DazMashaly commited on
Commit
de73430
1 Parent(s): 55e5ac6

Upload folder

Browse files
checkpoint-3272/config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/kaggle/working/new_downloads/checkpoint-2863",
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-3272/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-3272/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8124c8d6c03c126791fc8f24ff4d462f908c3adca338a6ada1e7150d231a6e03
3
+ size 290403936
checkpoint-3272/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b183db398f676b59d139cb3de636542ff145799ad00888d39a36964806b577
3
+ size 574811514
checkpoint-3272/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-3272/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4510e82d4db5b0ca4d6517fce88dca6f1006dc0efe4ab2bd99bf62b073317a8e
3
+ size 14244
checkpoint-3272/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea2df03a7482ef1d12e91caa9dda9ccab057f5da344ec6da732dffbae85520d
3
+ size 1064
checkpoint-3272/trainer_state.json ADDED
@@ -0,0 +1,1023 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "DazMashaly/output/checkpoint-409",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3272,
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
+ "epoch": 4.034229828850855,
508
+ "grad_norm": 1.8639775514602661,
509
+ "learning_rate": 8.502604166666666e-06,
510
+ "loss": 5.684,
511
+ "step": 1650
512
+ },
513
+ {
514
+ "epoch": 4.095354523227384,
515
+ "grad_norm": 1.908738613128662,
516
+ "learning_rate": 8.470052083333335e-06,
517
+ "loss": 5.6709,
518
+ "step": 1675
519
+ },
520
+ {
521
+ "epoch": 4.156479217603912,
522
+ "grad_norm": 1.785302996635437,
523
+ "learning_rate": 8.4375e-06,
524
+ "loss": 5.6488,
525
+ "step": 1700
526
+ },
527
+ {
528
+ "epoch": 4.21760391198044,
529
+ "grad_norm": 2.2629177570343018,
530
+ "learning_rate": 8.404947916666667e-06,
531
+ "loss": 5.6633,
532
+ "step": 1725
533
+ },
534
+ {
535
+ "epoch": 4.278728606356968,
536
+ "grad_norm": 2.158043384552002,
537
+ "learning_rate": 8.372395833333334e-06,
538
+ "loss": 5.6558,
539
+ "step": 1750
540
+ },
541
+ {
542
+ "epoch": 4.3398533007334965,
543
+ "grad_norm": 2.032712936401367,
544
+ "learning_rate": 8.33984375e-06,
545
+ "loss": 5.661,
546
+ "step": 1775
547
+ },
548
+ {
549
+ "epoch": 4.400977995110025,
550
+ "grad_norm": 2.150649070739746,
551
+ "learning_rate": 8.307291666666668e-06,
552
+ "loss": 5.6587,
553
+ "step": 1800
554
+ },
555
+ {
556
+ "epoch": 4.462102689486553,
557
+ "grad_norm": 1.866034746170044,
558
+ "learning_rate": 8.274739583333334e-06,
559
+ "loss": 5.6306,
560
+ "step": 1825
561
+ },
562
+ {
563
+ "epoch": 4.52322738386308,
564
+ "grad_norm": 2.2522027492523193,
565
+ "learning_rate": 8.242187500000001e-06,
566
+ "loss": 5.6434,
567
+ "step": 1850
568
+ },
569
+ {
570
+ "epoch": 4.5843520782396086,
571
+ "grad_norm": 2.266977071762085,
572
+ "learning_rate": 8.209635416666666e-06,
573
+ "loss": 5.6378,
574
+ "step": 1875
575
+ },
576
+ {
577
+ "epoch": 4.645476772616137,
578
+ "grad_norm": 2.038745164871216,
579
+ "learning_rate": 8.177083333333335e-06,
580
+ "loss": 5.6404,
581
+ "step": 1900
582
+ },
583
+ {
584
+ "epoch": 4.706601466992665,
585
+ "grad_norm": 1.8621001243591309,
586
+ "learning_rate": 8.14453125e-06,
587
+ "loss": 5.651,
588
+ "step": 1925
589
+ },
590
+ {
591
+ "epoch": 4.767726161369193,
592
+ "grad_norm": 1.8880043029785156,
593
+ "learning_rate": 8.111979166666667e-06,
594
+ "loss": 5.6317,
595
+ "step": 1950
596
+ },
597
+ {
598
+ "epoch": 4.8288508557457215,
599
+ "grad_norm": 1.8351385593414307,
600
+ "learning_rate": 8.079427083333334e-06,
601
+ "loss": 5.5911,
602
+ "step": 1975
603
+ },
604
+ {
605
+ "epoch": 4.88997555012225,
606
+ "grad_norm": 1.9690709114074707,
607
+ "learning_rate": 8.046875e-06,
608
+ "loss": 5.6174,
609
+ "step": 2000
610
+ },
611
+ {
612
+ "epoch": 4.951100244498777,
613
+ "grad_norm": 1.8599187135696411,
614
+ "learning_rate": 8.014322916666668e-06,
615
+ "loss": 5.6252,
616
+ "step": 2025
617
+ },
618
+ {
619
+ "epoch": 5.0,
620
+ "eval_cer": 1.0,
621
+ "eval_loss": 5.2904744148254395,
622
