Upload 9 files
Browse files- config.json +52 -0
- generation_config.json +256 -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 +1189 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-base",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"apply_spec_augment": false,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"WhisperForConditionalGeneration"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"begin_suppress_tokens": [
|
| 11 |
+
220,
|
| 12 |
+
50257
|
| 13 |
+
],
|
| 14 |
+
"bos_token_id": 50257,
|
| 15 |
+
"classifier_proj_size": 256,
|
| 16 |
+
"d_model": 512,
|
| 17 |
+
"decoder_attention_heads": 8,
|
| 18 |
+
"decoder_ffn_dim": 2048,
|
| 19 |
+
"decoder_layerdrop": 0.0,
|
| 20 |
+
"decoder_layers": 6,
|
| 21 |
+
"decoder_start_token_id": 50258,
|
| 22 |
+
"dropout": 0.0,
|
| 23 |
+
"encoder_attention_heads": 8,
|
| 24 |
+
"encoder_ffn_dim": 2048,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 6,
|
| 27 |
+
"eos_token_id": 50257,
|
| 28 |
+
"forced_decoder_ids": 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": 6,
|
| 43 |
+
"num_mel_bins": 80,
|
| 44 |
+
"pad_token_id": 50257,
|
| 45 |
+
"scale_embedding": false,
|
| 46 |
+
"suppress_tokens": [],
|
| 47 |
+
"torch_dtype": "float32",
|
| 48 |
+
"transformers_version": "4.42.3",
|
| 49 |
+
"use_cache": true,
|
| 50 |
+
"use_weighted_layer_sum": false,
|
| 51 |
+
"vocab_size": 51865
|
| 52 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
3,
|
| 5 |
+
1
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
4,
|
| 9 |
+
2
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
4,
|
| 13 |
+
3
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
4,
|
| 17 |
+
7
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
5,
|
| 21 |
+
1
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
5,
|
| 25 |
+
2
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
5,
|
| 29 |
+
4
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
5,
|
| 33 |
+
6
|
| 34 |
+
]
|
| 35 |
+
],
|
| 36 |
+
"begin_suppress_tokens": [
|
| 37 |
+
220,
|
| 38 |
+
50257
|
| 39 |
+
],
|
| 40 |
+
"bos_token_id": 50257,
|
| 41 |
+
"decoder_start_token_id": 50258,
|
| 42 |
+
"eos_token_id": 50257,
|
| 43 |
+
"forced_decoder_ids": [
|
| 44 |
+
[
|
| 45 |
+
1,
|
| 46 |
+
null
|
| 47 |
+
],
|
| 48 |
+
[
|
| 49 |
+
2,
|
| 50 |
+
50359
|
| 51 |
+
]
|
| 52 |
+
],
|
| 53 |
+
"is_multilingual": true,
|
| 54 |
+
"lang_to_id": {
|
| 55 |
+
"<|af|>": 50327,
|
| 56 |
+
"<|am|>": 50334,
|
| 57 |
+
"<|ar|>": 50272,
|
| 58 |
+
"<|as|>": 50350,
|
| 59 |
+
"<|az|>": 50304,
|
| 60 |
+
"<|ba|>": 50355,
|
| 61 |
+
"<|be|>": 50330,
|
| 62 |
+
"<|bg|>": 50292,
|
| 63 |
+
"<|bn|>": 50302,
|
| 64 |
+
"<|bo|>": 50347,
|
| 65 |
+
"<|br|>": 50309,
|
| 66 |
+
"<|bs|>": 50315,
|
| 67 |
+
"<|ca|>": 50270,
|
| 68 |
+
"<|cs|>": 50283,
|
| 69 |
+
"<|cy|>": 50297,
|
| 70 |
+
"<|da|>": 50285,
|
| 71 |
+
"<|de|>": 50261,
|
| 72 |
+
"<|el|>": 50281,
|
| 73 |
+
"<|en|>": 50259,
|
| 74 |
+
"<|es|>": 50262,
|
| 75 |
+
"<|et|>": 50307,
|
| 76 |
+
"<|eu|>": 50310,
|
| 77 |
+
"<|fa|>": 50300,
|
| 78 |
+
"<|fi|>": 50277,
|
| 79 |
+
"<|fo|>": 50338,
|
| 80 |
+
"<|fr|>": 50265,
|
| 81 |
+
"<|gl|>": 50319,
|
| 82 |
+
"<|gu|>": 50333,
|
| 83 |
+
"<|haw|>": 50352,
|
| 84 |
+
"<|ha|>": 50354,
|
| 85 |
+
"<|he|>": 50279,
|
| 86 |
+
"<|hi|>": 50276,
|
| 87 |
+
"<|hr|>": 50291,
|
| 88 |
+
"<|ht|>": 50339,
|
| 89 |
+
"<|hu|>": 50286,
|
| 90 |
+
"<|hy|>": 50312,
|
| 91 |
+
"<|id|>": 50275,
|
| 92 |
+
"<|is|>": 50311,
|
| 93 |
+
"<|it|>": 50274,
|
| 94 |
+
"<|ja|>": 50266,
|
| 95 |
+
"<|jw|>": 50356,
|
| 96 |
+
"<|ka|>": 50329,
|
| 97 |
+
"<|kk|>": 50316,
|
| 98 |
+
"<|km|>": 50323,
|
| 99 |
+
"<|kn|>": 50306,
|
| 100 |
+
"<|ko|>": 50264,
|
| 101 |
+
"<|la|>": 50294,
|
| 102 |
+
"<|lb|>": 50345,
|
| 103 |
+
"<|ln|>": 50353,
|
| 104 |
+
"<|lo|>": 50336,
|
| 105 |
+
"<|lt|>": 50293,
|
| 106 |
+
"<|lv|>": 50301,
|
| 107 |
+
"<|mg|>": 50349,
|
| 108 |
+
"<|mi|>": 50295,
|
| 109 |
+
"<|mk|>": 50308,
|
| 110 |
+
"<|ml|>": 50296,
|
| 111 |
+
"<|mn|>": 50314,
|
| 112 |
+
"<|mr|>": 50320,
|
| 113 |
+
"<|ms|>": 50282,
|
| 114 |
+
"<|mt|>": 50343,
|
| 115 |
+
"<|my|>": 50346,
|
| 116 |
+
"<|ne|>": 50313,
|
| 117 |
+
"<|nl|>": 50271,
|
| 118 |
+
"<|nn|>": 50342,
|
| 119 |
+
"<|no|>": 50288,
|
| 120 |
+
"<|oc|>": 50328,
|
| 121 |
+
"<|pa|>": 50321,
|
| 122 |
+
"<|pl|>": 50269,
|
| 123 |
+
"<|ps|>": 50340,
|
| 124 |
+
"<|pt|>": 50267,
|
| 125 |
+
"<|ro|>": 50284,
|
| 126 |
+
"<|ru|>": 50263,
|
| 127 |
+
"<|sa|>": 50344,
|
| 128 |
+
"<|sd|>": 50332,
|
| 129 |
+
"<|si|>": 50322,
|
| 130 |
+
"<|sk|>": 50298,
|
| 131 |
+
"<|sl|>": 50305,
|
| 132 |
+
"<|sn|>": 50324,
|
| 133 |
+
"<|so|>": 50326,
|
| 134 |
+
"<|sq|>": 50317,
|
| 135 |
+
"<|sr|>": 50303,
|
| 136 |
+
"<|su|>": 50357,
|
| 137 |
+
"<|sv|>": 50273,
|
| 138 |
+
"<|sw|>": 50318,
|
| 139 |
+
"<|ta|>": 50287,
|
| 140 |
+
"<|te|>": 50299,
|
| 141 |
+
"<|tg|>": 50331,
|
| 142 |
+
"<|th|>": 50289,
|
| 143 |
+
"<|tk|>": 50341,
|
| 144 |
+
"<|tl|>": 50348,
|
| 145 |
+
"<|tr|>": 50268,
|
| 146 |
+
"<|tt|>": 50351,
|
| 147 |
+
"<|uk|>": 50280,
|
| 148 |
+
"<|ur|>": 50290,
|
| 149 |
+
"<|uz|>": 50337,
|
| 150 |
+
"<|vi|>": 50278,
|
| 151 |
+
"<|yi|>": 50335,
|
| 152 |
+
"<|yo|>": 50325,
|
| 153 |
+
"<|zh|>": 50260
|
| 154 |
+
},
|
| 155 |
+
"max_initial_timestamp_index": 50,
|
| 156 |
+
"max_length": 448,
|
| 157 |
+
"no_timestamps_token_id": 50363,
|
| 158 |
+
"pad_token_id": 50257,
|
| 159 |
+
"prev_sot_token_id": 50361,
|
| 160 |
+
"return_timestamps": false,
|
| 161 |
+
"suppress_tokens": [
|
| 162 |
+
1,
|
| 163 |
+
2,
|
| 164 |
+
7,
|
