AsemBadr commited on
Commit
fa5d330
1 Parent(s): ae740d1

Training in progress, step 2500, checkpoint

Browse files
checkpoint-2500/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-small",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 768,
17
+ "decoder_attention_heads": 12,
18
+ "decoder_ffn_dim": 3072,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50272
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": 12,
56
+ "num_mel_bins": 80,
57
+ "pad_token_id": 50257,
58
+ "scale_embedding": false,
59
+ "suppress_tokens": [],
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.41.0.dev0",
62
+ "use_cache": true,
63
+ "use_weighted_layer_sum": false,
64
+ "vocab_size": 51865
65
+ }
checkpoint-2500/generation_config.json ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 5,
5
+ 3
6
+ ],
7
+ [
8
+ 5,
9
+ 9
10
+ ],
11
+ [
12
+ 8,
13
+ 0
14
+ ],
15
+ [
16
+ 8,
17
+ 4
18
+ ],
19
+ [
20
+ 8,
21
+ 7
22
+ ],
23
+ [
24
+ 8,
25
+ 8
26
+ ],
27
+ [
28
+ 9,
29
+ 0
30
+ ],
31
+ [
32
+ 9,
33
+ 7
34
+ ],
35
+ [
36
+ 9,
37
+ 9
38
+ ],
39
+ [
40
+ 10,
41
+ 5
42
+ ]
43
+ ],
44
+ "begin_suppress_tokens": [
45
+ 220,
46
+ 50257
47
+ ],
48
+ "bos_token_id": 50257,
49
+ "decoder_start_token_id": 50258,
50
+ "eos_token_id": 50257,
51
+ "forced_decoder_ids": [
52
+ [
53
+ 1,
54
+ null
55
+ ],
56
+ [
57
+ 2,
58
+ 50359
59
+ ]
60
+ ],
61
+ "is_multilingual": true,
62
+ "lang_to_id": {
63
+ "<|af|>": 50327,
64
+ "<|am|>": 50334,
65
+ "<|ar|>": 50272,
66
+ "<|as|>": 50350,
67
+ "<|az|>": 50304,
68
+ "<|ba|>": 50355,
69
+ "<|be|>": 50330,
70
+ "<|bg|>": 50292,
71
+ "<|bn|>": 50302,
72
+ "<|bo|>": 50347,
73
+ "<|br|>": 50309,
74
+ "<|bs|>": 50315,
75
+ "<|ca|>": 50270,
76
+ "<|cs|>": 50283,
77
+ "<|cy|>": 50297,
78
+ "<|da|>": 50285,
79
+ "<|de|>": 50261,
80
+ "<|el|>": 50281,
81
+ "<|en|>": 50259,
82
+ "<|es|>": 50262,
83
+ "<|et|>": 50307,
84
+ "<|eu|>": 50310,
85
+ "<|fa|>": 50300,
86
+ "<|fi|>": 50277,
87
+ "<|fo|>": 50338,
88
+ "<|fr|>": 50265,
89
+ "<|gl|>": 50319,
90
+ "<|gu|>": 50333,
91
+ "<|haw|>": 50352,
92
+ "<|ha|>": 50354,
93
+ "<|he|>": 50279,
94
+ "<|hi|>": 50276,
95
+ "<|hr|>": 50291,
96
+ "<|ht|>": 50339,
97
+ "<|hu|>": 50286,
98
+ "<|hy|>": 50312,
99
+ "<|id|>": 50275,
100
+ "<|is|>": 50311,
101
+ "<|it|>": 50274,
102
+ "<|ja|>": 50266,
103
+ "<|jw|>": 50356,
104
+ "<|ka|>": 50329,
105
+ "<|kk|>": 50316,
106
+ "<|km|>": 50323,
107
+ "<|kn|>": 50306,
108
+ "<|ko|>": 50264,
109
+ "<|la|>": 50294,
110
+ "<|lb|>": 50345,
111
+ "<|ln|>": 50353,
112
+ "<|lo|>": 50336,
113
+ "<|lt|>": 50293,
114
+ "<|lv|>": 50301,
115
+ "<|mg|>": 50349,
116
+ "<|mi|>": 50295,
117
+ "<|mk|>": 50308,
118
+ "<|ml|>": 50296,
119
+ "<|mn|>": 50314,
120
+ "<|mr|>": 50320,
121
+ "<|ms|>": 50282,
122
+ "<|mt|>": 50343,
123
+ "<|my|>": 50346,
124
+ "<|ne|>": 50313,
125
+ "<|nl|>": 50271,
126
+ "<|nn|>": 50342,
127
+ "<|no|>": 50288,
128
+ "<|oc|>": 50328,
129
+ "<|pa|>": 50321,
130
+ "<|pl|>": 50269,
131
+ "<|ps|>": 50340,
132
+ "<|pt|>": 50267,
133
+ "<|ro|>": 50284,
134
+ "<|ru|>": 50263,
135
+ "<|sa|>": 50344,
136
+ "<|sd|>": 50332,
137
+ "<|si|>": 50322,
138
+ "<|sk|>": 50298,
139
+ "<|sl|>": 50305,
140
+ "<|sn|>": 50324,
