otozz commited on
Commit
4200c0b
·
verified ·
1 Parent(s): 136c6b4

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-small",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 768,
17
+ "decoder_attention_heads": 12,
18
+ "decoder_ffn_dim": 3072,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": null,
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "mask_feature_length": 10,
32
+ "mask_feature_min_masks": 0,
33
+ "mask_feature_prob": 0.0,
34
+ "mask_time_length": 10,
35
+ "mask_time_min_masks": 2,
36
+ "mask_time_prob": 0.05,
37
+ "max_length": 512,
38
+ "max_source_positions": 1500,
39
+ "max_target_positions": 448,
40
+ "median_filter_width": 7,
41
+ "model_type": "whisper",
42
+ "num_hidden_layers": 12,
43
+ "num_mel_bins": 80,
44
+ "pad_token_id": 50257,
45
+ "scale_embedding": false,
46
+ "suppress_tokens": [],
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.39.3",
49
+ "use_cache": true,
50
+ "use_weighted_layer_sum": false,
51
+ "vocab_size": 51865
52
+ }
generation_config.json ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 5,
5
+ 3
6
+ ],
7
+ [
8
+ 5,
9
+ 9
10
+ ],
11
+ [
12
+ 8,
13
+ 0
14
+ ],
15
+ [
16
+ 8,
17
+ 4
18
+ ],
19
+ [
20
+ 8,
21
+ 7
22
+ ],
23
+ [
24
+ 8,
25
+ 8
26
+ ],
27
+ [
28
+ 9,
29
+ 0
30
+ ],
31
+ [
32
+ 9,
33
+ 7
34
+ ],
35
+ [
36
+ 9,
37
+ 9
38
+ ],
39
+ [
40
+ 10,
41
+ 5
42
+ ]
43
+ ],
44
+ "begin_suppress_tokens": [
45
+ 220,
46
+ 50257
47
+ ],
48
+ "bos_token_id": 50257,
49
+ "decoder_start_token_id": 50258,
50
+ "eos_token_id": 50257,
51
+ "forced_decoder_ids": [
52
+ [
53
+ 1,
54
+ null
55
+ ],
56
+ [
57
+ 2,
58
+ 50359
59
+ ]
60
+ ],
61
+ "is_multilingual": true,
62
+ "lang_to_id": {
63
+ "<|af|>": 50327,
64
+ "<|am|>": 50334,
65
+ "<|ar|>": 50272,
66
+ "<|as|>": 50350,
67
+ "<|az|>": 50304,
68
+ "<|ba|>": 50355,
69
+ "<|be|>": 50330,
70
+ "<|bg|>": 50292,
71
+ "<|bn|>": 50302,
72
+ "<|bo|>": 50347,
73
+ "<|br|>": 50309,
74
+ "<|bs|>": 50315,
75
+ "<|ca|>": 50270,
76
+ "<|cs|>": 50283,
77
+ "<|cy|>": 50297,
78
+ "<|da|>": 50285,
79
+ "<|de|>": 50261,
80
+ "<|el|>": 50281,
81
+ "<|en|>": 50259,
82
+ "<|es|>": 50262,
83
+ "<|et|>": 50307,
84
+ "<|eu|>": 50310,
85
+ "<|fa|>": 50300,
86
+ "<|fi|>": 50277,
87
+ "<|fo|>": 50338,
88
+ "<|fr|>": 50265,
89
+ "<|gl|>": 50319,
90
+ "<|gu|>": 50333,
91
+ "<|haw|>": 50352,
92
+ "<|ha|>": 50354,
93
+ "<|he|>": 50279,
94
+ "<|hi|>": 50276,
95
+ "<|hr|>": 50291,
96
+ "<|ht|>": 50339,
97
+ "<|hu|>": 50286,
98
+ "<|hy|>": 50312,
99
+ "<|id|>": 50275,
100
+ "<|is|>": 50311,
101
+ "<|it|>": 50274,
102
+ "<|ja|>": 50266,
103
+ "<|jw|>": 50356,
104
+ "<|ka|>": 50329,
105
+ "<|kk|>": 50316,
106
+ "<|km|>": 50323,
107
+ "<|kn|>": 50306,
108
+ "<|ko|>": 50264,
109
+ "<|la|>": 50294,
110
+ "<|lb|>": 50345,
111
+ "<|ln|>": 50353,
112
+ "<|lo|>": 50336,
113
+ "<|lt|>": 50293,
114
+ "<|lv|>": 50301,
115
+ "<|mg|>": 50349,
116
+ "<|mi|>": 50295,
117
+ "<|mk|>": 50308,
118
+ "<|ml|>": 50296,
119
+ "<|mn|>": 50314,
120