| 165 |
+
8,
|
| 166 |
+
9,
|
| 167 |
+
10,
|
| 168 |
+
14,
|
| 169 |
+
25,
|
| 170 |
+
26,
|
| 171 |
+
27,
|
| 172 |
+
28,
|
| 173 |
+
29,
|
| 174 |
+
31,
|
| 175 |
+
58,
|
| 176 |
+
59,
|
| 177 |
+
60,
|
| 178 |
+
61,
|
| 179 |
+
62,
|
| 180 |
+
63,
|
| 181 |
+
90,
|
| 182 |
+
91,
|
| 183 |
+
92,
|
| 184 |
+
93,
|
| 185 |
+
359,
|
| 186 |
+
503,
|
| 187 |
+
522,
|
| 188 |
+
542,
|
| 189 |
+
873,
|
| 190 |
+
893,
|
| 191 |
+
902,
|
| 192 |
+
918,
|
| 193 |
+
922,
|
| 194 |
+
931,
|
| 195 |
+
1350,
|
| 196 |
+
1853,
|
| 197 |
+
1982,
|
| 198 |
+
2460,
|
| 199 |
+
2627,
|
| 200 |
+
3246,
|
| 201 |
+
3253,
|
| 202 |
+
3268,
|
| 203 |
+
3536,
|
| 204 |
+
3846,
|
| 205 |
+
3961,
|
| 206 |
+
4183,
|
| 207 |
+
4667,
|
| 208 |
+
6585,
|
| 209 |
+
6647,
|
| 210 |
+
7273,
|
| 211 |
+
9061,
|
| 212 |
+
9383,
|
| 213 |
+
10428,
|
| 214 |
+
10929,
|
| 215 |
+
11938,
|
| 216 |
+
12033,
|
| 217 |
+
12331,
|
| 218 |
+
12562,
|
| 219 |
+
13793,
|
| 220 |
+
14157,
|
| 221 |
+
14635,
|
| 222 |
+
15265,
|
| 223 |
+
15618,
|
| 224 |
+
16553,
|
| 225 |
+
16604,
|
| 226 |
+
18362,
|
| 227 |
+
18956,
|
| 228 |
+
20075,
|
| 229 |
+
21675,
|
| 230 |
+
22520,
|
| 231 |
+
26130,
|
| 232 |
+
26161,
|
| 233 |
+
26435,
|
| 234 |
+
28279,
|
| 235 |
+
29464,
|
| 236 |
+
31650,
|
| 237 |
+
32302,
|
| 238 |
+
32470,
|
| 239 |
+
36865,
|
| 240 |
+
42863,
|
| 241 |
+
47425,
|
| 242 |
+
49870,
|
| 243 |
+
50254,
|
| 244 |
+
50258,
|
| 245 |
+
50358,
|
| 246 |
+
50359,
|
| 247 |
+
50360,
|
| 248 |
+
50361,
|
| 249 |
+
50362
|
| 250 |
+
],
|
| 251 |
+
"task_to_id": {
|
| 252 |
+
"transcribe": 50359,
|
| 253 |
+
"translate": 50358
|
| 254 |
+
},
|
| 255 |
+
"transformers_version": "4.42.3"
|
| 256 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:865e8d8386978bb8771b918401749c5d6a018c1f3f51f0d043ad8e8c57801910
|
| 3 |
+
size 290403936
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ff6e6bb00f68d5701862423cbd3a9e58b3e5ecb99e398d17ebdbff84c0be6a6
|
| 3 |
+
size 574811514
|
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 sha256:830da7d6cf5c27b731f87279d1d54a1d29a59fab11ab019d34021e73ccb0dde7
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d8d32a187008bfe0e1458d8746399d5969c59e830b050a2420956778540bfd7
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 5.288159547738693,
|
| 3 |
+
"best_model_checkpoint": "/kaggle/working/checkpoint-4000",
|
| 4 |
+
"epoch": 2.873563218390805,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 4000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.017959770114942528,
|
| 13 |
+
"grad_norm": 24.085046768188477,
|
| 14 |
+
"learning_rate": 4.4e-07,
|
| 15 |
+
"loss": 1.4603,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.035919540229885055,
|
| 20 |
+
"grad_norm": 13.078679084777832,
|
| 21 |
+
"learning_rate": 9.400000000000001e-07,
|
| 22 |
+
"loss": 1.3305,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05387931034482758,
|
| 27 |
+
"grad_norm": 17.343385696411133,
|
| 28 |
+
"learning_rate": 1.44e-06,
|
| 29 |
+
"loss": 1.0971,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07183908045977011,
|
| 34 |
+
"grad_norm": 10.30687427520752,
|
| 35 |
+
"learning_rate": 1.94e-06,
|
| 36 |
+
"loss": 0.6573,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08979885057471264,
|
| 41 |
+
"grad_norm": 7.07254695892334,
|
| 42 |
+
"learning_rate": 2.4400000000000004e-06,
|
| 43 |
+
"loss": 0.5107,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.10775862068965517,
|
| 48 |
+
"grad_norm": 7.000039100646973,
|
| 49 |
+
"learning_rate": 2.9400000000000002e-06,
|
| 50 |
+
"loss": 0.4643,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1257183908045977,
|
| 55 |
+
"grad_norm": 7.2714972496032715,
|
| 56 |
+
"learning_rate": 3.44e-06,
|
| 57 |
+
"loss": 0.4358,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.14367816091954022,
|
| 62 |
+
"grad_norm": 6.5415730476379395,
|
| 63 |
+
"learning_rate": 3.94e-06,
|
| 64 |
+
"loss": 0.4219,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.16163793103448276,
|
| 69 |
+
"grad_norm": 7.611192226409912,
|
| 70 |
+
"learning_rate": 4.440000000000001e-06,
|
| 71 |
+
"loss": 0.4036,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.17959770114942528,
|
| 76 |
+
"grad_norm": 6.730944633483887,
|
| 77 |
+
"learning_rate": 4.94e-06,
|
| 78 |
+
"loss": 0.4024,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.19755747126436782,
|
| 83 |
+
"grad_norm": 6.479249000549316,
|
| 84 |
+
"learning_rate": 5.4400000000000004e-06,
|
| 85 |
+
"loss": 0.3915,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.21551724137931033,
|
| 90 |
+
"grad_norm": 6.75312614440918,
|
| 91 |
+
"learning_rate": 5.94e-06,
|
| 92 |
+
"loss": 0.3638,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.23347701149425287,
|
| 97 |
+
"grad_norm": 5.702291488647461,
|
| 98 |
+
"learning_rate": 6.440000000000001e-06,
|
| 99 |
+
"loss": 0.3708,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2514367816091954,
|
| 104 |
+
"grad_norm": 5.4078688621521,
|
| 105 |
+
"learning_rate": 6.9400000000000005e-06,
|
| 106 |
+
"loss": 0.3556,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.26939655172413796,
|
| 111 |
+
"grad_norm": 5.735648155212402,
|
| 112 |
+
"learning_rate": 7.440000000000001e-06,
|
| 113 |
+
"loss": 0.3444,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.28735632183908044,
|
| 118 |
+
"grad_norm": 6.246584892272949,
|
| 119 |
+
"learning_rate": 7.94e-06,
|
| 120 |
+
"loss": 0.3443,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.305316091954023,
|
| 125 |
+
"grad_norm": 6.741141319274902,
|
