Upload 9 files
Browse files- config.json +65 -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 +1742 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": [
|
| 29 |
+
[
|
| 30 |
+
1,
|
| 31 |
+
50266
|
| 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": 24,
|
| 56 |
+
"num_mel_bins": 80,
|
| 57 |
+
"pad_token_id": 50257,
|
| 58 |
+
"scale_embedding": false,
|
| 59 |
+
"suppress_tokens": [],
|
| 60 |
+
"torch_dtype": "float32",
|
| 61 |
+
"transformers_version": "4.44.2",
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"use_weighted_layer_sum": false,
|
| 64 |
+
"vocab_size": 51865
|
| 65 |
+
}
|
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": "4.44.2"
|
| 248 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a92adc0f6e311f1e32a452662339c3ddfa8345e3acdd860f6e9d863c26ec5ef3
|
| 3 |
+
size 3055544304
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa37f6a7556126f2d9076949f15df386c4f2a64376023cfa947a98583c2c1579
|
| 3 |
+
size 3653619038
|
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:f3d11e72c6be81e08d080a52df4f0e16adb27dedf145a913680acd9531ef65a4
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9247523a2a09e2300eda233d249b37d104af98f3bfd334c48fdfa496dd543bfb
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1742 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3294712007045746,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/Development/whisperfinetune/whisper-medium-20241208122604/20241208122604/checkpoint-100",
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 1.1317138671875,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 0.0573,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_loss": 2.347386121749878,
|
| 21 |
+
"eval_model_preparation_time": 0.0121,
|
| 22 |
+
"eval_runtime": 13.1236,
|
| 23 |
+
"eval_samples_per_second": 1.524,
|
| 24 |
+
"eval_steps_per_second": 0.229,
|
| 25 |
+
"eval_wer": 11.728395061728394,
|
| 26 |
+
"step": 1
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.0,
|
| 30 |
+
"grad_norm": 0.5305148959159851,
|
| 31 |
+
"learning_rate": 1e-05,
|
| 32 |
+
"loss": 0.0595,
|
| 33 |
+
"step": 2
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.0,
|
| 37 |
+
"eval_loss": 2.04854416847229,
|
| 38 |
+
"eval_model_preparation_time": 0.0121,
|
| 39 |
+
"eval_runtime": 13.3393,
|
| 40 |
+
"eval_samples_per_second": 1.499,
|
| 41 |
+
"eval_steps_per_second": 0.225,
|
| 42 |
+
"eval_wer": 8.641975308641975,
|
| 43 |
+
"step": 2
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 3.0,
|
| 47 |
+
"grad_norm": 0.47034594416618347,
|
| 48 |
+
"learning_rate": 1e-05,
|
| 49 |
+
"loss": 0.0515,
|
| 50 |
+
"step": 3
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.0,
|
| 54 |
+
"eval_loss": 1.7598810195922852,
|
| 55 |
+
"eval_model_preparation_time": 0.0121,
|
| 56 |
+
"eval_runtime": 13.2129,
|
| 57 |
+
"eval_samples_per_second": 1.514,
|
| 58 |
+
"eval_steps_per_second": 0.227,
|
| 59 |
+
"eval_wer": 5.555555555555555,
|
| 60 |
+
"step": 3
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.0,
|
| 64 |
+
"grad_norm": 0.8446077108383179,
|
| 65 |
+
"learning_rate": 1e-05,
|
| 66 |
+
"loss": 0.044,
|
| 67 |
+
"step": 4
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 4.0,
|
| 71 |
+
"eval_loss": 1.1538535356521606,
|
| 72 |
+
"eval_model_preparation_time": 0.0121,
|
| 73 |
+
"eval_runtime": 13.3081,
|
| 74 |
+
"eval_samples_per_second": 1.503,
|
| 75 |
+
"eval_steps_per_second": 0.225,
|
| 76 |
+
"eval_wer": 5.246913580246913,
|
| 77 |
+
"step": 4
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 5.0,
|
| 81 |
+
"grad_norm": 0.1741047352552414,
|
| 82 |
+
"learning_rate": 1e-05,
|
| 83 |
+
"loss": 0.0282,
|
| 84 |
+
"step": 5
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.0,
|
| 88 |
+
"eval_loss": 1.1221383810043335,
|
| 89 |
+
"eval_model_preparation_time": 0.0121,
|
| 90 |
+
"eval_runtime": 13.1632,
|
| 91 |
+
"eval_samples_per_second": 1.519,
|
| 92 |
+
"eval_steps_per_second": 0.228,
|
| 93 |
+
"eval_wer": 4.938271604938271,
|
| 94 |
+
"step": 5
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 6.0,
|
| 98 |
+
"grad_norm": 0.16934086382389069,
|
| 99 |
+
"learning_rate": 1e-05,
|
| 100 |
+
"loss": 0.0276,
|
| 101 |
+
"step": 6
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 6.0,
|
| 105 |
+
"eval_loss": 1.0995134115219116,
|
| 106 |
+
"eval_model_preparation_time": 0.0121,
|
| 107 |
+
"eval_runtime": 13.2456,
|
| 108 |
+
"eval_samples_per_second": 1.51,
|
| 109 |
+
"eval_steps_per_second": 0.226,
|
| 110 |
+
"eval_wer": 4.320987654320987,
|
| 111 |
+
"step": 6
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 7.0,
|
| 115 |
+
"grad_norm": 0.166069895029068,
|
| 116 |
+
"learning_rate": 1e-05,
|
| 117 |
+
"loss": 0.0271,
|
| 118 |
+
"step": 7
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 7.0,
|
| 122 |
+
"eval_loss": 1.0805295705795288,
|
| 123 |
+
"eval_model_preparation_time": 0.0121,
|
| 124 |
+
"eval_runtime": 13.0555,
|
| 125 |
+
"eval_samples_per_second": 1.532,
|
| 126 |
+
"eval_steps_per_second": 0.23,
|
| 127 |
+
"eval_wer": 4.320987654320987,
|
| 128 |
+
"step": 7
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"grad_norm": 0.1637350171804428,
|
| 133 |
+
"learning_rate": 1e-05,
|
| 134 |
+
"loss": 0.0266,
|
| 135 |
+
"step": 8
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.0,
|
| 139 |
+
"eval_loss": 1.0605648756027222,
|
| 140 |
+
"eval_model_preparation_time": 0.0121,
|
| 141 |
+
"eval_runtime": 13.2511,
|
| 142 |
+
"eval_samples_per_second": 1.509,
|
| 143 |
+
"eval_steps_per_second": 0.226,
|
| 144 |
+
"eval_wer": 4.320987654320987,
|
| 145 |
+
"step": 8
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 9.0,
|
| 149 |
+
"grad_norm": 0.16157877445220947,
|
| 150 |
+
"learning_rate": 1e-05,
|
| 151 |
+
"loss": 0.026,
|
| 152 |
+
"step": 9
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 9.0,
|
| 156 |
+
"eval_loss": 1.0405693054199219,
|
| 157 |
+
"eval_model_preparation_time": 0.0121,
|
| 158 |
+
"eval_runtime": 13.1332,
|
| 159 |
+
"eval_samples_per_second": 1.523,
|
| 160 |
+
"eval_steps_per_second": 0.228,
|
| 161 |
+
"eval_wer": 4.62962962962963,
|
| 162 |
+
"step": 9
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 10.0,
|
| 166 |
+
"grad_norm": 0.1597001850605011,
|
| 167 |
+
"learning_rate": 1e-05,
|
| 168 |
+
"loss": 0.0255,
|
| 169 |
+
"step": 10
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 10.0,
|
| 173 |
+
"eval_loss": 1.021639347076416,
|
| 174 |
+
"eval_model_preparation_time": 0.0121,
|
| 175 |
+
"eval_runtime": 13.0982,
|
| 176 |
+
"eval_samples_per_second": 1.527,
|
| 177 |
+
"eval_steps_per_second": 0.229,
|
| 178 |
+
"eval_wer": 4.62962962962963,
|
| 179 |
+
"step": 10
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 11.0,
|
| 183 |
+
"grad_norm": 0.15809614956378937,
|
| 184 |
+
"learning_rate": 1e-05,
|
| 185 |
+
"loss": 0.025,
|
| 186 |
+
"step": 11
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 11.0,
|
| 190 |
+
"eval_loss": 1.0027821063995361,
|
| 191 |
+
"eval_model_preparation_time": 0.0121,
|
| 192 |
+
"eval_runtime": 13.2797,
|
| 193 |
+
"eval_samples_per_second": 1.506,