+ "<|mr|>": 50320,
121
+ "<|ms|>": 50282,
122
+ "<|mt|>": 50343,
123
+ "<|my|>": 50346,
124
+ "<|ne|>": 50313,
125
+ "<|nl|>": 50271,
126
+ "<|nn|>": 50342,
127
+ "<|no|>": 50288,
128
+ "<|oc|>": 50328,
129
+ "<|pa|>": 50321,
130
+ "<|pl|>": 50269,
131
+ "<|ps|>": 50340,
132
+ "<|pt|>": 50267,
133
+ "<|ro|>": 50284,
134
+ "<|ru|>": 50263,
135
+ "<|sa|>": 50344,
136
+ "<|sd|>": 50332,
137
+ "<|si|>": 50322,
138
+ "<|sk|>": 50298,
139
+ "<|sl|>": 50305,
140
+ "<|sn|>": 50324,
141
+ "<|so|>": 50326,
142
+ "<|sq|>": 50317,
143
+ "<|sr|>": 50303,
144
+ "<|su|>": 50357,
145
+ "<|sv|>": 50273,
146
+ "<|sw|>": 50318,
147
+ "<|ta|>": 50287,
148
+ "<|te|>": 50299,
149
+ "<|tg|>": 50331,
150
+ "<|th|>": 50289,
151
+ "<|tk|>": 50341,
152
+ "<|tl|>": 50348,
153
+ "<|tr|>": 50268,
154
+ "<|tt|>": 50351,
155
+ "<|uk|>": 50280,
156
+ "<|ur|>": 50290,
157
+ "<|uz|>": 50337,
158
+ "<|vi|>": 50278,
159
+ "<|yi|>": 50335,
160
+ "<|yo|>": 50325,
161
+ "<|zh|>": 50260
162
+ },
163
+ "language": "ar",
164
+ "max_initial_timestamp_index": 50,
165
+ "max_length": 448,
166
+ "no_timestamps_token_id": 50363,
167
+ "pad_token_id": 50257,
168
+ "prev_sot_token_id": 50361,
169
+ "return_timestamps": false,
170
+ "suppress_tokens": [
171
+ 1,
172
+ 2,
173
+ 7,
174
+ 8,
175
+ 9,
176
+ 10,
177
+ 14,
178
+ 25,
179
+ 26,
180
+ 27,
181
+ 28,
182
+ 29,
183
+ 31,
184
+ 58,
185
+ 59,
186
+ 60,
187
+ 61,
188
+ 62,
189
+ 63,
190
+ 90,
191
+ 91,
192
+ 92,
193
+ 93,
194
+ 359,
195
+ 503,
196
+ 522,
197
+ 542,
198
+ 873,
199
+ 893,
200
+ 902,
201
+ 918,
202
+ 922,
203
+ 931,
204
+ 1350,
205
+ 1853,
206
+ 1982,
207
+ 2460,
208
+ 2627,
209
+ 3246,
210
+ 3253,
211
+ 3268,
212
+ 3536,
213
+ 3846,
214
+ 3961,
215
+ 4183,
216
+ 4667,
217
+ 6585,
218
+ 6647,
219
+ 7273,
220
+ 9061,
221
+ 9383,
222
+ 10428,
223
+ 10929,
224
+ 11938,
225
+ 12033,
226
+ 12331,
227
+ 12562,
228
+ 13793,
229
+ 14157,
230
+ 14635,
231
+ 15265,
232
+ 15618,
233
+ 16553,
234
+ 16604,
235
+ 18362,
236
+ 18956,
237
+ 20075,
238
+ 21675,
239
+ 22520,
240
+ 26130,
241
+ 26161,
242
+ 26435,
243
+ 28279,
244
+ 29464,
245
+ 31650,
246
+ 32302,
247
+ 32470,
248
+ 36865,
249
+ 42863,
250
+ 47425,
251
+ 49870,
252
+ 50254,
253
+ 50258,
254
+ 50358,
255
+ 50359,
256
+ 50360,
257
+ 50361,
258
+ 50362
259
+ ],
260
+ "task_to_id": {
261
+ "transcribe": 50359,
262
+ "translate": 50358
263
+ },
264
+ "transformers_version": "4.39.3"
265
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8bb247253ea2966a74a361343c73623842576618724c38cacd6fcd154ee80d4
3
+ size 966995080
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a346a133140db8307bd05d7ea49ab66dc641dd29674152401620a84b48b6e8b9
3
+ size 1925050668
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b5997bc4fdd29179b741a577f58e46867d294ae313d95d0c1425b3ce3869bc2
3
+ size 13990
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf786698b267e06674b8927eb6873f2d551ce11636290e5ddb5430fc024a0c9
