106788635254,
155
+ "learning_rate": 5e-05,
156
+ "loss": 0.4238,
157
+ "step": 1000
158
+ },
159
+ {
160
+ "epoch": 88.39779005524862,
161
+ "eval_loss": 0.4078540802001953,
162
+ "eval_runtime": 14.8436,
163
+ "eval_samples_per_second": 10.846,
164
+ "eval_steps_per_second": 1.415,
165
+ "step": 1000
166
+ },
167
+ {
168
+ "epoch": 92.81767955801105,
169
+ "grad_norm": 3.1851751804351807,
170
+ "learning_rate": 5.25e-05,
171
+ "loss": 0.4234,
172
+ "step": 1050
173
+ },
174
+ {
175
+ "epoch": 97.23756906077348,
176
+ "grad_norm": 1.3754140138626099,
177
+ "learning_rate": 5.500000000000001e-05,
178
+ "loss": 0.4209,
179
+ "step": 1100
180
+ },
181
+ {
182
+ "epoch": 101.65745856353591,
183
+ "grad_norm": 1.6143475770950317,
184
+ "learning_rate": 5.7499999999999995e-05,
185
+ "loss": 0.4228,
186
+ "step": 1150
187
+ },
188
+ {
189
+ "epoch": 106.07734806629834,
190
+ "grad_norm": 1.9961720705032349,
191
+ "learning_rate": 6e-05,
192
+ "loss": 0.4162,
193
+ "step": 1200
194
+ },
195
+ {
196
+ "epoch": 110.49723756906077,
197
+ "grad_norm": 1.9125347137451172,
198
+ "learning_rate": 6.25e-05,
199
+ "loss": 0.4178,
200
+ "step": 1250
201
+ },
202
+ {
203
+ "epoch": 114.9171270718232,
204
+ "grad_norm": 3.1913959980010986,
205
+ "learning_rate": 6.500000000000001e-05,
206
+ "loss": 0.4143,
207
+ "step": 1300
208
+ },
209
+ {
210
+ "epoch": 119.33701657458563,
211
+ "grad_norm": 2.1010069847106934,
212
+ "learning_rate": 6.750000000000001e-05,
213
+ "loss": 0.4118,
214
+ "step": 1350
215
+ },
216
+ {
217
+ "epoch": 123.75690607734806,
218
+ "grad_norm": 1.3079431056976318,
219
+ "learning_rate": 7e-05,
220
+ "loss": 0.4091,
221
+ "step": 1400
222
+ },
223
+ {
224
+ "epoch": 128.1767955801105,
225
+ "grad_norm": 2.3663132190704346,
226
+ "learning_rate": 7.25e-05,
227
+ "loss": 0.4092,
228
+ "step": 1450
229
+ },
230
+ {
231
+ "epoch": 132.59668508287294,
232
+ "grad_norm": 1.031698226928711,
233
+ "learning_rate": 7.500000000000001e-05,
234
+ "loss": 0.4083,
235
+ "step": 1500
236
+ },
237
+ {
238
+ "epoch": 132.59668508287294,
239
+ "eval_loss": 0.4082767069339752,
240
+ "eval_runtime": 15.1068,
241
+ "eval_samples_per_second": 10.657,
242
+ "eval_steps_per_second": 1.39,
243
+ "step": 1500
244
+ },
245
+ {
246
+ "epoch": 137.01657458563537,
247
+ "grad_norm": 2.7781426906585693,
248
+ "learning_rate": 7.75e-05,
249
+ "loss": 0.4079,
250
+ "step": 1550
251
+ },
252
+ {
253
+ "epoch": 141.4364640883978,
254
+ "grad_norm": 1.136169672012329,
255
+ "learning_rate": 8e-05,
256
+ "loss": 0.4028,
257
+ "step": 1600
258
+ },
259
+ {
260
+ "epoch": 145.85635359116023,
261
+ "grad_norm": 1.7299158573150635,
262
+ "learning_rate": 8.25e-05,
263
+ "loss": 0.4034,
264
+ "step": 1650
265
+ },
266
+ {
267
+ "epoch": 150.27624309392266,
268
+ "grad_norm": 2.4281983375549316,
269
+ "learning_rate": 8.5e-05,
270
+ "loss": 0.3992,
271
+ "step": 1700
272
+ },
273
+ {
274
+ "epoch": 154.6961325966851,
275
+ "grad_norm": 3.6834373474121094,
276
+ "learning_rate": 8.75e-05,
277
+ "loss": 0.3997,
278
+ "step": 1750
279
+ },
280
+ {
281
+ "epoch": 159.11602209944752,
282
+ "grad_norm": 3.1484293937683105,
283
+ "learning_rate": 9e-05,
284
+ "loss": 0.396,
285
+ "step": 1800
286
+ },
287
+ {
288
+ "epoch": 163.53591160220995,
289
+ "grad_norm": 3.978259563446045,
290
+ "learning_rate": 9.250000000000001e-05,
291
+ "loss": 0.3969,
292
+ "step": 1850
