DazMashaly commited on
Commit
3ed624b
1 Parent(s): 70095f5

Upload folder

Browse files
checkpoint-1227/config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "DazMashaly/output",
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": 512,
17
+ "decoder_attention_heads": 8,
18
+ "decoder_ffn_dim": 2048,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 6,
21
+ "decoder_start_token_id": 50257,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 8,
24
+ "encoder_ffn_dim": 2048,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "mask_feature_length": 10,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "median_filter_width": 7,
54
+ "model_type": "whisper",
55
+ "num_hidden_layers": 6,
56
+ "num_mel_bins": 80,
57
+ "pad_token_id": 50257,
58
+ "scale_embedding": false,
59
+ "suppress_tokens": [
60
+ 1,
61
+ 2,
62
+ 7,
63
+ 8,
64
+ 9,
65
+ 10,
66
+ 14,
67
+ 25,
68
+ 26,
69
+ 27,
70
+ 28,
71
+ 29,
72
+ 31,
73
+ 58,
74
+ 59,
75
+ 60,
76
+ 61,
77
+ 62,
78
+ 63,
79
+ 90,
80
+ 91,
81
+ 92,
82
+ 93,
83
+ 359,
84
+ 503,
85
+ 522,
86
+ 542,
87
+ 873,
88
+ 893,
89
+ 902,
90
+ 918,
91
+ 922,
92
+ 931,
93
+ 1350,
94
+ 1853,
95
+ 1982,
96
+ 2460,
97
+ 2627,
98
+ 3246,
99
+ 3253,
100
+ 3268,
101
+ 3536,
102
+ 3846,
103
+ 3961,
104
+ 4183,
105
+ 4667,
106
+ 6585,
107
+ 6647,
108
+ 7273,
109
+ 9061,
110
+ 9383,
111
+ 10428,
112
+ 10929,
113
+ 11938,
114
+ 12033,
115
+ 12331,
116
+ 12562,
117
+ 13793,
118
+ 14157,
119
+ 14635,
120
+ 15265,
121
+ 15618,
122
+ 16553,
123
+ 16604,
124
+ 18362,
125
+ 18956,
126
+ 20075,
127
+ 21675,
128
+ 22520,
129
+ 26130,
130
+ 26161,
131
+ 26435,
132
+ 28279,
133
+ 29464,
134
+ 31650,
135
+ 32302,
136
+ 32470,
137
+ 36865,
138
+ 42863,
139
+ 47425,
140
+ 49870,
141
+ 50254,
142
+ 50258,
143
+ 50358,
144
+ 50359,
145
+ 50360,
146
+ 50361,
147
+ 50362
148
+ ],
149
+ "torch_dtype": "float32",
150
+ "transformers_version": "4.41.2",
151
+ "use_cache": true,
152
+ "use_weighted_layer_sum": false,
153
+ "vocab_size": 51865
154
+ }
checkpoint-1227/generation_config.json ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 3,
5
+ 1
6
+ ],
7
+ [
8
+ 4,
9
+ 2
10
+ ],
11
+ [
12
+ 4,
13
+ 3
14
+ ],
15
+ [
16
+ 4,
17
+ 7
18
+ ],
19
+ [
20
+ 5,
21
+ 1
22
+ ],
23
+ [
24
+ 5,
25
+ 2
26
+ ],
27
+ [
28
+ 5,
29
+ 4
30
+ ],
31
+ [
32
+ 5,
33
+ 6
34
+ ]
35
+ ],
36
+ "begin_suppress_tokens": [
37
+ 220,
38
+ 50257
39
+ ],
40
+ "bos_token_id": 50257,
41
+ "decoder_start_token_id": 50258,
42
+ "eos_token_id": 50257,
43
+ "is_multilingual": true,
44
+ "lang_to_id": {
45
+ "<|af|>": 50327,
46
+ "<|am|>": 50334,
47
+ "<|ar|>": 50272,
48
+ "<|as|>": 50350,
49
+ "<|az|>": 50304,
50
+ "<|ba|>": 50355,
51
+ "<|be|>": 50330,
52
+ "<|bg|>": 50292,
53
+ "<|bn|>": 50302,
54
+ "<|bo|>": 50347,
55
+ "<|br|>": 50309,
56
+ "<|bs|>": 50315,
57
+ "<|ca|>": 50270,
58
+ "<|cs|>": 50283,
59
+ "<|cy|>": 50297,
60
+ "<|da|>": 50285,
61
+ "<|de|>": 50261,
62
+ "<|el|>": 50281,
63
+ "<|en|>": 50259,
64
+ "<|es|>": 50262,
65
+ "<|et|>": 50307,
66
+ "<|eu|>": 50310,
67
+ "<|fa|>": 50300,
68
+ "<|fi|>": 50277,
69
+ "<|fo|>": 50338,
70
+ "<|fr|>": 50265,
71
+ "<|gl|>": 50319,
72
+ "<|gu|>": 50333,
73
+ "<|haw|>": 50352,
74
+ "<|ha|>": 50354,
75
+ "<|he|>": 50279,
76
+ "<|hi|>": 50276,
77
+ "<|hr|>": 50291,
78
+ "<|ht|>": 50339,
79
+ "<|hu|>": 50286,
80
+ "<|hy|>": 50312,
81
+ "<|id|>": 50275,
82
+ "<|is|>": 50311,
83
+ "<|it|>": 50274,
84
+ "<|ja|>": 50266,
85
+ "<|jw|>": 50356,
86
+ "<|ka|>": 50329,
87
+ "<|kk|>": 50316,
88
+ "<|km|>": 50323,
89
+ "<|kn|>": 50306,
90
+ "<|ko|>": 50264,
91
+ "<|la|>": 50294,
92
+ "<|lb|>": 50345,
93
+ "<|ln|>": 50353,
94
+ "<|lo|>": 50336,
95
+ "<|lt|>": 50293,
96
+ "<|lv|>": 50301,
97
+ "<|mg|>": 50349,
98
+ "<|mi|>": 50295,
99
+ "<|mk|>": 50308,
100
+ "<|ml|>": 50296,
101
+ "<|mn|>": 50314,
102
+ "<|mr|>": 50320,
103
+ "<|ms|>": 50282,
104
+ "<|mt|>": 50343,
105
+ "<|my|>": 50346,
106
+ "<|ne|>": 50313,
107
+ "<|nl|>": 50271,
108
+ "<|nn|>": 50342,
109
+ "<|no|>": 50288,
110
+ "<|oc|>": 50328,
111
+ "<|pa|>": 50321,
112
+ "<|pl|>": 50269,
113
+ "<|ps|>": 50340,
114
+ "<|pt|>": 50267,
115
+ "<|ro|>": 50284,
116
+ "<|ru|>": 50263,
117
+ "<|sa|>": 50344,
118
+ "<|sd|>": 50332,
119
+ "<|si|>": 50322,
120
+ "<|sk|>": 50298,
121
+ "<|sl|>": 50305,
122
+ "<|sn|>": 50324,
123
+ "<|so|>": 50326,
124
+ "<|sq|>": 50317,
125
+ "<|sr|>": 50303,
126
+ "<|su|>": 50357,
127
+ "<|sv|>": 50273,
128
+ "<|sw|>": 50318,
129
+ "<|ta|>": 50287,
130
+ "<|te|>": 50299,
131
+ "<|tg|>": 50331,
132
+ "<|th|>": 50289,
133
+ "<|tk|>": 50341,
134
+ "<|tl|>": 50348,
135
+ "<|tr|>": 50268,
136
+ "<|tt|>": 50351,
137
+ "<|uk|>": 50280,
138
+ "<|ur|>": 50290,
139
+ "<|uz|>": 50337,