| 126 |
+
"learning_rate": 8.44e-06,
|
| 127 |
+
"loss": 0.3192,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3232758620689655,
|
| 132 |
+
"grad_norm": 6.674511432647705,
|
| 133 |
+
"learning_rate": 8.94e-06,
|
| 134 |
+
"loss": 0.3249,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.34123563218390807,
|
| 139 |
+
"grad_norm": 6.338778018951416,
|
| 140 |
+
"learning_rate": 9.440000000000001e-06,
|
| 141 |
+
"loss": 0.3331,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.35919540229885055,
|
| 146 |
+
"grad_norm": 6.05772590637207,
|
| 147 |
+
"learning_rate": 9.940000000000001e-06,
|
| 148 |
+
"loss": 0.3067,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3771551724137931,
|
| 153 |
+
"grad_norm": 6.442326545715332,
|
| 154 |
+
"learning_rate": 9.937142857142858e-06,
|
| 155 |
+
"loss": 0.3275,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.39511494252873564,
|
| 160 |
+
"grad_norm": 5.767732620239258,
|
| 161 |
+
"learning_rate": 9.865714285714285e-06,
|
| 162 |
+
"loss": 0.3218,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.4130747126436782,
|
| 167 |
+
"grad_norm": 5.053823471069336,
|
| 168 |
+
"learning_rate": 9.794285714285714e-06,
|
| 169 |
+
"loss": 0.3078,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.43103448275862066,
|
| 174 |
+
"grad_norm": 5.843025207519531,
|
| 175 |
+
"learning_rate": 9.722857142857143e-06,
|
| 176 |
+
"loss": 0.2923,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4489942528735632,
|
| 181 |
+
"grad_norm": 6.414527893066406,
|
| 182 |
+
"learning_rate": 9.651428571428572e-06,
|
| 183 |
+
"loss": 0.2823,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.46695402298850575,
|
| 188 |
+
"grad_norm": 5.519237041473389,
|
| 189 |
+
"learning_rate": 9.58e-06,
|
| 190 |
+
"loss": 0.2789,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4849137931034483,
|
| 195 |
+
"grad_norm": 4.679568290710449,
|
| 196 |
+
"learning_rate": 9.508571428571429e-06,
|
| 197 |
+
"loss": 0.2856,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5028735632183908,
|
| 202 |
+
"grad_norm": 5.241317272186279,
|
| 203 |
+
"learning_rate": 9.437142857142858e-06,
|
| 204 |
+
"loss": 0.2765,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5208333333333334,
|
| 209 |
+
"grad_norm": 5.156564235687256,
|
| 210 |
+
"learning_rate": 9.365714285714287e-06,
|
| 211 |
+
"loss": 0.2715,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5387931034482759,
|
| 216 |
+
"grad_norm": 5.449781894683838,
|
| 217 |
+
"learning_rate": 9.294285714285714e-06,
|
| 218 |
+
"loss": 0.2713,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5567528735632183,
|
| 223 |
+
"grad_norm": 5.37013053894043,
|
| 224 |
+
"learning_rate": 9.222857142857143e-06,
|
| 225 |
+
"loss": 0.2662,
|
| 226 |
+
"step": 775
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5747126436781609,
|
| 230 |
+
"grad_norm": 5.62649393081665,
|
| 231 |
+
"learning_rate": 9.151428571428572e-06,
|
| 232 |
+
"loss": 0.2814,
|
| 233 |
+
"step": 800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5926724137931034,
|
| 237 |
+
"grad_norm": 5.46066427230835,
|
| 238 |
+
"learning_rate": 9.080000000000001e-06,
|
| 239 |
+
"loss": 0.2606,
|
| 240 |
+
"step": 825
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.610632183908046,
|
| 244 |
+
"grad_norm": 5.137524604797363,
|
| 245 |
+
"learning_rate": 9.00857142857143e-06,
|
| 246 |
+
"loss": 0.2329,
|
| 247 |
+
"step": 850
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6285919540229885,
|
| 251 |
+
"grad_norm": 5.287104606628418,
|
| 252 |
+
"learning_rate": 8.937142857142857e-06,
|
| 253 |
+
"loss": 0.2595,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.646551724137931,
|
| 258 |
+
"grad_norm": 6.085468292236328,
|
| 259 |
+
"learning_rate": 8.865714285714287e-06,
|
| 260 |
+
"loss": 0.2558,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6645114942528736,
|
| 265 |
+
"grad_norm": 6.9088826179504395,
|
| 266 |
+
"learning_rate": 8.794285714285716e-06,
|
| 267 |
+
"loss": 0.2408,
|
| 268 |
+
"step": 925
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6824712643678161,
|
| 272 |
+
"grad_norm": 5.21582555770874,
|
| 273 |
+
"learning_rate": 8.722857142857145e-06,
|
| 274 |
+
"loss": 0.2255,
|
| 275 |
+
"step": 950
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7004310344827587,
|
| 279 |
+
"grad_norm": 4.872750759124756,
|
| 280 |
+
"learning_rate": 8.651428571428572e-06,
|
| 281 |
+
"loss": 0.2292,
|
| 282 |
+
"step": 975
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.7183908045977011,
|
| 286 |
+
"grad_norm": 5.2055583000183105,
|
| 287 |
+
"learning_rate": 8.580000000000001e-06,
|
| 288 |
+
"loss": 0.2542,
|
| 289 |
+
"step": 1000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7183908045977011,
|
| 293 |
+
"eval_cer": 9.284704773869347,
|
| 294 |
+
"eval_loss": 0.27573877573013306,
|
| 295 |
+
"eval_runtime": 208.7308,
|
| 296 |
+
"eval_samples_per_second": 2.189,
|
| 297 |
+
"eval_steps_per_second": 0.278,
|
| 298 |
+
"step": 1000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.7363505747126436,
|
| 302 |
+
"grad_norm": 5.838357925415039,
|
| 303 |
+
"learning_rate": 8.50857142857143e-06,
|
| 304 |
+
"loss": 0.2147,
|
| 305 |
+
"step": 1025
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.7543103448275862,
|
| 309 |
+
"grad_norm": 5.988395690917969,
|
| 310 |
+
"learning_rate": 8.437142857142859e-06,
|
| 311 |
+
"loss": 0.2399,
|
| 312 |
+
"step": 1050
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.7722701149425287,
|
| 316 |
+
"grad_norm": 4.545289993286133,