141
+ "<|so|>": 50326,
142
+ "<|sq|>": 50317,
143
+ "<|sr|>": 50303,
144
+ "<|su|>": 50357,
145
+ "<|sv|>": 50273,
146
+ "<|sw|>": 50318,
147
+ "<|ta|>": 50287,
148
+ "<|te|>": 50299,
149
+ "<|tg|>": 50331,
150
+ "<|th|>": 50289,
151
+ "<|tk|>": 50341,
152
+ "<|tl|>": 50348,
153
+ "<|tr|>": 50268,
154
+ "<|tt|>": 50351,
155
+ "<|uk|>": 50280,
156
+ "<|ur|>": 50290,
157
+ "<|uz|>": 50337,
158
+ "<|vi|>": 50278,
159
+ "<|yi|>": 50335,
160
+ "<|yo|>": 50325,
161
+ "<|zh|>": 50260
162
+ },
163
+ "language": "ar",
164
+ "max_initial_timestamp_index": 50,
165
+ "max_length": 448,
166
+ "no_timestamps_token_id": 50363,
167
+ "pad_token_id": 50257,
168
+ "prev_sot_token_id": 50361,
169
+ "return_timestamps": false,
170
+ "suppress_tokens": [
171
+ 1,
172
+ 2,
173
+ 7,
174
+ 8,
175
+ 9,
176
+ 10,
177
+ 14,
178
+ 25,
179
+ 26,
180
+ 27,
181
+ 28,
182
+ 29,
183
+ 31,
184
+ 58,
185
+ 59,
186
+ 60,
187
+ 61,
188
+ 62,
189
+ 63,
190
+ 90,
191
+ 91,
192
+ 92,
193
+ 93,
194
+ 359,
195
+ 503,
196
+ 522,
197
+ 542,
198
+ 873,
199
+ 893,
200
+ 902,
201
+ 918,
202
+ 922,
203
+ 931,
204
+ 1350,
205
+ 1853,
206
+ 1982,
207
+ 2460,
208
+ 2627,
209
+ 3246,
210
+ 3253,
211
+ 3268,
212
+ 3536,
213
+ 3846,
214
+ 3961,
215
+ 4183,
216
+ 4667,
217
+ 6585,
218
+ 6647,
219
+ 7273,
220
+ 9061,
221
+ 9383,
222
+ 10428,
223
+ 10929,
224
+ 11938,
225
+ 12033,
226
+ 12331,
227
+ 12562,
228
+ 13793,
229
+ 14157,
230
+ 14635,
231
+ 15265,
232
+ 15618,
233
+ 16553,
234
+ 16604,
235
+ 18362,
236
+ 18956,
237
+ 20075,
238
+ 21675,
239
+ 22520,
240
+ 26130,
241
+ 26161,
242
+ 26435,
243
+ 28279,
244
+ 29464,
245
+ 31650,
246
+ 32302,
247
+ 32470,
248
+ 36865,
249
+ 42863,
250
+ 47425,
251
+ 49870,
252
+ 50254,
253
+ 50258,
254
+ 50358,
255
+ 50359,
256
+ 50360,
257
+ 50361,
258
+ 50362
259
+ ],
260
+ "task_to_id": {
261
+ "transcribe": 50359,
262
+ "translate": 50358
263
+ },
264
+ "transformers_version": "4.41.0.dev0"
265
+ }
checkpoint-2500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83aefda8194db04297dde5062ced4110340824ccbd6446cb6235cfd0b1860df9
3
+ size 966995080
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117ba95fc83a51f9c03b0915559f2273c5e3dcb2b04aaf3c9fd1646ed895e1ff
3
+ size 1925064044
checkpoint-2500/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-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f96028e00e2cf11fde3349787c6b035a4c93f649c4644a5af337ace40180ac9
3
+ size 14244
checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d6995b95c5110bc236d96ddb7599bbe5f6656490b4fbc52061c42b1a212629c
3
+ size 1064
checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,766 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.9130738755534837,
3
+ "best_model_checkpoint": "./final-whisper-for-initial-publish/checkpoint-2500",
4
+ "epoch": 4.118616144975288,
5
+ "eval_steps": 500,
6
+ "global_step": 2500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04118616144975288,
13
+ "grad_norm": 67.08393096923828,
14
+ "learning_rate": 4.2000000000000006e-07,
15
+ "loss": 2.8367,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.08237232289950576,
20
+ "grad_norm": 17.447174072265625,
21
+ "learning_rate": 9.200000000000001e-07,