140
+ "<|vi|>": 50278,
141
+ "<|yi|>": 50335,
142
+ "<|yo|>": 50325,
143
+ "<|zh|>": 50260
144
+ },
145
+ "language": "arabic",
146
+ "max_initial_timestamp_index": 50,
147
+ "max_length": 448,
148
+ "no_timestamps_token_id": 50363,
149
+ "pad_token_id": 50257,
150
+ "prev_sot_token_id": 50361,
151
+ "return_timestamps": false,
152
+ "suppress_tokens": [
153
+ 1,
154
+ 2,
155
+ 7,
156
+ 8,
157
+ 9,
158
+ 10,
159
+ 14,
160
+ 25,
161
+ 26,
162
+ 27,
163
+ 28,
164
+ 29,
165
+ 31,
166
+ 58,
167
+ 59,
168
+ 60,
169
+ 61,
170
+ 62,
171
+ 63,
172
+ 90,
173
+ 91,
174
+ 92,
175
+ 93,
176
+ 359,
177
+ 503,
178
+ 522,
179
+ 542,
180
+ 873,
181
+ 893,
182
+ 902,
183
+ 918,
184
+ 922,
185
+ 931,
186
+ 1350,
187
+ 1853,
188
+ 1982,
189
+ 2460,
190
+ 2627,
191
+ 3246,
192
+ 3253,
193
+ 3268,
194
+ 3536,
195
+ 3846,
196
+ 3961,
197
+ 4183,
198
+ 4667,
199
+ 6585,
200
+ 6647,
201
+ 7273,
202
+ 9061,
203
+ 9383,
204
+ 10428,
205
+ 10929,
206
+ 11938,
207
+ 12033,
208
+ 12331,
209
+ 12562,
210
+ 13793,
211
+ 14157,
212
+ 14635,
213
+ 15265,
214
+ 15618,
215
+ 16553,
216
+ 16604,
217
+ 18362,
218
+ 18956,
219
+ 20075,
220
+ 21675,
221
+ 22520,
222
+ 26130,
223
+ 26161,
224
+ 26435,
225
+ 28279,
226
+ 29464,
227
+ 31650,
228
+ 32302,
229
+ 32470,
230
+ 36865,
231
+ 42863,
232
+ 47425,
233
+ 49870,
234
+ 50254,
235
+ 50258,
236
+ 50358,
237
+ 50359,
238
+ 50360,
239
+ 50361,
240
+ 50362
241
+ ],
242
+ "task": "transcribe",
243
+ "task_to_id": {
244
+ "transcribe": 50359,
245
+ "translate": 50358
246
+ },
247
+ "transformers_version": "4.41.2"
248
+ }
checkpoint-1227/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ecb79dec746d356b98d4f6967a29618daef5f51ac96508ff6a0e203b5147557
3
+ size 290403936
checkpoint-1227/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a9b2c237af95ddb5f2afea12a15143335a6bf3cfc0b7e967e88f0fe16148503
3
+ size 574811514
checkpoint-1227/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
+ }
checkpoint-1227/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f765d5b40698951383e3834b380c6469bf09e3fc28e95cb3d663dedb8ba09ae
3
+ size 14244
checkpoint-1227/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5afe01bca8b9ffe0714ed30a6bcf0bbd5d5c3fa8011fcfff12daf668ef00bf34
3
+ size 1064
checkpoint-1227/trainer_state.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "DazMashaly/output/checkpoint-409",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1227,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.061124694376528114,
13
+ "grad_norm": 1.064210295677185,
14
+ "learning_rate": 5.000000000000001e-07,
15
+ "loss": 6.0673,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.12224938875305623,
20
+ "grad_norm": 0.982063889503479,
21
+ "learning_rate": 1.0000000000000002e-06,
22
+ "loss": 6.0659,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.18337408312958436,
27
+ "grad_norm": 0.9887572526931763,
28
+ "learning_rate": 1.5e-06,
29
+ "loss": 6.069,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.24449877750611246,
34
+ "grad_norm": 1.076440691947937,
35
+ "learning_rate": 2.0000000000000003e-06,
36
+ "loss": 6.0588,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.3056234718826406,
41
+ "grad_norm": 1.1176767349243164,
42
+ "learning_rate": 2.5e-06,
43
+ "loss": 6.0642,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.36674816625916873,
48
+ "grad_norm": 1.0234830379486084,
49
+ "learning_rate": 3e-06,
50
+ "loss": 6.0708,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.4278728606356968,
55
+ "grad_norm": 1.090944528579712,
56
+ "learning_rate": 3.5e-06,
57
+ "loss": 6.0339,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.4889975550122249,
62
+ "grad_norm": 1.1804206371307373,
63
+ "learning_rate": 4.000000000000001e-06,
64
+ "loss": 6.0542,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.5501222493887531,
69
+ "grad_norm": 1.3007625341415405,
70
+ "learning_rate": 4.5e-06,
71
+ "loss": 6.0549,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.6112469437652812,
76
+ "grad_norm": 1.2753345966339111,
77
+ "learning_rate": 5e-06,
78
+ "loss": 6.0535,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.6723716381418093,
83
+ "grad_norm": 1.321979284286499,
84
+ "learning_rate": 5.500000000000001e-06,
85
+ "loss": 6.0401,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.7334963325183375,
90
+ "grad_norm": 1.1843823194503784,
91
+ "learning_rate": 6e-06,
92
+ "loss": 6.0463,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.7946210268948656,
97
+ "grad_norm": 1.2534185647964478,
98
+ "learning_rate": 6.5000000000000004e-06,
99
+ "loss": 6.0248,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.8557457212713936,