+ "eval_runtime": 980.786,
623
+ "eval_samples_per_second": 2.242,
624
+ "eval_steps_per_second": 0.018,
625
+ "eval_wer": 1.0,
626
+ "step": 2045
627
+ },
628
+ {
629
+ "epoch": 5.012224938875305,
630
+ "grad_norm": 2.098679780960083,
631
+ "learning_rate": 7.981770833333335e-06,
632
+ "loss": 5.5864,
633
+ "step": 2050
634
+ },
635
+ {
636
+ "epoch": 5.0733496332518335,
637
+ "grad_norm": 2.3753552436828613,
638
+ "learning_rate": 7.949218750000001e-06,
639
+ "loss": 5.5792,
640
+ "step": 2075
641
+ },
642
+ {
643
+ "epoch": 5.134474327628362,
644
+ "grad_norm": 2.645547866821289,
645
+ "learning_rate": 7.916666666666667e-06,
646
+ "loss": 5.5911,
647
+ "step": 2100
648
+ },
649
+ {
650
+ "epoch": 5.19559902200489,
651
+ "grad_norm": 2.3270106315612793,
652
+ "learning_rate": 7.884114583333335e-06,
653
+ "loss": 5.6018,
654
+ "step": 2125
655
+ },
656
+ {
657
+ "epoch": 5.256723716381418,
658
+ "grad_norm": 1.961776852607727,
659
+ "learning_rate": 7.8515625e-06,
660
+ "loss": 5.5717,
661
+ "step": 2150
662
+ },
663
+ {
664
+ "epoch": 5.3178484107579465,
665
+ "grad_norm": 2.229034662246704,
666
+ "learning_rate": 7.819010416666667e-06,
667
+ "loss": 5.5855,
668
+ "step": 2175
669
+ },
670
+ {
671
+ "epoch": 5.378973105134475,
672
+ "grad_norm": 2.431147575378418,
673
+ "learning_rate": 7.786458333333334e-06,
674
+ "loss": 5.5863,
675
+ "step": 2200
676
+ },
677
+ {
678
+ "epoch": 5.440097799511002,
679
+ "grad_norm": 2.657665967941284,
680
+ "learning_rate": 7.753906250000001e-06,
681
+ "loss": 5.5782,
682
+ "step": 2225
683
+ },
684
+ {
685
+ "epoch": 5.50122249388753,
686
+ "grad_norm": 1.991417646408081,
687
+ "learning_rate": 7.721354166666668e-06,
688
+ "loss": 5.5418,
689
+ "step": 2250
690
+ },
691
+ {
692
+ "epoch": 5.5623471882640585,
693
+ "grad_norm": 2.1882779598236084,
694
+ "learning_rate": 7.688802083333335e-06,
695
+ "loss": 5.5776,
696
+ "step": 2275
697
+ },
698
+ {
699
+ "epoch": 5.623471882640587,
700
+ "grad_norm": 1.843143343925476,
701
+ "learning_rate": 7.656250000000001e-06,
702
+ "loss": 5.588,
703
+ "step": 2300
704
+ },
705
+ {
706
+ "epoch": 5.684596577017115,
707
+ "grad_norm": 2.3870656490325928,
708
+ "learning_rate": 7.623697916666667e-06,
709
+ "loss": 5.5632,
710
+ "step": 2325
711
+ },
712
+ {
713
+ "epoch": 5.745721271393643,
714
+ "grad_norm": 2.0239953994750977,
715
+ "learning_rate": 7.591145833333334e-06,
716
+ "loss": 5.5445,
717
+ "step": 2350
718
+ },
719
+ {
720
+ "epoch": 5.806845965770171,
721
+ "grad_norm": 2.3642804622650146,
722
+ "learning_rate": 7.55859375e-06,
723
+ "loss": 5.5608,
724
+ "step": 2375
725
+ },
726
+ {
727
+ "epoch": 5.8679706601467,
728
+ "grad_norm": 3.237014055252075,
729
+ "learning_rate": 7.526041666666667e-06,
730
+ "loss": 5.5308,
731
+ "step": 2400
732
+ },
733
+ {
734
+ "epoch": 5.929095354523227,
735
+ "grad_norm": 2.084507942199707,
736
+ "learning_rate": 7.493489583333334e-06,
737
+ "loss": 5.5418,
738
+ "step": 2425
739
+ },
740
+ {
741
+ "epoch": 5.990220048899755,
742
+ "grad_norm": 1.9642763137817383,
743
+ "learning_rate": 7.460937500000001e-06,
744
+ "loss": 5.5532,
745
+ "step": 2450
746
+ },
747
+ {
748
+ "epoch": 6.0,
749
+ "eval_cer": 1.0,
750
+ "eval_loss": 5.23870325088501,
751
+ "eval_runtime": 909.9853,
752
+ "eval_samples_per_second": 2.417,
753
+ "eval_steps_per_second": 0.02,
754
+ "eval_wer": 1.0,
755
+ "step": 2454
756
+ },
757
+ {
758
+ "epoch": 6.0513447432762835,
759
+ "grad_norm": 2.086639404296875,
760
+ "learning_rate": 7.428385416666667e-06,
761
+ "loss": 5.5231,
762
+ "step": 2475
763
+ },
764
+ {
765
+ "epoch": 6.112469437652812,
766
+ "grad_norm": 1.9924498796463013,
767
+ "learning_rate": 7.395833333333335e-06,
768
+ "loss": 5.5191,
769
+ "step": 2500
770
+ },
771
+ {
772
+ "epoch": 6.17359413202934,
773
+ "grad_norm": 2.331226348876953,
774
+ "learning_rate": 7.363281250000001e-06,
775
+ "loss": 5.5092,
776
+ "step": 2525
777
+ },
778
+ {
779
+ "epoch": 6.234718826405868,
780
+ "grad_norm": 2.276024580001831,
781
+ "learning_rate": 7.330729166666667e-06,
782
+ "loss": 5.5208,
783
+ "step": 2550
784
+ },
785
+ {
786
