Upload full training state for checkpoint-7000
Browse files- checkpoint-7000/config.json +65 -0
- checkpoint-7000/generation_config.json +264 -0
- checkpoint-7000/model.safetensors +3 -0
- checkpoint-7000/optimizer.pt +3 -0
- checkpoint-7000/preprocessor_config.json +14 -0
- checkpoint-7000/rng_state.pth +3 -0
- checkpoint-7000/scheduler.pt +3 -0
- checkpoint-7000/trainer_state.json +581 -0
- checkpoint-7000/training_args.bin +3 -0
checkpoint-7000/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 |
+
50302
|
| 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": "4.36.2",
|
| 62 |
+
"use_cache": false,
|
| 63 |
+
"use_weighted_layer_sum": false,
|
| 64 |
+
"vocab_size": 51865
|
| 65 |
+
}
|
checkpoint-7000/generation_config.json
ADDED
|
@@ -0,0 +1,264 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
50358,
|
| 254 |
+
50359,
|
| 255 |
+
50360,
|
| 256 |
+
50361,
|
| 257 |
+
50362
|
| 258 |
+
],
|
| 259 |
+
"task_to_id": {
|
| 260 |
+
"transcribe": 50359,
|
| 261 |
+
"translate": 50358
|
| 262 |
+
},
|
| 263 |
+
"transformers_version": "4.36.2"
|
| 264 |
+
}
|
checkpoint-7000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:053945de1e14dfcbaaa254d648fc53dcd7fa4781434b3b19211e436e40bc091b
|
| 3 |
+
size 966995080
|
checkpoint-7000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0c00e13325c605a87d23368d1fd7e429f859557669199328b9746191c87e46d
|
| 3 |
+
size 1925064509
|
checkpoint-7000/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-7000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:260fcb63f4efd81714ef75f6f87c57026199053b29365d71f9fc23eedb93edcc
|
| 3 |
+
size 14645
|
checkpoint-7000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78553e0d8f7164fd934324330911507d8400f599547a11b31f23fbe21b567ba3
|
| 3 |
+
size 1465
|
checkpoint-7000/trainer_state.json
ADDED
|
@@ -0,0 +1,581 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 83.17927042175872,
|
| 3 |
+
"best_model_checkpoint": "./whisper-bangla-hf/checkpoint-6000",
|
| 4 |
+
"epoch": 6.2048726467331115,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 7000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09,
|
| 13 |
+
"learning_rate": 1.98e-06,
|
| 14 |
+
"loss": 1.6147,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.18,
|
| 19 |
+
"learning_rate": 3.980000000000001e-06,
|
| 20 |
+
"loss": 1.0704,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.27,
|
| 25 |
+
"learning_rate": 5.98e-06,
|
| 26 |
+
"loss": 0.7217,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.35,
|
| 31 |
+
"learning_rate": 7.980000000000002e-06,
|
| 32 |
+
"loss": 0.611,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.44,
|
| 37 |
+
"learning_rate": 9.980000000000001e-06,
|
| 38 |
+
"loss": 0.5574,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.44,
|
| 43 |
+
"eval_cer": 61.38752058108099,
|
| 44 |
+
"eval_loss": 0.5316746234893799,
|
| 45 |
+
"eval_runtime": 8394.2071,
|
| 46 |
+
"eval_samples_per_second": 0.19,
|
| 47 |
+
"eval_steps_per_second": 0.19,
|
| 48 |
+
"eval_wer": 92.7630249012221,
|
| 49 |
+
"step": 500
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.53,
|
| 53 |
+
"learning_rate": 9.717142857142858e-06,
|
| 54 |
+
"loss": 0.5109,
|
| 55 |
+
"step": 600
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.62,
|
| 59 |
+
"learning_rate": 9.431428571428573e-06,
|
| 60 |
+
"loss": 0.4898,
|
| 61 |
+
"step": 700
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.71,
|
| 65 |
+
"learning_rate": 9.145714285714287e-06,
|
| 66 |
+
"loss": 0.4577,
|
| 67 |
+
"step": 800
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.8,
|
| 71 |
+
"learning_rate": 8.860000000000002e-06,
|
| 72 |
+
"loss": 0.4492,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.89,
