Upload folder using huggingface_hub
Browse files- config.json +52 -0
- generation_config.json +248 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +14 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +537 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-medium",
|
| 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": 1024,
|
| 17 |
+
"decoder_attention_heads": 16,
|
| 18 |
+
"decoder_ffn_dim": 4096,
|
| 19 |
+
"decoder_layerdrop": 0.0,
|
| 20 |
+
"decoder_layers": 24,
|
| 21 |
+
"decoder_start_token_id": 50258,
|
| 22 |
+
"dropout": 0.0,
|
| 23 |
+
"encoder_attention_heads": 16,
|
| 24 |
+
"encoder_ffn_dim": 4096,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 24,
|
| 27 |
+
"eos_token_id": 50257,
|
| 28 |
+
"forced_decoder_ids": null,
|
| 29 |
+
"init_std": 0.02,
|
| 30 |
+
"is_encoder_decoder": true,
|
| 31 |
+
"mask_feature_length": 10,
|
| 32 |
+
"mask_feature_min_masks": 0,
|
| 33 |
+
"mask_feature_prob": 0.0,
|
| 34 |
+
"mask_time_length": 10,
|
| 35 |
+
"mask_time_min_masks": 2,
|
| 36 |
+
"mask_time_prob": 0.05,
|
| 37 |
+
"max_length": 448,
|
| 38 |
+
"max_source_positions": 1500,
|
| 39 |
+
"max_target_positions": 448,
|
| 40 |
+
"median_filter_width": 7,
|
| 41 |
+
"model_type": "whisper",
|
| 42 |
+
"num_hidden_layers": 24,
|
| 43 |
+
"num_mel_bins": 80,
|
| 44 |
+
"pad_token_id": 50257,
|
| 45 |
+
"scale_embedding": false,
|
| 46 |
+
"suppress_tokens": [],
|
| 47 |
+
"torch_dtype": "float32",
|
| 48 |
+
"transformers_version": "4.36.2",
|
| 49 |
+
"use_cache": true,
|
| 50 |
+
"use_weighted_layer_sum": false,
|
| 51 |
+
"vocab_size": 51865
|
| 52 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
13,
|
| 5 |
+
15
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
15,
|
| 9 |
+
4
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
15,
|
| 13 |
+
15
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
16,
|
| 17 |
+
1
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
20,
|
| 21 |
+
0
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
23,
|
| 25 |
+
4
|
| 26 |
+
]
|
| 27 |
+
],
|
| 28 |
+
"begin_suppress_tokens": [
|
| 29 |
+
220,
|
| 30 |
+
50257
|
| 31 |
+
],
|
| 32 |
+
"bos_token_id": 50257,
|
| 33 |
+
"decoder_start_token_id": 50258,
|
| 34 |
+
"eos_token_id": 50257,
|
| 35 |
+
"forced_decoder_ids": [
|
| 36 |
+
[
|
| 37 |
+
1,
|
| 38 |
+
null
|
| 39 |
+
],
|
| 40 |
+
[
|
| 41 |
+
2,
|
| 42 |
+
50359
|
| 43 |
+
]
|
| 44 |
+
],
|
| 45 |
+
"is_multilingual": true,
|
| 46 |
+
"lang_to_id": {
|
| 47 |
+
"<|af|>": 50327,
|
| 48 |
+
"<|am|>": 50334,
|
| 49 |
+
"<|ar|>": 50272,
|
| 50 |
+
"<|as|>": 50350,
|
| 51 |
+
"<|az|>": 50304,
|
| 52 |
+
"<|ba|>": 50355,
|
| 53 |
+
"<|be|>": 50330,
|
| 54 |
+
"<|bg|>": 50292,
|
| 55 |
+
"<|bn|>": 50302,
|
| 56 |
+
"<|bo|>": 50347,
|
| 57 |
+
"<|br|>": 50309,
|
| 58 |
+
"<|bs|>": 50315,
|
| 59 |
+
"<|ca|>": 50270,
|
| 60 |
+
"<|cs|>": 50283,
|
| 61 |
+
"<|cy|>": 50297,
|
| 62 |
+
"<|da|>": 50285,
|
| 63 |
+
"<|de|>": 50261,
|
| 64 |
+
"<|el|>": 50281,
|
| 65 |
+
"<|en|>": 50259,
|
| 66 |
+
"<|es|>": 50262,
|
| 67 |
+
"<|et|>": 50307,
|
| 68 |
+
"<|eu|>": 50310,
|
| 69 |
+
"<|fa|>": 50300,
|
| 70 |
+
"<|fi|>": 50277,
|
| 71 |
+
"<|fo|>": 50338,
|
| 72 |
+
"<|fr|>": 50265,
|
| 73 |