+ "epoch": 6.295843520782396,
787
+ "grad_norm": 2.2748773097991943,
788
+ "learning_rate": 7.298177083333334e-06,
789
+ "loss": 5.5241,
790
+ "step": 2575
791
+ },
792
+ {
793
+ "epoch": 6.356968215158924,
794
+ "grad_norm": 2.164454460144043,
795
+ "learning_rate": 7.265625e-06,
796
+ "loss": 5.4821,
797
+ "step": 2600
798
+ },
799
+ {
800
+ "epoch": 6.418092909535452,
801
+ "grad_norm": 2.0158824920654297,
802
+ "learning_rate": 7.233072916666667e-06,
803
+ "loss": 5.5143,
804
+ "step": 2625
805
+ },
806
+ {
807
+ "epoch": 6.47921760391198,
808
+ "grad_norm": 2.3213398456573486,
809
+ "learning_rate": 7.200520833333334e-06,
810
+ "loss": 5.5244,
811
+ "step": 2650
812
+ },
813
+ {
814
+ "epoch": 6.540342298288508,
815
+ "grad_norm": 3.5166070461273193,
816
+ "learning_rate": 7.16796875e-06,
817
+ "loss": 5.5251,
818
+ "step": 2675
819
+ },
820
+ {
821
+ "epoch": 6.601466992665037,
822
+ "grad_norm": 2.501091480255127,
823
+ "learning_rate": 7.135416666666667e-06,
824
+ "loss": 5.5072,
825
+ "step": 2700
826
+ },
827
+ {
828
+ "epoch": 6.662591687041565,
829
+ "grad_norm": 2.1940529346466064,
830
+ "learning_rate": 7.102864583333334e-06,
831
+ "loss": 5.5146,
832
+ "step": 2725
833
+ },
834
+ {
835
+ "epoch": 6.723716381418093,
836
+ "grad_norm": 2.563851833343506,
837
+ "learning_rate": 7.070312500000001e-06,
838
+ "loss": 5.4957,
839
+ "step": 2750
840
+ },
841
+ {
842
+ "epoch": 6.784841075794621,
843
+ "grad_norm": 2.2761764526367188,
844
+ "learning_rate": 7.037760416666667e-06,
845
+ "loss": 5.4873,
846
+ "step": 2775
847
+ },
848
+ {
849
+ "epoch": 6.84596577017115,
850
+ "grad_norm": 2.4268720149993896,
851
+ "learning_rate": 7.0052083333333345e-06,
852
+ "loss": 5.4818,
853
+ "step": 2800
854
+ },
855
+ {
856
+ "epoch": 6.907090464547677,
857
+ "grad_norm": 2.075167179107666,
858
+ "learning_rate": 6.9726562500000005e-06,
859
+ "loss": 5.517,
860
+ "step": 2825
861
+ },
862
+ {
863
+ "epoch": 6.968215158924205,
864
+ "grad_norm": 2.1719608306884766,
865
+ "learning_rate": 6.9401041666666665e-06,
866
+ "loss": 5.485,
867
+ "step": 2850
868
+ },
869
+ {
870
+ "epoch": 7.0,
871
+ "eval_cer": 1.0,
872
+ "eval_loss": 5.207675457000732,
873
+ "eval_runtime": 852.4911,
874
+ "eval_samples_per_second": 2.579,
875
+ "eval_steps_per_second": 0.021,
876
+ "eval_wer": 1.0,
877
+ "step": 2863
878
+ },
879
+ {
880
+ "epoch": 7.029339853300733,
881
+ "grad_norm": 1.9253339767456055,
882
+ "learning_rate": 6.907552083333334e-06,
883
+ "loss": 5.4902,
884
+ "step": 2875
885
+ },
886
+ {
887
+ "epoch": 7.090464547677262,
888
+ "grad_norm": 2.6965110301971436,
889
+ "learning_rate": 6.875e-06,
890
+ "loss": 5.4694,
891
+ "step": 2900
892
+ },
893
+ {
894
+ "epoch": 7.15158924205379,
895
+ "grad_norm": 3.292003870010376,
896
+ "learning_rate": 6.842447916666667e-06,
897
+ "loss": 5.457,
898
+ "step": 2925
899
+ },
900
+ {
901
+ "epoch": 7.212713936430318,
902
+ "grad_norm": 3.321614980697632,
903
+ "learning_rate": 6.809895833333334e-06,
904
+ "loss": 5.475,
905
+ "step": 2950
906
+ },
907
+ {
908
+ "epoch": 7.273838630806846,
909
+ "grad_norm": 2.9773731231689453,
910
+ "learning_rate": 6.777343750000001e-06,
911
+ "loss": 5.4533,
912
+ "step": 2975
913
+ },
914
+ {
915
+ "epoch": 7.334963325183374,
916
+ "grad_norm": 2.3799688816070557,
917
+ "learning_rate": 6.744791666666667e-06,
918
+ "loss": 5.4699,
919
+ "step": 3000
920
+ },
921
+ {
922
+ "epoch": 7.396088019559902,
923
+ "grad_norm": 2.3236491680145264,
924
+ "learning_rate": 6.7122395833333346e-06,
925
+ "loss": 5.4694,
926
+ "step": 3025
927
+ },
928
+ {
929
+ "epoch": 7.45721271393643,
930
+ "grad_norm": 2.295271635055542,
931
+ "learning_rate": 6.679687500000001e-06,
932
+ "loss": 5.4637,
933
+ "step": 3050
934
+ },
935
+ {
936
+ "epoch": 7.518337408312958,
937
+ "grad_norm": 2.130282402038574,
938
+ "learning_rate": 6.647135416666667e-06,
939
+ "loss": 5.4752,
940
+ "step": 3075
941
+ },
942
+ {
943
+ "epoch": 7.579462102689487,
944
+ "grad_norm": 2.148224115371704,
945
+ "learning_rate": 6.614583333333334e-06,
946
+ "loss": 5.4303,
947
+ "step": 3100
948
+ },
949
+ {
950