104
+ "grad_norm": 1.2556980848312378,
105
+ "learning_rate": 7e-06,
106
+ "loss": 6.045,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.9168704156479217,
111
+ "grad_norm": 1.263355016708374,
112
+ "learning_rate": 7.500000000000001e-06,
113
+ "loss": 6.034,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.9779951100244498,
118
+ "grad_norm": 1.1825202703475952,
119
+ "learning_rate": 8.000000000000001e-06,
120
+ "loss": 5.9866,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 1.0,
125
+ "eval_cer": 1.0,
126
+ "eval_loss": 5.615485191345215,
127
+ "eval_runtime": 703.3832,
128
+ "eval_samples_per_second": 3.126,
129
+ "eval_steps_per_second": 0.026,
130
+ "eval_wer": 1.0,
131
+ "step": 409
132
+ },
133
+ {
134
+ "epoch": 1.039119804400978,
135
+ "grad_norm": 1.388098955154419,
136
+ "learning_rate": 8.5e-06,
137
+ "loss": 6.0005,
138
+ "step": 425
139
+ },
140
+ {
141
+ "epoch": 1.1002444987775062,
142
+ "grad_norm": 1.1844673156738281,
143
+ "learning_rate": 9e-06,
144
+ "loss": 5.9922,
145
+ "step": 450
146
+ },
147
+ {
148
+ "epoch": 1.1613691931540342,
149
+ "grad_norm": 1.2709770202636719,
150
+ "learning_rate": 9.5e-06,
151
+ "loss": 5.9917,
152
+ "step": 475
153
+ },
154
+ {
155
+ "epoch": 1.2224938875305624,
156
+ "grad_norm": 1.331032395362854,
157
+ "learning_rate": 1e-05,
158
+ "loss": 5.9767,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 1.2836185819070904,
163
+ "grad_norm": 1.436553955078125,
164
+ "learning_rate": 9.967447916666668e-06,
165
+ "loss": 5.984,
166
+ "step": 525
167
+ },
168
+ {
169
+ "epoch": 1.3447432762836184,
170
+ "grad_norm": 1.2195194959640503,
171
+ "learning_rate": 9.934895833333335e-06,
172
+ "loss": 5.9959,
173
+ "step": 550
174
+ },
175
+ {
176
+ "epoch": 1.4058679706601467,
177
+ "grad_norm": 1.265336036682129,
178
+ "learning_rate": 9.902343750000001e-06,
179
+ "loss": 5.9657,
180
+ "step": 575
181
+ },
182
+ {
183
+ "epoch": 1.466992665036675,
184
+ "grad_norm": 1.2491796016693115,
185
+ "learning_rate": 9.869791666666667e-06,
186
+ "loss": 5.9545,
187
+ "step": 600
188
+ },
189
+ {
190
+ "epoch": 1.528117359413203,
191
+ "grad_norm": 1.5214732885360718,
192
+ "learning_rate": 9.837239583333335e-06,
193
+ "loss": 5.9556,
194
+ "step": 625
195
+ },
196
+ {
197
+ "epoch": 1.589242053789731,
198
+ "grad_norm": 1.478154182434082,
199
+ "learning_rate": 9.8046875e-06,
200
+ "loss": 5.9557,
201
+ "step": 650
202
+ },
203
+ {
204
+ "epoch": 1.6503667481662592,
205
+ "grad_norm": 1.4325579404830933,
206
+ "learning_rate": 9.772135416666667e-06,
207
+ "loss": 5.9392,
208
+ "step": 675
209
+ },
210
+ {
211
+ "epoch": 1.7114914425427874,
212
+ "grad_norm": 1.258053183555603,
213
+ "learning_rate": 9.739583333333334e-06,
214
+ "loss": 5.9329,
215
+ "step": 700
216
+ },
217
+ {
218
+ "epoch": 1.7726161369193154,
219
+ "grad_norm": 1.439457893371582,
220
+ "learning_rate": 9.707031250000001e-06,
221
+ "loss": 5.9353,
222
+ "step": 725
223
+ },
224
+ {
225
+ "epoch": 1.8337408312958434,
226
+ "grad_norm": 2.1067497730255127,
227
+ "learning_rate": 9.674479166666668e-06,
228
+ "loss": 5.9253,
229
+ "step": 750
230
+ },
231
+ {
232
+ "epoch": 1.8948655256723717,
233
+ "grad_norm": 1.6002326011657715,
234
+ "learning_rate": 9.641927083333335e-06,
235
+ "loss": 5.8955,
236
+ "step": 775
237
+ },
238
+ {
239
+ "epoch": 1.9559902200488999,
240
+ "grad_norm": 1.249984622001648,
241
+ "learning_rate": 9.609375000000001e-06,
242
+ "loss": 5.8937,
243
+ "step": 800
244
+ },
245
+ {
246
+ "epoch": 2.0,
247
+ "eval_cer": 1.0,
248
+ "eval_loss": 5.5135722160339355,
249
+ "eval_runtime": 702.4432,
250
+ "eval_samples_per_second": 3.131,
251
+ "eval_steps_per_second": 0.026,
252
+ "eval_wer": 1.0,
253
+ "step": 818
254
+ },
255
+ {
256
+ "epoch": 2.0171149144254277,
257
+ "grad_norm": 1.5596375465393066,
258
+ "learning_rate": 9.576822916666667e-06,
259
+ "loss": 5.8783,
260
+ "step": 825
261
+ },
262
+ {
263
+ "epoch": 2.078239608801956,
264
+ "grad_norm": 1.5268152952194214,
265
+ "learning_rate": 9.544270833333335e-06,
266
+ "loss": 5.8633,
267
+ "step": 850
268
+ },
269
+ {
270
+ "epoch": 2.139364303178484,
271
+ "grad_norm": 1.8570572137832642,
272
+ "learning_rate": 9.51171875e-06,
273
+ "loss": 5.875,
274
+ "step": 875
275
+ },
276
+ {
277
+ "epoch": 2.2004889975550124,
278
+ "grad_norm": 1.7126903533935547,
279
+ "learning_rate": 9.479166666666667e-06,
280
+ "loss": 5.844,
281
+ "step": 900
282
+ },
283
+ {
284
+ "epoch": 2.26161369193154,
285
+ "grad_norm": 1.4625195264816284,
286
+ "learning_rate": 9.446614583333334e-06,
287
+ "loss": 5.8778,
288
+ "step": 925
289
+ },
290
+ {
291