|
| 77 |
+
"learning_rate": 8.574285714285714e-06,
|
| 78 |
+
"loss": 0.4346,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.89,
|
| 83 |
+
"eval_cer": 58.214138101594315,
|
| 84 |
+
"eval_loss": 0.4306719899177551,
|
| 85 |
+
"eval_runtime": 8331.4518,
|
| 86 |
+
"eval_samples_per_second": 0.191,
|
| 87 |
+
"eval_steps_per_second": 0.191,
|
| 88 |
+
"eval_wer": 88.11173389690343,
|
| 89 |
+
"step": 1000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.97,
|
| 93 |
+
"learning_rate": 8.288571428571429e-06,
|
| 94 |
+
"loss": 0.4204,
|
| 95 |
+
"step": 1100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.06,
|
| 99 |
+
"learning_rate": 8.002857142857143e-06,
|
| 100 |
+
"loss": 0.3878,
|
| 101 |
+
"step": 1200
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.15,
|
| 105 |
+
"learning_rate": 7.717142857142857e-06,
|
| 106 |
+
"loss": 0.3772,
|
| 107 |
+
"step": 1300
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.24,
|
| 111 |
+
"learning_rate": 7.431428571428572e-06,
|
| 112 |
+
"loss": 0.3754,
|
| 113 |
+
"step": 1400
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.33,
|
| 117 |
+
"learning_rate": 7.145714285714286e-06,
|
| 118 |
+
"loss": 0.3697,
|
| 119 |
+
"step": 1500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.33,
|
| 123 |
+
"eval_cer": 57.30145609030606,
|
| 124 |
+
"eval_loss": 0.39850279688835144,
|
| 125 |
+
"eval_runtime": 8325.9634,
|
| 126 |
+
"eval_samples_per_second": 0.191,
|
| 127 |
+
"eval_steps_per_second": 0.191,
|
| 128 |
+
"eval_wer": 86.46880455756684,
|
| 129 |
+
"step": 1500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.42,
|
| 133 |
+
"learning_rate": 6.860000000000001e-06,
|
| 134 |
+
"loss": 0.3644,
|
| 135 |
+
"step": 1600
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.51,
|
| 139 |
+
"learning_rate": 6.574285714285716e-06,
|
| 140 |
+
"loss": 0.3548,
|
| 141 |
+
"step": 1700
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.59,
|
| 145 |
+
"learning_rate": 6.288571428571429e-06,
|
| 146 |
+
"loss": 0.3504,
|
| 147 |
+
"step": 1800
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.68,
|
| 151 |
+
"learning_rate": 6.0028571428571435e-06,
|
| 152 |
+
"loss": 0.3564,
|
| 153 |
+
"step": 1900
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.77,
|
| 157 |
+
"learning_rate": 5.717142857142858e-06,
|
| 158 |
+
"loss": 0.3485,
|
| 159 |
+
"step": 2000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.77,
|
| 163 |
+
"eval_cer": 55.88703612106758,
|
| 164 |
+
"eval_loss": 0.3795246481895447,
|
| 165 |
+
"eval_runtime": 8397.4514,
|
| 166 |
+
"eval_samples_per_second": 0.19,
|
| 167 |
+
"eval_steps_per_second": 0.19,
|
| 168 |
+
"eval_wer": 84.98575760360195,
|
| 169 |
+
"step": 2000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.86,
|
| 173 |
+
"learning_rate": 5.431428571428572e-06,
|
| 174 |
+
"loss": 0.3461,
|
| 175 |
+
"step": 2100
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.95,
|
| 179 |
+
"learning_rate": 5.145714285714286e-06,
|
| 180 |
+
"loss": 0.3411,
|
| 181 |
+
"step": 2200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.04,
|
| 185 |
+
"learning_rate": 4.86e-06,
|
| 186 |
+
"loss": 0.3177,
|
| 187 |
+
"step": 2300
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 2.13,
|
| 191 |
+
"learning_rate": 4.574285714285714e-06,
|
| 192 |
+
"loss": 0.2882,
|
| 193 |
+
"step": 2400
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.22,
|
| 197 |
+
"learning_rate": 4.288571428571429e-06,
|
| 198 |
+
"loss": 0.2929,
|
| 199 |
+
"step": 2500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 2.22,
|
| 203 |
+
"eval_cer": 56.317290818297,
|
| 204 |
+
"eval_loss": 0.37166279554367065,
|
| 205 |
+