22
+ "loss": 2.0282,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.12355848434925865,
27
+ "grad_norm": 12.4807710647583,
28
+ "learning_rate": 1.42e-06,
29
+ "loss": 1.3152,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.16474464579901152,
34
+ "grad_norm": 8.900789260864258,
35
+ "learning_rate": 1.9200000000000003e-06,
36
+ "loss": 0.7248,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.20593080724876442,
41
+ "grad_norm": 7.897016525268555,
42
+ "learning_rate": 2.42e-06,
43
+ "loss": 0.5731,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.2471169686985173,
48
+ "grad_norm": 9.260579109191895,
49
+ "learning_rate": 2.92e-06,
50
+ "loss": 0.474,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.2883031301482702,
55
+ "grad_norm": 6.941812515258789,
56
+ "learning_rate": 3.4200000000000007e-06,
57
+ "loss": 0.4304,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.32948929159802304,
62
+ "grad_norm": 6.919547080993652,
63
+ "learning_rate": 3.920000000000001e-06,
64
+ "loss": 0.3514,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.37067545304777594,
69
+ "grad_norm": 6.444908618927002,
70
+ "learning_rate": 4.42e-06,
71
+ "loss": 0.273,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.41186161449752884,
76
+ "grad_norm": 5.828249454498291,
77
+ "learning_rate": 4.92e-06,
78
+ "loss": 0.1655,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.45304777594728174,
83
+ "grad_norm": 2.492833137512207,
84
+ "learning_rate": 5.420000000000001e-06,
85
+ "loss": 0.0894,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.4942339373970346,
90
+ "grad_norm": 3.24698805809021,
91
+ "learning_rate": 5.92e-06,
92
+ "loss": 0.076,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.5354200988467874,
97
+ "grad_norm": 4.378988265991211,
98
+ "learning_rate": 6.42e-06,
99
+ "loss": 0.0763,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.5766062602965404,
104
+ "grad_norm": 3.146955728530884,
105
+ "learning_rate": 6.92e-06,
106
+ "loss": 0.0679,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.6177924217462932,
111
+ "grad_norm": 3.8782553672790527,
112
+ "learning_rate": 7.420000000000001e-06,
113
+ "loss": 0.0524,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.6589785831960461,
118
+ "grad_norm": 6.15730094909668,
119
+ "learning_rate": 7.92e-06,
120
+ "loss": 0.0554,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.700164744645799,
125
+ "grad_norm": 6.1213812828063965,
126
+ "learning_rate": 8.42e-06,
127
+ "loss": 0.0535,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.7413509060955519,
132
+ "grad_norm": 4.010768890380859,
133
+ "learning_rate": 8.920000000000001e-06,
134
+ "loss": 0.0465,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.7825370675453048,
139
+ "grad_norm": 3.509321451187134,
140
+ "learning_rate": 9.42e-06,
141
+ "loss": 0.0436,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.8237232289950577,
146
+ "grad_norm": 2.744082450866699,
147
+ "learning_rate": 9.920000000000002e-06,
148
+ "loss": 0.0468,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.8237232289950577,
153
+ "eval_loss": 0.04186907038092613,
154