+ "epoch": 2.3227383863080684,
292
+ "grad_norm": 1.4512864351272583,
293
+ "learning_rate": 9.414062500000001e-06,
294
+ "loss": 5.8592,
295
+ "step": 950
296
+ },
297
+ {
298
+ "epoch": 2.3838630806845966,
299
+ "grad_norm": 1.7913607358932495,
300
+ "learning_rate": 9.381510416666668e-06,
301
+ "loss": 5.8493,
302
+ "step": 975
303
+ },
304
+ {
305
+ "epoch": 2.444987775061125,
306
+ "grad_norm": 1.9679557085037231,
307
+ "learning_rate": 9.348958333333335e-06,
308
+ "loss": 5.8396,
309
+ "step": 1000
310
+ },
311
+ {
312
+ "epoch": 2.5061124694376526,
313
+ "grad_norm": 1.8194330930709839,
314
+ "learning_rate": 9.316406250000002e-06,
315
+ "loss": 5.8435,
316
+ "step": 1025
317
+ },
318
+ {
319
+ "epoch": 2.567237163814181,
320
+ "grad_norm": 1.9096548557281494,
321
+ "learning_rate": 9.283854166666667e-06,
322
+ "loss": 5.8206,
323
+ "step": 1050
324
+ },
325
+ {
326
+ "epoch": 2.628361858190709,
327
+ "grad_norm": 1.6974539756774902,
328
+ "learning_rate": 9.251302083333335e-06,
329
+ "loss": 5.8062,
330
+ "step": 1075
331
+ },
332
+ {
333
+ "epoch": 2.689486552567237,
334
+ "grad_norm": 1.7971349954605103,
335
+ "learning_rate": 9.21875e-06,
336
+ "loss": 5.8371,
337
+ "step": 1100
338
+ },
339
+ {
340
+ "epoch": 2.750611246943765,
341
+ "grad_norm": 1.5566753149032593,
342
+ "learning_rate": 9.186197916666667e-06,
343
+ "loss": 5.8337,
344
+ "step": 1125
345
+ },
346
+ {
347
+ "epoch": 2.8117359413202934,
348
+ "grad_norm": 1.7522369623184204,
349
+ "learning_rate": 9.153645833333334e-06,
350
+ "loss": 5.7644,
351
+ "step": 1150
352
+ },
353
+ {
354
+ "epoch": 2.8728606356968216,
355
+ "grad_norm": 1.545310378074646,
356
+ "learning_rate": 9.121093750000001e-06,
357
+ "loss": 5.7901,
358
+ "step": 1175
359
+ },
360
+ {
361
+ "epoch": 2.93398533007335,
362
+ "grad_norm": 1.4376916885375977,
363
+ "learning_rate": 9.088541666666666e-06,
364
+ "loss": 5.7892,
365
+ "step": 1200
366
+ },
367
+ {
368
+ "epoch": 2.9951100244498776,
369
+ "grad_norm": 1.7640162706375122,
370
+ "learning_rate": 9.055989583333335e-06,
371
+ "loss": 5.7924,
372
+ "step": 1225
373
+ },
374
+ {
375
+ "epoch": 3.0,
376
+ "eval_cer": 1.0,
377
+ "eval_loss": 5.430821895599365,
378
+ "eval_runtime": 955.8928,
379
+ "eval_samples_per_second": 2.3,
380
+ "eval_steps_per_second": 0.019,
381
+ "eval_wer": 1.0,
382
+ "step": 1227
383
+ }
384
+ ],
385
+ "logging_steps": 25,
386
+ "max_steps": 8180,
387
+ "num_input_tokens_seen": 0,
388
+ "num_train_epochs": 20,
389
+ "save_steps": 500,
390
+ "stateful_callbacks": {
391
+ "TrainerControl": {
392
+ "args": {
393
+ "should_epoch_stop": false,
394
+ "should_evaluate": false,
395
+ "should_log": false,
396
+ "should_save": true,
397
+ "should_training_stop": false
398
+ },
399
+ "attributes": {}
400
+ }
401
+ },
402
+ "total_flos": 9.8681241157632e+18,
403
+ "train_batch_size": 124,
404
+ "trial_name": null,
405
+ "trial_params": null
406
+ }
checkpoint-1227/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df180bbc58c0a7714e8beb26c654c1c1a085db2c02893349f4f27f5b8880fbe
3
+ size 5304
checkpoint-1636/config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "DazMashaly/output",
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": 512,
17
+ "decoder_attention_heads": 8,
18
+ "decoder_ffn_dim": 2048,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 6,
21
+ "decoder_start_token_id": 50257,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 8,
24
+ "encoder_ffn_dim": 2048,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "mask_feature_length": 10,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "median_filter_width": 7,
54
+ "model_type": "whisper",
55
+ "num_hidden_layers": 6,
56
+ "num_mel_bins": 80,
57
+ "pad_token_id": 50257,
58
+ "scale_embedding": false,
59
+ "suppress_tokens": [
60
+ 1,
61
+ 2,
62
+ 7,
63
+ 8,
64
+ 9,
65
+ 10,
66
+ 14,
67
+ 25,
68
+ 26,
69
+ 27,
70
+ 28,
71
+ 29,
72
+ 31,
73
+ 58,
74
+ 59,
75
+ 60,
76
+ 61,
77
+ 62,
78
+ 63,
79
+ 90,
80
+ 91,
81
+ 92,
82
+ 93,
83
+ 359,
84
+ 503,
85
+ 522,
86
+ 542,
87
+ 873,
88
+ 893,
89
+ 902,
90
+ 918,
91
+ 922,
92
+ 931,
93
+ 1350,
94
+ 1853,
95
+ 1982,
96
+ 2460,
97
+ 2627,
98
+ 3246,
99
+ 3253,
100
+ 3268,
101
+ 3536,
102
+ 3846,
103
+ 3961,
104
+ 4183,
105
+ 4667,
106
+ 6585,
107
+ 6647,
108
+ 7273,
109
+ 9061,
110
+ 9383,
111
+ 10428,
112
+ 10929,
113
+ 11938,
114
+ 12033,
115
+ 12331,
116
+ 12562,
117
+ 13793,
118
+ 14157,
119
+ 14635,
120
+ 15265,
121
+ 15618,
122
+ 16553,
123
+ 16604,
124
+ 18362,
125
+ 18956,
126
+ 20075,
127
+ 21675,
128
+ 22520,
129
+ 26130,
130
+ 26161,
131
+ 26435,
132
+ 28279,
133
+ 29464,
134
+ 31650,
135
+ 32302,
136
+ 32470,
137
+ 36865,