"eval_runtime": 7512.7652,
|
| 206 |
+
"eval_samples_per_second": 0.212,
|
| 207 |
+
"eval_steps_per_second": 0.212,
|
| 208 |
+
"eval_wer": 84.28006983368557,
|
| 209 |
+
"step": 2500
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.3,
|
| 213 |
+
"learning_rate": 4.002857142857143e-06,
|
| 214 |
+
"loss": 0.295,
|
| 215 |
+
"step": 2600
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.39,
|
| 219 |
+
"learning_rate": 3.7171428571428575e-06,
|
| 220 |
+
"loss": 0.2915,
|
| 221 |
+
"step": 2700
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.48,
|
| 225 |
+
"learning_rate": 3.431428571428572e-06,
|
| 226 |
+
"loss": 0.2875,
|
| 227 |
+
"step": 2800
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.57,
|
| 231 |
+
"learning_rate": 3.1457142857142858e-06,
|
| 232 |
+
"loss": 0.2839,
|
| 233 |
+
"step": 2900
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.66,
|
| 237 |
+
"learning_rate": 2.86e-06,
|
| 238 |
+
"loss": 0.2917,
|
| 239 |
+
"step": 3000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.66,
|
| 243 |
+
"eval_cer": 55.279597796553894,
|
| 244 |
+
"eval_loss": 0.36236926913261414,
|
| 245 |
+
"eval_runtime": 7483.763,
|
| 246 |
+
"eval_samples_per_second": 0.213,
|
| 247 |
+
"eval_steps_per_second": 0.213,
|
| 248 |
+
"eval_wer": 83.4328769640724,
|
| 249 |
+
"step": 3000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.75,
|
| 253 |
+
"learning_rate": 2.574285714285715e-06,
|
| 254 |
+
"loss": 0.2861,
|
| 255 |
+
"step": 3100
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.84,
|
| 259 |
+
"learning_rate": 2.288571428571429e-06,
|
| 260 |
+
"loss": 0.2838,
|
| 261 |
+
"step": 3200
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.92,
|
| 265 |
+
"learning_rate": 2.0028571428571432e-06,
|
| 266 |
+
"loss": 0.2787,
|
| 267 |
+
"step": 3300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.01,
|
| 271 |
+
"learning_rate": 1.7171428571428572e-06,
|
| 272 |
+
"loss": 0.2762,
|
| 273 |
+
"step": 3400
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 3.1,
|
| 277 |
+
"learning_rate": 1.4314285714285717e-06,
|
| 278 |
+
"loss": 0.2522,
|
| 279 |
+
"step": 3500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 3.1,
|
| 283 |
+
"eval_cer": 55.887713687519906,
|
| 284 |
+
"eval_loss": 0.3631547689437866,
|
| 285 |
+
"eval_runtime": 7499.8064,
|
| 286 |
+
"eval_samples_per_second": 0.213,
|
| 287 |
+
"eval_steps_per_second": 0.213,
|
| 288 |
+
"eval_wer": 83.74161536341083,
|
| 289 |
+
"step": 3500
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.19,
|
| 293 |
+
"learning_rate": 1.1457142857142859e-06,
|
| 294 |
+
"loss": 0.2496,
|
| 295 |
+
"step": 3600
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.28,
|
| 299 |
+
"learning_rate": 8.6e-07,
|
| 300 |
+
"loss": 0.2463,
|
| 301 |
+
"step": 3700
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 3.37,
|
| 305 |
+
"learning_rate": 5.742857142857143e-07,
|
| 306 |
+
"loss": 0.2428,
|
| 307 |
+
"step": 3800
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 3.46,
|
| 311 |
+
"learning_rate": 2.885714285714286e-07,
|
| 312 |
+
"loss": 0.2489,
|
| 313 |
+
"step": 3900
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.54,
|
| 317 |
+
"learning_rate": 2.8571428571428576e-09,
|
| 318 |
+
"loss": 0.2461,
|
| 319 |
+
"step": 4000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 3.54,
|
| 323 |
+
"eval_cer": 55.61363805755249,
|
| 324 |
+
"eval_loss": 0.36201152205467224,
|
| 325 |
+
"eval_runtime": 7527.7128,
|
| 326 |
+
"eval_samples_per_second": 0.212,
|
| 327 |
+
"eval_steps_per_second": 0.212,
|
| 328 |
+
"eval_wer": 83.20316089313609,
|
| 329 |
+
"step": 4000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.63,
|
| 333 |
+
