Upload 9 files
Browse files- config.json +61 -0
- generation_config.json +262 -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 +1153 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-small",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"apply_spec_augment": false,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"WhisperForConditionalGeneration"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"begin_suppress_tokens": null,
|
| 11 |
+
"bos_token_id": 50257,
|
| 12 |
+
"classifier_proj_size": 256,
|
| 13 |
+
"d_model": 768,
|
| 14 |
+
"decoder_attention_heads": 12,
|
| 15 |
+
"decoder_ffn_dim": 3072,
|
| 16 |
+
"decoder_layerdrop": 0.0,
|
| 17 |
+
"decoder_layers": 12,
|
| 18 |
+
"decoder_start_token_id": 50258,
|
| 19 |
+
"dropout": 0.0,
|
| 20 |
+
"encoder_attention_heads": 12,
|
| 21 |
+
"encoder_ffn_dim": 3072,
|
| 22 |
+
"encoder_layerdrop": 0.0,
|
| 23 |
+
"encoder_layers": 12,
|
| 24 |
+
"eos_token_id": 50257,
|
| 25 |
+
"forced_decoder_ids": [
|
| 26 |
+
[
|
| 27 |
+
1,
|
| 28 |
+
50259
|
| 29 |
+
],
|
| 30 |
+
[
|
| 31 |
+
2,
|
| 32 |
+
50359
|
| 33 |
+
],
|
| 34 |
+
[
|
| 35 |
+
3,
|
| 36 |
+
50363
|
| 37 |
+
]
|
| 38 |
+
],
|
| 39 |
+
"init_std": 0.02,
|
| 40 |
+
"is_encoder_decoder": true,
|
| 41 |
+
"mask_feature_length": 10,
|
| 42 |
+
"mask_feature_min_masks": 0,
|
| 43 |
+
"mask_feature_prob": 0.0,
|
| 44 |
+
"mask_time_length": 10,
|
| 45 |
+
"mask_time_min_masks": 2,
|
| 46 |
+
"mask_time_prob": 0.05,
|
| 47 |
+
"max_length": null,
|
| 48 |
+
"max_source_positions": 1500,
|
| 49 |
+
"max_target_positions": 448,
|
| 50 |
+
"median_filter_width": 7,
|
| 51 |
+
"model_type": "whisper",
|
| 52 |
+
"num_hidden_layers": 12,
|
| 53 |
+
"num_mel_bins": 80,
|
| 54 |
+
"pad_token_id": 50257,
|
| 55 |
+
"scale_embedding": false,
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.46.2",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"use_weighted_layer_sum": false,
|
| 60 |
+
"vocab_size": 51865
|
| 61 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
5,
|
| 5 |
+
3
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
5,
|
| 9 |
+
9
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
8,
|
| 13 |
+
0
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
8,
|
| 17 |
+
4
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
8,
|
| 21 |
+
7
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
8,
|
| 25 |
+
8
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
9,
|
| 29 |
+
0
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
9,
|
| 33 |
+
7
|