|
| 194 |
+
"eval_steps_per_second": 0.226,
|
| 195 |
+
"eval_wer": 4.62962962962963,
|
| 196 |
+
"step": 11
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 12.0,
|
| 200 |
+
"grad_norm": 0.15653067827224731,
|
| 201 |
+
"learning_rate": 1e-05,
|
| 202 |
+
"loss": 0.0244,
|
| 203 |
+
"step": 12
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 12.0,
|
| 207 |
+
"eval_loss": 0.9836124777793884,
|
| 208 |
+
"eval_model_preparation_time": 0.0121,
|
| 209 |
+
"eval_runtime": 18.954,
|
| 210 |
+
"eval_samples_per_second": 1.055,
|
| 211 |
+
"eval_steps_per_second": 0.158,
|
| 212 |
+
"eval_wer": 32.407407407407405,
|
| 213 |
+
"step": 12
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 13.0,
|
| 217 |
+
"grad_norm": 0.15485768020153046,
|
| 218 |
+
"learning_rate": 1e-05,
|
| 219 |
+
"loss": 0.0239,
|
| 220 |
+
"step": 13
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 13.0,
|
| 224 |
+
"eval_loss": 0.9660758376121521,
|
| 225 |
+
"eval_model_preparation_time": 0.0121,
|
| 226 |
+
"eval_runtime": 19.023,
|
| 227 |
+
"eval_samples_per_second": 1.051,
|
| 228 |
+
"eval_steps_per_second": 0.158,
|
| 229 |
+
"eval_wer": 32.407407407407405,
|
| 230 |
+
"step": 13
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 14.0,
|
| 234 |
+
"grad_norm": 0.1532512605190277,
|
| 235 |
+
"learning_rate": 1e-05,
|
| 236 |
+
"loss": 0.0234,
|
| 237 |
+
"step": 14
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 14.0,
|
| 241 |
+
"eval_loss": 0.9473101496696472,
|
| 242 |
+
"eval_model_preparation_time": 0.0121,
|
| 243 |
+
"eval_runtime": 19.1218,
|
| 244 |
+
"eval_samples_per_second": 1.046,
|
| 245 |
+
"eval_steps_per_second": 0.157,
|
| 246 |
+
"eval_wer": 32.407407407407405,
|
| 247 |
+
"step": 14
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 15.0,
|
| 251 |
+
"grad_norm": 0.15129534900188446,
|
| 252 |
+
"learning_rate": 1e-05,
|
| 253 |
+
"loss": 0.0229,
|
| 254 |
+
"step": 15
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 15.0,
|
| 258 |
+
"eval_loss": 0.9287378191947937,
|
| 259 |
+
"eval_model_preparation_time": 0.0121,
|
| 260 |
+
"eval_runtime": 18.9602,
|
| 261 |
+
"eval_samples_per_second": 1.055,
|
| 262 |
+
"eval_steps_per_second": 0.158,
|
| 263 |
+
"eval_wer": 32.407407407407405,
|
| 264 |
+
"step": 15
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 16.0,
|
| 268 |
+
"grad_norm": 0.1490040421485901,
|
| 269 |
+
"learning_rate": 1e-05,
|
| 270 |
+
"loss": 0.0224,
|
| 271 |
+
"step": 16
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 16.0,
|
| 275 |
+
"eval_loss": 0.9106081128120422,
|
| 276 |
+
"eval_model_preparation_time": 0.0121,
|
| 277 |
+
"eval_runtime": 19.0132,
|
| 278 |
+
"eval_samples_per_second": 1.052,
|
| 279 |
+
"eval_steps_per_second": 0.158,
|
| 280 |
+
"eval_wer": 30.555555555555557,
|
| 281 |
+
"step": 16
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 17.0,
|
| 285 |
+
"grad_norm": 0.14625835418701172,
|
| 286 |
+
"learning_rate": 1e-05,
|
| 287 |
+
"loss": 0.0218,
|
| 288 |
+
"step": 17
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 17.0,
|
| 292 |
+
"eval_loss": 0.8923694491386414,
|
| 293 |
+
"eval_model_preparation_time": 0.0121,
|
| 294 |
+
"eval_runtime": 19.1496,
|
| 295 |
+
"eval_samples_per_second": 1.044,
|
| 296 |
+
"eval_steps_per_second": 0.157,
|
| 297 |
+
"eval_wer": 32.098765432098766,
|
| 298 |
+
"step": 17
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 18.0,
|
| 302 |
+
"grad_norm": 0.1428905576467514,
|
| 303 |
+
"learning_rate": 1e-05,
|
| 304 |
+
"loss": 0.0213,
|
| 305 |
+
"step": 18
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 18.0,
|
| 309 |
+
"eval_loss": 0.8747221827507019,
|
| 310 |
+
"eval_model_preparation_time": 0.0121,
|
| 311 |
+
"eval_runtime": 18.9828,
|
| 312 |
+
"eval_samples_per_second": 1.054,
|
| 313 |
+
"eval_steps_per_second": 0.158,
|
| 314 |
+
"eval_wer": 30.555555555555557,
|
| 315 |
+
"step": 18
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 19.0,
|
| 319 |
+
"grad_norm": 0.13874377310276031,
|
| 320 |
+
"learning_rate": 1e-05,
|
| 321 |
+
"loss": 0.0209,
|
| 322 |
+
"step": 19
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 19.0,
|
| 326 |
+
"eval_loss": 0.8583929538726807,
|
| 327 |
+
"eval_model_preparation_time": 0.0121,
|
| 328 |
+
"eval_runtime": 13.0296,
|
| 329 |
+
"eval_samples_per_second": 1.535,
|
| 330 |
+
"eval_steps_per_second": 0.23,
|
| 331 |
+
"eval_wer": 4.320987654320987,
|
| 332 |
+
"step": 19
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 20.0,
|
| 336 |
+
"grad_norm": 0.13400524854660034,
|
| 337 |
+
"learning_rate": 1e-05,
|
| 338 |
+
"loss": 0.0204,
|
| 339 |
+
"step": 20
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 20.0,
|
| 343 |
+
"eval_loss": 0.842006504535675,
|
| 344 |
+
"eval_model_preparation_time": 0.0121,
|
| 345 |
+
"eval_runtime": 13.0362,
|
| 346 |
+
"eval_samples_per_second": 1.534,
|
| 347 |
+
"eval_steps_per_second": 0.23,
|
| 348 |
+
"eval_wer": 4.320987654320987,
|
| 349 |
+
"step": 20
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 21.0,
|
| 353 |
+
"grad_norm": 0.128588005900383,
|
| 354 |
+
"learning_rate": 1e-05,
|
| 355 |
+
"loss": 0.02,
|
| 356 |
+
"step": 21
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 21.0,
|
| 360 |
+
"eval_loss": 0.8266332745552063,
|
| 361 |
+
"eval_model_preparation_time": 0.0121,
|
| 362 |
+
"eval_runtime": 13.1349,
|
| 363 |
+
"eval_samples_per_second": 1.523,
|
| 364 |
+
"eval_steps_per_second": 0.228,
|
| 365 |
+
"eval_wer": 4.320987654320987,
|
| 366 |
+
"step": 21
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 22.0,
|
| 370 |
+
"grad_norm": 0.12290169298648834,
|
| 371 |
+
"learning_rate": 1e-05,
|
| 372 |
+
"loss": 0.0196,
|
| 373 |
+
"step": 22
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 22.0,
|
| 377 |
+
"eval_loss": 0.812411367893219,
|
| 378 |
+
"eval_model_preparation_time": 0.0121,
|
| 379 |
+
"eval_runtime": 13.0331,
|
| 380 |
+
"eval_samples_per_second": 1.535,
|
| 381 |
+
"eval_steps_per_second": 0.23,
|
| 382 |
+
"eval_wer": 4.320987654320987,
|
| 383 |
+
"step": 22
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 23.0,
|
| 387 |
+
"grad_norm": 0.11754843592643738,
|
| 388 |
+
"learning_rate": 1e-05,
|
| 389 |
+
"loss": 0.0193,
|
| 390 |
+
"step": 23
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 23.0,
|
| 394 |
+
"eval_loss": 0.7992361187934875,
|
| 395 |
+
"eval_model_preparation_time": 0.0121,
|
| 396 |
+
"eval_runtime": 13.0451,
|
| 397 |
+
"eval_samples_per_second": 1.533,
|
| 398 |
+
"eval_steps_per_second": 0.23,
|
| 399 |
+
"eval_wer": 4.320987654320987,
|
| 400 |
+
"step": 23
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 24.0,
|
| 404 |
+
"grad_norm": 0.11315960437059402,
|
| 405 |
+
"learning_rate": 1e-05,
|
| 406 |
+
"loss": 0.019,
|
| 407 |
+
"step": 24
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 24.0,
|
| 411 |
+
"eval_loss": 0.7874162197113037,
|
| 412 |
+
"eval_model_preparation_time": 0.0121,
|
| 413 |
+
"eval_runtime": 13.0108,
|
| 414 |
+
"eval_samples_per_second": 1.537,
|
| 415 |
+
"eval_steps_per_second": 0.231,
|
| 416 |
+
"eval_wer": 4.320987654320987,