"learning_rate": 6.211578947368422e-06,
|
| 334 |
+
"loss": 0.262,
|
| 335 |
+
"step": 4100
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.72,
|
| 339 |
+
"learning_rate": 6.106315789473684e-06,
|
| 340 |
+
"loss": 0.2608,
|
| 341 |
+
"step": 4200
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 3.81,
|
| 345 |
+
"learning_rate": 6.001052631578948e-06,
|
| 346 |
+
"loss": 0.2647,
|
| 347 |
+
"step": 4300
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.9,
|
| 351 |
+
"learning_rate": 5.895789473684212e-06,
|
| 352 |
+
"loss": 0.259,
|
| 353 |
+
"step": 4400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.99,
|
| 357 |
+
"learning_rate": 5.790526315789474e-06,
|
| 358 |
+
"loss": 0.2662,
|
| 359 |
+
"step": 4500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.99,
|
| 363 |
+
"eval_cer": 56.444673311335016,
|
| 364 |
+
"eval_loss": 0.36721161007881165,
|
| 365 |
+
"eval_runtime": 7464.0511,
|
| 366 |
+
"eval_samples_per_second": 0.214,
|
| 367 |
+
"eval_steps_per_second": 0.214,
|
| 368 |
+
"eval_wer": 83.63318937792889,
|
| 369 |
+
"step": 4500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 4.08,
|
| 373 |
+
"learning_rate": 5.685263157894737e-06,
|
| 374 |
+
"loss": 0.2382,
|
| 375 |
+
"step": 4600
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.17,
|
| 379 |
+
"learning_rate": 5.580000000000001e-06,
|
| 380 |
+
"loss": 0.2343,
|
| 381 |
+
"step": 4700
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.25,
|
| 385 |
+
"learning_rate": 5.474736842105264e-06,
|
| 386 |
+
"loss": 0.2397,
|
| 387 |
+
"step": 4800
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.34,
|
| 391 |
+
"learning_rate": 5.3694736842105265e-06,
|
| 392 |
+
"loss": 0.2363,
|
| 393 |
+
"step": 4900
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.43,
|
| 397 |
+
"learning_rate": 5.26421052631579e-06,
|
| 398 |
+
"loss": 0.2453,
|
| 399 |
+
"step": 5000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.43,
|
| 403 |
+
"eval_cer": 55.7477962151138,
|
| 404 |
+
"eval_loss": 0.368756502866745,
|
| 405 |
+
"eval_runtime": 7467.8653,
|
| 406 |
+
"eval_samples_per_second": 0.213,
|
| 407 |
+
"eval_steps_per_second": 0.213,
|
| 408 |
+
"eval_wer": 83.38142056418268,
|
| 409 |
+
"step": 5000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.52,
|
| 413 |
+
"learning_rate": 5.158947368421053e-06,
|
| 414 |
+
"loss": 0.2374,
|
| 415 |
+
"step": 5100
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 4.61,
|
| 419 |
+
"learning_rate": 5.053684210526316e-06,
|
| 420 |
+
"loss": 0.2277,
|
| 421 |
+
"step": 5200
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 4.7,
|
| 425 |
+
"learning_rate": 4.94842105263158e-06,
|
| 426 |
+
"loss": 0.2354,
|
| 427 |
+
"step": 5300
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 4.79,
|
| 431 |
+
"learning_rate": 4.843157894736842e-06,
|
| 432 |
+
"loss": 0.2378,
|
| 433 |
+
"step": 5400
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 4.87,
|
| 437 |
+
"learning_rate": 4.737894736842106e-06,
|
| 438 |
+
"loss": 0.2392,
|
| 439 |
+
"step": 5500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 4.87,
|
| 443 |
+
"eval_cer": 55.59974794527973,
|
| 444 |
+
"eval_loss": 0.3686603903770447,
|
| 445 |
+
"eval_runtime": 7471.7087,
|
| 446 |
+
"eval_samples_per_second": 0.213,
|
| 447 |
+
"eval_steps_per_second": 0.213,
|
| 448 |
+
"eval_wer": 83.19580997886612,
|
| 449 |
+
"step": 5500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 4.96,
|
| 453 |
+
"learning_rate": 4.6326315789473686e-06,
|
| 454 |
+
"loss": 0.231,
|
| 455 |
+
"step": 5600
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 5.05,
|
| 459 |
+
"learning_rate": 4.527368421052632e-06,
|
| 460 |
+
"loss": 0.2076,