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,501 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 69.88019949611805,
3
+ "best_model_checkpoint": "./whisper-small-dialect_maghrebi_seed84/checkpoint-750",
4
+ "epoch": 0.8987417615338527,
5
+ "eval_steps": 250,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 19.220966339111328,
14
+ "learning_rate": 5.000000000000001e-07,
15
+ "loss": 0.9005,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.03,
20
+ "grad_norm": 17.66954803466797,
21
+ "learning_rate": 1.0000000000000002e-06,
22
+ "loss": 0.8714,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.04,
27
+ "grad_norm": 17.077091217041016,
28
+ "learning_rate": 1.5e-06,
29
+ "loss": 0.8328,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.06,
34
+ "grad_norm": 16.432138442993164,
35
+ "learning_rate": 2.0000000000000003e-06,
36
+ "loss": 1.0755,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.07,
41
+ "grad_norm": 21.556360244750977,
42
+ "learning_rate": 2.5e-06,
43
+ "loss": 0.8058,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.09,
48
+ "grad_norm": 19.02596664428711,
49
+ "learning_rate": 3e-06,
50
+ "loss": 0.9495,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.1,
55
+ "grad_norm": 20.26993179321289,
56
+ "learning_rate": 3.5e-06,
57
+ "loss": 0.9317,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.12,
62
+ "grad_norm": 12.603343963623047,
63
+ "learning_rate": 4.000000000000001e-06,
64
+ "loss": 0.9204,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.13,
69
+ "grad_norm": 20.808399200439453,
70
+ "learning_rate": 4.5e-06,
71
+ "loss": 0.9252,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.15,
76
+ "grad_norm": 24.03095245361328,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.9429,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.15,
83
+ "eval_cer": 46.92968187777876,
84
+ "eval_loss": 0.9126096367835999,
85
+ "eval_runtime": 1678.9252,
86
+ "eval_samples_per_second": 1.988,
87
+ "eval_steps_per_second": 0.249,
88
+ "eval_wer": 69.91104941128079,
89
+ "step": 250
90
+ },
91
+ {
92
+ "epoch": 0.16,
93
+ "grad_norm": 19.214086532592773,
94
+ "learning_rate": 5.500000000000001e-06,
95
+ "loss": 0.9231,
96
+ "step": 275
97
+ },
98
+ {
99
+ "epoch": 0.18,
100
+ "grad_norm": 26.120920181274414,
101
+ "learning_rate": 6e-06,
102
+ "loss": 1.0259,
103
+ "step": 300
104
+ },
105
+ {
106
+ "epoch": 0.19,
107
+ "grad_norm": 25.76575469970703,
108
+ "learning_rate": 6.5000000000000004e-06,
109
+ "loss": 0.9332,
110
+ "step": 325
111
+ },
112
+ {
113
+ "epoch": 0.21,
114
+ "grad_norm": 21.174556732177734,
115
+ "learning_rate": 7e-06,
116
+ "loss": 0.8916,
117
+ "step": 350
118
+ },
119
+ {
120
+ "epoch": 0.22,
121
+ "grad_norm": 14.330324172973633,
122
+ "learning_rate": 7.500000000000001e-06,
123
+ "loss": 1.0117,
124
+ "step": 375
125
+ },
126
+ {
127
+ "epoch": 0.24,
128
+ "grad_norm": 19.678129196166992,
129
+ "learning_rate": 8.000000000000001e-06,
130
+ "loss": 0.9618,
131
+ "step": 400