138
+ 42863,
139
+ 47425,
140
+ 49870,
141
+ 50254,
142
+ 50258,
143
+ 50358,
144
+ 50359,
145
+ 50360,
146
+ 50361,
147
+ 50362
148
+ ],
149
+ "torch_dtype": "float32",
150
+ "transformers_version": "4.41.2",
151
+ "use_cache": true,
152
+ "use_weighted_layer_sum": false,
153
+ "vocab_size": 51865
154
+ }
checkpoint-1636/generation_config.json ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 3,
5
+ 1
6
+ ],
7
+ [
8
+ 4,
9
+ 2
10
+ ],
11
+ [
12
+ 4,
13
+ 3
14
+ ],
15
+ [
16
+ 4,
17
+ 7
18
+ ],
19
+ [
20
+ 5,
21
+ 1
22
+ ],
23
+ [
24
+ 5,
25
+ 2
26
+ ],
27
+ [
28
+ 5,
29
+ 4
30
+ ],
31
+ [
32
+ 5,
33
+ 6
34
+ ]
35
+ ],
36
+ "begin_suppress_tokens": [
37
+ 220,
38
+ 50257
39
+ ],
40
+ "bos_token_id": 50257,
41
+ "decoder_start_token_id": 50258,
42
+ "eos_token_id": 50257,
43
+ "is_multilingual": true,
44
+ "lang_to_id": {
45
+ "<|af|>": 50327,
46
+ "<|am|>": 50334,
47
+ "<|ar|>": 50272,
48
+ "<|as|>": 50350,
49
+ "<|az|>": 50304,
50
+ "<|ba|>": 50355,
51
+ "<|be|>": 50330,
52
+ "<|bg|>": 50292,
53
+ "<|bn|>": 50302,
54
+ "<|bo|>": 50347,
55
+ "<|br|>": 50309,
56
+ "<|bs|>": 50315,
57
+ "<|ca|>": 50270,
58
+ "<|cs|>": 50283,
59
+ "<|cy|>": 50297,
60
+ "<|da|>": 50285,
61
+ "<|de|>": 50261,
62
+ "<|el|>": 50281,
63
+ "<|en|>": 50259,
64
+ "<|es|>": 50262,
65
+ "<|et|>": 50307,
66
+ "<|eu|>": 50310,
67
+ "<|fa|>": 50300,
68
+ "<|fi|>": 50277,
69
+ "<|fo|>": 50338,
70
+ "<|fr|>": 50265,
71
+ "<|gl|>": 50319,
72
+ "<|gu|>": 50333,
73
+ "<|haw|>": 50352,
74
+ "<|ha|>": 50354,
75
+ "<|he|>": 50279,
76
+ "<|hi|>": 50276,
77
+ "<|hr|>": 50291,
78
+ "<|ht|>": 50339,
79
+ "<|hu|>": 50286,
80
+ "<|hy|>": 50312,
81
+ "<|id|>": 50275,
82
+ "<|is|>": 50311,
83
+ "<|it|>": 50274,
84
+ "<|ja|>": 50266,
85
+ "<|jw|>": 50356,
86
+ "<|ka|>": 50329,
87
+ "<|kk|>": 50316,
88
+ "<|km|>": 50323,
89
+ "<|kn|>": 50306,
90
+ "<|ko|>": 50264,
91
+ "<|la|>": 50294,
92
+ "<|lb|>": 50345,
93
+ "<|ln|>": 50353,
94
+ "<|lo|>": 50336,
95
+ "<|lt|>": 50293,
96
+ "<|lv|>": 50301,
97
+ "<|mg|>": 50349,
98
+ "<|mi|>": 50295,
99
+ "<|mk|>": 50308,
100
+ "<|ml|>": 50296,
101
+ "<|mn|>": 50314,
102
+ "<|mr|>": 50320,
103
+ "<|ms|>": 50282,
104
+ "<|mt|>": 50343,
105
+ "<|my|>": 50346,
106
+ "<|ne|>": 50313,
107
+ "<|nl|>": 50271,
108
+ "<|nn|>": 50342,
109
+ "<|no|>": 50288,
110
+ "<|oc|>": 50328,
111
+ "<|pa|>": 50321,
112
+ "<|pl|>": 50269,
113
+ "<|ps|>": 50340,
114
+ "<|pt|>": 50267,
115
+ "<|ro|>": 50284,
116
+ "<|ru|>": 50263,
117
+ "<|sa|>": 50344,
118
+ "<|sd|>": 50332,
119
+ "<|si|>": 50322,
120
+ "<|sk|>": 50298,
121
+ "<|sl|>": 50305,
122
+ "<|sn|>": 50324,
123
+ "<|so|>": 50326,
124
+ "<|sq|>": 50317,
125
+ "<|sr|>": 50303,
126
+ "<|su|>": 50357,
127
+ "<|sv|>": 50273,
128
+ "<|sw|>": 50318,
129
+ "<|ta|>": 50287,
130
+ "<|te|>": 50299,
131
+ "<|tg|>": 50331,
132
+ "<|th|>": 50289,
133
+ "<|tk|>": 50341,
134
+ "<|tl|>": 50348,
135
+ "<|tr|>": 50268,
136
+ "<|tt|>": 50351,
137
+ "<|uk|>": 50280,
138
+ "<|ur|>": 50290,
139
+ "<|uz|>": 50337,
140
+ "<|vi|>": 50278,
141
+ "<|yi|>": 50335,
142
+ "<|yo|>": 50325,
143
+ "<|zh|>": 50260
144
+ },
145
+ "language": "arabic",
146
+ "max_initial_timestamp_index": 50,
147
+ "max_length": 448,
148
+ "no_timestamps_token_id": 50363,
149
+ "pad_token_id": 50257,
150
+ "prev_sot_token_id": 50361,
151
+ "return_timestamps": false,
152
+ "suppress_tokens": [
153
+ 1,
154
+ 2,
155
+ 7,
156
+ 8,
157
+ 9,
158
+ 10,
159
+ 14,
160
+ 25,
161
+ 26,
162
+ 27,
163
+ 28,
164
+ 29,
165
+ 31,
166
+ 58,
167
+ 59,
168
+ 60,
169
+ 61,
170
+ 62,
171
+ 63,
172
+ 90,
173
+ 91,
174
+ 92,
175
+ 93,
176
+ 359,
177
+ 503,
178
+ 522,
179
+ 542,
180
+ 873,
181
+ 893,
182
+ 902,
183
+ 918,
184
+ 922,
185
+ 931,
186
+ 1350,
187
+ 1853,
188
+ 1982,
189
+ 2460,
190
+ 2627,
191
+ 3246,
192
+ 3253,
193
+ 3268,
194
+ 3536,
195
+ 3846,
196
+ 3961,
197
+ 4183,
198
+ 4667,
199
+ 6585,
200
+ 6647,
201
+ 7273,
202
+ 9061,
203
+ 9383,
204
+ 10428,
205
+ 10929,
206
+ 11938,
207
+ 12033,
208
+ 12331,
209
+ 12562,
210
+ 13793,
211
+ 14157,
212
+ 14635,
213
+ 15265,
214
+ 15618,
215
+ 16553,
216
+ 16604,
217
+ 18362,
218
+ 18956,
219
+ 20075,
220
+ 21675,
221
+ 22520,
222
+ 26130,
223
+ 26161,
224
+ 26435,
225
+ 28279,
226
+ 29464,
227
+ 31650,
228
+ 32302,
229
+ 32470,
230
+ 36865,
231
+ 42863,
232
+ 47425,
233
+ 49870,
234
+ 50254,
235
+ 50258,
236
+ 50358,
237
+ 50359,
238
+ 50360,
239
+ 50361,
240
+ 50362
241
+ ],
242
+ "task": "transcribe",
243
+ "task_to_id": {
244
+ "transcribe": 50359,
245
+ "translate": 50358
246
+ },
247
+ "transformers_version": "4.41.2"
248
+ }
checkpoint-1636/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d40a88d9aea5347e48d396c7ecf3d905585f37ef00f55caf38a0f8035ae9b9e
