Upload folder using huggingface_hub
Browse files- config.json +60 -0
- generation_config.json +262 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +15 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +379 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.1,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"begin_suppress_tokens": null,
|
| 10 |
+
"bos_token_id": 50257,
|
| 11 |
+
"classifier_proj_size": 256,
|
| 12 |
+
"d_model": 768,
|
| 13 |
+
"decoder_attention_heads": 12,
|
| 14 |
+
"decoder_ffn_dim": 3072,
|
| 15 |
+
"decoder_layerdrop": 0.0,
|
| 16 |
+
"decoder_layers": 12,
|
| 17 |
+
"decoder_start_token_id": 50258,
|
| 18 |
+
"dropout": 0.1,
|
| 19 |
+
"encoder_attention_heads": 12,
|
| 20 |
+
"encoder_ffn_dim": 3072,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 12,
|
| 23 |
+
"eos_token_id": 50257,
|
| 24 |
+
"forced_decoder_ids": [
|
| 25 |
+
[
|
| 26 |
+
1,
|
| 27 |
+
50259
|
| 28 |
+
],
|
| 29 |
+
[
|
| 30 |
+
2,
|
| 31 |
+
50359
|
| 32 |
+
],
|
| 33 |
+
[
|
| 34 |
+
3,
|
| 35 |
+
50363
|
| 36 |
+
]
|
| 37 |
+
],
|
| 38 |
+
"init_std": 0.02,
|
| 39 |
+
"is_encoder_decoder": true,
|
| 40 |
+
"mask_feature_length": 10,
|
| 41 |
+
"mask_feature_min_masks": 0,
|
| 42 |
+
"mask_feature_prob": 0.0,
|
| 43 |
+
"mask_time_length": 10,
|
| 44 |
+
"mask_time_min_masks": 2,
|
| 45 |
+
"mask_time_prob": 0.05,
|
| 46 |
+
"max_length": null,
|
| 47 |
+
"max_source_positions": 1500,
|
| 48 |
+
"max_target_positions": 448,
|
| 49 |
+
"median_filter_width": 7,
|
| 50 |
+
"model_type": "whisper",
|
| 51 |
+
"num_hidden_layers": 12,
|
| 52 |
+
"num_mel_bins": 80,
|
| 53 |
+
"pad_token_id": 50257,
|
| 54 |
+
"scale_embedding": false,
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.51.3",
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"use_weighted_layer_sum": false,
|
| 59 |
+
"vocab_size": 51865
|
| 60 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"max_initial_timestamp_index": 50,
|
| 164 |
+
"max_length": 448,
|
| 165 |
+
"no_timestamps_token_id": 50363,
|
| 166 |
+
"pad_token_id": 50257,
|
| 167 |
+
"prev_sot_token_id": 50361,
|
| 168 |
+
"return_timestamps": false,
|
| 169 |
+
"suppress_tokens": [
|
| 170 |
+
1,
|
| 171 |
+
2,
|
| 172 |
+
7,
|
| 173 |
+
8,
|
| 174 |
+
9,
|
| 175 |
+
10,
|
| 176 |
+
14,
|
| 177 |
+
25,
|
| 178 |
+
26,
|
| 179 |
+
27,
|
| 180 |
+
28,
|
| 181 |
+
29,
|
| 182 |
+
31,
|
| 183 |
+
58,
|
| 184 |
+
59,
|
| 185 |
+
60,
|
| 186 |
+
61,
|
| 187 |
+
62,
|
| 188 |
+
63,
|
| 189 |
+
90,
|
| 190 |
+
91,
|
| 191 |
+
92,
|
| 192 |
+
93,
|
| 193 |
+
359,
|
| 194 |
+
503,
|
| 195 |
+
522,
|
| 196 |
+
542,
|
| 197 |
+
873,
|
| 198 |
+
893,
|
| 199 |
+
902,
|
| 200 |
+
918,
|
| 201 |
+
922,
|
| 202 |
+
931,
|
| 203 |
+
1350,
|
| 204 |
+
1853,
|
| 205 |
+
1982,
|
| 206 |
+
2460,
|
| 207 |
+
2627,
|
| 208 |
+
3246,
|
| 209 |
+
3253,
|
| 210 |
+
3268,
|
| 211 |
+
3536,
|
| 212 |
+
3846,
|
| 213 |
+
3961,
|
| 214 |
+
4183,
|
| 215 |
+
4667,
|
| 216 |
+
6585,
|
| 217 |
+
6647,
|
| 218 |
+
7273,
|
| 219 |
+
9061,
|
| 220 |
+
9383,
|
| 221 |
+
10428,
|
| 222 |
+
10929,
|
| 223 |
+
11938,
|
| 224 |
+
12033,
|
| 225 |
+
12331,
|
| 226 |
+
12562,
|
| 227 |
+
13793,
|
| 228 |
+
14157,
|
| 229 |
+
14635,
|
| 230 |
+
15265,
|
| 231 |
+
15618,
|
| 232 |
+
16553,
|
| 233 |
+
16604,
|
| 234 |
+
18362,
|
| 235 |
+
18956,
|
| 236 |
+
20075,
|
| 237 |
+
21675,
|
| 238 |
+
22520,
|
| 239 |
+
26130,
|