132
+ },
133
+ {
134
+ "epoch": 0.25,
135
+ "grad_norm": 18.452356338500977,
136
+ "learning_rate": 8.5e-06,
137
+ "loss": 0.9955,
138
+ "step": 425
139
+ },
140
+ {
141
+ "epoch": 0.27,
142
+ "grad_norm": 23.46295166015625,
143
+ "learning_rate": 9e-06,
144
+ "loss": 1.1065,
145
+ "step": 450
146
+ },
147
+ {
148
+ "epoch": 0.28,
149
+ "grad_norm": 19.779064178466797,
150
+ "learning_rate": 9.5e-06,
151
+ "loss": 1.005,
152
+ "step": 475
153
+ },
154
+ {
155
+ "epoch": 0.3,
156
+ "grad_norm": 21.45060920715332,
157
+ "learning_rate": 1e-05,
158
+ "loss": 1.0113,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 0.3,
163
+ "eval_cer": 49.18029554707755,
164
+ "eval_loss": 0.9492183327674866,
165
+ "eval_runtime": 1704.5882,
166
+ "eval_samples_per_second": 1.958,
167
+ "eval_steps_per_second": 0.245,
168
+ "eval_wer": 74.3585788472415,
169
+ "step": 500
170
+ },
171
+ {
172
+ "epoch": 0.31,
173
+ "grad_norm": 19.71759796142578,
174
+ "learning_rate": 9.944444444444445e-06,
175
+ "loss": 0.949,
176
+ "step": 525
177
+ },
178
+ {
179
+ "epoch": 0.33,
180
+ "grad_norm": 25.79039192199707,
181
+ "learning_rate": 9.88888888888889e-06,
182
+ "loss": 0.8964,
183
+ "step": 550
184
+ },
185
+ {
186
+ "epoch": 0.34,
187
+ "grad_norm": 22.74810791015625,
188
+ "learning_rate": 9.833333333333333e-06,
189
+ "loss": 0.998,
190
+ "step": 575
191
+ },
192
+ {
193
+ "epoch": 0.36,
194
+ "grad_norm": 22.6362361907959,
195
+ "learning_rate": 9.777777777777779e-06,
196
+ "loss": 0.9873,
197
+ "step": 600
198
+ },
199
+ {
200
+ "epoch": 0.37,
201
+ "grad_norm": 18.466838836669922,
202
+ "learning_rate": 9.722222222222223e-06,
203
+ "loss": 0.9074,
204
+ "step": 625
205
+ },
206
+ {
207
+ "epoch": 0.39,
208
+ "grad_norm": 17.53104019165039,
209
+ "learning_rate": 9.666666666666667e-06,
210
+ "loss": 0.862,
211
+ "step": 650
212
+ },
213
+ {
214
+ "epoch": 0.4,
215
+ "grad_norm": 24.415746688842773,
216
+ "learning_rate": 9.611111111111112e-06,
217
+ "loss": 0.909,
218
+ "step": 675
219
+ },
220
+ {
221
+ "epoch": 0.42,
222
+ "grad_norm": 20.081430435180664,
223
+ "learning_rate": 9.555555555555556e-06,
224
+ "loss": 0.9771,
225
+ "step": 700
226
+ },
227
+ {
228
+ "epoch": 0.43,
229
+ "grad_norm": 16.662582397460938,
230
+ "learning_rate": 9.5e-06,
231
+ "loss": 0.9596,
232
+ "step": 725
233
+ },
234
+ {
235
+ "epoch": 0.45,
236
+ "grad_norm": 19.556798934936523,
237
+ "learning_rate": 9.444444444444445e-06,
238
+ "loss": 0.89,
239
+ "step": 750
240
+ },
241
+ {
242
+ "epoch": 0.45,
243
+ "eval_cer": 49.37844418813277,
244
+ "eval_loss": 0.9669607281684875,
245
+ "eval_runtime": 1709.3776,
246
+ "eval_samples_per_second": 1.953,
247
+ "eval_steps_per_second": 0.245,
248
+ "eval_wer": 69.88019949611805,
249
+ "step": 750
250
+ },
251
+ {
252
+ "epoch": 0.46,
253
+ "grad_norm": 17.074756622314453,
254
+ "learning_rate": 9.38888888888889e-06,
255
+ "loss": 0.8954,
256
+ "step": 775
257
+ },
258
+ {
259
+ "epoch": 0.48,
260