|
| 417 |
+
"step": 24
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 25.0,
|
| 421 |
+
"grad_norm": 0.10973851382732391,
|
| 422 |
+
"learning_rate": 1e-05,
|
| 423 |
+
"loss": 0.0187,
|
| 424 |
+
"step": 25
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 25.0,
|
| 428 |
+
"eval_loss": 0.7770275473594666,
|
| 429 |
+
"eval_model_preparation_time": 0.0121,
|
| 430 |
+
"eval_runtime": 13.0113,
|
| 431 |
+
"eval_samples_per_second": 1.537,
|
| 432 |
+
"eval_steps_per_second": 0.231,
|
| 433 |
+
"eval_wer": 4.320987654320987,
|
| 434 |
+
"step": 25
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 26.0,
|
| 438 |
+
"grad_norm": 0.10730645060539246,
|
| 439 |
+
"learning_rate": 1e-05,
|
| 440 |
+
"loss": 0.0185,
|
| 441 |
+
"step": 26
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 26.0,
|
| 445 |
+
"eval_loss": 0.7670324444770813,
|
| 446 |
+
"eval_model_preparation_time": 0.0121,
|
| 447 |
+
"eval_runtime": 13.0264,
|
| 448 |
+
"eval_samples_per_second": 1.535,
|
| 449 |
+
"eval_steps_per_second": 0.23,
|
| 450 |
+
"eval_wer": 4.320987654320987,
|
| 451 |
+
"step": 26
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 27.0,
|
| 455 |
+
"grad_norm": 0.10558220744132996,
|
| 456 |
+
"learning_rate": 1e-05,
|
| 457 |
+
"loss": 0.0183,
|
| 458 |
+
"step": 27
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 27.0,
|
| 462 |
+
"eval_loss": 0.7583534121513367,
|
| 463 |
+
"eval_model_preparation_time": 0.0121,
|
| 464 |
+
"eval_runtime": 13.0554,
|
| 465 |
+
"eval_samples_per_second": 1.532,
|
| 466 |
+
"eval_steps_per_second": 0.23,
|
| 467 |
+
"eval_wer": 4.320987654320987,
|
| 468 |
+
"step": 27
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 28.0,
|
| 472 |
+
"grad_norm": 0.10448750853538513,
|
| 473 |
+
"learning_rate": 1e-05,
|
| 474 |
+
"loss": 0.0181,
|
| 475 |
+
"step": 28
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 28.0,
|
| 479 |
+
"eval_loss": 0.7502322793006897,
|
| 480 |
+
"eval_model_preparation_time": 0.0121,
|
| 481 |
+
"eval_runtime": 13.0142,
|
| 482 |
+
"eval_samples_per_second": 1.537,
|
| 483 |
+
"eval_steps_per_second": 0.231,
|
| 484 |
+
"eval_wer": 4.320987654320987,
|
| 485 |
+
"step": 28
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 29.0,
|
| 489 |
+
"grad_norm": 0.10369043797254562,
|
| 490 |
+
"learning_rate": 1e-05,
|
| 491 |
+
"loss": 0.0179,
|
| 492 |
+
"step": 29
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 29.0,
|
| 496 |
+
"eval_loss": 0.7425273060798645,
|
| 497 |
+
"eval_model_preparation_time": 0.0121,
|
| 498 |
+
"eval_runtime": 13.024,
|
| 499 |
+
"eval_samples_per_second": 1.536,
|
| 500 |
+
"eval_steps_per_second": 0.23,
|
| 501 |
+
"eval_wer": 4.012345679012346,
|
| 502 |
+
"step": 29
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 30.0,
|
| 506 |
+
"grad_norm": 0.10316835343837738,
|
| 507 |
+
"learning_rate": 1e-05,
|
| 508 |
+
"loss": 0.0177,
|
| 509 |
+
"step": 30
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 30.0,
|
| 513 |
+
"eval_loss": 0.7353512644767761,
|
| 514 |
+
"eval_model_preparation_time": 0.0121,
|
| 515 |
+
"eval_runtime": 13.0504,
|
| 516 |
+
"eval_samples_per_second": 1.533,
|
| 517 |
+
"eval_steps_per_second": 0.23,
|
| 518 |
+
"eval_wer": 4.012345679012346,
|
| 519 |
+
"step": 30
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 31.0,
|
| 523 |
+
"grad_norm": 0.10271348059177399,
|
| 524 |
+
"learning_rate": 1e-05,
|
| 525 |
+
"loss": 0.0175,
|
| 526 |
+
"step": 31
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 31.0,
|
| 530 |
+
"eval_loss": 0.7285407185554504,
|
| 531 |
+
"eval_model_preparation_time": 0.0121,
|
| 532 |
+
"eval_runtime": 13.0146,
|
| 533 |
+
"eval_samples_per_second": 1.537,
|
| 534 |
+
"eval_steps_per_second": 0.231,
|
| 535 |
+
"eval_wer": 4.012345679012346,
|
| 536 |
+
"step": 31
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 32.0,
|
| 540 |
+
"grad_norm": 0.10236351937055588,
|
| 541 |
+
"learning_rate": 1e-05,
|
| 542 |
+
"loss": 0.0174,
|
| 543 |
+
"step": 32
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 32.0,
|
| 547 |
+
"eval_loss": 0.7218928337097168,
|
| 548 |
+
"eval_model_preparation_time": 0.0121,
|
| 549 |
+
"eval_runtime": 12.9915,
|
| 550 |
+
"eval_samples_per_second": 1.539,
|
| 551 |
+
"eval_steps_per_second": 0.231,
|
| 552 |
+
"eval_wer": 4.012345679012346,
|
| 553 |
+
"step": 32
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 33.0,
|
| 557 |
+
"grad_norm": 0.1020871251821518,
|
| 558 |
+
"learning_rate": 1e-05,
|
| 559 |
+
"loss": 0.0172,
|
| 560 |
+
"step": 33
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 33.0,
|
| 564 |
+
"eval_loss": 0.7155935764312744,
|
| 565 |
+
"eval_model_preparation_time": 0.0121,
|
| 566 |
+
"eval_runtime": 13.03,
|
| 567 |
+
"eval_samples_per_second": 1.535,
|
| 568 |
+
"eval_steps_per_second": 0.23,
|
| 569 |
+
"eval_wer": 4.012345679012346,
|
| 570 |
+
"step": 33
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 34.0,
|
| 574 |
+
"grad_norm": 0.10186725854873657,
|
| 575 |
+
"learning_rate": 1e-05,
|
| 576 |
+
"loss": 0.0171,
|
| 577 |
+
"step": 34
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 34.0,
|
| 581 |
+
"eval_loss": 0.7092947959899902,
|
| 582 |
+
"eval_model_preparation_time": 0.0121,
|
| 583 |
+
"eval_runtime": 13.0366,
|
| 584 |
+
"eval_samples_per_second": 1.534,
|
| 585 |
+
"eval_steps_per_second": 0.23,
|
| 586 |
+
"eval_wer": 4.012345679012346,
|
| 587 |
+
"step": 34
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 35.0,
|
| 591 |
+
"grad_norm": 0.10165821760892868,
|
| 592 |
+
"learning_rate": 1e-05,
|
| 593 |
+
"loss": 0.0169,
|
| 594 |
+
"step": 35
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 35.0,
|
| 598 |
+
"eval_loss": 0.703009307384491,
|
| 599 |
+
"eval_model_preparation_time": 0.0121,
|
| 600 |
+
"eval_runtime": 13.0457,
|
| 601 |
+
"eval_samples_per_second": 1.533,
|
| 602 |
+
"eval_steps_per_second": 0.23,
|
| 603 |
+
"eval_wer": 4.012345679012346,
|
| 604 |
+
"step": 35
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 36.0,
|
| 608 |
+
"grad_norm": 0.10144059360027313,
|
| 609 |
+
"learning_rate": 1e-05,
|
| 610 |
+
"loss": 0.0167,
|
| 611 |
+
"step": 36
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 36.0,
|
| 615 |
+
"eval_loss": 0.6968026161193848,
|
| 616 |
+
"eval_model_preparation_time": 0.0121,
|
| 617 |
+
"eval_runtime": 13.0191,
|
| 618 |
+
"eval_samples_per_second": 1.536,
|
| 619 |
+
"eval_steps_per_second": 0.23,
|
| 620 |
+
"eval_wer": 4.012345679012346,
|
| 621 |
+
"step": 36
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 37.0,
|
| 625 |
+
"grad_norm": 0.1012805923819542,
|
| 626 |
+
"learning_rate": 1e-05,
|
| 627 |
+
"loss": 0.0166,
|
| 628 |
+
"step": 37
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 37.0,
|
| 632 |
+
"eval_loss": 0.6906681060791016,
|
| 633 |
+
"eval_model_preparation_time": 0.0121,
|
| 634 |
+
"eval_runtime": 13.0242,
|
| 635 |
+
"eval_samples_per_second": 1.536,
|
| 636 |
+
"eval_steps_per_second": 0.23,
|
| 637 |
+
"eval_wer": 4.012345679012346,
|
| 638 |
+
"step": 37
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 38.0,
|
| 642 |