+ "eval_runtime": 1739.4189,
155
+ "eval_samples_per_second": 1.395,
156
+ "eval_steps_per_second": 0.175,
157
+ "eval_wer": 10.859939408063388,
158
+ "step": 500
159
+ },
160
+ {
161
+ "epoch": 0.8649093904448105,
162
+ "grad_norm": 2.581739664077759,
163
+ "learning_rate": 9.953333333333333e-06,
164
+ "loss": 0.0387,
165
+ "step": 525
166
+ },
167
+ {
168
+ "epoch": 0.9060955518945635,
169
+ "grad_norm": 1.7439745664596558,
170
+ "learning_rate": 9.89777777777778e-06,
171
+ "loss": 0.0372,
172
+ "step": 550
173
+ },
174
+ {
175
+ "epoch": 0.9472817133443163,
176
+ "grad_norm": 3.0741066932678223,
177
+ "learning_rate": 9.842222222222223e-06,
178
+ "loss": 0.0344,
179
+ "step": 575
180
+ },
181
+ {
182
+ "epoch": 0.9884678747940692,
183
+ "grad_norm": 2.640840530395508,
184
+ "learning_rate": 9.786666666666667e-06,
185
+ "loss": 0.0331,
186
+ "step": 600
187
+ },
188
+ {
189
+ "epoch": 1.029654036243822,
190
+ "grad_norm": 0.908171534538269,
191
+ "learning_rate": 9.731111111111113e-06,
192
+ "loss": 0.0267,
193
+ "step": 625
194
+ },
195
+ {
196
+ "epoch": 1.0708401976935749,
197
+ "grad_norm": 1.0449379682540894,
198
+ "learning_rate": 9.675555555555555e-06,
199
+ "loss": 0.0203,
200
+ "step": 650
201
+ },
202
+ {
203
+ "epoch": 1.112026359143328,
204
+ "grad_norm": 2.090158700942993,
205
+ "learning_rate": 9.620000000000001e-06,
206
+ "loss": 0.0185,
207
+ "step": 675
208
+ },
209
+ {
210
+ "epoch": 1.1532125205930808,
211
+ "grad_norm": 3.4184322357177734,
212
+ "learning_rate": 9.564444444444445e-06,
213
+ "loss": 0.0226,
214
+ "step": 700
215
+ },
216
+ {
217
+ "epoch": 1.1943986820428336,
218
+ "grad_norm": 2.6463236808776855,
219
+ "learning_rate": 9.508888888888889e-06,
220
+ "loss": 0.0155,
221
+ "step": 725
222
+ },
223
+ {
224
+ "epoch": 1.2355848434925865,
225
+ "grad_norm": 0.7438070774078369,
226
+ "learning_rate": 9.453333333333335e-06,
227
+ "loss": 0.0184,
228
+ "step": 750
229
+ },
230
+ {
231
+ "epoch": 1.2767710049423393,
232
+ "grad_norm": 1.7319138050079346,
233
+ "learning_rate": 9.397777777777779e-06,
234
+ "loss": 0.0161,
235
+ "step": 775
236
+ },
237
+ {
238
+ "epoch": 1.3179571663920924,
239
+ "grad_norm": 1.9704327583312988,
240
+ "learning_rate": 9.342222222222223e-06,
241
+ "loss": 0.0137,
242
+ "step": 800
243
+ },
244
+ {
245
+ "epoch": 1.3591433278418452,
246
+ "grad_norm": 1.808190107345581,
247
+ "learning_rate": 9.286666666666667e-06,
248
+ "loss": 0.0169,
249
+ "step": 825
250
+ },
251
+ {
252
+ "epoch": 1.400329489291598,
253
+ "grad_norm": 2.1106882095336914,
254
+ "learning_rate": 9.231111111111111e-06,
255
+ "loss": 0.0141,
256
+ "step": 850
257
+ },
258
+ {
259
+ "epoch": 1.441515650741351,
260
+ "grad_norm": 1.5317939519882202,
261
+ "learning_rate": 9.175555555555557e-06,
262
+ "loss": 0.0114,
263
+ "step": 875
264
+ },
265
+ {
266
+ "epoch": 1.4827018121911038,
267
+ "grad_norm": 2.758979082107544,
268
+ "learning_rate": 9.12e-06,
269
+ "loss": 0.0123,
270
+ "step": 900
271
+ },
272
+ {
273
+ "epoch": 1.5238879736408566,
274
+ "grad_norm": 2.9624338150024414,
275
+ "learning_rate": 9.064444444444447e-06,
276
+ "loss": 0.014,
277
+ "step": 925
278
+ },
279