| 240 |
+
26161,
|
| 241 |
+
26435,
|
| 242 |
+
28279,
|
| 243 |
+
29464,
|
| 244 |
+
31650,
|
| 245 |
+
32302,
|
| 246 |
+
32470,
|
| 247 |
+
36865,
|
| 248 |
+
42863,
|
| 249 |
+
47425,
|
| 250 |
+
49870,
|
| 251 |
+
50254,
|
| 252 |
+
50258,
|
| 253 |
+
50360,
|
| 254 |
+
50361,
|
| 255 |
+
50362
|
| 256 |
+
],
|
| 257 |
+
"task_to_id": {
|
| 258 |
+
"transcribe": 50359,
|
| 259 |
+
"translate": 50358
|
| 260 |
+
},
|
| 261 |
+
"transformers_version": "4.51.3"
|
| 262 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a73d9aeab83525ee7e8c81e90f91476c2c9b7e2ca4dc2d89281be12eedc31166
|
| 3 |
+
size 966995080
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62178d815f3300444c0eed1cf34bb976ed15ee5cfb9eb219bbd30f4cd862b97f
|
| 3 |
+
size 1925064044
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 80,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"processor_class": "WhisperProcessor",
|
| 13 |
+
"return_attention_mask": false,
|
| 14 |
+
"sampling_rate": 16000
|
| 15 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f40a1e34e1b5499777b9991cb77553fcdecb7a67fe3aa81eda7fac41cc586bd6
|
| 3 |
+
size 14244
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f40e71be06de8fb9ae6a5f8fea216cb8368dbe5f20e37d014ae1c975692ad02f
|
| 3 |
+
size 988
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e69d23420047be011a10f60dd1967b2bc18f0252772668dad3447ec41167ec4e
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,379 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 400,
|
| 3 |
+
"best_metric": 0.4180468303826385,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5574136008918618,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01858045336306206,
|
| 14 |
+
"grad_norm": 34.34955596923828,
|
| 15 |
+
"learning_rate": 9.829145728643216e-07,
|
| 16 |
+
"loss": 5.3485,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03716090672612412,
|
| 21 |
+
"grad_norm": 22.25047492980957,
|
| 22 |
+
"learning_rate": 9.57788944723618e-07,
|
| 23 |
+
"loss": 2.4671,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03716090672612412,
|
| 28 |
+
"eval_loss": 1.6380335092544556,
|
| 29 |
+
"eval_runtime": 805.1735,
|
| 30 |
+
"eval_samples_per_second": 1.584,
|
| 31 |
+
"eval_steps_per_second": 0.099,
|
| 32 |
+
"eval_wer": 1.5022844089091947,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.055741360089186176,
|
| 37 |
+
"grad_norm": 21.50294303894043,
|
| 38 |
+
"learning_rate": 9.326633165829145e-07,
|
| 39 |
+
"loss": 1.7199,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.07432181345224824,
|
| 44 |
+
"grad_norm": 19.382465362548828,
|
| 45 |
+
"learning_rate": 9.07537688442211e-07,
|
| 46 |
+
"loss": 1.582,
|
| 47 |
+
"step": 200
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.07432181345224824,
|
| 51 |
+
"eval_loss": 1.4373680353164673,
|
| 52 |
+
"eval_runtime": 693.6852,
|
| 53 |
+
"eval_samples_per_second": 1.838,
|
| 54 |
+
"eval_steps_per_second": 0.115,
|
| 55 |
+
"eval_wer": 0.5612031220255093,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.09290226681531029,
|
| 60 |
+
"grad_norm": 20.734386444091797,
|
| 61 |
+
"learning_rate": 8.824120603015076e-07,
|
| 62 |
+
"loss": 1.5038,
|
| 63 |
+
"step": 250
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.11148272017837235,
|
| 67 |
+
"grad_norm": 18.240798950195312,
|
| 68 |
+
"learning_rate": 8.57286432160804e-07,
|
| 69 |
+