+
"grad_norm": 0.10113769769668579,
|
| 643 |
+
"learning_rate": 1e-05,
|
| 644 |
+
"loss": 0.0164,
|
| 645 |
+
"step": 38
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 38.0,
|
| 649 |
+
"eval_loss": 0.6843755841255188,
|
| 650 |
+
"eval_model_preparation_time": 0.0121,
|
| 651 |
+
"eval_runtime": 13.0667,
|
| 652 |
+
"eval_samples_per_second": 1.531,
|
| 653 |
+
"eval_steps_per_second": 0.23,
|
| 654 |
+
"eval_wer": 4.012345679012346,
|
| 655 |
+
"step": 38
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 39.0,
|
| 659 |
+
"grad_norm": 0.10098178684711456,
|
| 660 |
+
"learning_rate": 1e-05,
|
| 661 |
+
"loss": 0.0162,
|
| 662 |
+
"step": 39
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 39.0,
|
| 666 |
+
"eval_loss": 0.6783390045166016,
|
| 667 |
+
"eval_model_preparation_time": 0.0121,
|
| 668 |
+
"eval_runtime": 13.0465,
|
| 669 |
+
"eval_samples_per_second": 1.533,
|
| 670 |
+
"eval_steps_per_second": 0.23,
|
| 671 |
+
"eval_wer": 4.012345679012346,
|
| 672 |
+
"step": 39
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 40.0,
|
| 676 |
+
"grad_norm": 0.1008835956454277,
|
| 677 |
+
"learning_rate": 1e-05,
|
| 678 |
+
"loss": 0.0161,
|
| 679 |
+
"step": 40
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 40.0,
|
| 683 |
+
"eval_loss": 0.6723348498344421,
|
| 684 |
+
"eval_model_preparation_time": 0.0121,
|
| 685 |
+
"eval_runtime": 13.0472,
|
| 686 |
+
"eval_samples_per_second": 1.533,
|
| 687 |
+
"eval_steps_per_second": 0.23,
|
| 688 |
+
"eval_wer": 4.012345679012346,
|
| 689 |
+
"step": 40
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 41.0,
|
| 693 |
+
"grad_norm": 0.10077005624771118,
|
| 694 |
+
"learning_rate": 1e-05,
|
| 695 |
+
"loss": 0.0159,
|
| 696 |
+
"step": 41
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 41.0,
|
| 700 |
+
"eval_loss": 0.6662711501121521,
|
| 701 |
+
"eval_model_preparation_time": 0.0121,
|
| 702 |
+
"eval_runtime": 13.0732,
|
| 703 |
+
"eval_samples_per_second": 1.53,
|
| 704 |
+
"eval_steps_per_second": 0.229,
|
| 705 |
+
"eval_wer": 4.012345679012346,
|
| 706 |
+
"step": 41
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 42.0,
|
| 710 |
+
"grad_norm": 0.1006632074713707,
|
| 711 |
+
"learning_rate": 1e-05,
|
| 712 |
+
"loss": 0.0158,
|
| 713 |
+
"step": 42
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 42.0,
|
| 717 |
+
"eval_loss": 0.6601687073707581,
|
| 718 |
+
"eval_model_preparation_time": 0.0121,
|
| 719 |
+
"eval_runtime": 13.104,
|
| 720 |
+
"eval_samples_per_second": 1.526,
|
| 721 |
+
"eval_steps_per_second": 0.229,
|
| 722 |
+
"eval_wer": 4.012345679012346,
|
| 723 |
+
"step": 42
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 43.0,
|
| 727 |
+
"grad_norm": 0.10058455169200897,
|
| 728 |
+
"learning_rate": 1e-05,
|
| 729 |
+
"loss": 0.0156,
|
| 730 |
+
"step": 43
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 43.0,
|
| 734 |
+
"eval_loss": 0.6541077494621277,
|
| 735 |
+
"eval_model_preparation_time": 0.0121,
|
| 736 |
+
"eval_runtime": 13.0457,
|
| 737 |
+
"eval_samples_per_second": 1.533,
|
| 738 |
+
"eval_steps_per_second": 0.23,
|
| 739 |
+
"eval_wer": 4.012345679012346,
|
| 740 |
+
"step": 43
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 44.0,
|
| 744 |
+
"grad_norm": 0.10048093646764755,
|
| 745 |
+
"learning_rate": 1e-05,
|
| 746 |
+
"loss": 0.0154,
|
| 747 |
+
"step": 44
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 44.0,
|
| 751 |
+
"eval_loss": 0.6480630040168762,
|
| 752 |
+
"eval_model_preparation_time": 0.0121,
|
| 753 |
+
"eval_runtime": 13.0213,
|
| 754 |
+
"eval_samples_per_second": 1.536,
|
| 755 |
+
"eval_steps_per_second": 0.23,
|
| 756 |
+
"eval_wer": 4.012345679012346,
|
| 757 |
+
"step": 44
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 45.0,
|
| 761 |
+
"grad_norm": 0.10042457282543182,
|
| 762 |
+
"learning_rate": 1e-05,
|
| 763 |
+
"loss": 0.0153,
|
| 764 |
+
"step": 45
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 45.0,
|
| 768 |
+
"eval_loss": 0.6420673131942749,
|
| 769 |
+
"eval_model_preparation_time": 0.0121,
|
| 770 |
+
"eval_runtime": 12.994,
|
| 771 |
+
"eval_samples_per_second": 1.539,
|
| 772 |
+
"eval_steps_per_second": 0.231,
|
| 773 |
+
"eval_wer": 4.012345679012346,
|
| 774 |
+
"step": 45
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 46.0,
|
| 778 |
+
"grad_norm": 0.1003439873456955,
|
| 779 |
+
"learning_rate": 1e-05,
|
| 780 |
+
"loss": 0.0151,
|
| 781 |
+
"step": 46
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 46.0,
|
| 785 |
+
"eval_loss": 0.6359073519706726,
|
| 786 |
+
"eval_model_preparation_time": 0.0121,
|
| 787 |
+
"eval_runtime": 13.0936,
|
| 788 |
+
"eval_samples_per_second": 1.527,
|
| 789 |
+
"eval_steps_per_second": 0.229,
|
| 790 |
+
"eval_wer": 4.012345679012346,
|
| 791 |
+
"step": 46
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 47.0,
|
| 795 |
+
"grad_norm": 0.10026626288890839,
|
| 796 |
+
"learning_rate": 1e-05,
|
| 797 |
+
"loss": 0.0149,
|
| 798 |
+
"step": 47
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 47.0,
|
| 802 |
+
"eval_loss": 0.6298264861106873,
|
| 803 |
+
"eval_model_preparation_time": 0.0121,
|
| 804 |
+
"eval_runtime": 13.0519,
|
| 805 |
+
"eval_samples_per_second": 1.532,
|
| 806 |
+
"eval_steps_per_second": 0.23,
|
| 807 |
+
"eval_wer": 4.012345679012346,
|
| 808 |
+
"step": 47
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 48.0,
|
| 812 |
+
"grad_norm": 0.10018378496170044,
|
| 813 |
+
"learning_rate": 1e-05,
|
| 814 |
+
"loss": 0.0148,
|
| 815 |
+
"step": 48
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 48.0,
|
| 819 |
+
"eval_loss": 0.6237847208976746,
|
| 820 |
+
"eval_model_preparation_time": 0.0121,
|
| 821 |
+
"eval_runtime": 13.1033,
|
| 822 |
+
"eval_samples_per_second": 1.526,
|
| 823 |
+
"eval_steps_per_second": 0.229,
|
| 824 |
+
"eval_wer": 4.012345679012346,
|
| 825 |
+
"step": 48
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 49.0,
|
| 829 |
+
"grad_norm": 0.10017245262861252,
|
| 830 |
+
"learning_rate": 1e-05,
|
| 831 |
+
"loss": 0.0146,
|
| 832 |
+
"step": 49
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 49.0,
|
| 836 |
+
"eval_loss": 0.617721438407898,
|
| 837 |
+
"eval_model_preparation_time": 0.0121,
|
| 838 |
+
"eval_runtime": 13.0808,
|
| 839 |
+
"eval_samples_per_second": 1.529,
|
| 840 |
+
"eval_steps_per_second": 0.229,
|
| 841 |
+
"eval_wer": 4.012345679012346,
|
| 842 |
+
"step": 49
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 50.0,
|
| 846 |
+
"grad_norm": 0.10012275725603104,
|
| 847 |
+
"learning_rate": 1e-05,
|
| 848 |
+
"loss": 0.0144,
|
| 849 |
+
"step": 50
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 50.0,
|
| 853 |
+
"eval_loss": 0.6115495562553406,
|
| 854 |
+
"eval_model_preparation_time": 0.0121,
|
| 855 |
+
"eval_runtime": 13.0424,
|
| 856 |
+
"eval_samples_per_second": 1.533,
|
| 857 |
+
"eval_steps_per_second": 0.23,
|
| 858 |
+
"eval_wer": 4.012345679012346,
|
| 859 |
+
"step": 50
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 51.0,
|
| 863 |
+
"grad_norm": 0.10007242113351822,
|
| 864 |
+
"learning_rate": 1e-05,
|
| 865 |
+
"loss": 0.0142,