|
| 317 |
+
"learning_rate": 8.365714285714286e-06,
|
| 318 |
+
"loss": 0.2243,
|
| 319 |
+
"step": 1075
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.7902298850574713,
|
| 323 |
+
"grad_norm": 4.793825626373291,
|
| 324 |
+
"learning_rate": 8.294285714285715e-06,
|
| 325 |
+
"loss": 0.2275,
|
| 326 |
+
"step": 1100
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.8081896551724138,
|
| 330 |
+
"grad_norm": 5.085103988647461,
|
| 331 |
+
"learning_rate": 8.222857142857144e-06,
|
| 332 |
+
"loss": 0.2228,
|
| 333 |
+
"step": 1125
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.8261494252873564,
|
| 337 |
+
"grad_norm": 4.345165729522705,
|
| 338 |
+
"learning_rate": 8.151428571428572e-06,
|
| 339 |
+
"loss": 0.2246,
|
| 340 |
+
"step": 1150
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.8441091954022989,
|
| 344 |
+
"grad_norm": 5.478984355926514,
|
| 345 |
+
"learning_rate": 8.08e-06,
|
| 346 |
+
"loss": 0.2041,
|
| 347 |
+
"step": 1175
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.8620689655172413,
|
| 351 |
+
"grad_norm": 5.148238182067871,
|
| 352 |
+
"learning_rate": 8.00857142857143e-06,
|
| 353 |
+
"loss": 0.2123,
|
| 354 |
+
"step": 1200
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.8800287356321839,
|
| 358 |
+
"grad_norm": 5.2301106452941895,
|
| 359 |
+
"learning_rate": 7.937142857142857e-06,
|
| 360 |
+
"loss": 0.2135,
|
| 361 |
+
"step": 1225
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.8979885057471264,
|
| 365 |
+
"grad_norm": 5.3838019371032715,
|
| 366 |
+
"learning_rate": 7.865714285714286e-06,
|
| 367 |
+
"loss": 0.1978,
|
| 368 |
+
"step": 1250
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.915948275862069,
|
| 372 |
+
"grad_norm": 5.178905487060547,
|
| 373 |
+
"learning_rate": 7.794285714285715e-06,
|
| 374 |
+
"loss": 0.2127,
|
| 375 |
+
"step": 1275
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.9339080459770115,
|
| 379 |
+
"grad_norm": 5.5203351974487305,
|
| 380 |
+
"learning_rate": 7.722857142857142e-06,
|
| 381 |
+
"loss": 0.2128,
|
| 382 |
+
"step": 1300
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.951867816091954,
|
| 386 |
+
"grad_norm": 5.354878902435303,
|
| 387 |
+
"learning_rate": 7.651428571428571e-06,
|
| 388 |
+
"loss": 0.1924,
|
| 389 |
+
"step": 1325
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.9698275862068966,
|
| 393 |
+
"grad_norm": 5.155806064605713,
|
| 394 |
+
"learning_rate": 7.58e-06,
|
| 395 |
+
"loss": 0.209,
|
| 396 |
+
"step": 1350
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.9877873563218391,
|
| 400 |
+
"grad_norm": 4.325410842895508,
|
| 401 |
+
"learning_rate": 7.508571428571429e-06,
|
| 402 |
+
"loss": 0.2019,
|
| 403 |
+
"step": 1375
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.0057471264367817,
|
| 407 |
+
"grad_norm": 3.931236743927002,
|
| 408 |
+
"learning_rate": 7.4371428571428575e-06,
|
| 409 |
+
"loss": 0.2028,
|
| 410 |
+
"step": 1400
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.0237068965517242,
|
| 414 |
+
"grad_norm": 4.375692844390869,
|
| 415 |
+
"learning_rate": 7.365714285714286e-06,
|
| 416 |
+
"loss": 0.1572,
|
| 417 |
+
"step": 1425
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.0416666666666667,
|
| 421 |
+
"grad_norm": 3.4934616088867188,
|
| 422 |
+
"learning_rate": 7.294285714285715e-06,
|
| 423 |
+
"loss": 0.1423,
|
| 424 |
+
"step": 1450
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.0596264367816093,
|
| 428 |
+
"grad_norm": 4.1985249519348145,
|
| 429 |
+
"learning_rate": 7.222857142857144e-06,
|
| 430 |
+
"loss": 0.1477,
|
| 431 |
+
"step": 1475
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.0775862068965518,
|
| 435 |
+
"grad_norm": 4.258643627166748,
|
| 436 |
+
"learning_rate": 7.151428571428573e-06,
|
| 437 |
+
"loss": 0.145,
|
| 438 |
+
"step": 1500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.0955459770114944,
|
| 442 |
+
"grad_norm": 3.0669021606445312,
|
| 443 |
+
"learning_rate": 7.08e-06,
|
| 444 |
+
"loss": 0.1404,
|
| 445 |
+
"step": 1525
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.1135057471264367,
|
| 449 |
+
"grad_norm": 4.19215726852417,
|
| 450 |
+
"learning_rate": 7.008571428571429e-06,
|
| 451 |
+
"loss": 0.1427,
|
| 452 |
+
"step": 1550
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.1314655172413792,
|
| 456 |
+
"grad_norm": 4.806066989898682,
|
| 457 |
+
"learning_rate": 6.937142857142858e-06,
|
| 458 |
+
"loss": 0.1339,
|
| 459 |
+
"step": 1575
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.1494252873563218,
|
| 463 |
+
"grad_norm": 4.574463367462158,
|
| 464 |
+
"learning_rate": 6.865714285714287e-06,
|
| 465 |
+
"loss": 0.1427,
|
| 466 |
+
"step": 1600
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.1673850574712643,
|
| 470 |
+
"grad_norm": 4.810680866241455,
|
| 471 |
+
"learning_rate": 6.794285714285714e-06,
|
| 472 |
+
"loss": 0.1313,
|
| 473 |
+
"step": 1625
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.1853448275862069,
|
| 477 |
+
"grad_norm": 4.358596324920654,
|
| 478 |
+
"learning_rate": 6.722857142857143e-06,
|
| 479 |
+
"loss": 0.1487,
|
| 480 |
+
"step": 1650
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.2033045977011494,
|
| 484 |
+
"grad_norm": 3.6320159435272217,
|
| 485 |
+
"learning_rate": 6.651428571428572e-06,
|
| 486 |
+
"loss": 0.1373,
|
| 487 |
+
"step": 1675
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.221264367816092,
|
| 491 |
+
"grad_norm": 4.551269054412842,
|
| 492 |
+
"learning_rate": 6.5800000000000005e-06,
|
| 493 |
+