+ {
280
+ "epoch": 1.5650741350906094,
281
+ "grad_norm": 2.520521402359009,
282
+ "learning_rate": 9.008888888888889e-06,
283
+ "loss": 0.0107,
284
+ "step": 950
285
+ },
286
+ {
287
+ "epoch": 1.6062602965403623,
288
+ "grad_norm": 1.0015959739685059,
289
+ "learning_rate": 8.953333333333335e-06,
290
+ "loss": 0.0111,
291
+ "step": 975
292
+ },
293
+ {
294
+ "epoch": 1.6474464579901154,
295
+ "grad_norm": 2.2675178050994873,
296
+ "learning_rate": 8.897777777777779e-06,
297
+ "loss": 0.0124,
298
+ "step": 1000
299
+ },
300
+ {
301
+ "epoch": 1.6474464579901154,
302
+ "eval_loss": 0.02125450409948826,
303
+ "eval_runtime": 1730.2385,
304
+ "eval_samples_per_second": 1.403,
305
+ "eval_steps_per_second": 0.176,
306
+ "eval_wer": 5.243532975996271,
307
+ "step": 1000
308
+ },
309
+ {
310
+ "epoch": 1.6886326194398682,
311
+ "grad_norm": 1.1241651773452759,
312
+ "learning_rate": 8.842222222222223e-06,
313
+ "loss": 0.0108,
314
+ "step": 1025
315
+ },
316
+ {
317
+ "epoch": 1.729818780889621,
318
+ "grad_norm": 0.9443243145942688,
319
+ "learning_rate": 8.786666666666668e-06,
320
+ "loss": 0.01,
321
+ "step": 1050
322
+ },
323
+ {
324
+ "epoch": 1.771004942339374,
325
+ "grad_norm": 1.7507250308990479,
326
+ "learning_rate": 8.73111111111111e-06,
327
+ "loss": 0.0108,
328
+ "step": 1075
329
+ },
330
+ {
331
+ "epoch": 1.812191103789127,
332
+ "grad_norm": 0.8334024548530579,
333
+ "learning_rate": 8.675555555555556e-06,
334
+ "loss": 0.0108,
335
+ "step": 1100
336
+ },
337
+ {
338
+ "epoch": 1.8533772652388798,
339
+ "grad_norm": 2.0746381282806396,
340
+ "learning_rate": 8.62e-06,
341
+ "loss": 0.009,
342
+ "step": 1125
343
+ },
344
+ {
345
+ "epoch": 1.8945634266886326,
346
+ "grad_norm": 1.5471493005752563,
347
+ "learning_rate": 8.564444444444445e-06,
348
+ "loss": 0.0124,
349
+ "step": 1150
350
+ },
351
+ {
352
+ "epoch": 1.9357495881383855,
353
+ "grad_norm": 1.4362578392028809,
354
+ "learning_rate": 8.50888888888889e-06,
355
+ "loss": 0.009,
356
+ "step": 1175
357
+ },
358
+ {
359
+ "epoch": 1.9769357495881383,
360
+ "grad_norm": 1.5219734907150269,
361
+ "learning_rate": 8.453333333333334e-06,
362
+ "loss": 0.0108,
363
+ "step": 1200
364
+ },
365
+ {
366
+ "epoch": 2.018121911037891,
367
+ "grad_norm": 0.7635548710823059,
368
+ "learning_rate": 8.397777777777778e-06,
369
+ "loss": 0.0069,
370
+ "step": 1225
371
+ },
372
+ {
373
+ "epoch": 2.059308072487644,
374
+ "grad_norm": 0.622107982635498,
375
+ "learning_rate": 8.342222222222222e-06,
376
+ "loss": 0.0045,
377
+ "step": 1250
378
+ },
379
+ {
380
+ "epoch": 2.100494233937397,
381
+ "grad_norm": 3.157203197479248,
382
+ "learning_rate": 8.286666666666668e-06,
383
+ "loss": 0.0055,
384
+ "step": 1275
385
+ },
386
+ {
387
+ "epoch": 2.1416803953871497,
388
+ "grad_norm": 0.8712319731712341,
389
+ "learning_rate": 8.231111111111112e-06,
390
+ "loss": 0.0025,
391
+ "step": 1300
392
+ },
393
+ {
394
+ "epoch": 2.182866556836903,
395
+ "grad_norm": 0.7438367605209351,
396
+ "learning_rate": 8.175555555555556e-06,
397
+ "loss": 0.0038,
398
+ "step": 1325
399
+ },
400
+ {
401
+ "epoch": 2.224052718286656,
402
+ "grad_norm": 0.4088328778743744,
403