|
| 866 |
+
"step": 51
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 51.0,
|
| 870 |
+
"eval_loss": 0.6055248379707336,
|
| 871 |
+
"eval_model_preparation_time": 0.0121,
|
| 872 |
+
"eval_runtime": 13.1155,
|
| 873 |
+
"eval_samples_per_second": 1.525,
|
| 874 |
+
"eval_steps_per_second": 0.229,
|
| 875 |
+
"eval_wer": 4.012345679012346,
|
| 876 |
+
"step": 51
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 52.0,
|
| 880 |
+
"grad_norm": 0.1000462993979454,
|
| 881 |
+
"learning_rate": 1e-05,
|
| 882 |
+
"loss": 0.0141,
|
| 883 |
+
"step": 52
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 52.0,
|
| 887 |
+
"eval_loss": 0.5995514988899231,
|
| 888 |
+
"eval_model_preparation_time": 0.0121,
|
| 889 |
+
"eval_runtime": 13.0374,
|
| 890 |
+
"eval_samples_per_second": 1.534,
|
| 891 |
+
"eval_steps_per_second": 0.23,
|
| 892 |
+
"eval_wer": 4.012345679012346,
|
| 893 |
+
"step": 52
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 53.0,
|
| 897 |
+
"grad_norm": 0.09999983012676239,
|
| 898 |
+
"learning_rate": 1e-05,
|
| 899 |
+
"loss": 0.0139,
|
| 900 |
+
"step": 53
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 53.0,
|
| 904 |
+
"eval_loss": 0.5934532284736633,
|
| 905 |
+
"eval_model_preparation_time": 0.0121,
|
| 906 |
+
"eval_runtime": 13.0708,
|
| 907 |
+
"eval_samples_per_second": 1.53,
|
| 908 |
+
"eval_steps_per_second": 0.23,
|
| 909 |
+
"eval_wer": 4.012345679012346,
|
| 910 |
+
"step": 53
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 54.0,
|
| 914 |
+
"grad_norm": 0.10001446306705475,
|
| 915 |
+
"learning_rate": 1e-05,
|
| 916 |
+
"loss": 0.0137,
|
| 917 |
+
"step": 54
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 54.0,
|
| 921 |
+
"eval_loss": 0.5873024463653564,
|
| 922 |
+
"eval_model_preparation_time": 0.0121,
|
| 923 |
+
"eval_runtime": 13.0551,
|
| 924 |
+
"eval_samples_per_second": 1.532,
|
| 925 |
+
"eval_steps_per_second": 0.23,
|
| 926 |
+
"eval_wer": 4.012345679012346,
|
| 927 |
+
"step": 54
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 55.0,
|
| 931 |
+
"grad_norm": 0.09999886900186539,
|
| 932 |
+
"learning_rate": 1e-05,
|
| 933 |
+
"loss": 0.0136,
|
| 934 |
+
"step": 55
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 55.0,
|
| 938 |
+
"eval_loss": 0.5811672210693359,
|
| 939 |
+
"eval_model_preparation_time": 0.0121,
|
| 940 |
+
"eval_runtime": 13.0575,
|
| 941 |
+
"eval_samples_per_second": 1.532,
|
| 942 |
+
"eval_steps_per_second": 0.23,
|
| 943 |
+
"eval_wer": 4.012345679012346,
|
| 944 |
+
"step": 55
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 56.0,
|
| 948 |
+
"grad_norm": 0.09996996074914932,
|
| 949 |
+
"learning_rate": 1e-05,
|
| 950 |
+
"loss": 0.0134,
|
| 951 |
+
"step": 56
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 56.0,
|
| 955 |
+
"eval_loss": 0.5749332308769226,
|
| 956 |
+
"eval_model_preparation_time": 0.0121,
|
| 957 |
+
"eval_runtime": 13.0147,
|
| 958 |
+
"eval_samples_per_second": 1.537,
|
| 959 |
+
"eval_steps_per_second": 0.231,
|
| 960 |
+
"eval_wer": 4.012345679012346,
|
| 961 |
+
"step": 56
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 57.0,
|
| 965 |
+
"grad_norm": 0.09995821118354797,
|
| 966 |
+
"learning_rate": 1e-05,
|
| 967 |
+
"loss": 0.0132,
|
| 968 |
+
"step": 57
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 57.0,
|
| 972 |
+
"eval_loss": 0.5688786506652832,
|
| 973 |
+
"eval_model_preparation_time": 0.0121,
|
| 974 |
+
"eval_runtime": 13.0009,
|
| 975 |
+
"eval_samples_per_second": 1.538,
|
| 976 |
+
"eval_steps_per_second": 0.231,
|
| 977 |
+
"eval_wer": 4.012345679012346,
|
| 978 |
+
"step": 57
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 58.0,
|
| 982 |
+
"grad_norm": 0.09996328502893448,
|
| 983 |
+
"learning_rate": 1e-05,
|
| 984 |
+
"loss": 0.013,
|
| 985 |
+
"step": 58
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 58.0,
|
| 989 |
+
"eval_loss": 0.5627100467681885,
|
| 990 |
+
"eval_model_preparation_time": 0.0121,
|
| 991 |
+
"eval_runtime": 13.0166,
|
| 992 |
+
"eval_samples_per_second": 1.536,
|
| 993 |
+
"eval_steps_per_second": 0.23,
|
| 994 |
+
"eval_wer": 4.012345679012346,
|
| 995 |
+
"step": 58
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 59.0,
|
| 999 |
+
"grad_norm": 0.09995493292808533,
|
| 1000 |
+
"learning_rate": 1e-05,
|
| 1001 |
+
"loss": 0.0128,
|
| 1002 |
+
"step": 59
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 59.0,
|
| 1006 |
+
"eval_loss": 0.5565866827964783,
|
| 1007 |
+
"eval_model_preparation_time": 0.0121,
|
| 1008 |
+
"eval_runtime": 13.0199,
|
| 1009 |
+
"eval_samples_per_second": 1.536,
|
| 1010 |
+
"eval_steps_per_second": 0.23,
|
| 1011 |
+
"eval_wer": 4.012345679012346,
|
| 1012 |
+
"step": 59
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 60.0,
|
| 1016 |
+
"grad_norm": 0.09997319430112839,
|
| 1017 |
+
"learning_rate": 1e-05,
|
| 1018 |
+
"loss": 0.0127,
|
| 1019 |
+
"step": 60
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 60.0,
|
| 1023 |
+
"eval_loss": 0.5505630373954773,
|
| 1024 |
+
"eval_model_preparation_time": 0.0121,
|
| 1025 |
+
"eval_runtime": 13.0285,
|
| 1026 |
+
"eval_samples_per_second": 1.535,
|
| 1027 |
+
"eval_steps_per_second": 0.23,
|
| 1028 |
+
"eval_wer": 4.012345679012346,
|
| 1029 |
+
"step": 60
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 61.0,
|
| 1033 |
+
"grad_norm": 0.0999804213643074,
|
| 1034 |
+
"learning_rate": 1e-05,
|
| 1035 |
+
"loss": 0.0125,
|
| 1036 |
+
"step": 61
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 61.0,
|
| 1040 |
+
"eval_loss": 0.5444908738136292,
|
| 1041 |
+
"eval_model_preparation_time": 0.0121,
|
| 1042 |
+
"eval_runtime": 13.0398,
|
| 1043 |
+
"eval_samples_per_second": 1.534,
|
| 1044 |
+
"eval_steps_per_second": 0.23,
|
| 1045 |
+
"eval_wer": 4.012345679012346,
|
| 1046 |
+
"step": 61
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 62.0,
|
| 1050 |
+
"grad_norm": 0.10000340640544891,
|
| 1051 |
+
"learning_rate": 1e-05,
|
| 1052 |
+
"loss": 0.0123,
|
| 1053 |
+
"step": 62
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 62.0,
|
| 1057 |
+
"eval_loss": 0.5383059978485107,
|
| 1058 |
+
"eval_model_preparation_time": 0.0121,
|
| 1059 |
+
"eval_runtime": 13.0216,
|
| 1060 |
+
"eval_samples_per_second": 1.536,
|
| 1061 |
+
"eval_steps_per_second": 0.23,
|
| 1062 |
+
"eval_wer": 4.012345679012346,
|
| 1063 |
+
"step": 62
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 63.0,
|
| 1067 |
+
"grad_norm": 0.10002919286489487,
|
| 1068 |
+
"learning_rate": 1e-05,
|
| 1069 |
+
"loss": 0.0121,
|
| 1070 |
+
"step": 63
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 63.0,
|
| 1074 |
+
"eval_loss": 0.5322217345237732,
|
| 1075 |
+
"eval_model_preparation_time": 0.0121,
|
| 1076 |
+
"eval_runtime": 13.027,
|
| 1077 |
+
"eval_samples_per_second": 1.535,
|
| 1078 |
+
"eval_steps_per_second": 0.23,
|
| 1079 |
+
"eval_wer": 4.012345679012346,
|
| 1080 |
+
"step": 63
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 64.0,
|
| 1084 |
+
"grad_norm": 0.10005642473697662,
|
| 1085 |
+
"learning_rate": 1e-05,
|
| 1086 |
+
"loss": 0.0119,
|
| 1087 |
+
"step": 64