+ "grad_norm": 21.096834182739258,
261
+ "learning_rate": 9.333333333333334e-06,
262
+ "loss": 0.9173,
263
+ "step": 800
264
+ },
265
+ {
266
+ "epoch": 0.49,
267
+ "grad_norm": 24.211389541625977,
268
+ "learning_rate": 9.277777777777778e-06,
269
+ "loss": 1.1099,
270
+ "step": 825
271
+ },
272
+ {
273
+ "epoch": 0.51,
274
+ "grad_norm": 23.231773376464844,
275
+ "learning_rate": 9.222222222222224e-06,
276
+ "loss": 1.0465,
277
+ "step": 850
278
+ },
279
+ {
280
+ "epoch": 0.52,
281
+ "grad_norm": 16.78921890258789,
282
+ "learning_rate": 9.166666666666666e-06,
283
+ "loss": 0.8914,
284
+ "step": 875
285
+ },
286
+ {
287
+ "epoch": 0.54,
288
+ "grad_norm": 22.17947006225586,
289
+ "learning_rate": 9.111111111111112e-06,
290
+ "loss": 0.9389,
291
+ "step": 900
292
+ },
293
+ {
294
+ "epoch": 0.55,
295
+ "grad_norm": 18.280820846557617,
296
+ "learning_rate": 9.055555555555556e-06,
297
+ "loss": 0.9669,
298
+ "step": 925
299
+ },
300
+ {
301
+ "epoch": 0.57,
302
+ "grad_norm": 13.514604568481445,
303
+ "learning_rate": 9e-06,
304
+ "loss": 0.908,
305
+ "step": 950
306
+ },
307
+ {
308
+ "epoch": 0.58,
309
+ "grad_norm": 27.112810134887695,
310
+ "learning_rate": 8.944444444444446e-06,
311
+ "loss": 1.0055,
312
+ "step": 975
313
+ },
314
+ {
315
+ "epoch": 0.6,
316
+ "grad_norm": 19.524810791015625,
317
+ "learning_rate": 8.888888888888888e-06,
318
+ "loss": 0.9178,
319
+ "step": 1000
320
+ },
321
+ {
322
+ "epoch": 0.6,
323
+ "eval_cer": 55.686668835457766,
324
+ "eval_loss": 0.9589685201644897,
325
+ "eval_runtime": 1757.7978,
326
+ "eval_samples_per_second": 1.899,
327
+ "eval_steps_per_second": 0.238,
328
+ "eval_wer": 81.13013522546146,
329
+ "step": 1000
330
+ },
331
+ {
332
+ "epoch": 0.61,
333
+ "grad_norm": 20.15657615661621,
334
+ "learning_rate": 8.833333333333334e-06,
335
+ "loss": 0.9187,
336
+ "step": 1025
337
+ },
338
+ {
339
+ "epoch": 0.63,
340
+ "grad_norm": 15.911600112915039,
341
+ "learning_rate": 8.777777777777778e-06,
342
+ "loss": 0.9076,
343
+ "step": 1050
344
+ },
345
+ {
346
+ "epoch": 0.64,
347
+ "grad_norm": 28.166259765625,
348
+ "learning_rate": 8.722222222222224e-06,
349
+ "loss": 0.9496,
350
+ "step": 1075
351
+ },
352
+ {
353
+ "epoch": 0.66,
354
+ "grad_norm": 20.61066436767578,
355
+ "learning_rate": 8.666666666666668e-06,
356
+ "loss": 0.9898,
357
+ "step": 1100
358
+ },
359
+ {
360
+ "epoch": 0.67,
361
+ "grad_norm": 23.316091537475586,
362
+ "learning_rate": 8.611111111111112e-06,
363
+ "loss": 0.9375,
364
+ "step": 1125
365
+ },
366
+ {
367
+ "epoch": 0.69,
368
+ "grad_norm": 26.827373504638672,
369
+ "learning_rate": 8.555555555555556e-06,
370
+ "loss": 0.9523,
371
+ "step": 1150
372
+ },
373
+ {
374
+ "epoch": 0.7,
375
+ "grad_norm": 25.961198806762695,
376
+ "learning_rate": 8.5e-06,
377
+ "loss": 0.9358,
378
+ "step": 1175
379
+ },
380
+ {
381
+ "epoch": 0.72,
382
+ "grad_norm": 19.398683547973633,
383
+ "learning_rate": 8.444444444444446e-06,
384
+ "loss": 0.9371,