"loss": 0.1322,
|
| 494 |
+
"step": 1700
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.2392241379310345,
|
| 498 |
+
"grad_norm": 3.798658847808838,
|
| 499 |
+
"learning_rate": 6.5085714285714295e-06,
|
| 500 |
+
"loss": 0.1324,
|
| 501 |
+
"step": 1725
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.257183908045977,
|
| 505 |
+
"grad_norm": 3.2752606868743896,
|
| 506 |
+
"learning_rate": 6.437142857142858e-06,
|
| 507 |
+
"loss": 0.1409,
|
| 508 |
+
"step": 1750
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.2751436781609196,
|
| 512 |
+
"grad_norm": 3.7986721992492676,
|
| 513 |
+
"learning_rate": 6.365714285714286e-06,
|
| 514 |
+
"loss": 0.1316,
|
| 515 |
+
"step": 1775
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.293103448275862,
|
| 519 |
+
"grad_norm": 3.678849458694458,
|
| 520 |
+
"learning_rate": 6.294285714285715e-06,
|
| 521 |
+
"loss": 0.131,
|
| 522 |
+
"step": 1800
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.3110632183908046,
|
| 526 |
+
"grad_norm": 4.378350257873535,
|
| 527 |
+
"learning_rate": 6.222857142857144e-06,
|
| 528 |
+
"loss": 0.1213,
|
| 529 |
+
"step": 1825
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.3290229885057472,
|
| 533 |
+
"grad_norm": 4.888228893280029,
|
| 534 |
+
"learning_rate": 6.151428571428571e-06,
|
| 535 |
+
"loss": 0.1499,
|
| 536 |
+
"step": 1850
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.3469827586206897,
|
| 540 |
+
"grad_norm": 3.7335093021392822,
|
| 541 |
+
"learning_rate": 6.08e-06,
|
| 542 |
+
"loss": 0.1261,
|
| 543 |
+
"step": 1875
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.3649425287356323,
|
| 547 |
+
"grad_norm": 4.47926664352417,
|
| 548 |
+
"learning_rate": 6.008571428571429e-06,
|
| 549 |
+
"loss": 0.1361,
|
| 550 |
+
"step": 1900
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.3829022988505746,
|
| 554 |
+
"grad_norm": 3.6603622436523438,
|
| 555 |
+
"learning_rate": 5.937142857142858e-06,
|
| 556 |
+
"loss": 0.135,
|
| 557 |
+
"step": 1925
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.4008620689655173,
|
| 561 |
+
"grad_norm": 3.8697991371154785,
|
| 562 |
+
"learning_rate": 5.865714285714286e-06,
|
| 563 |
+
"loss": 0.1157,
|
| 564 |
+
"step": 1950
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.4188218390804597,
|
| 568 |
+
"grad_norm": 3.898298740386963,
|
| 569 |
+
"learning_rate": 5.794285714285715e-06,
|
| 570 |
+
"loss": 0.1262,
|
| 571 |
+
"step": 1975
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.4367816091954024,
|
| 575 |
+
"grad_norm": 6.249912261962891,
|
| 576 |
+
"learning_rate": 5.722857142857144e-06,
|
| 577 |
+
"loss": 0.128,
|
| 578 |
+
"step": 2000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.4367816091954024,
|
| 582 |
+
"eval_cer": 7.455244974874371,
|
| 583 |
+
"eval_loss": 0.20655690133571625,
|
| 584 |
+
"eval_runtime": 206.1569,
|
| 585 |
+
"eval_samples_per_second": 2.217,
|
| 586 |
+
"eval_steps_per_second": 0.281,
|
| 587 |
+
"step": 2000
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.4547413793103448,
|
| 591 |
+
"grad_norm": 3.680793285369873,
|
| 592 |
+
"learning_rate": 5.651428571428572e-06,
|
| 593 |
+
"loss": 0.1249,
|
| 594 |
+
"step": 2025
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.4727011494252873,
|
| 598 |
+
"grad_norm": 4.394272804260254,
|
| 599 |
+
"learning_rate": 5.580000000000001e-06,
|
| 600 |
+
"loss": 0.1327,
|
| 601 |
+
"step": 2050
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.4906609195402298,
|
| 605 |
+
"grad_norm": 3.971735954284668,
|
| 606 |
+
"learning_rate": 5.508571428571429e-06,
|
| 607 |
+
"loss": 0.1256,
|
| 608 |
+
"step": 2075
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.5086206896551724,
|
| 612 |
+
"grad_norm": 3.7754571437835693,
|
| 613 |
+
"learning_rate": 5.437142857142857e-06,
|
| 614 |
+
"loss": 0.12,
|
| 615 |
+
"step": 2100
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.526580459770115,
|
| 619 |
+
"grad_norm": 5.009246826171875,
|
| 620 |
+
"learning_rate": 5.365714285714286e-06,
|
| 621 |
+
"loss": 0.1258,
|
| 622 |
+
"step": 2125
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.5445402298850575,
|
| 626 |
+
"grad_norm": 3.481464147567749,
|
| 627 |
+
"learning_rate": 5.294285714285715e-06,
|
| 628 |
+
"loss": 0.1174,
|
| 629 |
+
"step": 2150
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.5625,
|
| 633 |
+
"grad_norm": 3.6977555751800537,
|
| 634 |
+
"learning_rate": 5.2228571428571425e-06,
|
| 635 |
+
"loss": 0.1248,
|
| 636 |
+
"step": 2175
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.5804597701149425,
|
| 640 |
+
"grad_norm": 3.6558139324188232,
|
| 641 |
+
"learning_rate": 5.1514285714285715e-06,
|
| 642 |
+
"loss": 0.1145,
|
| 643 |
+
"step": 2200
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.598419540229885,
|
| 647 |
+
"grad_norm": 3.2170028686523438,
|
| 648 |
+
"learning_rate": 5.0800000000000005e-06,
|
| 649 |
+
"loss": 0.1181,
|
| 650 |
+
"step": 2225
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.6163793103448276,
|
| 654 |
+
"grad_norm": 3.2904043197631836,
|
| 655 |
+
"learning_rate": 5.0085714285714295e-06,
|
| 656 |
+
"loss": 0.1261,
|
| 657 |
+
"step": 2250
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.6343390804597702,
|
| 661 |
+
"grad_norm": 6.5361223220825195,
|
| 662 |
+
"learning_rate": 4.937142857142858e-06,
|
| 663 |
+
"loss": 0.1257,
|
| 664 |
+
"step": 2275
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.6522988505747125,
|
| 668 |
+
"grad_norm": 3.8789713382720947,
|
| 669 |
+
"learning_rate": 4.865714285714287e-06,