3
+ size 290403936
checkpoint-1636/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51bcb5982674aeaa2f53ef8e4d2d7e3eac00d965d9e91934e9e8b174cffdb434
3
+ size 574811514
checkpoint-1636/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
+ }
checkpoint-1636/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e9e26ea2d09a64243386e8bfd739de5ce68566c07bb47fd0d758a598a4fb173
3
+ size 14244
checkpoint-1636/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf301cc108fc6c01b6912428f44159d353c4f523b541b1caac65cc83fe968fcf
3
+ size 1064
checkpoint-1636/trainer_state.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "DazMashaly/output/checkpoint-409",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1636,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.061124694376528114,
13
+ "grad_norm": 1.064210295677185,
14
+ "learning_rate": 5.000000000000001e-07,
15
+ "loss": 6.0673,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.12224938875305623,
20
+ "grad_norm": 0.982063889503479,
21
+ "learning_rate": 1.0000000000000002e-06,
22
+ "loss": 6.0659,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.18337408312958436,
27
+ "grad_norm": 0.9887572526931763,
28
+ "learning_rate": 1.5e-06,
29
+ "loss": 6.069,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.24449877750611246,
34
+ "grad_norm": 1.076440691947937,
35
+ "learning_rate": 2.0000000000000003e-06,
36
+ "loss": 6.0588,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.3056234718826406,
41
+ "grad_norm": 1.1176767349243164,
42
+ "learning_rate": 2.5e-06,
43
+ "loss": 6.0642,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.36674816625916873,
48
+ "grad_norm": 1.0234830379486084,
49
+ "learning_rate": 3e-06,
50
+ "loss": 6.0708,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.4278728606356968,
55
+ "grad_norm": 1.090944528579712,
56
+ "learning_rate": 3.5e-06,
57
+ "loss": 6.0339,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.4889975550122249,
62
+ "grad_norm": 1.1804206371307373,
63
+ "learning_rate": 4.000000000000001e-06,
64
+ "loss": 6.0542,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.5501222493887531,
69
+ "grad_norm": 1.3007625341415405,
70
+ "learning_rate": 4.5e-06,
71
+ "loss": 6.0549,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.6112469437652812,
76
+ "grad_norm": 1.2753345966339111,
77
+ "learning_rate": 5e-06,
78
+ "loss": 6.0535,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.6723716381418093,
83
+ "grad_norm": 1.321979284286499,
84
+ "learning_rate": 5.500000000000001e-06,
85
+ "loss": 6.0401,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.7334963325183375,
90
+ "grad_norm": 1.1843823194503784,
91
+ "learning_rate": 6e-06,
92
+ "loss": 6.0463,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.7946210268948656,
97
+ "grad_norm": 1.2534185647964478,
98
+ "learning_rate": 6.5000000000000004e-06,
99
+ "loss": 6.0248,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.8557457212713936,
104
+ "grad_norm": 1.2556980848312378,
105
+ "learning_rate": 7e-06,
106
+ "loss": 6.045,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.9168704156479217,
111
+ "grad_norm": 1.263355016708374,
112
+ "learning_rate": 7.500000000000001e-06,
113
+ "loss": 6.034,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.9779951100244498,
118
+ "grad_norm": 1.1825202703475952,
119
+ "learning_rate": 8.000000000000001e-06,
120
+ "loss": 5.9866,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 1.0,
125
+ "eval_cer": 1.0,
126
+ "eval_loss": 5.615485191345215,
127
+ "eval_runtime": 703.3832,
128
+ "eval_samples_per_second": 3.126,
129
+ "eval_steps_per_second": 0.026,
130
+ "eval_wer": 1.0,
131
+ "step": 409
132
+ },
133
+ {
134
+ "epoch": 1.039119804400978,
135
+ "grad_norm": 1.388098955154419,
136
+ "learning_rate": 8.5e-06,
137
+ "loss": 6.0005,
138
+ "step": 425
139
+ },
140
+ {
141
+ "epoch": 1.1002444987775062,
142
+ "grad_norm": 1.1844673156738281,
143
+ "learning_rate": 9e-06,
144
+ "loss": 5.9922,
145
+ "step": 450
146
+ },
147
+ {
148
+ "epoch": 1.1613691931540342,
149
+ "grad_norm": 1.2709770202636719,
150
+ "learning_rate": 9.5e-06,
151
+ "loss": 5.9917,
152
+ "step": 475
153
+ },
154
+ {
155
+ "epoch": 1.2224938875305624,
156
+ "grad_norm": 1.331032395362854,
157
+ "learning_rate": 1e-05,
158
+ "loss": 5.9767,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 1.2836185819070904,
163
+ "grad_norm": 1.436553955078125,
164
+ "learning_rate": 9.967447916666668e-06,
165
+ "loss": 5.984,
166
+ "step": 525
167
+ },
168
+ {
169
+ "epoch": 1.3447432762836184,
170
+ "grad_norm": 1.2195194959640503,
171
+ "learning_rate": 9.934895833333335e-06,