+
"<|gl|>": 50319,
|
| 74 |
+
"<|gu|>": 50333,
|
| 75 |
+
"<|haw|>": 50352,
|
| 76 |
+
"<|ha|>": 50354,
|
| 77 |
+
"<|he|>": 50279,
|
| 78 |
+
"<|hi|>": 50276,
|
| 79 |
+
"<|hr|>": 50291,
|
| 80 |
+
"<|ht|>": 50339,
|
| 81 |
+
"<|hu|>": 50286,
|
| 82 |
+
"<|hy|>": 50312,
|
| 83 |
+
"<|id|>": 50275,
|
| 84 |
+
"<|is|>": 50311,
|
| 85 |
+
"<|it|>": 50274,
|
| 86 |
+
"<|ja|>": 50266,
|
| 87 |
+
"<|jw|>": 50356,
|
| 88 |
+
"<|ka|>": 50329,
|
| 89 |
+
"<|kk|>": 50316,
|
| 90 |
+
"<|km|>": 50323,
|
| 91 |
+
"<|kn|>": 50306,
|
| 92 |
+
"<|ko|>": 50264,
|
| 93 |
+
"<|la|>": 50294,
|
| 94 |
+
"<|lb|>": 50345,
|
| 95 |
+
"<|ln|>": 50353,
|
| 96 |
+
"<|lo|>": 50336,
|
| 97 |
+
"<|lt|>": 50293,
|
| 98 |
+
"<|lv|>": 50301,
|
| 99 |
+
"<|mg|>": 50349,
|
| 100 |
+
"<|mi|>": 50295,
|
| 101 |
+
"<|mk|>": 50308,
|
| 102 |
+
"<|ml|>": 50296,
|
| 103 |
+
"<|mn|>": 50314,
|
| 104 |
+
"<|mr|>": 50320,
|
| 105 |
+
"<|ms|>": 50282,
|
| 106 |
+
"<|mt|>": 50343,
|
| 107 |
+
"<|my|>": 50346,
|
| 108 |
+
"<|ne|>": 50313,
|
| 109 |
+
"<|nl|>": 50271,
|
| 110 |
+
"<|nn|>": 50342,
|
| 111 |
+
"<|no|>": 50288,
|
| 112 |
+
"<|oc|>": 50328,
|
| 113 |
+
"<|pa|>": 50321,
|
| 114 |
+
"<|pl|>": 50269,
|
| 115 |
+
"<|ps|>": 50340,
|
| 116 |
+
"<|pt|>": 50267,
|
| 117 |
+
"<|ro|>": 50284,
|
| 118 |
+
"<|ru|>": 50263,
|
| 119 |
+
"<|sa|>": 50344,
|
| 120 |
+
"<|sd|>": 50332,
|
| 121 |
+
"<|si|>": 50322,
|
| 122 |
+
"<|sk|>": 50298,
|
| 123 |
+
"<|sl|>": 50305,
|
| 124 |
+
"<|sn|>": 50324,
|
| 125 |
+
"<|so|>": 50326,
|
| 126 |
+
"<|sq|>": 50317,
|
| 127 |
+
"<|sr|>": 50303,
|
| 128 |
+
"<|su|>": 50357,
|
| 129 |
+
"<|sv|>": 50273,
|
| 130 |
+
"<|sw|>": 50318,
|
| 131 |
+
"<|ta|>": 50287,
|
| 132 |
+
"<|te|>": 50299,
|
| 133 |
+
"<|tg|>": 50331,
|
| 134 |
+
"<|th|>": 50289,
|
| 135 |
+
"<|tk|>": 50341,
|
| 136 |
+
"<|tl|>": 50348,
|
| 137 |
+
"<|tr|>": 50268,
|
| 138 |
+
"<|tt|>": 50351,
|
| 139 |
+
"<|uk|>": 50280,
|
| 140 |
+
"<|ur|>": 50290,
|
| 141 |
+
"<|uz|>": 50337,
|
| 142 |
+
"<|vi|>": 50278,
|
| 143 |
+
"<|yi|>": 50335,
|
| 144 |
+
"<|yo|>": 50325,
|
| 145 |
+
"<|zh|>": 50260
|
| 146 |
+
},
|
| 147 |
+
"max_initial_timestamp_index": 50,
|
| 148 |
+
"max_length": 448,
|
| 149 |
+
"no_timestamps_token_id": 50363,
|
| 150 |
+
"pad_token_id": 50257,
|
| 151 |
+
"prev_sot_token_id": 50361,
|
| 152 |
+
"return_timestamps": false,
|
| 153 |
+
"suppress_tokens": [
|
| 154 |
+
1,
|
| 155 |
+
2,
|
| 156 |
+
7,
|
| 157 |
+
8,
|
| 158 |
+
9,
|
| 159 |
+
10,
|
| 160 |
+
14,
|
| 161 |
+
25,
|
| 162 |
+
26,
|
| 163 |
+
27,
|
| 164 |
+
28,
|
| 165 |
+
29,
|
| 166 |
+
31,
|
| 167 |
+
58,
|
| 168 |
+
59,
|
| 169 |
+
60,
|
| 170 |
+
61,
|
| 171 |
+
62,
|
| 172 |
+
63,
|
| 173 |
+
90,
|
| 174 |
+
91,
|
| 175 |
+
92,
|
| 176 |
+
93,
|
| 177 |
+
359,
|
| 178 |
+
503,
|
| 179 |
+
522,
|
| 180 |
+
542,
|
| 181 |
+
873,
|
| 182 |
+
893,
|
| 183 |
+
902,
|
| 184 |
+
918,
|
| 185 |
+
922,
|
| 186 |
+
931,
|
| 187 |
+
1350,
|
| 188 |
+
1853,
|
| 189 |
+
1982,
|
| 190 |
+
2460,
|
| 191 |
+
2627,
|
| 192 |
+
3246,
|
| 193 |
+
3253,
|
| 194 |
+
3268,
|
| 195 |
+
3536,
|
| 196 |
+
3846,
|
| 197 |
+
3961,
|
| 198 |
+
4183,
|
| 199 |
+
4667,
|
| 200 |
+
6585,
|
| 201 |
+
6647,
|
| 202 |
+
7273,
|
| 203 |
+
9061,
|
| 204 |
+