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 64.0,
|
| 1091 |
+
"eval_loss": 0.5260897278785706,
|
| 1092 |
+
"eval_model_preparation_time": 0.0121,
|
| 1093 |
+
"eval_runtime": 13.0762,
|
| 1094 |
+
"eval_samples_per_second": 1.529,
|
| 1095 |
+
"eval_steps_per_second": 0.229,
|
| 1096 |
+
"eval_wer": 4.012345679012346,
|
| 1097 |
+
"step": 64
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 65.0,
|
| 1101 |
+
"grad_norm": 0.1000811904668808,
|
| 1102 |
+
"learning_rate": 1e-05,
|
| 1103 |
+
"loss": 0.0117,
|
| 1104 |
+
"step": 65
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 65.0,
|
| 1108 |
+
"eval_loss": 0.5198546648025513,
|
| 1109 |
+
"eval_model_preparation_time": 0.0121,
|
| 1110 |
+
"eval_runtime": 13.0323,
|
| 1111 |
+
"eval_samples_per_second": 1.535,
|
| 1112 |
+
"eval_steps_per_second": 0.23,
|
| 1113 |
+
"eval_wer": 4.012345679012346,
|
| 1114 |
+
"step": 65
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 66.0,
|
| 1118 |
+
"grad_norm": 0.10011852532625198,
|
| 1119 |
+
"learning_rate": 1e-05,
|
| 1120 |
+
"loss": 0.0115,
|
| 1121 |
+
"step": 66
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 66.0,
|
| 1125 |
+
"eval_loss": 0.513763964176178,
|
| 1126 |
+
"eval_model_preparation_time": 0.0121,
|
| 1127 |
+
"eval_runtime": 13.0426,
|
| 1128 |
+
"eval_samples_per_second": 1.533,
|
| 1129 |
+
"eval_steps_per_second": 0.23,
|
| 1130 |
+
"eval_wer": 4.012345679012346,
|
| 1131 |
+
"step": 66
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 67.0,
|
| 1135 |
+
"grad_norm": 0.10016665607690811,
|
| 1136 |
+
"learning_rate": 1e-05,
|
| 1137 |
+
"loss": 0.0114,
|
| 1138 |
+
"step": 67
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 67.0,
|
| 1142 |
+
"eval_loss": 0.5077674388885498,
|
| 1143 |
+
"eval_model_preparation_time": 0.0121,
|
| 1144 |
+
"eval_runtime": 13.0559,
|
| 1145 |
+
"eval_samples_per_second": 1.532,
|
| 1146 |
+
"eval_steps_per_second": 0.23,
|
| 1147 |
+
"eval_wer": 4.012345679012346,
|
| 1148 |
+
"step": 67
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 68.0,
|
| 1152 |
+
"grad_norm": 0.10022170841693878,
|
| 1153 |
+
"learning_rate": 1e-05,
|
| 1154 |
+
"loss": 0.0112,
|
| 1155 |
+
"step": 68
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 68.0,
|
| 1159 |
+
"eval_loss": 0.5016047358512878,
|
| 1160 |
+
"eval_model_preparation_time": 0.0121,
|
| 1161 |
+
"eval_runtime": 13.0439,
|
| 1162 |
+
"eval_samples_per_second": 1.533,
|
| 1163 |
+
"eval_steps_per_second": 0.23,
|
| 1164 |
+
"eval_wer": 4.012345679012346,
|
| 1165 |
+
"step": 68
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 69.0,
|
| 1169 |
+
"grad_norm": 0.10022887587547302,
|
| 1170 |
+
"learning_rate": 1e-05,
|
| 1171 |
+
"loss": 0.011,
|
| 1172 |
+
"step": 69
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 69.0,
|
| 1176 |
+
"eval_loss": 0.49558281898498535,
|
| 1177 |
+
"eval_model_preparation_time": 0.0121,
|
| 1178 |
+
"eval_runtime": 13.0145,
|
| 1179 |
+
"eval_samples_per_second": 1.537,
|
| 1180 |
+
"eval_steps_per_second": 0.231,
|
| 1181 |
+
"eval_wer": 4.012345679012346,
|
| 1182 |
+
"step": 69
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 70.0,
|
| 1186 |
+
"grad_norm": 0.10028593987226486,
|
| 1187 |
+
"learning_rate": 1e-05,
|
| 1188 |
+
"loss": 0.0108,
|
| 1189 |
+
"step": 70
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 70.0,
|
| 1193 |
+
"eval_loss": 0.4895244538784027,
|
| 1194 |
+
"eval_model_preparation_time": 0.0121,
|
| 1195 |
+
"eval_runtime": 13.0373,
|
| 1196 |
+
"eval_samples_per_second": 1.534,
|
| 1197 |
+
"eval_steps_per_second": 0.23,
|
| 1198 |
+
"eval_wer": 4.012345679012346,
|
| 1199 |
+
"step": 70
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 71.0,
|
| 1203 |
+
"grad_norm": 0.10034992545843124,
|
| 1204 |
+
"learning_rate": 1e-05,
|
| 1205 |
+
"loss": 0.0106,
|
| 1206 |
+
"step": 71
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 71.0,
|
| 1210 |
+
"eval_loss": 0.4835710823535919,
|
| 1211 |
+
"eval_model_preparation_time": 0.0121,
|
| 1212 |
+
"eval_runtime": 12.9895,
|
| 1213 |
+
"eval_samples_per_second": 1.54,
|
| 1214 |
+
"eval_steps_per_second": 0.231,
|
| 1215 |
+
"eval_wer": 4.012345679012346,
|
| 1216 |
+
"step": 71
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 72.0,
|
| 1220 |
+
"grad_norm": 0.10041330754756927,
|
| 1221 |
+
"learning_rate": 1e-05,
|
| 1222 |
+
"loss": 0.0104,
|
| 1223 |
+
"step": 72
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 72.0,
|
| 1227 |
+
"eval_loss": 0.4775284230709076,
|
| 1228 |
+
"eval_model_preparation_time": 0.0121,
|
| 1229 |
+
"eval_runtime": 13.0996,
|
| 1230 |
+
"eval_samples_per_second": 1.527,
|
| 1231 |
+
"eval_steps_per_second": 0.229,
|
| 1232 |
+
"eval_wer": 4.012345679012346,
|
| 1233 |
+
"step": 72
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 73.0,
|
| 1237 |
+
"grad_norm": 0.10046479851007462,
|
| 1238 |
+
"learning_rate": 1e-05,
|
| 1239 |
+
"loss": 0.0102,
|
| 1240 |
+
"step": 73
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 73.0,
|
| 1244 |
+
"eval_loss": 0.47157832980155945,
|
| 1245 |
+
"eval_model_preparation_time": 0.0121,
|
| 1246 |
+
"eval_runtime": 13.0539,
|
| 1247 |
+
"eval_samples_per_second": 1.532,
|
| 1248 |
+
"eval_steps_per_second": 0.23,
|
| 1249 |
+
"eval_wer": 4.012345679012346,
|
| 1250 |
+
"step": 73
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 74.0,
|
| 1254 |
+
"grad_norm": 0.10052894800901413,
|
| 1255 |
+
"learning_rate": 1e-05,
|
| 1256 |
+
"loss": 0.01,
|
| 1257 |
+
"step": 74
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 74.0,
|
| 1261 |
+
"eval_loss": 0.4655916392803192,
|
| 1262 |
+
"eval_model_preparation_time": 0.0121,
|
| 1263 |
+
"eval_runtime": 13.0131,
|
| 1264 |
+
"eval_samples_per_second": 1.537,
|
| 1265 |
+
"eval_steps_per_second": 0.231,
|
| 1266 |
+
"eval_wer": 4.012345679012346,
|
| 1267 |
+
"step": 74
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 75.0,
|
| 1271 |
+
"grad_norm": 0.10059099644422531,
|
| 1272 |
+
"learning_rate": 1e-05,
|
| 1273 |
+
"loss": 0.0098,
|
| 1274 |
+
"step": 75
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 75.0,
|
| 1278 |
+
"eval_loss": 0.4597587287425995,
|
| 1279 |
+
"eval_model_preparation_time": 0.0121,
|
| 1280 |
+
"eval_runtime": 13.0097,
|
| 1281 |
+
"eval_samples_per_second": 1.537,
|
| 1282 |
+
"eval_steps_per_second": 0.231,
|
| 1283 |
+
"eval_wer": 4.012345679012346,
|
| 1284 |
+
"step": 75
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 76.0,
|
| 1288 |
+
"grad_norm": 0.10066922754049301,
|
| 1289 |
+
"learning_rate": 1e-05,
|
| 1290 |
+
"loss": 0.0096,
|
| 1291 |
+
"step": 76
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 76.0,
|
| 1295 |
+
"eval_loss": 0.4539148807525635,
|
| 1296 |
+
"eval_model_preparation_time": 0.0121,
|
| 1297 |
+
"eval_runtime": 13.1072,
|
| 1298 |
+
"eval_samples_per_second": 1.526,
|
| 1299 |
+
"eval_steps_per_second": 0.229,
|
| 1300 |
+
"eval_wer": 4.012345679012346,
|
| 1301 |
+
"step": 76
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 77.0,
|
| 1305 |
+
"grad_norm": 0.10073923319578171,
|
| 1306 |
+
"learning_rate": 1e-05,
|