+ "epoch": 7.640586797066015,
951
+ "grad_norm": 2.275786876678467,
952
+ "learning_rate": 6.58203125e-06,
953
+ "loss": 5.4389,
954
+ "step": 3125
955
+ },
956
+ {
957
+ "epoch": 7.701711491442543,
958
+ "grad_norm": 2.203730583190918,
959
+ "learning_rate": 6.549479166666667e-06,
960
+ "loss": 5.4531,
961
+ "step": 3150
962
+ },
963
+ {
964
+ "epoch": 7.76283618581907,
965
+ "grad_norm": 2.1406664848327637,
966
+ "learning_rate": 6.516927083333334e-06,
967
+ "loss": 5.4607,
968
+ "step": 3175
969
+ },
970
+ {
971
+ "epoch": 7.823960880195599,
972
+ "grad_norm": 2.7617645263671875,
973
+ "learning_rate": 6.484375000000001e-06,
974
+ "loss": 5.4426,
975
+ "step": 3200
976
+ },
977
+ {
978
+ "epoch": 7.885085574572127,
979
+ "grad_norm": 2.337761878967285,
980
+ "learning_rate": 6.451822916666667e-06,
981
+ "loss": 5.453,
982
+ "step": 3225
983
+ },
984
+ {
985
+ "epoch": 7.946210268948655,
986
+ "grad_norm": 2.157966375350952,
987
+ "learning_rate": 6.419270833333335e-06,
988
+ "loss": 5.4253,
989
+ "step": 3250
990
+ },
991
+ {
992
+ "epoch": 8.0,
993
+ "eval_cer": 1.0,
994
+ "eval_loss": 5.176779747009277,
995
+ "eval_runtime": 850.0532,
996
+ "eval_samples_per_second": 2.587,
997
+ "eval_steps_per_second": 0.021,
998
+ "eval_wer": 1.0,
999
+ "step": 3272
1000
+ }
1001
+ ],
1002
+ "logging_steps": 25,
1003
+ "max_steps": 8180,
1004
+ "num_input_tokens_seen": 0,
1005
+ "num_train_epochs": 20,
1006
+ "save_steps": 500,
1007
+ "stateful_callbacks": {
1008
+ "TrainerControl": {
1009
+ "args": {
1010
+ "should_epoch_stop": false,
1011
+ "should_evaluate": false,
1012
+ "should_log": false,
1013
+ "should_save": true,
1014
+ "should_training_stop": false
1015
+ },
1016
+ "attributes": {}
1017
+ }
1018
+ },
1019
+ "total_flos": 2.63149976420352e+19,
1020
+ "train_batch_size": 124,
1021
+ "trial_name": null,
1022
+ "trial_params": null
1023
+ }
checkpoint-3272/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32fd048d0fc7461f5c6f38ce39faa81e6f5f8b3ff36cd5081d0ac78893e55ebc
3
+ size 5304
checkpoint-3681/config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/kaggle/working/new_downloads/checkpoint-2863",
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-3681/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-3681/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6716ac010719c2ff3113a52749eb5d2dd8206dd4e4af95288d80f568980d8237
3
+ size 290403936
checkpoint-3681/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6c3a4e705a6827db729d5fffa82ab9dedf5a967efd316ed74c9f04e2be79ad
3
+ size 574811514
checkpoint-3681/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-3681/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ff420fcbdd1b957ac927c9c931f84ff701cce3559fa048e9902f553af95cd2
3
+ size 14244
checkpoint-3681/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d700084a85970fcc0f69f5da248d787f3e30d3cfc3098ee52750f78e6415319
3
+ size 1064
checkpoint-3681/trainer_state.json ADDED
@@ -0,0 +1,1152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "DazMashaly/output/checkpoint-409",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3681,
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
+ "epoch": 4.034229828850855,
508
+ "grad_norm": 1.8639775514602661,
509
+ "learning_rate": 8.502604166666666e-06,
510
+ "loss": 5.684,
511
+ "step": 1650
512
+ },
513
+ {
514
+ "epoch": 4.095354523227384,
515
+ "grad_norm": 1.908738613128662,
516
+ "learning_rate": 8.470052083333335e-06,
517
+ "loss": 5.6709,
518
+ "step": 1675
519
+ },
520
+ {
521
+ "epoch": 4.156479217603912,
522
+ "grad_norm": 1.785302996635437,
523
+ "learning_rate": 8.4375e-06,
524
+ "loss": 5.6488,
525
+ "step": 1700
526
+ },
527
+ {
528
+ "epoch": 4.21760391198044,
529
+ "grad_norm": 2.2629177570343018,
530
+ "learning_rate": 8.404947916666667e-06,
531
+ "loss": 5.6633,
532
+ "step": 1725
533
+ },
534
+ {
535
+ "epoch": 4.278728606356968,
536
+ "grad_norm": 2.158043384552002,
537
+ "learning_rate": 8.372395833333334e-06,
538
+ "loss": 5.6558,
539
+ "step": 1750
540
+ },
541
+ {
542
+ "epoch": 4.3398533007334965,
543
+ "grad_norm": 2.032712936401367,
544
+ "learning_rate": 8.33984375e-06,