|
| 461 |
+
"step": 5700
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 5.14,
|
| 465 |
+
"learning_rate": 4.422105263157895e-06,
|
| 466 |
+
"loss": 0.1938,
|
| 467 |
+
"step": 5800
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.23,
|
| 471 |
+
"learning_rate": 4.316842105263158e-06,
|
| 472 |
+
"loss": 0.192,
|
| 473 |
+
"step": 5900
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 5.32,
|
| 477 |
+
"learning_rate": 4.211578947368422e-06,
|
| 478 |
+
"loss": 0.1924,
|
| 479 |
+
"step": 6000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 5.32,
|
| 483 |
+
"eval_cer": 56.24241972531456,
|
| 484 |
+
"eval_loss": 0.386189341545105,
|
| 485 |
+
"eval_runtime": 7495.2144,
|
| 486 |
+
"eval_samples_per_second": 0.213,
|
| 487 |
+
"eval_steps_per_second": 0.213,
|
| 488 |
+
"eval_wer": 83.17927042175872,
|
| 489 |
+
"step": 6000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 5.41,
|
| 493 |
+
"learning_rate": 4.106315789473684e-06,
|
| 494 |
+
"loss": 0.194,
|
| 495 |
+
"step": 6100
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 5.5,
|
| 499 |
+
"learning_rate": 4.001052631578947e-06,
|
| 500 |
+
"loss": 0.1958,
|
| 501 |
+
"step": 6200
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 5.58,
|
| 505 |
+
"learning_rate": 3.8957894736842115e-06,
|
| 506 |
+
"loss": 0.1949,
|
| 507 |
+
"step": 6300
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 5.67,
|
| 511 |
+
"learning_rate": 3.790526315789474e-06,
|
| 512 |
+
"loss": 0.1857,
|
| 513 |
+
"step": 6400
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 5.76,
|
| 517 |
+
"learning_rate": 3.685263157894737e-06,
|
| 518 |
+
"loss": 0.1885,
|
| 519 |
+
"step": 6500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 5.76,
|
| 523 |
+
"eval_cer": 55.90024866688801,
|
| 524 |
+
"eval_loss": 0.38409024477005005,
|
| 525 |
+
"eval_runtime": 8147.6523,
|
| 526 |
+
"eval_samples_per_second": 0.196,
|
| 527 |
+
"eval_steps_per_second": 0.196,
|
| 528 |
+
"eval_wer": 83.25645502159331,
|
| 529 |
+
"step": 6500
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 5.85,
|
| 533 |
+
"learning_rate": 3.58e-06,
|
| 534 |
+
"loss": 0.1935,
|
| 535 |
+
"step": 6600
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 5.94,
|
| 539 |
+
"learning_rate": 3.4747368421052637e-06,
|
| 540 |
+
"loss": 0.1902,
|
| 541 |
+
"step": 6700
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 6.03,
|
| 545 |
+
"learning_rate": 3.369473684210526e-06,
|
| 546 |
+
"loss": 0.1765,
|
| 547 |
+
"step": 6800
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 6.12,
|
| 551 |
+
"learning_rate": 3.26421052631579e-06,
|
| 552 |
+
"loss": 0.1474,
|
| 553 |
+
"step": 6900
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.2,
|
| 557 |
+
"learning_rate": 3.158947368421053e-06,
|
| 558 |
+
"loss": 0.1539,
|
| 559 |
+
"step": 7000
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 6.2,
|
| 563 |
+
"eval_cer": 56.261730369205964,
|
| 564 |
+
"eval_loss": 0.41215547919273376,
|
| 565 |
+
"eval_runtime": 8199.818,
|
| 566 |
+
"eval_samples_per_second": 0.194,
|
| 567 |
+
"eval_steps_per_second": 0.194,
|
| 568 |
+
"eval_wer": 83.54130294955435,
|
| 569 |
+
"step": 7000
|
| 570 |
+
}
|
| 571 |
+
],
|
| 572 |
+
"logging_steps": 100,
|
| 573 |
+
"max_steps": 10000,
|
| 574 |
+
"num_input_tokens_seen": 0,
|
| 575 |
+
"num_train_epochs": 9,
|
| 576 |
+
"save_steps": 1000,
|
| 577 |
+
"total_flos": 1.615905090551808e+19,
|
| 578 |
+
"train_batch_size": 2,
|
| 579 |
+
"trial_name": null,
|
| 580 |
+
"trial_params": null
|
| 581 |
+
}
|
checkpoint-7000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fd4757ee074e468f1bc9acb69b6fbf589054c0879b708513cbfb6123c0654f4
|
| 3 |
+
size 5265
|