| 1307 |
+
"loss": 0.0094,
|
| 1308 |
+
"step": 77
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 77.0,
|
| 1312 |
+
"eval_loss": 0.44823265075683594,
|
| 1313 |
+
"eval_model_preparation_time": 0.0121,
|
| 1314 |
+
"eval_runtime": 13.0093,
|
| 1315 |
+
"eval_samples_per_second": 1.537,
|
| 1316 |
+
"eval_steps_per_second": 0.231,
|
| 1317 |
+
"eval_wer": 4.012345679012346,
|
| 1318 |
+
"step": 77
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 78.0,
|
| 1322 |
+
"grad_norm": 0.1008358970284462,
|
| 1323 |
+
"learning_rate": 1e-05,
|
| 1324 |
+
"loss": 0.0091,
|
| 1325 |
+
"step": 78
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 78.0,
|
| 1329 |
+
"eval_loss": 0.442667692899704,
|
| 1330 |
+
"eval_model_preparation_time": 0.0121,
|
| 1331 |
+
"eval_runtime": 13.0167,
|
| 1332 |
+
"eval_samples_per_second": 1.536,
|
| 1333 |
+
"eval_steps_per_second": 0.23,
|
| 1334 |
+
"eval_wer": 4.012345679012346,
|
| 1335 |
+
"step": 78
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 79.0,
|
| 1339 |
+
"grad_norm": 0.10090507566928864,
|
| 1340 |
+
"learning_rate": 1e-05,
|
| 1341 |
+
"loss": 0.0089,
|
| 1342 |
+
"step": 79
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 79.0,
|
| 1346 |
+
"eval_loss": 0.43717432022094727,
|
| 1347 |
+
"eval_model_preparation_time": 0.0121,
|
| 1348 |
+
"eval_runtime": 13.0261,
|
| 1349 |
+
"eval_samples_per_second": 1.535,
|
| 1350 |
+
"eval_steps_per_second": 0.23,
|
| 1351 |
+
"eval_wer": 4.012345679012346,
|
| 1352 |
+
"step": 79
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 80.0,
|
| 1356 |
+
"grad_norm": 0.10097309201955795,
|
| 1357 |
+
"learning_rate": 1e-05,
|
| 1358 |
+
"loss": 0.0087,
|
| 1359 |
+
"step": 80
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 80.0,
|
| 1363 |
+
"eval_loss": 0.43188872933387756,
|
| 1364 |
+
"eval_model_preparation_time": 0.0121,
|
| 1365 |
+
"eval_runtime": 13.0257,
|
| 1366 |
+
"eval_samples_per_second": 1.535,
|
| 1367 |
+
"eval_steps_per_second": 0.23,
|
| 1368 |
+
"eval_wer": 4.012345679012346,
|
| 1369 |
+
"step": 80
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 81.0,
|
| 1373 |
+
"grad_norm": 0.10104646533727646,
|
| 1374 |
+
"learning_rate": 1e-05,
|
| 1375 |
+
"loss": 0.0085,
|
| 1376 |
+
"step": 81
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 81.0,
|
| 1380 |
+
"eval_loss": 0.4267992079257965,
|
| 1381 |
+
"eval_model_preparation_time": 0.0121,
|
| 1382 |
+
"eval_runtime": 13.0831,
|
| 1383 |
+
"eval_samples_per_second": 1.529,
|
| 1384 |
+
"eval_steps_per_second": 0.229,
|
| 1385 |
+
"eval_wer": 4.012345679012346,
|
| 1386 |
+
"step": 81
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 82.0,
|
| 1390 |
+
"grad_norm": 0.10112679749727249,
|
| 1391 |
+
"learning_rate": 1e-05,
|
| 1392 |
+
"loss": 0.0083,
|
| 1393 |
+
"step": 82
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 82.0,
|
| 1397 |
+
"eval_loss": 0.4219636917114258,
|
| 1398 |
+
"eval_model_preparation_time": 0.0121,
|
| 1399 |
+
"eval_runtime": 13.0252,
|
| 1400 |
+
"eval_samples_per_second": 1.535,
|
| 1401 |
+
"eval_steps_per_second": 0.23,
|
| 1402 |
+
"eval_wer": 4.012345679012346,
|
| 1403 |
+
"step": 82
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 83.0,
|
| 1407 |
+
"grad_norm": 0.10117711871862411,
|
| 1408 |
+
"learning_rate": 1e-05,
|
| 1409 |
+
"loss": 0.008,
|
| 1410 |
+
"step": 83
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 83.0,
|
| 1414 |
+
"eval_loss": 0.4172472655773163,
|
| 1415 |
+
"eval_model_preparation_time": 0.0121,
|
| 1416 |
+
"eval_runtime": 13.0112,
|
| 1417 |
+
"eval_samples_per_second": 1.537,
|
| 1418 |
+
"eval_steps_per_second": 0.231,
|
| 1419 |
+
"eval_wer": 4.012345679012346,
|
| 1420 |
+
"step": 83
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 84.0,
|
| 1424 |
+
"grad_norm": 0.1012597382068634,
|
| 1425 |
+
"learning_rate": 1e-05,
|
| 1426 |
+
"loss": 0.0078,
|
| 1427 |
+
"step": 84
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 84.0,
|
| 1431 |
+
"eval_loss": 0.41286230087280273,
|
| 1432 |
+
"eval_model_preparation_time": 0.0121,
|
| 1433 |
+
"eval_runtime": 13.0229,
|
| 1434 |
+
"eval_samples_per_second": 1.536,
|
| 1435 |
+
"eval_steps_per_second": 0.23,
|
| 1436 |
+
"eval_wer": 4.012345679012346,
|
| 1437 |
+
"step": 84
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 85.0,
|
| 1441 |
+
"grad_norm": 0.101369209587574,
|
| 1442 |
+
"learning_rate": 1e-05,
|
| 1443 |
+
"loss": 0.0076,
|
| 1444 |
+
"step": 85
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 85.0,
|
| 1448 |
+
"eval_loss": 0.40860816836357117,
|
| 1449 |
+
"eval_model_preparation_time": 0.0121,
|
| 1450 |
+
"eval_runtime": 13.0992,
|
| 1451 |
+
"eval_samples_per_second": 1.527,
|
| 1452 |
+
"eval_steps_per_second": 0.229,
|
| 1453 |
+
"eval_wer": 4.012345679012346,
|
| 1454 |
+
"step": 85
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 86.0,
|
| 1458 |
+
"grad_norm": 0.10140149295330048,
|
| 1459 |
+
"learning_rate": 1e-05,
|
| 1460 |
+
"loss": 0.0073,
|
| 1461 |
+
"step": 86
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 86.0,
|
| 1465 |
+
"eval_loss": 0.4042428433895111,
|
| 1466 |
+
"eval_model_preparation_time": 0.0121,
|
| 1467 |
+
"eval_runtime": 13.03,
|
| 1468 |
+
"eval_samples_per_second": 1.535,
|
| 1469 |
+
"eval_steps_per_second": 0.23,
|
| 1470 |
+
"eval_wer": 4.012345679012346,
|
| 1471 |
+
"step": 86
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 87.0,
|
| 1475 |
+
"grad_norm": 0.10143295675516129,
|
| 1476 |
+
"learning_rate": 1e-05,
|
| 1477 |
+
"loss": 0.0071,
|
| 1478 |
+
"step": 87
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 87.0,
|
| 1482 |
+
"eval_loss": 0.3998439311981201,
|
| 1483 |
+
"eval_model_preparation_time": 0.0121,
|
| 1484 |
+
"eval_runtime": 13.005,
|
| 1485 |
+
"eval_samples_per_second": 1.538,
|
| 1486 |
+
"eval_steps_per_second": 0.231,
|
| 1487 |
+
"eval_wer": 4.012345679012346,
|
| 1488 |
+
"step": 87
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 88.0,
|
| 1492 |
+
"grad_norm": 0.1014971062541008,
|
| 1493 |
+
"learning_rate": 1e-05,
|
| 1494 |
+
"loss": 0.0069,
|
| 1495 |
+
"step": 88
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 88.0,
|
| 1499 |
+
"eval_loss": 0.39532041549682617,
|
| 1500 |
+
"eval_model_preparation_time": 0.0121,
|
| 1501 |
+
"eval_runtime": 13.0078,
|
| 1502 |
+
"eval_samples_per_second": 1.538,
|
| 1503 |
+
"eval_steps_per_second": 0.231,
|
| 1504 |
+
"eval_wer": 4.012345679012346,
|
| 1505 |
+
"step": 88
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 89.0,
|
| 1509 |
+
"grad_norm": 0.10153479129076004,
|
| 1510 |
+
"learning_rate": 1e-05,
|
| 1511 |
+
"loss": 0.0066,
|
| 1512 |
+
"step": 89
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 89.0,
|
| 1516 |
+
"eval_loss": 0.3908376693725586,
|
| 1517 |
+
"eval_model_preparation_time": 0.0121,
|
| 1518 |
+
"eval_runtime": 13.0794,
|
| 1519 |
+
"eval_samples_per_second": 1.529,
|
| 1520 |
+
"eval_steps_per_second": 0.229,
|
| 1521 |
+
"eval_wer": 4.012345679012346,
|
| 1522 |
+
"step": 89
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 90.0,
|
| 1526 |
+
"grad_norm": 0.10166627168655396,