|
| 670 |
+
"loss": 0.1166,
|
| 671 |
+
"step": 2300
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.6702586206896552,
|
| 675 |
+
"grad_norm": 3.6503453254699707,
|
| 676 |
+
"learning_rate": 4.794285714285715e-06,
|
| 677 |
+
"loss": 0.1166,
|
| 678 |
+
"step": 2325
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.6882183908045976,
|
| 682 |
+
"grad_norm": 2.955310344696045,
|
| 683 |
+
"learning_rate": 4.722857142857144e-06,
|
| 684 |
+
"loss": 0.1148,
|
| 685 |
+
"step": 2350
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.7061781609195403,
|
| 689 |
+
"grad_norm": 3.2080459594726562,
|
| 690 |
+
"learning_rate": 4.651428571428572e-06,
|
| 691 |
+
"loss": 0.1153,
|
| 692 |
+
"step": 2375
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.7241379310344827,
|
| 696 |
+
"grad_norm": 2.9274492263793945,
|
| 697 |
+
"learning_rate": 4.58e-06,
|
| 698 |
+
"loss": 0.1263,
|
| 699 |
+
"step": 2400
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.7420977011494254,
|
| 703 |
+
"grad_norm": 3.9885170459747314,
|
| 704 |
+
"learning_rate": 4.508571428571429e-06,
|
| 705 |
+
"loss": 0.1041,
|
| 706 |
+
"step": 2425
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.7600574712643677,
|
| 710 |
+
"grad_norm": 5.113827228546143,
|
| 711 |
+
"learning_rate": 4.437142857142857e-06,
|
| 712 |
+
"loss": 0.1179,
|
| 713 |
+
"step": 2450
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.7780172413793105,
|
| 717 |
+
"grad_norm": 5.254714012145996,
|
| 718 |
+
"learning_rate": 4.3657142857142855e-06,
|
| 719 |
+
"loss": 0.1183,
|
| 720 |
+
"step": 2475
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.7959770114942528,
|
| 724 |
+
"grad_norm": 5.9119696617126465,
|
| 725 |
+
"learning_rate": 4.2942857142857146e-06,
|
| 726 |
+
"loss": 0.1183,
|
| 727 |
+
"step": 2500
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.8139367816091954,
|
| 731 |
+
"grad_norm": 3.5279624462127686,
|
| 732 |
+
"learning_rate": 4.222857142857143e-06,
|
| 733 |
+
"loss": 0.1174,
|
| 734 |
+
"step": 2525
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.831896551724138,
|
| 738 |
+
"grad_norm": 3.6319098472595215,
|
| 739 |
+
"learning_rate": 4.151428571428572e-06,
|
| 740 |
+
"loss": 0.1084,
|
| 741 |
+
"step": 2550
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.8498563218390804,
|
| 745 |
+
"grad_norm": 4.165521621704102,
|
| 746 |
+
"learning_rate": 4.08e-06,
|
| 747 |
+
"loss": 0.1086,
|
| 748 |
+
"step": 2575
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.867816091954023,
|
| 752 |
+
"grad_norm": 3.5935449600219727,
|
| 753 |
+
"learning_rate": 4.008571428571429e-06,
|
| 754 |
+
"loss": 0.1013,
|
| 755 |
+
"step": 2600
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.8857758620689655,
|
| 759 |
+
"grad_norm": 4.520440101623535,
|
| 760 |
+
"learning_rate": 3.937142857142858e-06,
|
| 761 |
+
"loss": 0.1085,
|
| 762 |
+
"step": 2625
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.903735632183908,
|
| 766 |
+
"grad_norm": 4.8552327156066895,
|
| 767 |
+
"learning_rate": 3.865714285714286e-06,
|
| 768 |
+
"loss": 0.1075,
|
| 769 |
+
"step": 2650
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.9216954022988506,
|
| 773 |
+
"grad_norm": 5.094956874847412,
|
| 774 |
+
"learning_rate": 3.7942857142857147e-06,
|
| 775 |
+
"loss": 0.1153,
|
| 776 |
+
"step": 2675
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 1.9396551724137931,
|
| 780 |
+
"grad_norm": 4.34927225112915,
|
| 781 |
+
"learning_rate": 3.722857142857143e-06,
|
| 782 |
+
"loss": 0.1092,
|
| 783 |
+
"step": 2700
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.9576149425287355,
|
| 787 |
+
"grad_norm": 2.9122841358184814,
|
| 788 |
+
"learning_rate": 3.651428571428572e-06,
|
| 789 |
+
"loss": 0.1094,
|
| 790 |
+
"step": 2725
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.9755747126436782,
|
| 794 |
+
"grad_norm": 4.0797529220581055,
|
| 795 |
+
"learning_rate": 3.58e-06,
|
| 796 |
+
"loss": 0.1031,
|
| 797 |
+
"step": 2750
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.9935344827586206,
|
| 801 |
+
"grad_norm": 3.478084087371826,
|
| 802 |
+
"learning_rate": 3.508571428571429e-06,
|
| 803 |
+
"loss": 0.1035,
|
| 804 |
+
"step": 2775
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 2.0114942528735633,
|
| 808 |
+
"grad_norm": 2.5905420780181885,
|
| 809 |
+
"learning_rate": 3.437142857142857e-06,
|
| 810 |
+
"loss": 0.086,
|
| 811 |
+
"step": 2800
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 2.0294540229885056,
|
| 815 |
+
"grad_norm": 2.674304246902466,
|
| 816 |
+
"learning_rate": 3.3657142857142862e-06,
|
| 817 |
+
"loss": 0.0741,
|
| 818 |
+
"step": 2825
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.0474137931034484,
|
| 822 |
+
"grad_norm": 3.0569241046905518,
|
| 823 |
+
"learning_rate": 3.2942857142857144e-06,
|
| 824 |
+
"loss": 0.0722,
|
| 825 |
+
"step": 2850
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.0653735632183907,
|
| 829 |
+
"grad_norm": 2.8325390815734863,
|
| 830 |
+
"learning_rate": 3.222857142857143e-06,
|
| 831 |
+
"loss": 0.0759,
|
| 832 |
+
"step": 2875
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 2.0833333333333335,
|
| 836 |
+
"grad_norm": 3.281291961669922,
|
| 837 |
+
"learning_rate": 3.151428571428572e-06,
|
| 838 |
+
"loss": 0.0803,
|
| 839 |
+
"step": 2900
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 2.101293103448276,
|
| 843 |
+
"grad_norm": 2.3541665077209473,
|
| 844 |
+
"learning_rate": 3.08e-06,
|
| 845 |
+
"loss": 0.0672,
|
| 846 |
+
"step": 2925