545
+ "loss": 5.661,
546
+ "step": 1775
547
+ },
548
+ {
549
+ "epoch": 4.400977995110025,
550
+ "grad_norm": 2.150649070739746,
551
+ "learning_rate": 8.307291666666668e-06,
552
+ "loss": 5.6587,
553
+ "step": 1800
554
+ },
555
+ {
556
+ "epoch": 4.462102689486553,
557
+ "grad_norm": 1.866034746170044,
558
+ "learning_rate": 8.274739583333334e-06,
559
+ "loss": 5.6306,
560
+ "step": 1825
561
+ },
562
+ {
563
+ "epoch": 4.52322738386308,
564
+ "grad_norm": 2.2522027492523193,
565
+ "learning_rate": 8.242187500000001e-06,
566
+ "loss": 5.6434,
567
+ "step": 1850
568
+ },
569
+ {
570
+ "epoch": 4.5843520782396086,
571
+ "grad_norm": 2.266977071762085,
572
+ "learning_rate": 8.209635416666666e-06,
573
+ "loss": 5.6378,
574
+ "step": 1875
575
+ },
576
+ {
577
+ "epoch": 4.645476772616137,
578
+ "grad_norm": 2.038745164871216,
579
+ "learning_rate": 8.177083333333335e-06,
580
+ "loss": 5.6404,
581
+ "step": 1900
582
+ },
583
+ {
584
+ "epoch": 4.706601466992665,
585
+ "grad_norm": 1.8621001243591309,
586
+ "learning_rate": 8.14453125e-06,
587
+ "loss": 5.651,
588
+ "step": 1925
589
+ },
590
+ {
591
+ "epoch": 4.767726161369193,
592
+ "grad_norm": 1.8880043029785156,
593
+ "learning_rate": 8.111979166666667e-06,
594
+ "loss": 5.6317,
595
+ "step": 1950
596
+ },
597
+ {
598
+ "epoch": 4.8288508557457215,
599
+ "grad_norm": 1.8351385593414307,
600
+ "learning_rate": 8.079427083333334e-06,
601
+ "loss": 5.5911,
602
+ "step": 1975
603
+ },
604
+ {
605
+ "epoch": 4.88997555012225,
606
+ "grad_norm": 1.9690709114074707,
607
+ "learning_rate": 8.046875e-06,
608
+ "loss": 5.6174,
609
+ "step": 2000
610
+ },
611
+ {
612
+ "epoch": 4.951100244498777,
613
+ "grad_norm": 1.8599187135696411,
614
+ "learning_rate": 8.014322916666668e-06,
615
+ "loss": 5.6252,
616
+ "step": 2025
617
+ },
618
+ {
619
+ "epoch": 5.0,
620
+ "eval_cer": 1.0,
621
+ "eval_loss": 5.2904744148254395,
622
+ "eval_runtime": 980.786,
623
+ "eval_samples_per_second": 2.242,
624
+ "eval_steps_per_second": 0.018,
625
+ "eval_wer": 1.0,
626
+ "step": 2045
627
+ },
628
+ {
629
+ "epoch": 5.012224938875305,
630
+ "grad_norm": 2.098679780960083,
631
+ "learning_rate": 7.981770833333335e-06,
632
+ "loss": 5.5864,
633
+ "step": 2050
634
+ },
635
+ {
636
+ "epoch": 5.0733496332518335,
637
+ "grad_norm": 2.3753552436828613,
638
+ "learning_rate": 7.949218750000001e-06,
639
+ "loss": 5.5792,
640
+ "step": 2075
641
+ },
642
+ {
643
+ "epoch": 5.134474327628362,
644
+ "grad_norm": 2.645547866821289,
645
+ "learning_rate": 7.916666666666667e-06,
646
+ "loss": 5.5911,
647
+ "step": 2100
648
+ },
649
+ {
650
+ "epoch": 5.19559902200489,
651
+ "grad_norm": 2.3270106315612793,
652
+ "learning_rate": 7.884114583333335e-06,
653
+ "loss": 5.6018,
654
+ "step": 2125
655
+ },
656
+ {
657
+ "epoch": 5.256723716381418,
658
+ "grad_norm": 1.961776852607727,
659
+ "learning_rate": 7.8515625e-06,
660
+ "loss": 5.5717,
661
+ "step": 2150
662
+ },
663
+ {
664
+ "epoch": 5.3178484107579465,
665
+ "grad_norm": 2.229034662246704,
666
+ "learning_rate": 7.819010416666667e-06,
667
+ "loss": 5.5855,
668
+ "step": 2175
669
+ },
670
+ {
671
+ "epoch": 5.378973105134475,
672
+ "grad_norm": 2.431147575378418,
673
+ "learning_rate": 7.786458333333334e-06,
674
+ "loss": 5.5863,
675
+ "step": 2200
676
+ },
677
+ {
678
+ "epoch": 5.440097799511002,
679
+ "grad_norm": 2.657665967941284,
680
+ "learning_rate": 7.753906250000001e-06,
681
+ "loss": 5.5782,
682
+ "step": 2225
683
+ },
684
+ {
685
+ "epoch": 5.50122249388753,
686
+ "grad_norm": 1.991417646408081,
687
+ "learning_rate": 7.721354166666668e-06,
688
+ "loss": 5.5418,
689
+ "step": 2250
690
+ },
691
+ {
692
+ "epoch": 5.5623471882640585,
693
+ "grad_norm": 2.1882779598236084,
694
+ "learning_rate": 7.688802083333335e-06,
695
+ "loss": 5.5776,
696
+ "step": 2275
697
+ },
698
+ {
699
+ "epoch": 5.623471882640587,
700
+ "grad_norm": 1.843143343925476,
701
+ "learning_rate": 7.656250000000001e-06,
702
+ "loss": 5.588,
703
+ "step": 2300
704
+ },
705
+ {
706
+ "epoch": 5.684596577017115,
707
+ "grad_norm": 2.3870656490325928,
708
+ "learning_rate": 7.623697916666667e-06,