+ "learning_rate": 8.120000000000002e-06,
404
+ "loss": 0.004,
405
+ "step": 1350
406
+ },
407
+ {
408
+ "epoch": 2.2652388797364087,
409
+ "grad_norm": 0.34847044944763184,
410
+ "learning_rate": 8.064444444444444e-06,
411
+ "loss": 0.003,
412
+ "step": 1375
413
+ },
414
+ {
415
+ "epoch": 2.3064250411861615,
416
+ "grad_norm": 0.08477868884801865,
417
+ "learning_rate": 8.00888888888889e-06,
418
+ "loss": 0.0024,
419
+ "step": 1400
420
+ },
421
+ {
422
+ "epoch": 2.3476112026359144,
423
+ "grad_norm": 0.5055556297302246,
424
+ "learning_rate": 7.953333333333334e-06,
425
+ "loss": 0.004,
426
+ "step": 1425
427
+ },
428
+ {
429
+ "epoch": 2.3887973640856672,
430
+ "grad_norm": 0.27648621797561646,
431
+ "learning_rate": 7.897777777777778e-06,
432
+ "loss": 0.0037,
433
+ "step": 1450
434
+ },
435
+ {
436
+ "epoch": 2.42998352553542,
437
+ "grad_norm": 2.3948631286621094,
438
+ "learning_rate": 7.842222222222224e-06,
439
+ "loss": 0.0022,
440
+ "step": 1475
441
+ },
442
+ {
443
+ "epoch": 2.471169686985173,
444
+ "grad_norm": 0.3471105694770813,
445
+ "learning_rate": 7.786666666666666e-06,
446
+ "loss": 0.0034,
447
+ "step": 1500
448
+ },
449
+ {
450
+ "epoch": 2.471169686985173,
451
+ "eval_loss": 0.017010504379868507,
452
+ "eval_runtime": 1743.3725,
453
+ "eval_samples_per_second": 1.392,
454
+ "eval_steps_per_second": 0.174,
455
+ "eval_wer": 3.821952924726171,
456
+ "step": 1500
457
+ },
458
+ {
459
+ "epoch": 2.5123558484349258,
460
+ "grad_norm": 0.14169706404209137,
461
+ "learning_rate": 7.731111111111112e-06,
462
+ "loss": 0.0043,
463
+ "step": 1525
464
+ },
465
+ {
466
+ "epoch": 2.5535420098846786,
467
+ "grad_norm": 0.4921598732471466,
468
+ "learning_rate": 7.675555555555556e-06,
469
+ "loss": 0.0024,
470
+ "step": 1550
471
+ },
472
+ {
473
+ "epoch": 2.594728171334432,
474
+ "grad_norm": 0.20753732323646545,
475
+ "learning_rate": 7.620000000000001e-06,
476
+ "loss": 0.004,
477
+ "step": 1575
478
+ },
479
+ {
480
+ "epoch": 2.6359143327841847,
481
+ "grad_norm": 0.10961499810218811,
482
+ "learning_rate": 7.564444444444446e-06,
483
+ "loss": 0.004,
484
+ "step": 1600
485
+ },
486
+ {
487
+ "epoch": 2.6771004942339376,
488
+ "grad_norm": 1.0841516256332397,
489
+ "learning_rate": 7.50888888888889e-06,
490
+ "loss": 0.0046,
491
+ "step": 1625
492
+ },
493
+ {
494
+ "epoch": 2.7182866556836904,
495
+ "grad_norm": 0.12003188580274582,
496
+ "learning_rate": 7.453333333333334e-06,
497
+ "loss": 0.0023,
498
+ "step": 1650
499
+ },
500
+ {
501
+ "epoch": 2.7594728171334433,
502
+ "grad_norm": 0.055499833077192307,
503
+ "learning_rate": 7.3977777777777786e-06,
504
+ "loss": 0.0035,
505
+ "step": 1675
506
+ },
507
+ {
508
+ "epoch": 2.800658978583196,
509
+ "grad_norm": 2.9141526222229004,
510
+ "learning_rate": 7.342222222222223e-06,
511
+ "loss": 0.0023,
512
+ "step": 1700
513
+ },
514
+ {
515
+ "epoch": 2.841845140032949,
516
+ "grad_norm": 0.025740938261151314,
517
+ "learning_rate": 7.2866666666666675e-06,
518
+ "loss": 0.0024,
519
+ "step": 1725
520
+ },
521
+ {
522
+ "epoch": 2.883031301482702,
523
+ "grad_norm": 0.6345125436782837,
524
+ "learning_rate": 7.231111111111112e-06,
525
+ "loss": 0.004,