"loss": 1.429,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.11148272017837235,
|
| 74 |
+
"eval_loss": 1.3298848867416382,
|
| 75 |
+
"eval_runtime": 606.9157,
|
| 76 |
+
"eval_samples_per_second": 2.101,
|
| 77 |
+
"eval_steps_per_second": 0.132,
|
| 78 |
+
"eval_wer": 0.45202741290691034,
|
| 79 |
+
"step": 300
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1300631735414344,
|
| 83 |
+
"grad_norm": 21.94469451904297,
|
| 84 |
+
"learning_rate": 8.321608040201005e-07,
|
| 85 |
+
"loss": 1.3683,
|
| 86 |
+
"step": 350
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.14864362690449648,
|
| 90 |
+
"grad_norm": 19.457420349121094,
|
| 91 |
+
"learning_rate": 8.07035175879397e-07,
|
| 92 |
+
"loss": 1.3,
|
| 93 |
+
"step": 400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.14864362690449648,
|
| 97 |
+
"eval_loss": 1.2301665544509888,
|
| 98 |
+
"eval_runtime": 677.8506,
|
| 99 |
+
"eval_samples_per_second": 1.881,
|
| 100 |
+
"eval_steps_per_second": 0.118,
|
| 101 |
+
"eval_wer": 0.4180468303826385,
|
| 102 |
+
"step": 400
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.16722408026755853,
|
| 106 |
+
"grad_norm": 17.751752853393555,
|
| 107 |
+
"learning_rate": 7.819095477386934e-07,
|
| 108 |
+
"loss": 1.2282,
|
| 109 |
+
"step": 450
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.18580453363062058,
|
| 113 |
+
"grad_norm": 18.627307891845703,
|
| 114 |
+
"learning_rate": 7.567839195979899e-07,
|
| 115 |
+
"loss": 1.1276,
|
| 116 |
+
"step": 500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.18580453363062058,
|
| 120 |
+
"eval_loss": 1.1017953157424927,
|
| 121 |
+
"eval_runtime": 590.5238,
|
| 122 |
+
"eval_samples_per_second": 2.159,
|
| 123 |
+
"eval_steps_per_second": 0.135,
|
| 124 |
+
"eval_wer": 0.5512088330477822,
|
| 125 |
+
"step": 500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.20438498699368265,
|
| 129 |
+
"grad_norm": 20.09351921081543,
|
| 130 |
+
"learning_rate": 7.316582914572864e-07,
|
| 131 |
+
"loss": 1.0899,
|
| 132 |
+
"step": 550
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.2229654403567447,
|
| 136 |
+
"grad_norm": 18.62831687927246,
|
| 137 |
+
"learning_rate": 7.065326633165829e-07,
|
| 138 |
+
"loss": 0.9529,
|
| 139 |
+
"step": 600
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.2229654403567447,
|
| 143 |
+
"eval_loss": 0.8959304690361023,
|
| 144 |
+
"eval_runtime": 727.8831,
|
| 145 |
+
"eval_samples_per_second": 1.752,
|
| 146 |
+
"eval_steps_per_second": 0.11,
|
| 147 |
+
"eval_wer": 0.9183323814962878,
|
| 148 |
+
"step": 600
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.24154589371980675,
|
| 152 |
+
"grad_norm": 10.14380931854248,
|
| 153 |
+
"learning_rate": 6.814070351758794e-07,
|
| 154 |
+
"loss": 0.6041,
|
| 155 |
+
"step": 650
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.2601263470828688,
|
| 159 |
+
"grad_norm": 3.76615571975708,
|
| 160 |
+
"learning_rate": 6.562814070351759e-07,
|
| 161 |
+
"loss": 0.1477,
|
| 162 |
+
"step": 700
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.2601263470828688,
|
| 166 |
+
"eval_loss": 0.2668490707874298,
|
| 167 |
+
"eval_runtime": 600.2013,
|
| 168 |
+
"eval_samples_per_second": 2.124,
|
| 169 |
+
"eval_steps_per_second": 0.133,
|
| 170 |
+
"eval_wer": 1.4350847134970492,
|
| 171 |
+
"step": 700
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2787068004459309,
|
| 175 |
+