709
+ "loss": 5.5632,
710
+ "step": 2325
711
+ },
712
+ {
713
+ "epoch": 5.745721271393643,
714
+ "grad_norm": 2.0239953994750977,
715
+ "learning_rate": 7.591145833333334e-06,
716
+ "loss": 5.5445,
717
+ "step": 2350
718
+ },
719
+ {
720
+ "epoch": 5.806845965770171,
721
+ "grad_norm": 2.3642804622650146,
722
+ "learning_rate": 7.55859375e-06,
723
+ "loss": 5.5608,
724
+ "step": 2375
725
+ },
726
+ {
727
+ "epoch": 5.8679706601467,
728
+ "grad_norm": 3.237014055252075,
729
+ "learning_rate": 7.526041666666667e-06,
730
+ "loss": 5.5308,
731
+ "step": 2400
732
+ },
733
+ {
734
+ "epoch": 5.929095354523227,
735
+ "grad_norm": 2.084507942199707,
736
+ "learning_rate": 7.493489583333334e-06,
737
+ "loss": 5.5418,
738
+ "step": 2425
739
+ },
740
+ {
741
+ "epoch": 5.990220048899755,
742
+ "grad_norm": 1.9642763137817383,
743
+ "learning_rate": 7.460937500000001e-06,
744
+ "loss": 5.5532,
745
+ "step": 2450
746
+ },
747
+ {
748
+ "epoch": 6.0,
749
+ "eval_cer": 1.0,
750
+ "eval_loss": 5.23870325088501,
751
+ "eval_runtime": 909.9853,
752
+ "eval_samples_per_second": 2.417,
753
+ "eval_steps_per_second": 0.02,
754
+ "eval_wer": 1.0,
755
+ "step": 2454
756
+ },
757
+ {
758
+ "epoch": 6.0513447432762835,
759
+ "grad_norm": 2.086639404296875,
760
+ "learning_rate": 7.428385416666667e-06,
761
+ "loss": 5.5231,
762
+ "step": 2475
763
+ },
764
+ {
765
+ "epoch": 6.112469437652812,
766
+ "grad_norm": 1.9924498796463013,
767
+ "learning_rate": 7.395833333333335e-06,
768
+ "loss": 5.5191,
769
+ "step": 2500
770
+ },
771
+ {
772
+ "epoch": 6.17359413202934,
773
+ "grad_norm": 2.331226348876953,
774
+ "learning_rate": 7.363281250000001e-06,
775
+ "loss": 5.5092,
776
+ "step": 2525
777
+ },
778
+ {
779
+ "epoch": 6.234718826405868,
780
+ "grad_norm": 2.276024580001831,
781
+ "learning_rate": 7.330729166666667e-06,
782
+ "loss": 5.5208,
783
+ "step": 2550
784
+ },
785
+ {
786
+ "epoch": 6.295843520782396,
787
+ "grad_norm": 2.2748773097991943,
788
+ "learning_rate": 7.298177083333334e-06,
789
+ "loss": 5.5241,
790
+ "step": 2575
791
+ },
792
+ {
793
+ "epoch": 6.356968215158924,
794
+ "grad_norm": 2.164454460144043,
795
+ "learning_rate": 7.265625e-06,
796
+ "loss": 5.4821,
797
+ "step": 2600
798
+ },
799
+ {
800
+ "epoch": 6.418092909535452,
801
+ "grad_norm": 2.0158824920654297,
802
+ "learning_rate": 7.233072916666667e-06,
803
+ "loss": 5.5143,
804
+ "step": 2625
805
+ },
806
+ {
807
+ "epoch": 6.47921760391198,
808
+ "grad_norm": 2.3213398456573486,
809
+ "learning_rate": 7.200520833333334e-06,
810
+ "loss": 5.5244,
811
+ "step": 2650
812
+ },
813
+ {
814
+ "epoch": 6.540342298288508,
815
+ "grad_norm": 3.5166070461273193,
816
+ "learning_rate": 7.16796875e-06,
817
+ "loss": 5.5251,
818
+ "step": 2675
819
+ },
820
+ {
821
+ "epoch": 6.601466992665037,
822
+ "grad_norm": 2.501091480255127,
823
+ "learning_rate": 7.135416666666667e-06,
824
+ "loss": 5.5072,
825
+ "step": 2700
826
+ },
827
+ {
828
+ "epoch": 6.662591687041565,
829
+ "grad_norm": 2.1940529346466064,
830
+ "learning_rate": 7.102864583333334e-06,
831
+ "loss": 5.5146,
832
+ "step": 2725
833
+ },
834
+ {
835
+ "epoch": 6.723716381418093,
836
+ "grad_norm": 2.563851833343506,
837
+ "learning_rate": 7.070312500000001e-06,
838
+ "loss": 5.4957,
839
+ "step": 2750
840
+ },
841
+ {
842
+ "epoch": 6.784841075794621,
843
+ "grad_norm": 2.2761764526367188,
844
+ "learning_rate": 7.037760416666667e-06,
845
+ "loss": 5.4873,
846
+ "step": 2775
847
+ },
848
+ {
849
+ "epoch": 6.84596577017115,
850
+ "grad_norm": 2.4268720149993896,
851
+ "learning_rate": 7.0052083333333345e-06,
852
+ "loss": 5.4818,
853
+ "step": 2800
854
+ },
855
+ {
856
+ "epoch": 6.907090464547677,
857
+ "grad_norm": 2.075167179107666,
858
+ "learning_rate": 6.9726562500000005e-06,
859
+ "loss": 5.517,
860
+ "step": 2825
861
+ },
862
+ {
863
+ "epoch": 6.968215158924205,
864
+ "grad_norm": 2.1719608306884766,
865
+ "learning_rate": 6.9401041666666665e-06,
866
+ "loss": 5.485,
867
+ "step": 2850
868
+ },
869
+ {
870
+ "epoch": 7.0,
871
+ "eval_cer": 1.0,
872
+ "eval_loss": 5.207675457000732,
873
+ "eval_runtime": 852.4911,