172
+ "loss": 5.9959,
173
+ "step": 550
174
+ },
175
+ {
176
+ "epoch": 1.4058679706601467,
177
+ "grad_norm": 1.265336036682129,
178
+ "learning_rate": 9.902343750000001e-06,
179
+ "loss": 5.9657,
180
+ "step": 575
181
+ },
182
+ {
183
+ "epoch": 1.466992665036675,
184
+ "grad_norm": 1.2491796016693115,
185
+ "learning_rate": 9.869791666666667e-06,
186
+ "loss": 5.9545,
187
+ "step": 600
188
+ },
189
+ {
190
+ "epoch": 1.528117359413203,
191
+ "grad_norm": 1.5214732885360718,
192
+ "learning_rate": 9.837239583333335e-06,
193
+ "loss": 5.9556,
194
+ "step": 625
195
+ },
196
+ {
197
+ "epoch": 1.589242053789731,
198
+ "grad_norm": 1.478154182434082,
199
+ "learning_rate": 9.8046875e-06,
200
+ "loss": 5.9557,
201
+ "step": 650
202
+ },
203
+ {
204
+ "epoch": 1.6503667481662592,
205
+ "grad_norm": 1.4325579404830933,
206
+ "learning_rate": 9.772135416666667e-06,
207
+ "loss": 5.9392,
208
+ "step": 675
209
+ },
210
+ {
211
+ "epoch": 1.7114914425427874,
212
+ "grad_norm": 1.258053183555603,
213
+ "learning_rate": 9.739583333333334e-06,
214
+ "loss": 5.9329,
215
+ "step": 700
216
+ },
217
+ {
218
+ "epoch": 1.7726161369193154,
219
+ "grad_norm": 1.439457893371582,
220
+ "learning_rate": 9.707031250000001e-06,
221
+ "loss": 5.9353,
222
+ "step": 725
223
+ },
224
+ {
225
+ "epoch": 1.8337408312958434,
226
+ "grad_norm": 2.1067497730255127,
227
+ "learning_rate": 9.674479166666668e-06,
228
+ "loss": 5.9253,
229
+ "step": 750
230
+ },
231
+ {
232
+ "epoch": 1.8948655256723717,
233
+ "grad_norm": 1.6002326011657715,
234
+ "learning_rate": 9.641927083333335e-06,
235
+ "loss": 5.8955,
236
+ "step": 775
237
+ },
238
+ {
239
+ "epoch": 1.9559902200488999,
240
+ "grad_norm": 1.249984622001648,
241
+ "learning_rate": 9.609375000000001e-06,
242
+ "loss": 5.8937,
243
+ "step": 800
244
+ },
245
+ {
246
+ "epoch": 2.0,
247
+ "eval_cer": 1.0,
248
+ "eval_loss": 5.5135722160339355,
249
+ "eval_runtime": 702.4432,
250
+ "eval_samples_per_second": 3.131,
251
+ "eval_steps_per_second": 0.026,
252
+ "eval_wer": 1.0,
253
+ "step": 818
254
+ },
255
+ {
256
+ "epoch": 2.0171149144254277,
257
+ "grad_norm": 1.5596375465393066,
258
+ "learning_rate": 9.576822916666667e-06,
259
+ "loss": 5.8783,
260
+ "step": 825
261
+ },
262
+ {
263
+ "epoch": 2.078239608801956,
264
+ "grad_norm": 1.5268152952194214,
265
+ "learning_rate": 9.544270833333335e-06,
266
+ "loss": 5.8633,
267
+ "step": 850
268
+ },
269
+ {
270
+ "epoch": 2.139364303178484,
271
+ "grad_norm": 1.8570572137832642,
272
+ "learning_rate": 9.51171875e-06,
273
+ "loss": 5.875,
274
+ "step": 875
275
+ },
276
+ {
277
+ "epoch": 2.2004889975550124,
278
+ "grad_norm": 1.7126903533935547,
279
+ "learning_rate": 9.479166666666667e-06,
280
+ "loss": 5.844,
281
+ "step": 900
282
+ },
283
+ {
284
+ "epoch": 2.26161369193154,
285
+ "grad_norm": 1.4625195264816284,
286
+ "learning_rate": 9.446614583333334e-06,
287
+ "loss": 5.8778,
288
+ "step": 925
289
+ },
290
+ {
291
+ "epoch": 2.3227383863080684,
292
+ "grad_norm": 1.4512864351272583,
293
+ "learning_rate": 9.414062500000001e-06,
294
+ "loss": 5.8592,
295
+ "step": 950
296
+ },
297
+ {
298
+ "epoch": 2.3838630806845966,
299
+ "grad_norm": 1.7913607358932495,
300
+ "learning_rate": 9.381510416666668e-06,
301
+ "loss": 5.8493,
302
+ "step": 975
303
+ },
304
+ {
305
+ "epoch": 2.444987775061125,
306
+ "grad_norm": 1.9679557085037231,
307
+ "learning_rate": 9.348958333333335e-06,
308
+ "loss": 5.8396,
309
+ "step": 1000
310
+ },
311
+ {
312
+ "epoch": 2.5061124694376526,
313
+ "grad_norm": 1.8194330930709839,
314
+ "learning_rate": 9.316406250000002e-06,
315
+ "loss": 5.8435,
316
+ "step": 1025
317
+ },
318
+ {
319
+ "epoch": 2.567237163814181,
320
+ "grad_norm": 1.9096548557281494,
321
+ "learning_rate": 9.283854166666667e-06,
322
+ "loss": 5.8206,
323
+ "step": 1050
324
+ },
325
+ {
326
+ "epoch": 2.628361858190709,
327
+ "grad_norm": 1.6974539756774902,
328
+ "learning_rate": 9.251302083333335e-06,
329
+ "loss": 5.8062,
330
+ "step": 1075
331
+ },
332
+ {
333
+ "epoch": 2.689486552567237,
334
+ "grad_norm": 1.7971349954605103,
335
+ "learning_rate": 9.21875e-06,
336
+ "loss": 5.8371,
337
+ "step": 1100
338
+ },
339
+ {
340
+ "epoch": 2.750611246943765,
341
+ "grad_norm": 1.5566753149032593,
342
+ "learning_rate": 9.186197916666667e-06,
343
+ "loss": 5.8337,
344
+ "step": 1125
345
+ },
346
+ {
347
+ "epoch": 2.8117359413202934,
348
+ "grad_norm": 1.7522369623184204,
349
+ "learning_rate": 9.153645833333334e-06,
350
+ "loss": 5.7644,
351
+ "step": 1150
352
+ },
353
+ {
354
+ "epoch": 2.8728606356968216,
355
+ "grad_norm": 1.545310378074646,
356
+ "learning_rate": 9.121093750000001e-06,