| 34 |
+
],
|
| 35 |
+
[
|
| 36 |
+
9,
|
| 37 |
+
9
|
| 38 |
+
],
|
| 39 |
+
[
|
| 40 |
+
10,
|
| 41 |
+
5
|
| 42 |
+
]
|
| 43 |
+
],
|
| 44 |
+
"begin_suppress_tokens": [
|
| 45 |
+
220,
|
| 46 |
+
50257
|
| 47 |
+
],
|
| 48 |
+
"bos_token_id": 50257,
|
| 49 |
+
"decoder_start_token_id": 50258,
|
| 50 |
+
"eos_token_id": 50257,
|
| 51 |
+
"forced_decoder_ids": [
|
| 52 |
+
[
|
| 53 |
+
1,
|
| 54 |
+
null
|
| 55 |
+
],
|
| 56 |
+
[
|
| 57 |
+
2,
|
| 58 |
+
50359
|
| 59 |
+
]
|
| 60 |
+
],
|
| 61 |
+
"is_multilingual": true,
|
| 62 |
+
"lang_to_id": {
|
| 63 |
+
"<|af|>": 50327,
|
| 64 |
+
"<|am|>": 50334,
|
| 65 |
+
"<|ar|>": 50272,
|
| 66 |
+
"<|as|>": 50350,
|
| 67 |
+
"<|az|>": 50304,
|
| 68 |
+
"<|ba|>": 50355,
|
| 69 |
+
"<|be|>": 50330,
|
| 70 |
+
"<|bg|>": 50292,
|
| 71 |
+
"<|bn|>": 50302,
|
| 72 |
+
"<|bo|>": 50347,
|
| 73 |
+
"<|br|>": 50309,
|
| 74 |
+
"<|bs|>": 50315,
|
| 75 |
+
"<|ca|>": 50270,
|
| 76 |
+
"<|cs|>": 50283,
|
| 77 |
+
"<|cy|>": 50297,
|
| 78 |
+
"<|da|>": 50285,
|
| 79 |
+
"<|de|>": 50261,
|
| 80 |
+
"<|el|>": 50281,
|
| 81 |
+
"<|en|>": 50259,
|
| 82 |
+
"<|es|>": 50262,
|
| 83 |
+
"<|et|>": 50307,
|
| 84 |
+
"<|eu|>": 50310,
|
| 85 |
+
"<|fa|>": 50300,
|
| 86 |
+
"<|fi|>": 50277,
|
| 87 |
+
"<|fo|>": 50338,
|
| 88 |
+
"<|fr|>": 50265,
|
| 89 |
+
"<|gl|>": 50319,
|
| 90 |
+
"<|gu|>": 50333,
|
| 91 |
+
"<|haw|>": 50352,
|
| 92 |
+
"<|ha|>": 50354,
|
| 93 |
+
"<|he|>": 50279,
|
| 94 |
+
"<|hi|>": 50276,
|
| 95 |
+
"<|hr|>": 50291,
|
| 96 |
+
"<|ht|>": 50339,
|
| 97 |
+
"<|hu|>": 50286,
|
| 98 |
+
"<|hy|>": 50312,
|
| 99 |
+
"<|id|>": 50275,
|
| 100 |
+
"<|is|>": 50311,
|
| 101 |
+
"<|it|>": 50274,
|
| 102 |
+
"<|ja|>": 50266,
|
| 103 |
+
"<|jw|>": 50356,
|
| 104 |
+
"<|ka|>": 50329,
|
| 105 |
+
"<|kk|>": 50316,
|
| 106 |
+
"<|km|>": 50323,
|
| 107 |
+
"<|kn|>": 50306,
|
| 108 |
+
"<|ko|>": 50264,
|
| 109 |
+
"<|la|>": 50294,
|
| 110 |
+
"<|lb|>": 50345,
|
| 111 |
+
"<|ln|>": 50353,
|
| 112 |
+
"<|lo|>": 50336,
|
| 113 |
+
"<|lt|>": 50293,
|
| 114 |
+
"<|lv|>": 50301,
|
| 115 |
+
"<|mg|>": 50349,
|
| 116 |
+
"<|mi|>": 50295,
|
| 117 |
+
"<|mk|>": 50308,
|
| 118 |
+
"<|ml|>": 50296,
|
| 119 |
+
"<|mn|>": 50314,
|
| 120 |
+
"<|mr|>": 50320,
|
| 121 |
+
"<|ms|>": 50282,
|
| 122 |
+
"<|mt|>": 50343,
|
| 123 |
+
"<|my|>": 50346,
|
| 124 |
+
"<|ne|>": 50313,
|
| 125 |
+
"<|nl|>": 50271,
|
| 126 |
+
"<|nn|>": 50342,
|
| 127 |
+
"<|no|>": 50288,
|
| 128 |
+
"<|oc|>": 50328,
|
| 129 |
+
"<|pa|>": 50321,
|
| 130 |
+
"<|pl|>": 50269,
|
| 131 |
+
"<|ps|>": 50340,
|
| 132 |