"grad_norm": 6.2711405754089355,
|
| 176 |
+
"learning_rate": 6.311557788944724e-07,
|
| 177 |
+
"loss": 0.1256,
|
| 178 |
+
"step": 750
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.29728725380899296,
|
| 182 |
+
"grad_norm": 5.286526679992676,
|
| 183 |
+
"learning_rate": 6.060301507537688e-07,
|
| 184 |
+
"loss": 0.1072,
|
| 185 |
+
"step": 800
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.29728725380899296,
|
| 189 |
+
"eval_loss": 0.24842901527881622,
|
| 190 |
+
"eval_runtime": 552.4605,
|
| 191 |
+
"eval_samples_per_second": 2.308,
|
| 192 |
+
"eval_steps_per_second": 0.145,
|
| 193 |
+
"eval_wer": 1.1959832476679992,
|
| 194 |
+
"step": 800
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.315867707172055,
|
| 198 |
+
"grad_norm": 3.480281114578247,
|
| 199 |
+
"learning_rate": 5.809045226130653e-07,
|
| 200 |
+
"loss": 0.0907,
|
| 201 |
+
"step": 850
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.33444816053511706,
|
| 205 |
+
"grad_norm": 5.403326034545898,
|
| 206 |
+
"learning_rate": 5.557788944723618e-07,
|
| 207 |
+
"loss": 0.0954,
|
| 208 |
+
"step": 900
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.33444816053511706,
|
| 212 |
+
"eval_loss": 0.23930072784423828,
|
| 213 |
+
"eval_runtime": 560.9273,
|
| 214 |
+
"eval_samples_per_second": 2.273,
|
| 215 |
+
"eval_steps_per_second": 0.143,
|
| 216 |
+
"eval_wer": 1.3522748905387398,
|
| 217 |
+
"step": 900
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.35302861389817913,
|
| 221 |
+
"grad_norm": 5.204483509063721,
|
| 222 |
+
"learning_rate": 5.306532663316583e-07,
|
| 223 |
+
"loss": 0.0927,
|
| 224 |
+
"step": 950
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.37160906726124115,
|
| 228 |
+
"grad_norm": 3.2576818466186523,
|
| 229 |
+
"learning_rate": 5.055276381909547e-07,
|
| 230 |
+
"loss": 0.0848,
|
| 231 |
+
"step": 1000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.37160906726124115,
|
| 235 |
+
"eval_loss": 0.23669640719890594,
|
| 236 |
+
"eval_runtime": 548.8862,
|
| 237 |
+
"eval_samples_per_second": 2.323,
|
| 238 |
+
"eval_steps_per_second": 0.146,
|
| 239 |
+
"eval_wer": 1.30001903674091,
|
| 240 |
+
"step": 1000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.39018952062430323,
|
| 244 |
+
"grad_norm": 3.704416036605835,
|
| 245 |
+
"learning_rate": 4.804020100502513e-07,
|
| 246 |
+
"loss": 0.0882,
|
| 247 |
+
"step": 1050
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4087699739873653,
|
| 251 |
+
"grad_norm": 5.242008209228516,
|
| 252 |
+
"learning_rate": 4.552763819095477e-07,
|
| 253 |
+
"loss": 0.0718,
|
| 254 |
+
"step": 1100
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4087699739873653,
|
| 258 |
+
"eval_loss": 0.2329600602388382,
|
| 259 |
+
"eval_runtime": 546.5227,
|
| 260 |
+
"eval_samples_per_second": 2.333,
|
| 261 |
+
"eval_steps_per_second": 0.146,
|
| 262 |
+
"eval_wer": 1.222158766419189,
|
| 263 |
+
"step": 1100
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.42735042735042733,
|
| 267 |
+
"grad_norm": 5.1349778175354,
|
| 268 |
+
"learning_rate": 4.301507537688442e-07,
|
| 269 |
+
"loss": 0.0906,
|
| 270 |
+
"step": 1150
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.4459308807134894,
|
| 274 |
+
"grad_norm": 3.793863534927368,
|
| 275 |
+
"learning_rate": 4.050251256281407e-07,
|
| 276 |
+
"loss": 0.0701,
|
| 277 |
+
"step": 1200