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 2.1192528735632186,
|
| 850 |
+
"grad_norm": 3.7438085079193115,
|
| 851 |
+
"learning_rate": 3.008571428571429e-06,
|
| 852 |
+
"loss": 0.0737,
|
| 853 |
+
"step": 2950
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 2.137212643678161,
|
| 857 |
+
"grad_norm": 2.571523427963257,
|
| 858 |
+
"learning_rate": 2.9371428571428573e-06,
|
| 859 |
+
"loss": 0.065,
|
| 860 |
+
"step": 2975
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 2.1551724137931036,
|
| 864 |
+
"grad_norm": 2.559622287750244,
|
| 865 |
+
"learning_rate": 2.865714285714286e-06,
|
| 866 |
+
"loss": 0.0725,
|
| 867 |
+
"step": 3000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.1551724137931036,
|
| 871 |
+
"eval_cer": 5.755339195979899,
|
| 872 |
+
"eval_loss": 0.17403484880924225,
|
| 873 |
+
"eval_runtime": 203.7679,
|
| 874 |
+
"eval_samples_per_second": 2.243,
|
| 875 |
+
"eval_steps_per_second": 0.285,
|
| 876 |
+
"step": 3000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 2.173132183908046,
|
| 880 |
+
"grad_norm": 2.8300039768218994,
|
| 881 |
+
"learning_rate": 2.7942857142857145e-06,
|
| 882 |
+
"loss": 0.0691,
|
| 883 |
+
"step": 3025
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 2.1910919540229887,
|
| 887 |
+
"grad_norm": 2.468639850616455,
|
| 888 |
+
"learning_rate": 2.722857142857143e-06,
|
| 889 |
+
"loss": 0.0834,
|
| 890 |
+
"step": 3050
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.209051724137931,
|
| 894 |
+
"grad_norm": 3.254262685775757,
|
| 895 |
+
"learning_rate": 2.6514285714285713e-06,
|
| 896 |
+
"loss": 0.0727,
|
| 897 |
+
"step": 3075
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 2.2270114942528734,
|
| 901 |
+
"grad_norm": 3.118223190307617,
|
| 902 |
+
"learning_rate": 2.5800000000000003e-06,
|
| 903 |
+
"loss": 0.0783,
|
| 904 |
+
"step": 3100
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 2.244971264367816,
|
| 908 |
+
"grad_norm": 2.0613930225372314,
|
| 909 |
+
"learning_rate": 2.5085714285714285e-06,
|
| 910 |
+
"loss": 0.0677,
|
| 911 |
+
"step": 3125
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 2.2629310344827585,
|
| 915 |
+
"grad_norm": 4.234766483306885,
|
| 916 |
+
"learning_rate": 2.4371428571428575e-06,
|
| 917 |
+
"loss": 0.0695,
|
| 918 |
+
"step": 3150
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 2.280890804597701,
|
| 922 |
+
"grad_norm": 3.091860294342041,
|
| 923 |
+
"learning_rate": 2.365714285714286e-06,
|
| 924 |
+
"loss": 0.0674,
|
| 925 |
+
"step": 3175
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 2.2988505747126435,
|
| 929 |
+
"grad_norm": 2.968728542327881,
|
| 930 |
+
"learning_rate": 2.2942857142857146e-06,
|
| 931 |
+
"loss": 0.0793,
|
| 932 |
+
"step": 3200
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 2.3168103448275863,
|
| 936 |
+
"grad_norm": 2.635185956954956,
|
| 937 |
+
"learning_rate": 2.222857142857143e-06,
|
| 938 |
+
"loss": 0.0669,
|
| 939 |
+
"step": 3225
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 2.3347701149425286,
|
| 943 |
+
"grad_norm": 4.698062896728516,
|
| 944 |
+
"learning_rate": 2.1514285714285714e-06,
|
| 945 |
+
"loss": 0.0792,
|
| 946 |
+
"step": 3250
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.3527298850574714,
|
| 950 |
+
"grad_norm": 2.380126953125,
|
| 951 |
+
"learning_rate": 2.08e-06,
|
| 952 |
+
"loss": 0.0686,
|
| 953 |
+
"step": 3275
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 2.3706896551724137,
|
| 957 |
+
"grad_norm": 2.4431111812591553,
|
| 958 |
+
"learning_rate": 2.0085714285714286e-06,
|
| 959 |
+
"loss": 0.0683,
|
| 960 |
+
"step": 3300
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 2.3886494252873565,
|
| 964 |
+
"grad_norm": 2.8130743503570557,
|
| 965 |
+
"learning_rate": 1.9371428571428576e-06,
|
| 966 |
+
"loss": 0.0726,
|
| 967 |
+
"step": 3325
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 2.406609195402299,
|
| 971 |
+
"grad_norm": 2.115403890609741,
|
| 972 |
+
"learning_rate": 1.865714285714286e-06,
|
| 973 |
+
"loss": 0.0715,
|
| 974 |
+
"step": 3350
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.4245689655172415,
|
| 978 |
+
"grad_norm": 3.2712090015411377,
|
| 979 |
+
"learning_rate": 1.7942857142857146e-06,
|
| 980 |
+
"loss": 0.0677,
|
| 981 |
+
"step": 3375
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 2.442528735632184,
|
| 985 |
+
"grad_norm": 2.903533697128296,
|
| 986 |
+
"learning_rate": 1.7228571428571432e-06,
|
| 987 |
+
"loss": 0.0722,
|
| 988 |
+
"step": 3400
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 2.4604885057471266,
|
| 992 |
+
"grad_norm": 2.4043657779693604,
|
| 993 |
+
"learning_rate": 1.6514285714285715e-06,
|
| 994 |
+
"loss": 0.0723,
|
| 995 |
+
"step": 3425
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 2.478448275862069,
|
| 999 |
+
"grad_norm": 2.5334341526031494,
|
| 1000 |
+
"learning_rate": 1.5800000000000001e-06,
|
| 1001 |
+
"loss": 0.0729,
|
| 1002 |
+
"step": 3450
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 2.4964080459770113,
|
| 1006 |
+
"grad_norm": 2.8699309825897217,
|
| 1007 |
+
"learning_rate": 1.5085714285714287e-06,
|
| 1008 |
+
"loss": 0.0733,
|
| 1009 |
+
"step": 3475
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 2.514367816091954,
|
| 1013 |
+
"grad_norm": 3.6407063007354736,
|
| 1014 |
+
"learning_rate": 1.4371428571428573e-06,
|
| 1015 |
+
"loss": 0.0912,
|
| 1016 |
+
"step": 3500
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 2.532327586206897,
|
| 1020 |
+
"grad_norm": 2.9028170108795166,
|