357
+ "loss": 5.7901,
358
+ "step": 1175
359
+ },
360
+ {
361
+ "epoch": 2.93398533007335,
362
+ "grad_norm": 1.4376916885375977,
363
+ "learning_rate": 9.088541666666666e-06,
364
+ "loss": 5.7892,
365
+ "step": 1200
366
+ },
367
+ {
368
+ "epoch": 2.9951100244498776,
369
+ "grad_norm": 1.7640162706375122,
370
+ "learning_rate": 9.055989583333335e-06,
371
+ "loss": 5.7924,
372
+ "step": 1225
373
+ },
374
+ {
375
+ "epoch": 3.0,
376
+ "eval_cer": 1.0,
377
+ "eval_loss": 5.430821895599365,
378
+ "eval_runtime": 955.8928,
379
+ "eval_samples_per_second": 2.3,
380
+ "eval_steps_per_second": 0.019,
381
+ "eval_wer": 1.0,
382
+ "step": 1227
383
+ },
384
+ {
385
+ "epoch": 3.056234718826406,
386
+ "grad_norm": 1.6651889085769653,
387
+ "learning_rate": 9.0234375e-06,
388
+ "loss": 5.778,
389
+ "step": 1250
390
+ },
391
+ {
392
+ "epoch": 3.117359413202934,
393
+ "grad_norm": 2.1398913860321045,
394
+ "learning_rate": 8.990885416666667e-06,
395
+ "loss": 5.75,
396
+ "step": 1275
397
+ },
398
+ {
399
+ "epoch": 3.178484107579462,
400
+ "grad_norm": 1.9647698402404785,
401
+ "learning_rate": 8.958333333333334e-06,
402
+ "loss": 5.7652,
403
+ "step": 1300
404
+ },
405
+ {
406
+ "epoch": 3.23960880195599,
407
+ "grad_norm": 1.7572517395019531,
408
+ "learning_rate": 8.92578125e-06,
409
+ "loss": 5.7267,
410
+ "step": 1325
411
+ },
412
+ {
413
+ "epoch": 3.3007334963325183,
414
+ "grad_norm": 2.1968727111816406,
415
+ "learning_rate": 8.893229166666667e-06,
416
+ "loss": 5.7432,
417
+ "step": 1350
418
+ },
419
+ {
420
+ "epoch": 3.3618581907090466,
421
+ "grad_norm": 1.857980728149414,
422
+ "learning_rate": 8.860677083333334e-06,
423
+ "loss": 5.7513,
424
+ "step": 1375
425
+ },
426
+ {
427
+ "epoch": 3.422982885085575,
428
+ "grad_norm": 1.9934026002883911,
429
+ "learning_rate": 8.828125000000001e-06,
430
+ "loss": 5.7348,
431
+ "step": 1400
432
+ },
433
+ {
434
+ "epoch": 3.4841075794621026,
435
+ "grad_norm": 2.0249619483947754,
436
+ "learning_rate": 8.795572916666666e-06,
437
+ "loss": 5.7324,
438
+ "step": 1425
439
+ },
440
+ {
441
+ "epoch": 3.545232273838631,
442
+ "grad_norm": 2.061025381088257,
443
+ "learning_rate": 8.763020833333335e-06,
444
+ "loss": 5.7322,
445
+ "step": 1450
446
+ },
447
+ {
448
+ "epoch": 3.606356968215159,
449
+ "grad_norm": 1.7257977724075317,
450
+ "learning_rate": 8.73046875e-06,
451
+ "loss": 5.7322,
452
+ "step": 1475
453
+ },
454
+ {
455
+ "epoch": 3.667481662591687,
456
+ "grad_norm": 1.7211699485778809,
457
+ "learning_rate": 8.697916666666667e-06,
458
+ "loss": 5.6969,
459
+ "step": 1500
460
+ },
461
+ {
462
+ "epoch": 3.728606356968215,
463
+ "grad_norm": 2.0788753032684326,
464
+ "learning_rate": 8.665364583333334e-06,
465
+ "loss": 5.7322,
466
+ "step": 1525
467
+ },
468
+ {
469
+ "epoch": 3.7897310513447433,
470
+ "grad_norm": 1.8665424585342407,
471
+ "learning_rate": 8.6328125e-06,
472
+ "loss": 5.7221,
473
+ "step": 1550
474
+ },
475
+ {
476
+ "epoch": 3.8508557457212715,
477
+ "grad_norm": 2.3112571239471436,
478
+ "learning_rate": 8.600260416666667e-06,
479
+ "loss": 5.6939,
480
+ "step": 1575
481
+ },
482
+ {
483
+ "epoch": 3.9119804400977998,
484
+ "grad_norm": 1.8274345397949219,
485
+ "learning_rate": 8.567708333333334e-06,
486
+ "loss": 5.6866,
487
+ "step": 1600
488
+ },
489
+ {
490
+ "epoch": 3.9731051344743276,
491
+ "grad_norm": 1.6363919973373413,
492
+ "learning_rate": 8.535156250000001e-06,
493
+ "loss": 5.7078,
494
+ "step": 1625
495
+ },
496
+ {
497
+ "epoch": 4.0,
498
+ "eval_cer": 1.0,
499
+ "eval_loss": 5.3543291091918945,
500
+ "eval_runtime": 973.8534,
501
+ "eval_samples_per_second": 2.258,
502
+ "eval_steps_per_second": 0.018,
503
+ "eval_wer": 1.0,
504
+ "step": 1636
505
+ }
506
+ ],
507
+ "logging_steps": 25,
508
+ "max_steps": 8180,
509
+ "num_input_tokens_seen": 0,
510
+ "num_train_epochs": 20,
511
+ "save_steps": 500,
512
+ "stateful_callbacks": {
513
+ "TrainerControl": {
514
+ "args": {
515
+ "should_epoch_stop": false,
516
+ "should_evaluate": false,
517
+ "should_log": false,
518
+ "should_save": true,
519
+ "should_training_stop": false
520
+ },
521
+ "attributes": {}
522
+ }
523
+ },
524
+ "total_flos": 1.31574988210176e+19,
525
+ "train_batch_size": 124,
526
+ "trial_name": null,
527
+ "trial_params": null
528
+ }
checkpoint-1636/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df180bbc58c0a7714e8beb26c654c1c1a085db2c02893349f4f27f5b8880fbe
3
+ size 5304
runs/Jun24_17-32-55_72b34f4b466c/events.out.tfevents.1719250652.72b34f4b466c.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f967a05fe317b70253fadb4fd16af18fb606b3fbf8277839fbcf2119ab341d24
3
+ size 17485