526
+ "step": 1750
527
+ },
528
+ {
529
+ "epoch": 2.9242174629324547,
530
+ "grad_norm": 0.5243808627128601,
531
+ "learning_rate": 7.1755555555555556e-06,
532
+ "loss": 0.0024,
533
+ "step": 1775
534
+ },
535
+ {
536
+ "epoch": 2.9654036243822075,
537
+ "grad_norm": 0.44930708408355713,
538
+ "learning_rate": 7.1200000000000004e-06,
539
+ "loss": 0.0025,
540
+ "step": 1800
541
+ },
542
+ {
543
+ "epoch": 3.0065897858319603,
544
+ "grad_norm": 1.6802186965942383,
545
+ "learning_rate": 7.0644444444444445e-06,
546
+ "loss": 0.0044,
547
+ "step": 1825
548
+ },
549
+ {
550
+ "epoch": 3.047775947281713,
551
+ "grad_norm": 0.2793377637863159,
552
+ "learning_rate": 7.008888888888889e-06,
553
+ "loss": 0.0015,
554
+ "step": 1850
555
+ },
556
+ {
557
+ "epoch": 3.088962108731466,
558
+ "grad_norm": 0.07968737185001373,
559
+ "learning_rate": 6.953333333333334e-06,
560
+ "loss": 0.0015,
561
+ "step": 1875
562
+ },
563
+ {
564
+ "epoch": 3.130148270181219,
565
+ "grad_norm": 0.04705784469842911,
566
+ "learning_rate": 6.897777777777779e-06,
567
+ "loss": 0.001,
568
+ "step": 1900
569
+ },
570
+ {
571
+ "epoch": 3.171334431630972,
572
+ "grad_norm": 0.1313919574022293,
573
+ "learning_rate": 6.842222222222222e-06,
574
+ "loss": 0.0008,
575
+ "step": 1925
576
+ },
577
+ {
578
+ "epoch": 3.212520593080725,
579
+ "grad_norm": 0.4405129551887512,
580
+ "learning_rate": 6.786666666666667e-06,
581
+ "loss": 0.0011,
582
+ "step": 1950
583
+ },
584
+ {
585
+ "epoch": 3.253706754530478,
586
+ "grad_norm": 1.2785202264785767,
587
+ "learning_rate": 6.731111111111111e-06,
588
+ "loss": 0.0017,
589
+ "step": 1975
590
+ },
591
+ {
592
+ "epoch": 3.2948929159802307,
593
+ "grad_norm": 0.04460221529006958,
594
+ "learning_rate": 6.675555555555556e-06,
595
+ "loss": 0.0008,
596
+ "step": 2000
597
+ },
598
+ {
599
+ "epoch": 3.2948929159802307,
600
+ "eval_loss": 0.015330803580582142,
601
+ "eval_runtime": 1719.9199,
602
+ "eval_samples_per_second": 1.411,
603
+ "eval_steps_per_second": 0.177,
604
+ "eval_wer": 3.5733706206789404,
605
+ "step": 2000
606
+ },
607
+ {
608
+ "epoch": 3.3360790774299836,
609
+ "grad_norm": 0.10665885359048843,
610
+ "learning_rate": 6.620000000000001e-06,
611
+ "loss": 0.0022,
612
+ "step": 2025
613
+ },
614
+ {
615
+ "epoch": 3.3772652388797364,
616
+ "grad_norm": 4.365774631500244,
617
+ "learning_rate": 6.564444444444446e-06,
618
+ "loss": 0.0013,
619
+ "step": 2050
620
+ },
621
+ {
622
+ "epoch": 3.4184514003294892,
623
+ "grad_norm": 0.2422148883342743,
624
+ "learning_rate": 6.508888888888889e-06,
625
+ "loss": 0.0011,
626
+ "step": 2075
627
+ },
628
+ {
629
+ "epoch": 3.459637561779242,
630
+ "grad_norm": 0.14427553117275238,
631
+ "learning_rate": 6.453333333333334e-06,
632
+ "loss": 0.0009,
633
+ "step": 2100
634
+ },
635
+ {
636
+ "epoch": 3.500823723228995,
637
+ "grad_norm": 0.0224087405949831,
638
+ "learning_rate": 6.397777777777778e-06,
639
+ "loss": 0.0005,
640
+ "step": 2125
641
+ },
642
+ {
643
+ "epoch": 3.5420098846787478,
644
+ "grad_norm": 0.052274756133556366,
645
+ "learning_rate": 6.342222222222223e-06,
646
+ "loss": 0.0012,
647
+ "step": 2150
648
+ },
649
+ {
650