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.4459308807134894,
|
| 281 |
+
"eval_loss": 0.23290176689624786,
|
| 282 |
+
"eval_runtime": 535.3453,
|
| 283 |
+
"eval_samples_per_second": 2.382,
|
| 284 |
+
"eval_steps_per_second": 0.149,
|
| 285 |
+
"eval_wer": 1.2410051399200457,
|
| 286 |
+
"step": 1200
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.4645113340765515,
|
| 290 |
+
"grad_norm": 5.521825790405273,
|
| 291 |
+
"learning_rate": 3.7989949748743716e-07,
|
| 292 |
+
"loss": 0.0645,
|
| 293 |
+
"step": 1250
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.4830917874396135,
|
| 297 |
+
"grad_norm": 4.690304756164551,
|
| 298 |
+
"learning_rate": 3.547738693467336e-07,
|
| 299 |
+
"loss": 0.0712,
|
| 300 |
+
"step": 1300
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.4830917874396135,
|
| 304 |
+
"eval_loss": 0.23211538791656494,
|
| 305 |
+
"eval_runtime": 551.1009,
|
| 306 |
+
"eval_samples_per_second": 2.314,
|
| 307 |
+
"eval_steps_per_second": 0.145,
|
| 308 |
+
"eval_wer": 1.1816105082809822,
|
| 309 |
+
"step": 1300
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.5016722408026756,
|
| 313 |
+
"grad_norm": 4.859287738800049,
|
| 314 |
+
"learning_rate": 3.2964824120603014e-07,
|
| 315 |
+
"loss": 0.0716,
|
| 316 |
+
"step": 1350
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.5202526941657376,
|
| 320 |
+
"grad_norm": 7.05725622177124,
|
| 321 |
+
"learning_rate": 3.045226130653266e-07,
|
| 322 |
+
"loss": 0.062,
|
| 323 |
+
"step": 1400
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.5202526941657376,
|
| 327 |
+
"eval_loss": 0.2323189228773117,
|
| 328 |
+
"eval_runtime": 524.7467,
|
| 329 |
+
"eval_samples_per_second": 2.43,
|
| 330 |
+
"eval_steps_per_second": 0.152,
|
| 331 |
+
"eval_wer": 1.0801446792309157,
|
| 332 |
+
"step": 1400
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5388331475287997,
|
| 336 |
+
"grad_norm": 5.441325664520264,
|
| 337 |
+
"learning_rate": 2.793969849246231e-07,
|
| 338 |
+
"loss": 0.0669,
|
| 339 |
+
"step": 1450
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5574136008918618,
|
| 343 |
+
"grad_norm": 6.692004680633545,
|
| 344 |
+
"learning_rate": 2.542713567839196e-07,
|
| 345 |
+
"loss": 0.0621,
|
| 346 |
+
"step": 1500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5574136008918618,
|
| 350 |
+
"eval_loss": 0.23031273484230042,
|
| 351 |
+
"eval_runtime": 523.517,
|
| 352 |
+
"eval_samples_per_second": 2.435,
|
| 353 |
+
"eval_steps_per_second": 0.153,
|
| 354 |
+
"eval_wer": 1.064724919093851,
|
| 355 |
+
"step": 1500
|
| 356 |
+
}
|
| 357 |
+
],
|
| 358 |
+
"logging_steps": 50,
|
| 359 |
+
"max_steps": 2000,
|
| 360 |
+
"num_input_tokens_seen": 0,
|
| 361 |
+
"num_train_epochs": 1,
|
| 362 |
+
"save_steps": 500,
|
| 363 |
+
"stateful_callbacks": {
|
| 364 |
+
"TrainerControl": {
|
| 365 |
+
"args": {
|
| 366 |
+
"should_epoch_stop": false,
|
| 367 |
+
"should_evaluate": false,
|
| 368 |
+
"should_log": false,
|
| 369 |
+
"should_save": true,
|
| 370 |
+
"should_training_stop": false
|
| 371 |
+
},
|
| 372 |
+
"attributes": {}
|
| 373 |
+
}
|
| 374 |
+
},
|
| 375 |
+
"total_flos": 6.92604960768e+18,
|
| 376 |
+
"train_batch_size": 16,
|
| 377 |
+
"trial_name": null,
|
| 378 |
+
"trial_params": null
|
| 379 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:953c4e492671f3a7ae54d46ed5191407672fe2f8334898c8fec5c583b227b7fa
|
| 3 |
+
size 5432
|