| 1021 |
+
"learning_rate": 1.3657142857142857e-06,
|
| 1022 |
+
"loss": 0.0704,
|
| 1023 |
+
"step": 3525
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 2.550287356321839,
|
| 1027 |
+
"grad_norm": 2.9066832065582275,
|
| 1028 |
+
"learning_rate": 1.2942857142857143e-06,
|
| 1029 |
+
"loss": 0.0666,
|
| 1030 |
+
"step": 3550
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 2.5682471264367814,
|
| 1034 |
+
"grad_norm": 3.7357940673828125,
|
| 1035 |
+
"learning_rate": 1.222857142857143e-06,
|
| 1036 |
+
"loss": 0.075,
|
| 1037 |
+
"step": 3575
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 2.586206896551724,
|
| 1041 |
+
"grad_norm": 2.8801915645599365,
|
| 1042 |
+
"learning_rate": 1.1514285714285714e-06,
|
| 1043 |
+
"loss": 0.0792,
|
| 1044 |
+
"step": 3600
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.6041666666666665,
|
| 1048 |
+
"grad_norm": 3.622131824493408,
|
| 1049 |
+
"learning_rate": 1.08e-06,
|
| 1050 |
+
"loss": 0.07,
|
| 1051 |
+
"step": 3625
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 2.6221264367816093,
|
| 1055 |
+
"grad_norm": 3.064757823944092,
|
| 1056 |
+
"learning_rate": 1.0085714285714286e-06,
|
| 1057 |
+
"loss": 0.066,
|
| 1058 |
+
"step": 3650
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 2.6400862068965516,
|
| 1062 |
+
"grad_norm": 2.172606945037842,
|
| 1063 |
+
"learning_rate": 9.371428571428571e-07,
|
| 1064 |
+
"loss": 0.0579,
|
| 1065 |
+
"step": 3675
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.6580459770114944,
|
| 1069 |
+
"grad_norm": 4.104800701141357,
|
| 1070 |
+
"learning_rate": 8.657142857142858e-07,
|
| 1071 |
+
"loss": 0.078,
|
| 1072 |
+
"step": 3700
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 2.6760057471264367,
|
| 1076 |
+
"grad_norm": 3.803704261779785,
|
| 1077 |
+
"learning_rate": 7.942857142857144e-07,
|
| 1078 |
+
"loss": 0.0768,
|
| 1079 |
+
"step": 3725
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 2.6939655172413794,
|
| 1083 |
+
"grad_norm": 1.876494288444519,
|
| 1084 |
+
"learning_rate": 7.228571428571429e-07,
|
| 1085 |
+
"loss": 0.066,
|
| 1086 |
+
"step": 3750
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 2.7119252873563218,
|
| 1090 |
+
"grad_norm": 4.310028076171875,
|
| 1091 |
+
"learning_rate": 6.514285714285715e-07,
|
| 1092 |
+
"loss": 0.0665,
|
| 1093 |
+
"step": 3775
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 2.7298850574712645,
|
| 1097 |
+
"grad_norm": 3.0695154666900635,
|
| 1098 |
+
"learning_rate": 5.800000000000001e-07,
|
| 1099 |
+
"loss": 0.0695,
|
| 1100 |
+
"step": 3800
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 2.747844827586207,
|
| 1104 |
+
"grad_norm": 3.2505669593811035,
|
| 1105 |
+
"learning_rate": 5.085714285714286e-07,
|
| 1106 |
+
"loss": 0.065,
|
| 1107 |
+
"step": 3825
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 2.765804597701149,
|
| 1111 |
+
"grad_norm": 2.551088809967041,
|
| 1112 |
+
"learning_rate": 4.371428571428572e-07,
|
| 1113 |
+
"loss": 0.0649,
|
| 1114 |
+
"step": 3850
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 2.783764367816092,
|
| 1118 |
+
"grad_norm": 3.110604763031006,
|
| 1119 |
+
"learning_rate": 3.657142857142858e-07,
|
| 1120 |
+
"loss": 0.0704,
|
| 1121 |
+
"step": 3875
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 2.8017241379310347,
|
| 1125 |
+
"grad_norm": 2.836848020553589,
|
| 1126 |
+
"learning_rate": 2.942857142857143e-07,
|
| 1127 |
+
"loss": 0.0698,
|
| 1128 |
+
"step": 3900
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 2.819683908045977,
|
| 1132 |
+
"grad_norm": 2.818726062774658,
|
| 1133 |
+
"learning_rate": 2.228571428571429e-07,
|
| 1134 |
+
"loss": 0.0722,
|
| 1135 |
+
"step": 3925
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 2.8376436781609193,
|
| 1139 |
+
"grad_norm": 2.192012071609497,
|
| 1140 |
+
"learning_rate": 1.5142857142857144e-07,
|
| 1141 |
+
"loss": 0.0657,
|
| 1142 |
+
"step": 3950
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 2.855603448275862,
|
| 1146 |
+
"grad_norm": 3.1882786750793457,
|
| 1147 |
+
"learning_rate": 8e-08,
|
| 1148 |
+
"loss": 0.0751,
|
| 1149 |
+
"step": 3975
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 2.873563218390805,
|
| 1153 |
+
"grad_norm": 3.386892557144165,
|
| 1154 |
+
"learning_rate": 8.571428571428572e-09,
|
| 1155 |
+
"loss": 0.0673,
|
| 1156 |
+
"step": 4000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 2.873563218390805,
|
| 1160 |
+
"eval_cer": 5.288159547738693,
|
| 1161 |
+
"eval_loss": 0.16544735431671143,
|
| 1162 |
+
"eval_runtime": 204.9568,
|
| 1163 |
+
"eval_samples_per_second": 2.23,
|
| 1164 |
+
"eval_steps_per_second": 0.283,
|
| 1165 |
+
"step": 4000
|
| 1166 |
+
}
|
| 1167 |
+
],
|
| 1168 |
+
"logging_steps": 25,
|
| 1169 |
+
"max_steps": 4000,
|
| 1170 |
+
"num_input_tokens_seen": 0,
|
| 1171 |
+
"num_train_epochs": 3,
|
| 1172 |
+
"save_steps": 1000,
|
| 1173 |
+
"stateful_callbacks": {
|
| 1174 |
+
"TrainerControl": {
|
| 1175 |
+
"args": {
|
| 1176 |
+
"should_epoch_stop": false,
|
| 1177 |
+
"should_evaluate": false,
|
| 1178 |
+
"should_log": false,
|
| 1179 |
+
"should_save": true,
|
| 1180 |
+
"should_training_stop": true
|
| 1181 |
+
},
|
| 1182 |
+
"attributes": {}
|
| 1183 |
+
}
|
| 1184 |
+
},
|
| 1185 |
+
"total_flos": 4.14987227430912e+18,
|
| 1186 |
+
"train_batch_size": 16,
|
| 1187 |
+
"trial_name": null,
|
| 1188 |
+
"trial_params": null
|
| 1189 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a9af4c937a63924924c297d8f403592de8fa3edb05a127db84ec471c068832a
|
| 3 |
+
size 5240
|