+ "epoch": 3.583196046128501,
651
+ "grad_norm": 0.12983651459217072,
652
+ "learning_rate": 6.286666666666668e-06,
653
+ "loss": 0.0011,
654
+ "step": 2175
655
+ },
656
+ {
657
+ "epoch": 3.624382207578254,
658
+ "grad_norm": 0.17136234045028687,
659
+ "learning_rate": 6.231111111111111e-06,
660
+ "loss": 0.0004,
661
+ "step": 2200
662
+ },
663
+ {
664
+ "epoch": 3.6655683690280068,
665
+ "grad_norm": 0.02376146800816059,
666
+ "learning_rate": 6.175555555555556e-06,
667
+ "loss": 0.0006,
668
+ "step": 2225
669
+ },
670
+ {
671
+ "epoch": 3.7067545304777596,
672
+ "grad_norm": 0.020898204296827316,
673
+ "learning_rate": 6.120000000000001e-06,
674
+ "loss": 0.0004,
675
+ "step": 2250
676
+ },
677
+ {
678
+ "epoch": 3.7479406919275124,
679
+ "grad_norm": 0.011864184401929379,
680
+ "learning_rate": 6.064444444444445e-06,
681
+ "loss": 0.0014,
682
+ "step": 2275
683
+ },
684
+ {
685
+ "epoch": 3.7891268533772653,
686
+ "grad_norm": 0.07441503554582596,
687
+ "learning_rate": 6.00888888888889e-06,
688
+ "loss": 0.0005,
689
+ "step": 2300
690
+ },
691
+ {
692
+ "epoch": 3.830313014827018,
693
+ "grad_norm": 0.09472518414258957,
694
+ "learning_rate": 5.9533333333333345e-06,
695
+ "loss": 0.0008,
696
+ "step": 2325
697
+ },
698
+ {
699
+ "epoch": 3.871499176276771,
700
+ "grad_norm": 0.5632221698760986,
701
+ "learning_rate": 5.897777777777778e-06,
702
+ "loss": 0.001,
703
+ "step": 2350
704
+ },
705
+ {
706
+ "epoch": 3.912685337726524,
707
+ "grad_norm": 0.02372151054441929,
708
+ "learning_rate": 5.8422222222222226e-06,
709
+ "loss": 0.0008,
710
+ "step": 2375
711
+ },
712
+ {
713
+ "epoch": 3.9538714991762767,
714
+ "grad_norm": 0.324942022562027,
715
+ "learning_rate": 5.7866666666666674e-06,
716
+ "loss": 0.0004,
717
+ "step": 2400
718
+ },
719
+ {
720
+ "epoch": 3.9950576606260295,
721
+ "grad_norm": 0.022629514336586,
722
+ "learning_rate": 5.7311111111111115e-06,
723
+ "loss": 0.0003,
724
+ "step": 2425
725
+ },
726
+ {
727
+ "epoch": 4.036243822075782,
728
+ "grad_norm": 0.012355553917586803,
729
+ "learning_rate": 5.675555555555556e-06,
730
+ "loss": 0.0005,
731
+ "step": 2450
732
+ },
733
+ {
734
+ "epoch": 4.077429983525535,
735
+ "grad_norm": 0.021213717758655548,
736
+ "learning_rate": 5.620000000000001e-06,
737
+ "loss": 0.0005,
738
+ "step": 2475
739
+ },
740
+ {
741
+ "epoch": 4.118616144975288,
742
+ "grad_norm": 0.01894320733845234,
743
+ "learning_rate": 5.5644444444444444e-06,
744
+ "loss": 0.0003,
745
+ "step": 2500
746
+ },
747
+ {
748
+ "epoch": 4.118616144975288,
749
+ "eval_loss": 0.013398992829024792,
750
+ "eval_runtime": 1739.4064,
751
+ "eval_samples_per_second": 1.395,
752
+ "eval_steps_per_second": 0.175,
753
+ "eval_wer": 2.9130738755534837,
754
+ "step": 2500
755
+ }
756
+ ],
757
+ "logging_steps": 25,
758
+ "max_steps": 5000,
759
+ "num_input_tokens_seen": 0,
760
+ "num_train_epochs": 9,
761
+ "save_steps": 500,
762
+ "total_flos": 1.153879864639488e+19,
763
+ "train_batch_size": 16,
764
+ "trial_name": null,
765
+ "trial_params": null
766
+ }
checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27edbd1e3a3b34ca0020e516a6bc9ecb1ba1e53637c8b43080efc2210b958bc1
3
+ size 5176