874
+ "eval_samples_per_second": 2.579,
875
+ "eval_steps_per_second": 0.021,
876
+ "eval_wer": 1.0,
877
+ "step": 2863
878
+ },
879
+ {
880
+ "epoch": 7.029339853300733,
881
+ "grad_norm": 1.9253339767456055,
882
+ "learning_rate": 6.907552083333334e-06,
883
+ "loss": 5.4902,
884
+ "step": 2875
885
+ },
886
+ {
887
+ "epoch": 7.090464547677262,
888
+ "grad_norm": 2.6965110301971436,
889
+ "learning_rate": 6.875e-06,
890
+ "loss": 5.4694,
891
+ "step": 2900
892
+ },
893
+ {
894
+ "epoch": 7.15158924205379,
895
+ "grad_norm": 3.292003870010376,
896
+ "learning_rate": 6.842447916666667e-06,
897
+ "loss": 5.457,
898
+ "step": 2925
899
+ },
900
+ {
901
+ "epoch": 7.212713936430318,
902
+ "grad_norm": 3.321614980697632,
903
+ "learning_rate": 6.809895833333334e-06,
904
+ "loss": 5.475,
905
+ "step": 2950
906
+ },
907
+ {
908
+ "epoch": 7.273838630806846,
909
+ "grad_norm": 2.9773731231689453,
910
+ "learning_rate": 6.777343750000001e-06,
911
+ "loss": 5.4533,
912
+ "step": 2975
913
+ },
914
+ {
915
+ "epoch": 7.334963325183374,
916
+ "grad_norm": 2.3799688816070557,
917
+ "learning_rate": 6.744791666666667e-06,
918
+ "loss": 5.4699,
919
+ "step": 3000
920
+ },
921
+ {
922
+ "epoch": 7.396088019559902,
923
+ "grad_norm": 2.3236491680145264,
924
+ "learning_rate": 6.7122395833333346e-06,
925
+ "loss": 5.4694,
926
+ "step": 3025
927
+ },
928
+ {
929
+ "epoch": 7.45721271393643,
930
+ "grad_norm": 2.295271635055542,
931
+ "learning_rate": 6.679687500000001e-06,
932
+ "loss": 5.4637,
933
+ "step": 3050
934
+ },
935
+ {
936
+ "epoch": 7.518337408312958,
937
+ "grad_norm": 2.130282402038574,
938
+ "learning_rate": 6.647135416666667e-06,
939
+ "loss": 5.4752,
940
+ "step": 3075
941
+ },
942
+ {
943
+ "epoch": 7.579462102689487,
944
+ "grad_norm": 2.148224115371704,
945
+ "learning_rate": 6.614583333333334e-06,
946
+ "loss": 5.4303,
947
+ "step": 3100
948
+ },
949
+ {
950
+ "epoch": 7.640586797066015,
951
+ "grad_norm": 2.275786876678467,
952
+ "learning_rate": 6.58203125e-06,
953
+ "loss": 5.4389,
954
+ "step": 3125
955
+ },
956
+ {
957
+ "epoch": 7.701711491442543,
958
+ "grad_norm": 2.203730583190918,
959
+ "learning_rate": 6.549479166666667e-06,
960
+ "loss": 5.4531,
961
+ "step": 3150
962
+ },
963
+ {
964
+ "epoch": 7.76283618581907,
965
+ "grad_norm": 2.1406664848327637,
966
+ "learning_rate": 6.516927083333334e-06,
967
+ "loss": 5.4607,
968
+ "step": 3175
969
+ },
970
+ {
971
+ "epoch": 7.823960880195599,
972
+ "grad_norm": 2.7617645263671875,
973
+ "learning_rate": 6.484375000000001e-06,
974
+ "loss": 5.4426,
975
+ "step": 3200
976
+ },
977
+ {
978
+ "epoch": 7.885085574572127,
979
+ "grad_norm": 2.337761878967285,
980
+ "learning_rate": 6.451822916666667e-06,
981
+ "loss": 5.453,
982
+ "step": 3225
983
+ },
984
+ {
985
+ "epoch": 7.946210268948655,
986
+ "grad_norm": 2.157966375350952,
987
+ "learning_rate": 6.419270833333335e-06,
988
+ "loss": 5.4253,
989
+ "step": 3250
990
+ },
991
+ {
992
+ "epoch": 8.0,
993
+ "eval_cer": 1.0,
994
+ "eval_loss": 5.176779747009277,
995
+ "eval_runtime": 850.0532,
996
+ "eval_samples_per_second": 2.587,
997
+ "eval_steps_per_second": 0.021,
998
+ "eval_wer": 1.0,
999
+ "step": 3272
1000
+ },
1001
+ {
1002
+ "epoch": 8.007334963325183,
1003
+ "grad_norm": 2.4567079544067383,
1004
+ "learning_rate": 6.386718750000001e-06,
1005
+ "loss": 5.4184,
1006
+ "step": 3275
1007
+ },
1008
+ {
1009
+ "epoch": 8.06845965770171,
1010
+ "grad_norm": 2.5252790451049805,
1011
+ "learning_rate": 6.354166666666667e-06,
1012
+ "loss": 5.4112,
1013
+ "step": 3300
1014
+ },
1015
+ {
1016
+ "epoch": 8.12958435207824,
1017
+ "grad_norm": 2.282362461090088,
1018
+ "learning_rate": 6.321614583333334e-06,
1019
+ "loss": 5.4263,
1020
+ "step": 3325
1021
+ },
1022
+ {
1023
+ "epoch": 8.190709046454767,
1024
+ "grad_norm": 2.0922985076904297,
1025
+ "learning_rate": 6.2890625e-06,
1026
+ "loss": 5.4201,
1027
+ "step": 3350
1028
+ },
1029
+ {
1030
+ "epoch": 8.251833740831296,
1031
+ "grad_norm": 2.4645814895629883,
1032
+ "learning_rate": 6.256510416666666e-06,
1033
+ "loss": 5.4055,
1034
+ "step": 3375
1035
+ },
1036
+ {