385
+ "step": 1200
386
+ },
387
+ {
388
+ "epoch": 0.73,
389
+ "grad_norm": 24.175716400146484,
390
+ "learning_rate": 8.38888888888889e-06,
391
+ "loss": 0.9249,
392
+ "step": 1225
393
+ },
394
+ {
395
+ "epoch": 0.75,
396
+ "grad_norm": 21.909639358520508,
397
+ "learning_rate": 8.333333333333334e-06,
398
+ "loss": 1.0317,
399
+ "step": 1250
400
+ },
401
+ {
402
+ "epoch": 0.75,
403
+ "eval_cer": 58.34639537061682,
404
+ "eval_loss": 0.9546337127685547,
405
+ "eval_runtime": 1825.9801,
406
+ "eval_samples_per_second": 1.828,
407
+ "eval_steps_per_second": 0.229,
408
+ "eval_wer": 77.47956193120469,
409
+ "step": 1250
410
+ },
411
+ {
412
+ "epoch": 0.76,
413
+ "grad_norm": 21.201881408691406,
414
+ "learning_rate": 8.277777777777778e-06,
415
+ "loss": 1.0033,
416
+ "step": 1275
417
+ },
418
+ {
419
+ "epoch": 0.78,
420
+ "grad_norm": 21.73763084411621,
421
+ "learning_rate": 8.222222222222222e-06,
422
+ "loss": 1.0113,
423
+ "step": 1300
424
+ },
425
+ {
426
+ "epoch": 0.79,
427
+ "grad_norm": 25.084646224975586,
428
+ "learning_rate": 8.166666666666668e-06,
429
+ "loss": 0.9414,
430
+ "step": 1325
431
+ },
432
+ {
433
+ "epoch": 0.81,
434
+ "grad_norm": 20.774850845336914,
435
+ "learning_rate": 8.111111111111112e-06,
436
+ "loss": 0.9428,
437
+ "step": 1350
438
+ },
439
+ {
440
+ "epoch": 0.82,
441
+ "grad_norm": 17.767702102661133,
442
+ "learning_rate": 8.055555555555557e-06,
443
+ "loss": 1.0388,
444
+ "step": 1375
445
+ },
446
+ {
447
+ "epoch": 0.84,
448
+ "grad_norm": 24.868619918823242,
449
+ "learning_rate": 8.000000000000001e-06,
450
+ "loss": 0.9034,
451
+ "step": 1400
452
+ },
453
+ {
454
+ "epoch": 0.85,
455
+ "grad_norm": 15.601224899291992,
456
+ "learning_rate": 7.944444444444445e-06,
457
+ "loss": 0.8871,
458
+ "step": 1425
459
+ },
460
+ {
461
+ "epoch": 0.87,
462
+ "grad_norm": 15.338399887084961,
463
+ "learning_rate": 7.88888888888889e-06,
464
+ "loss": 0.8334,
465
+ "step": 1450
466
+ },
467
+ {
468
+ "epoch": 0.88,
469
+ "grad_norm": 22.825489044189453,
470
+ "learning_rate": 7.833333333333333e-06,
471
+ "loss": 0.9114,
472
+ "step": 1475
473
+ },
474
+ {
475
+ "epoch": 0.9,
476
+ "grad_norm": 17.262100219726562,
477
+ "learning_rate": 7.77777777777778e-06,
478
+ "loss": 1.0252,
479
+ "step": 1500
480
+ },
481
+ {
482
+ "epoch": 0.9,
483
+ "eval_cer": 49.63278423486036,
484
+ "eval_loss": 0.9383214712142944,
485
+ "eval_runtime": 1684.5976,
486
+ "eval_samples_per_second": 1.981,
487
+ "eval_steps_per_second": 0.248,
488
+ "eval_wer": 71.67977788061083,
489
+ "step": 1500
490
+ }
491
+ ],
492
+ "logging_steps": 25,
493
+ "max_steps": 5000,
494
+ "num_input_tokens_seen": 0,
495
+ "num_train_epochs": 3,
496
+ "save_steps": 250,
497
+ "total_flos": 3.46302480384e+18,
498
+ "train_batch_size": 8,
499
+ "trial_name": null,
500
+ "trial_params": null
501
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3d4b38fee80e90795bb2ecab0c59f7951865310c5900082c9a6a58361ee550
3
+ size 5112