|
| 1527 |
+
"learning_rate": 1e-05,
|
| 1528 |
+
"loss": 0.0064,
|
| 1529 |
+
"step": 90
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 90.0,
|
| 1533 |
+
"eval_loss": 0.3862927258014679,
|
| 1534 |
+
"eval_model_preparation_time": 0.0121,
|
| 1535 |
+
"eval_runtime": 13.0683,
|
| 1536 |
+
"eval_samples_per_second": 1.53,
|
| 1537 |
+
"eval_steps_per_second": 0.23,
|
| 1538 |
+
"eval_wer": 4.320987654320987,
|
| 1539 |
+
"step": 90
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 91.0,
|
| 1543 |
+
"grad_norm": 0.10168776661157608,
|
| 1544 |
+
"learning_rate": 1e-05,
|
| 1545 |
+
"loss": 0.0062,
|
| 1546 |
+
"step": 91
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 91.0,
|
| 1550 |
+
"eval_loss": 0.38115009665489197,
|
| 1551 |
+
"eval_model_preparation_time": 0.0121,
|
| 1552 |
+
"eval_runtime": 13.0067,
|
| 1553 |
+
"eval_samples_per_second": 1.538,
|
| 1554 |
+
"eval_steps_per_second": 0.231,
|
| 1555 |
+
"eval_wer": 4.320987654320987,
|
| 1556 |
+
"step": 91
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 92.0,
|
| 1560 |
+
"grad_norm": 0.10173481702804565,
|
| 1561 |
+
"learning_rate": 1e-05,
|
| 1562 |
+
"loss": 0.0059,
|
| 1563 |
+
"step": 92
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 92.0,
|
| 1567 |
+
"eval_loss": 0.37574759125709534,
|
| 1568 |
+
"eval_model_preparation_time": 0.0121,
|
| 1569 |
+
"eval_runtime": 13.045,
|
| 1570 |
+
"eval_samples_per_second": 1.533,
|
| 1571 |
+
"eval_steps_per_second": 0.23,
|
| 1572 |
+
"eval_wer": 4.320987654320987,
|
| 1573 |
+
"step": 92
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 93.0,
|
| 1577 |
+
"grad_norm": 0.1017962321639061,
|
| 1578 |
+
"learning_rate": 1e-05,
|
| 1579 |
+
"loss": 0.0057,
|
| 1580 |
+
"step": 93
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 93.0,
|
| 1584 |
+
"eval_loss": 0.3700896203517914,
|
| 1585 |
+
"eval_model_preparation_time": 0.0121,
|
| 1586 |
+
"eval_runtime": 12.9624,
|
| 1587 |
+
"eval_samples_per_second": 1.543,
|
| 1588 |
+
"eval_steps_per_second": 0.231,
|
| 1589 |
+
"eval_wer": 4.320987654320987,
|
| 1590 |
+
"step": 93
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 94.0,
|
| 1594 |
+
"grad_norm": 0.10191880166530609,
|
| 1595 |
+
"learning_rate": 1e-05,
|
| 1596 |
+
"loss": 0.0055,
|
| 1597 |
+
"step": 94
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 94.0,
|
| 1601 |
+
"eval_loss": 0.3639739453792572,
|
| 1602 |
+
"eval_model_preparation_time": 0.0121,
|
| 1603 |
+
"eval_runtime": 12.9926,
|
| 1604 |
+
"eval_samples_per_second": 1.539,
|
| 1605 |
+
"eval_steps_per_second": 0.231,
|
| 1606 |
+
"eval_wer": 4.320987654320987,
|
| 1607 |
+
"step": 94
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 95.0,
|
| 1611 |
+
"grad_norm": 0.10210127383470535,
|
| 1612 |
+
"learning_rate": 1e-05,
|
| 1613 |
+
"loss": 0.0053,
|
| 1614 |
+
"step": 95
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 95.0,
|
| 1618 |
+
"eval_loss": 0.3575873374938965,
|
| 1619 |
+
"eval_model_preparation_time": 0.0121,
|
| 1620 |
+
"eval_runtime": 12.9753,
|
| 1621 |
+
"eval_samples_per_second": 1.541,
|
| 1622 |
+
"eval_steps_per_second": 0.231,
|
| 1623 |
+
"eval_wer": 5.246913580246913,
|
| 1624 |
+
"step": 95
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 96.0,
|
| 1628 |
+
"grad_norm": 0.10229586809873581,
|
| 1629 |
+
"learning_rate": 1e-05,
|
| 1630 |
+
"loss": 0.005,
|
| 1631 |
+
"step": 96
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 96.0,
|
| 1635 |
+
"eval_loss": 0.351242333650589,
|
| 1636 |
+
"eval_model_preparation_time": 0.0121,
|
| 1637 |
+
"eval_runtime": 12.9627,
|
| 1638 |
+
"eval_samples_per_second": 1.543,
|
| 1639 |
+
"eval_steps_per_second": 0.231,
|
| 1640 |
+
"eval_wer": 5.246913580246913,
|
| 1641 |
+
"step": 96
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 97.0,
|
| 1645 |
+
"grad_norm": 0.10258200764656067,
|
| 1646 |
+
"learning_rate": 1e-05,
|
| 1647 |
+
"loss": 0.0048,
|
| 1648 |
+
"step": 97
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 97.0,
|
| 1652 |
+
"eval_loss": 0.34528884291648865,
|
| 1653 |
+
"eval_model_preparation_time": 0.0121,
|
| 1654 |
+
"eval_runtime": 12.9959,
|
| 1655 |
+
"eval_samples_per_second": 1.539,
|
| 1656 |
+
"eval_steps_per_second": 0.231,
|
| 1657 |
+
"eval_wer": 5.246913580246913,
|
| 1658 |
+
"step": 97
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 98.0,
|
| 1662 |
+
"grad_norm": 0.1028934046626091,
|
| 1663 |
+
"learning_rate": 1e-05,
|
| 1664 |
+
"loss": 0.0046,
|
| 1665 |
+
"step": 98
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 98.0,
|
| 1669 |
+
"eval_loss": 0.3395444452762604,
|
| 1670 |
+
"eval_model_preparation_time": 0.0121,
|
| 1671 |
+
"eval_runtime": 13.0387,
|
| 1672 |
+
"eval_samples_per_second": 1.534,
|
| 1673 |
+
"eval_steps_per_second": 0.23,
|
| 1674 |
+
"eval_wer": 5.246913580246913,
|
| 1675 |
+
"step": 98
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 99.0,
|
| 1679 |
+
"grad_norm": 0.10328880697488785,
|
| 1680 |
+
"learning_rate": 1e-05,
|
| 1681 |
+
"loss": 0.0044,
|
| 1682 |
+
"step": 99
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 99.0,
|
| 1686 |
+
"eval_loss": 0.33414900302886963,
|
| 1687 |
+
"eval_model_preparation_time": 0.0121,
|
| 1688 |
+
"eval_runtime": 13.0468,
|
| 1689 |
+
"eval_samples_per_second": 1.533,
|
| 1690 |
+
"eval_steps_per_second": 0.23,
|
| 1691 |
+
"eval_wer": 5.864197530864197,
|
| 1692 |
+
"step": 99
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 100.0,
|
| 1696 |
+
"grad_norm": 0.10364117473363876,
|
| 1697 |
+
"learning_rate": 1e-05,
|
| 1698 |
+
"loss": 0.0042,
|
| 1699 |
+
"step": 100
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 100.0,
|
| 1703 |
+
"eval_loss": 0.3294712007045746,
|
| 1704 |
+
"eval_model_preparation_time": 0.0121,
|
| 1705 |
+
"eval_runtime": 13.0722,
|
| 1706 |
+
"eval_samples_per_second": 1.53,
|
| 1707 |
+
"eval_steps_per_second": 0.229,
|
| 1708 |
+
"eval_wer": 5.864197530864197,
|
| 1709 |
+
"step": 100
|
| 1710 |
+
}
|
| 1711 |
+
],
|
| 1712 |
+
"logging_steps": 1,
|
| 1713 |
+
"max_steps": 100,
|
| 1714 |
+
"num_input_tokens_seen": 0,
|
| 1715 |
+
"num_train_epochs": 100,
|
| 1716 |
+
"save_steps": 1000,
|
| 1717 |
+
"stateful_callbacks": {
|
| 1718 |
+
"EarlyStoppingCallback": {
|
| 1719 |
+
"args": {
|
| 1720 |
+
"early_stopping_patience": 3,
|
| 1721 |
+
"early_stopping_threshold": 0.0
|
| 1722 |
+
},
|
| 1723 |
+
"attributes": {
|
| 1724 |
+
"early_stopping_patience_counter": 0
|
| 1725 |
+
}
|
| 1726 |
+
},
|
| 1727 |
+
"TrainerControl": {
|
| 1728 |
+
"args": {
|
| 1729 |
+
"should_epoch_stop": false,
|
| 1730 |
+
"should_evaluate": false,
|
| 1731 |
+
"should_log": false,
|
| 1732 |
+
"should_save": true,
|
| 1733 |
+
"should_training_stop": true
|
| 1734 |
+
},
|
| 1735 |
+
"attributes": {}
|
| 1736 |
+
}
|
| 1737 |
+
},
|
| 1738 |
+
"total_flos": 6.12362944512e+17,
|
| 1739 |
+
"train_batch_size": 16,
|
| 1740 |
+
"trial_name": null,
|
| 1741 |
+
"trial_params": null
|
| 1742 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcebb509612029e0a3f035bd0445279e2aaf89270c378a9491d79b32a080d433
|
| 3 |
+
size 5496
|