1037
+ "epoch": 8.312958435207824,
1038
+ "grad_norm": 2.5172641277313232,
1039
+ "learning_rate": 6.223958333333334e-06,
1040
+ "loss": 5.4059,
1041
+ "step": 3400
1042
+ },
1043
+ {
1044
+ "epoch": 8.374083129584353,
1045
+ "grad_norm": 2.4925782680511475,
1046
+ "learning_rate": 6.19140625e-06,
1047
+ "loss": 5.4282,
1048
+ "step": 3425
1049
+ },
1050
+ {
1051
+ "epoch": 8.43520782396088,
1052
+ "grad_norm": 2.384561538696289,
1053
+ "learning_rate": 6.158854166666667e-06,
1054
+ "loss": 5.4223,
1055
+ "step": 3450
1056
+ },
1057
+ {
1058
+ "epoch": 8.496332518337407,
1059
+ "grad_norm": 2.8028838634490967,
1060
+ "learning_rate": 6.126302083333334e-06,
1061
+ "loss": 5.404,
1062
+ "step": 3475
1063
+ },
1064
+ {
1065
+ "epoch": 8.557457212713937,
1066
+ "grad_norm": 2.1153008937835693,
1067
+ "learning_rate": 6.093750000000001e-06,
1068
+ "loss": 5.4063,
1069
+ "step": 3500
1070
+ },
1071
+ {
1072
+ "epoch": 8.618581907090464,
1073
+ "grad_norm": 2.722527265548706,
1074
+ "learning_rate": 6.061197916666667e-06,
1075
+ "loss": 5.3986,
1076
+ "step": 3525
1077
+ },
1078
+ {
1079
+ "epoch": 8.679706601466993,
1080
+ "grad_norm": 2.9357943534851074,
1081
+ "learning_rate": 6.0286458333333345e-06,
1082
+ "loss": 5.3809,
1083
+ "step": 3550
1084
+ },
1085
+ {
1086
+ "epoch": 8.74083129584352,
1087
+ "grad_norm": 2.2688732147216797,
1088
+ "learning_rate": 5.9960937500000005e-06,
1089
+ "loss": 5.4155,
1090
+ "step": 3575
1091
+ },
1092
+ {
1093
+ "epoch": 8.80195599022005,
1094
+ "grad_norm": 2.988487958908081,
1095
+ "learning_rate": 5.9635416666666665e-06,
1096
+ "loss": 5.393,
1097
+ "step": 3600
1098
+ },
1099
+ {
1100
+ "epoch": 8.863080684596577,
1101
+ "grad_norm": 2.2804296016693115,
1102
+ "learning_rate": 5.930989583333334e-06,
1103
+ "loss": 5.4099,
1104
+ "step": 3625
1105
+ },
1106
+ {
1107
+ "epoch": 8.924205378973106,
1108
+ "grad_norm": 2.473313808441162,
1109
+ "learning_rate": 5.8984375e-06,
1110
+ "loss": 5.4092,
1111
+ "step": 3650
1112
+ },
1113
+ {
1114
+ "epoch": 8.985330073349633,
1115
+ "grad_norm": 2.255056142807007,
1116
+ "learning_rate": 5.865885416666667e-06,
1117
+ "loss": 5.3916,
1118
+ "step": 3675
1119
+ },
1120
+ {
1121
+ "epoch": 9.0,
1122
+ "eval_cer": 1.0,
1123
+ "eval_loss": 5.145139217376709,
1124
+ "eval_runtime": 883.7091,
1125
+ "eval_samples_per_second": 2.488,
1126
+ "eval_steps_per_second": 0.02,
1127
+ "eval_wer": 1.0,
1128
+ "step": 3681
1129
+ }
1130
+ ],
1131
+ "logging_steps": 25,
1132
+ "max_steps": 8180,
1133
+ "num_input_tokens_seen": 0,
1134
+ "num_train_epochs": 20,
1135
+ "save_steps": 500,
1136
+ "stateful_callbacks": {
1137
+ "TrainerControl": {
1138
+ "args": {
1139
+ "should_epoch_stop": false,
1140
+ "should_evaluate": false,
1141
+ "should_log": false,
1142
+ "should_save": true,
1143
+ "should_training_stop": false
1144
+ },
1145
+ "attributes": {}
1146
+ }
1147
+ },
1148
+ "total_flos": 2.96043723472896e+19,
1149
+ "train_batch_size": 124,
1150
+ "trial_name": null,
1151
+ "trial_params": null
1152
+ }
checkpoint-3681/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32fd048d0fc7461f5c6f38ce39faa81e6f5f8b3ff36cd5081d0ac78893e55ebc
3
+ size 5304
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/kaggle/working/new_downloads/checkpoint-2045",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
1
  {
2
+ "_name_or_path": "/kaggle/working/new_downloads/checkpoint-2863",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0be70406bf3e8229fbae08dbcaaf8f31be51ec9c0f36615682ca0cb36546ff07
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6716ac010719c2ff3113a52749eb5d2dd8206dd4e4af95288d80f568980d8237
3
  size 290403936
runs/Jun26_05-04-45_5bceb5efad52/events.out.tfevents.1719378292.5bceb5efad52.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff2d713584b7d308251ec3d2a8e60bea57b2d332934494c86e67ce3a83afa10
3
+ size 14347
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0f41a68086e0dd1e4976c0d9fd4b082d975442d7c7dc97ba96ea6d9376cc397
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32fd048d0fc7461f5c6f38ce39faa81e6f5f8b3ff36cd5081d0ac78893e55ebc
3
  size 5304