9383,
|
| 205 |
+
10428,
|
| 206 |
+
10929,
|
| 207 |
+
11938,
|
| 208 |
+
12033,
|
| 209 |
+
12331,
|
| 210 |
+
12562,
|
| 211 |
+
13793,
|
| 212 |
+
14157,
|
| 213 |
+
14635,
|
| 214 |
+
15265,
|
| 215 |
+
15618,
|
| 216 |
+
16553,
|
| 217 |
+
16604,
|
| 218 |
+
18362,
|
| 219 |
+
18956,
|
| 220 |
+
20075,
|
| 221 |
+
21675,
|
| 222 |
+
22520,
|
| 223 |
+
26130,
|
| 224 |
+
26161,
|
| 225 |
+
26435,
|
| 226 |
+
28279,
|
| 227 |
+
29464,
|
| 228 |
+
31650,
|
| 229 |
+
32302,
|
| 230 |
+
32470,
|
| 231 |
+
36865,
|
| 232 |
+
42863,
|
| 233 |
+
47425,
|
| 234 |
+
49870,
|
| 235 |
+
50254,
|
| 236 |
+
50258,
|
| 237 |
+
50358,
|
| 238 |
+
50359,
|
| 239 |
+
50360,
|
| 240 |
+
50361,
|
| 241 |
+
50362
|
| 242 |
+
],
|
| 243 |
+
"task_to_id": {
|
| 244 |
+
"transcribe": 50359,
|
| 245 |
+
"translate": 50358
|
| 246 |
+
},
|
| 247 |
+
"transformers_version": "4.36.2"
|
| 248 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffb198a044c8bc69d4586e8cc2086d1df33bfe9aab63acf303b243e80686e79e
|
| 3 |
+
size 3055544304
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f44e6ffcd0f0e0ff02bc80e55c47b6f0024e42f223ce25616b9611d4af46119b
|
| 3 |
+
size 6099375168
|
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 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c9d676ca86512a71d67b4470c4a349c349bdda4f27f274bd44b2f71cfbc4bf4
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98089693a2c1b2580efb7e5e08896546621f2b7c1c59ef1420362ae3f18b674e
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,537 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 99.96992047726177,
|
| 3 |
+
"best_model_checkpoint": "./checkpoint-1500",
|
| 4 |
+
"epoch": 1.697792869269949,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 7.000000000000001e-07,
|
| 14 |
+
"loss": 2.9314,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"learning_rate": 1.5333333333333334e-06,
|
| 20 |
+
"loss": 2.2727,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.06,
|
| 25 |
+
"learning_rate": 2.3666666666666667e-06,
|
| 26 |
+
"loss": 1.6894,
|
| 27 |
+
"step": 75
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.08,
|
| 31 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 32 |
+
"loss": 1.5086,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.11,
|
| 37 |
+
"learning_rate": 4.033333333333333e-06,
|
| 38 |
+
"loss": 1.2162,
|
| 39 |
+
"step": 125
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.13,
|
| 43 |
+
"learning_rate": 4.866666666666667e-06,
|
| 44 |
+
"loss": 0.7539,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.15,
|
| 49 |
+
"learning_rate": 5.7e-06,
|
| 50 |
+
"loss": 0.467,
|
| 51 |
+
"step": 175
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.17,
|
| 55 |
+
"learning_rate": 6.533333333333334e-06,
|
| 56 |
+
"loss": 0.5266,
|
| 57 |
+
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.19,
|
| 61 |
+
"learning_rate": 7.3666666666666676e-06,
|
| 62 |
+
"loss": 0.5119,
|
| 63 |
+
"step": 225
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.21,
|
| 67 |
+
"learning_rate": 8.2e-06,
|
| 68 |
+
"loss": 0.4819,
|
| 69 |
+
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.23,
|
| 73 |
+
"learning_rate": 9.033333333333334e-06,
|
| 74 |
+
"loss": 0.6088,