293
+ },
294
+ {
295
+ "epoch": 167.95580110497238,
296
+ "grad_norm": 2.906266212463379,
297
+ "learning_rate": 9.5e-05,
298
+ "loss": 0.4017,
299
+ "step": 1900
300
+ },
301
+ {
302
+ "epoch": 172.3756906077348,
303
+ "grad_norm": 1.1569880247116089,
304
+ "learning_rate": 9.75e-05,
305
+ "loss": 0.396,
306
+ "step": 1950
307
+ },
308
+ {
309
+ "epoch": 176.79558011049724,
310
+ "grad_norm": 2.2872982025146484,
311
+ "learning_rate": 0.0001,
312
+ "loss": 0.3928,
313
+ "step": 2000
314
+ },
315
+ {
316
+ "epoch": 176.79558011049724,
317
+ "eval_loss": 0.414584219455719,
318
+ "eval_runtime": 15.2895,
319
+ "eval_samples_per_second": 10.53,
320
+ "eval_steps_per_second": 1.373,
321
+ "step": 2000
322
+ },
323
+ {
324
+ "epoch": 181.21546961325967,
325
+ "grad_norm": 1.1768990755081177,
326
+ "learning_rate": 9.916666666666667e-05,
327
+ "loss": 0.3928,
328
+ "step": 2050
329
+ },
330
+ {
331
+ "epoch": 185.6353591160221,
332
+ "grad_norm": 1.2087491750717163,
333
+ "learning_rate": 9.833333333333333e-05,
334
+ "loss": 0.3901,
335
+ "step": 2100
336
+ },
337
+ {
338
+ "epoch": 190.05524861878453,
339
+ "grad_norm": 1.17588210105896,
340
+ "learning_rate": 9.75e-05,
341
+ "loss": 0.3877,
342
+ "step": 2150
343
+ },
344
+ {
345
+ "epoch": 194.47513812154696,
346
+ "grad_norm": 1.5979018211364746,
347
+ "learning_rate": 9.666666666666667e-05,
348
+ "loss": 0.3879,
349
+ "step": 2200
350
+ },
351
+ {
352
+ "epoch": 198.8950276243094,
353
+ "grad_norm": 1.0489567518234253,
354
+ "learning_rate": 9.583333333333334e-05,
355
+ "loss": 0.3869,
356
+ "step": 2250
357
+ },
358
+ {
359
+ "epoch": 203.31491712707182,
360
+ "grad_norm": 1.833038091659546,
361
+ "learning_rate": 9.501666666666668e-05,
362
+ "loss": 0.3859,
363
+ "step": 2300
364
+ },
365
+ {
366
+ "epoch": 207.73480662983425,
367
+ "grad_norm": 2.075849771499634,
368
+ "learning_rate": 9.418333333333334e-05,
369
+ "loss": 0.3843,
370
+ "step": 2350
371
+ },
372
+ {
373
+ "epoch": 212.15469613259668,
374
+ "grad_norm": 2.8613317012786865,
375
+ "learning_rate": 9.335e-05,
376
+ "loss": 0.381,
377
+ "step": 2400
378
+ },
379
+ {
380
+ "epoch": 216.5745856353591,
381
+ "grad_norm": 1.6291433572769165,
382
+ "learning_rate": 9.251666666666667e-05,
383
+ "loss": 0.3802,
384
+ "step": 2450
385
+ },
386
+ {
387
+ "epoch": 220.99447513812154,
388
+ "grad_norm": 1.1548006534576416,
389
+ "learning_rate": 9.168333333333333e-05,
390
+ "loss": 0.381,
391
+ "step": 2500
392
+ },
393
+ {
394
+ "epoch": 220.99447513812154,
395
+ "eval_loss": 0.4127160906791687,
396
+ "eval_runtime": 15.1026,
397
+ "eval_samples_per_second": 10.66,
398
+ "eval_steps_per_second": 1.39,
399
+ "step": 2500
400
+ }
401
+ ],
402
+ "logging_steps": 50,
403
+ "max_steps": 8000,
404
+ "num_input_tokens_seen": 0,
405
+ "num_train_epochs": 728,
406
+ "save_steps": 500,
407
+ "stateful_callbacks": {
408
+ "TrainerControl": {
409
+ "args": {
410
+ "should_epoch_stop": false,
411
+ "should_evaluate": false,
412
+ "should_log": false,
413
+ "should_save": true,
414
+ "should_training_stop": false
415
+ },
416
+ "attributes": {}
417
+ }
418
+ },
419
+ "total_flos": 5.660506148311872e+16,
420
+ "train_batch_size": 8,
421
+ "trial_name": null,
422
+ "trial_params": null
423
+ }
checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:067941ce54247f638979fecfb22f3bf44cd9bc2df99dac3a436b8b51c9f0dbc4
3
+ size 5304