|
| 75 |
+
"step": 275
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.25,
|
| 79 |
+
"learning_rate": 9.866666666666668e-06,
|
| 80 |
+
"loss": 0.4509,
|
| 81 |
+
"step": 300
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.28,
|
| 85 |
+
"learning_rate": 9.876470588235295e-06,
|
| 86 |
+
"loss": 0.4662,
|
| 87 |
+
"step": 325
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.3,
|
| 91 |
+
"learning_rate": 9.729411764705882e-06,
|
| 92 |
+
"loss": 0.4524,
|
| 93 |
+
"step": 350
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.32,
|
| 97 |
+
"learning_rate": 9.582352941176472e-06,
|
| 98 |
+
"loss": 0.4847,
|
| 99 |
+
"step": 375
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.34,
|
| 103 |
+
"learning_rate": 9.435294117647058e-06,
|
| 104 |
+
"loss": 0.4663,
|
| 105 |
+
"step": 400
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.36,
|
| 109 |
+
"learning_rate": 9.288235294117648e-06,
|
| 110 |
+
"loss": 0.436,
|
| 111 |
+
"step": 425
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.38,
|
| 115 |
+
"learning_rate": 9.141176470588235e-06,
|
| 116 |
+
"loss": 0.3966,
|
| 117 |
+
"step": 450
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.4,
|
| 121 |
+
"learning_rate": 8.994117647058825e-06,
|
| 122 |
+
"loss": 0.4502,
|
| 123 |
+
"step": 475
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.42,
|
| 127 |
+
"learning_rate": 8.847058823529413e-06,
|
| 128 |
+
"loss": 0.4777,
|
| 129 |
+
"step": 500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.42,
|
| 133 |
+
"eval_cer": 100.25567594327502,
|
| 134 |
+
"eval_loss": 0.4232913851737976,
|
| 135 |
+
"eval_runtime": 729.5732,
|
| 136 |
+
"eval_samples_per_second": 5.559,
|
| 137 |
+
"eval_steps_per_second": 1.39,
|
| 138 |
+
"step": 500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.45,
|
| 142 |
+
"learning_rate": 8.700000000000001e-06,
|
| 143 |
+
"loss": 0.3991,
|
| 144 |
+
"step": 525
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.47,
|
| 148 |
+
"learning_rate": 8.55294117647059e-06,
|
| 149 |
+
"loss": 0.4605,
|
| 150 |
+
"step": 550
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.49,
|
| 154 |
+
"learning_rate": 8.405882352941176e-06,
|
| 155 |
+
"loss": 0.4279,
|
| 156 |
+
"step": 575
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.51,
|
| 160 |
+
"learning_rate": 8.258823529411766e-06,
|
| 161 |
+
"loss": 0.4136,
|
| 162 |
+
"step": 600
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.53,
|
| 166 |
+
"learning_rate": 8.111764705882353e-06,
|
| 167 |
+
"loss": 0.3983,
|
| 168 |
+
"step": 625
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.55,
|
| 172 |
+
"learning_rate": 7.964705882352943e-06,
|
| 173 |
+
"loss": 0.3877,
|
| 174 |
+
"step": 650
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.57,
|
| 178 |
+
"learning_rate": 7.81764705882353e-06,
|
| 179 |
+
"loss": 0.4127,
|
| 180 |
+
"step": 675
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.59,
|
| 184 |
+
"learning_rate": 7.670588235294119e-06,
|
| 185 |
+
"loss": 0.4799,
|
| 186 |
+
"step": 700
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.62,
|
| 190 |
+
"learning_rate": 7.5235294117647065e-06,
|
| 191 |
+
"loss": 0.4162,
|
| 192 |
+
"step": 725
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.64,
|
| 196 |
+
"learning_rate": 7.376470588235295e-06,
|
| 197 |
+
"loss": 0.4105,
|
| 198 |
+
"step": 750
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.66,
|
| 202 |
+
"learning_rate": 7.229411764705882e-06,
|
| 203 |
+
"loss": 0.4138,
|
| 204 |
+
"step": 775
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.68,
|
| 208 |
+
"learning_rate": 7.082352941176471e-06,
|
| 209 |
+
"loss": 0.3797,
|
| 210 |
+
"step": 800
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.7,
|
| 214 |
+
"learning_rate": 6.935294117647059e-06,
|
| 215 |
+
"loss": 0.4053,
|
| 216 |
+
"step": 825
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.72,
|
| 220 |
+
"learning_rate": 6.788235294117648e-06,
|
| 221 |
+
"loss": 0.4381,
|
| 222 |
+
"step": 850
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.74,
|
| 226 |
+
"learning_rate": 6.641176470588235e-06,
|
| 227 |
+
"loss": 0.3761,
|
| 228 |
+
"step": 875
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.76,
|
| 232 |
+
"learning_rate": 6.494117647058824e-06,
|
| 233 |
+
"loss": 0.3809,
|
| 234 |
+
"step": 900
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.79,
|
| 238 |
+
"learning_rate": 6.3470588235294125e-06,
|
| 239 |
+
"loss": 0.4605,
|
| 240 |
+
"step": 925
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.81,
|
| 244 |
+
"learning_rate": 6.200000000000001e-06,
|
| 245 |
+
"loss": 0.3224,
|
| 246 |
+
"step": 950
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.83,
|
| 250 |
+
"learning_rate": 6.052941176470589e-06,
|
| 251 |
+
"loss": 0.4161,
|
| 252 |
+
"step": 975
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.85,
|
| 256 |
+
"learning_rate": 5.9058823529411764e-06,
|
| 257 |
+
"loss": 0.3752,
|
| 258 |
+
"step": 1000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.85,
|
| 262 |
+
"eval_cer": 100.0,
|
| 263 |
+
"eval_loss": 0.37455084919929504,
|
| 264 |
+
"eval_runtime": 717.659,
|
| 265 |
+
"eval_samples_per_second": 5.652,
|
| 266 |
+
"eval_steps_per_second": 1.413,
|
| 267 |
+
"step": 1000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.87,
|
| 271 |
+
"learning_rate": 5.7588235294117655e-06,
|
| 272 |
+
"loss": 0.3822,
|
| 273 |
+
"step": 1025
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.89,
|
| 277 |
+
"learning_rate": 5.611764705882353e-06,
|
| 278 |
+
"loss": 0.3414,
|
| 279 |
+
"step": 1050
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.91,
|
| 283 |
+
"learning_rate": 5.464705882352942e-06,
|
| 284 |
+
"loss": 0.3784,
|
| 285 |
+
"step": 1075
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.93,
|
| 289 |
+
"learning_rate": 5.317647058823529e-06,
|
| 290 |
+
"loss": 0.3564,
|
| 291 |
+
"step": 1100
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.96,
|
| 295 |
+
"learning_rate": 5.1705882352941185e-06,
|
| 296 |
+
"loss": 0.3494,
|
| 297 |
+
"step": 1125
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.98,
|
| 301 |
+
"learning_rate": 5.023529411764706e-06,
|
| 302 |
+
"loss": 0.3765,
|
| 303 |
+
"step": 1150
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.0,
|
| 307 |
+
"learning_rate": 4.876470588235295e-06,
|
| 308 |
+
"loss": 0.3119,
|
| 309 |
+
"step": 1175
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.02,
|
| 313 |
+
"learning_rate": 4.729411764705883e-06,
|
| 314 |
+
"loss": 0.2587,
|
| 315 |
+
"step": 1200
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.04,
|
| 319 |
+
"learning_rate": 4.5823529411764715e-06,
|
| 320 |
+
"loss": 0.2118,
|
| 321 |
+
"step": 1225
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.06,
|
| 325 |
+
"learning_rate": 4.435294117647059e-06,
|
| 326 |
+
"loss": 0.1843,
|
| 327 |
+
"step": 1250
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.08,
|
| 331 |
+
"learning_rate": 4.288235294117647e-06,
|
| 332 |
+
"loss": 0.2489,
|
| 333 |
+
"step": 1275
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.1,
|
| 337 |
+
"learning_rate": 4.141176470588235e-06,
|
| 338 |
+
"loss": 0.3112,
|
| 339 |
+
"step": 1300
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.12,
|
| 343 |
+
"learning_rate": 3.994117647058824e-06,
|
| 344 |
+
"loss": 0.1702,
|
| 345 |
+
"step": 1325
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.15,
|
| 349 |
+
"learning_rate": 3.847058823529412e-06,
|
| 350 |
+
"loss": 0.2084,
|
| 351 |
+
"step": 1350
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.17,
|
| 355 |
+
"learning_rate": 3.7e-06,
|
| 356 |
+
"loss": 0.201,
|
| 357 |
+
"step": 1375
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.19,
|
| 361 |
+
"learning_rate": 3.5529411764705884e-06,
|
| 362 |
+
"loss": 0.2136,
|
| 363 |
+
"step": 1400
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.21,
|
| 367 |
+
"learning_rate": 3.4058823529411766e-06,
|
| 368 |
+
"loss": 0.2277,
|
| 369 |
+
"step": 1425
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.23,
|
| 373 |
+
"learning_rate": 3.258823529411765e-06,
|
| 374 |
+
"loss": 0.2316,
|
| 375 |
+
"step": 1450
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.25,
|
| 379 |
+
"learning_rate": 3.111764705882353e-06,
|
| 380 |
+
"loss": 0.1734,
|
| 381 |
+
"step": 1475
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.27,
|
| 385 |
+
"learning_rate": 2.9647058823529414e-06,
|
| 386 |
+
"loss": 0.2335,
|
| 387 |
+
"step": 1500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.27,
|
| 391 |
+
"eval_cer": 99.96992047726177,
|
| 392 |
+
"eval_loss": 0.35788390040397644,
|
| 393 |
+
"eval_runtime": 716.1555,
|
| 394 |
+
"eval_samples_per_second": 5.664,
|
| 395 |
+
"eval_steps_per_second": 1.416,
|
| 396 |
+
"step": 1500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.29,
|
| 400 |
+
"learning_rate": 2.8176470588235292e-06,
|
| 401 |
+
"loss": 0.1816,
|
| 402 |
+
"step": 1525
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.32,
|
| 406 |
+
"learning_rate": 2.6705882352941175e-06,
|
| 407 |
+
"loss": 0.1606,
|
| 408 |
+
"step": 1550
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.34,
|
| 412 |
+
"learning_rate": 2.523529411764706e-06,
|
| 413 |
+
"loss": 0.207,
|
| 414 |
+
"step": 1575
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.36,
|
| 418 |
+
"learning_rate": 2.3764705882352944e-06,
|
| 419 |
+
"loss": 0.1856,
|
| 420 |
+
"step": 1600
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.38,
|
| 424 |
+
"learning_rate": 2.2294117647058826e-06,
|
| 425 |
+
"loss": 0.2408,
|
| 426 |
+
"step": 1625
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.4,
|
| 430 |
+
"learning_rate": 2.0823529411764705e-06,
|
| 431 |
+
"loss": 0.2055,
|
| 432 |
+
"step": 1650
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.42,
|
| 436 |
+
"learning_rate": 1.935294117647059e-06,
|
| 437 |
+
"loss": 0.212,
|
| 438 |
+
"step": 1675
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.44,
|
| 442 |
+
"learning_rate": 1.7882352941176474e-06,
|
| 443 |
+
"loss": 0.188,
|
| 444 |
+
"step": 1700
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.46,
|
| 448 |
+
"learning_rate": 1.6411764705882354e-06,
|
| 449 |
+
"loss": 0.1912,
|
| 450 |
+
"step": 1725
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.49,
|
| 454 |
+
"learning_rate": 1.4941176470588237e-06,
|
| 455 |
+
"loss": 0.2205,
|
| 456 |
+
"step": 1750
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.51,
|
| 460 |
+
"learning_rate": 1.347058823529412e-06,
|
| 461 |
+
"loss": 0.1896,
|
| 462 |
+
"step": 1775
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.53,
|
| 466 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 467 |
+
"loss": 0.2089,
|
| 468 |
+
"step": 1800
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.55,
|
| 472 |
+
"learning_rate": 1.0529411764705884e-06,
|
| 473 |
+
"loss": 0.1547,
|
| 474 |
+
"step": 1825
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.57,
|
| 478 |
+
"learning_rate": 9.058823529411765e-07,
|
| 479 |
+
"loss": 0.236,
|
| 480 |
+
"step": 1850
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.59,
|
| 484 |
+
"learning_rate": 7.588235294117648e-07,
|
| 485 |
+
"loss": 0.165,
|
| 486 |
+
"step": 1875
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.61,
|
| 490 |
+
"learning_rate": 6.11764705882353e-07,
|
| 491 |
+
"loss": 0.209,
|
| 492 |
+
"step": 1900
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.63,
|
| 496 |
+
"learning_rate": 4.6470588235294124e-07,
|
| 497 |
+
"loss": 0.161,
|
| 498 |
+
"step": 1925
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.66,
|
| 502 |
+
"learning_rate": 3.176470588235294e-07,
|
| 503 |
+
"loss": 0.2468,
|
| 504 |
+
"step": 1950
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.68,
|
| 508 |
+
"learning_rate": 1.7058823529411766e-07,
|
| 509 |
+
"loss": 0.2276,
|
| 510 |
+
"step": 1975
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.7,
|
| 514 |
+
"learning_rate": 2.352941176470588e-08,
|
| 515 |
+
"loss": 0.1997,
|
| 516 |
+
"step": 2000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.7,
|
| 520 |
+
"eval_cer": 100.0,
|
| 521 |
+
"eval_loss": 0.3437291979789734,
|
| 522 |
+
"eval_runtime": 719.3517,
|
| 523 |
+
"eval_samples_per_second": 5.638,
|
| 524 |
+
"eval_steps_per_second": 1.41,
|
| 525 |
+
"step": 2000
|
| 526 |
+
}
|
| 527 |
+
],
|
| 528 |
+
"logging_steps": 25,
|
| 529 |
+
"max_steps": 2000,
|
| 530 |
+
"num_input_tokens_seen": 0,
|
| 531 |
+
"num_train_epochs": 2,
|
| 532 |
+
"save_steps": 500,
|
| 533 |
+
"total_flos": 1.632763731050496e+19,
|
| 534 |
+
"train_batch_size": 8,
|
| 535 |
+
"trial_name": null,
|
| 536 |
+
"trial_params": null
|
| 537 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f65973752d5d1de52e6da6104f9a43e2fe81dbf420e3a5e3ad316daf6050dcea
|
| 3 |
+
size 4792
|