+
"<|pt|>": 50267,
|
| 133 |
+
"<|ro|>": 50284,
|
| 134 |
+
"<|ru|>": 50263,
|
| 135 |
+
"<|sa|>": 50344,
|
| 136 |
+
"<|sd|>": 50332,
|
| 137 |
+
"<|si|>": 50322,
|
| 138 |
+
"<|sk|>": 50298,
|
| 139 |
+
"<|sl|>": 50305,
|
| 140 |
+
"<|sn|>": 50324,
|
| 141 |
+
"<|so|>": 50326,
|
| 142 |
+
"<|sq|>": 50317,
|
| 143 |
+
"<|sr|>": 50303,
|
| 144 |
+
"<|su|>": 50357,
|
| 145 |
+
"<|sv|>": 50273,
|
| 146 |
+
"<|sw|>": 50318,
|
| 147 |
+
"<|ta|>": 50287,
|
| 148 |
+
"<|te|>": 50299,
|
| 149 |
+
"<|tg|>": 50331,
|
| 150 |
+
"<|th|>": 50289,
|
| 151 |
+
"<|tk|>": 50341,
|
| 152 |
+
"<|tl|>": 50348,
|
| 153 |
+
"<|tr|>": 50268,
|
| 154 |
+
"<|tt|>": 50351,
|
| 155 |
+
"<|uk|>": 50280,
|
| 156 |
+
"<|ur|>": 50290,
|
| 157 |
+
"<|uz|>": 50337,
|
| 158 |
+
"<|vi|>": 50278,
|
| 159 |
+
"<|yi|>": 50335,
|
| 160 |
+
"<|yo|>": 50325,
|
| 161 |
+
"<|zh|>": 50260
|
| 162 |
+
},
|
| 163 |
+
"max_initial_timestamp_index": 50,
|
| 164 |
+
"max_length": 448,
|
| 165 |
+
"no_timestamps_token_id": 50363,
|
| 166 |
+
"pad_token_id": 50257,
|
| 167 |
+
"prev_sot_token_id": 50361,
|
| 168 |
+
"return_timestamps": false,
|
| 169 |
+
"suppress_tokens": [
|
| 170 |
+
1,
|
| 171 |
+
2,
|
| 172 |
+
7,
|
| 173 |
+
8,
|
| 174 |
+
9,
|
| 175 |
+
10,
|
| 176 |
+
14,
|
| 177 |
+
25,
|
| 178 |
+
26,
|
| 179 |
+
27,
|
| 180 |
+
28,
|
| 181 |
+
29,
|
| 182 |
+
31,
|
| 183 |
+
58,
|
| 184 |
+
59,
|
| 185 |
+
60,
|
| 186 |
+
61,
|
| 187 |
+
62,
|
| 188 |
+
63,
|
| 189 |
+
90,
|
| 190 |
+
91,
|
| 191 |
+
92,
|
| 192 |
+
93,
|
| 193 |
+
359,
|
| 194 |
+
503,
|
| 195 |
+
522,
|
| 196 |
+
542,
|
| 197 |
+
873,
|
| 198 |
+
893,
|
| 199 |
+
902,
|
| 200 |
+
918,
|
| 201 |
+
922,
|
| 202 |
+
931,
|
| 203 |
+
1350,
|
| 204 |
+
1853,
|
| 205 |
+
1982,
|
| 206 |
+
2460,
|
| 207 |
+
2627,
|
| 208 |
+
3246,
|
| 209 |
+
3253,
|
| 210 |
+
3268,
|
| 211 |
+
3536,
|
| 212 |
+
3846,
|
| 213 |
+
3961,
|
| 214 |
+
4183,
|
| 215 |
+
4667,
|
| 216 |
+
6585,
|
| 217 |
+
6647,
|
| 218 |
+
7273,
|
| 219 |
+
9061,
|
| 220 |
+
9383,
|
| 221 |
+
10428,
|
| 222 |
+
10929,
|
| 223 |
+
11938,
|
| 224 |
+
12033,
|
| 225 |
+
12331,
|
| 226 |
+
12562,
|
| 227 |
+
13793,
|
| 228 |
+
14157,
|
| 229 |
+
14635,
|
| 230 |
+
15265,
|
| 231 |
+
15618,
|
| 232 |
+
16553,
|
| 233 |
+
16604,
|
| 234 |
+
18362,
|
| 235 |
+
18956,
|
| 236 |
+
20075,
|
| 237 |
+
21675,
|
| 238 |
+
22520,
|
| 239 |
+
26130,
|
| 240 |
+
26161,
|
| 241 |
+
26435,
|
| 242 |
+
28279,
|
| 243 |
+
29464,
|
| 244 |
+
31650,
|
| 245 |
+
32302,
|
| 246 |
+
32470,
|
| 247 |
+
36865,
|
| 248 |
+
42863,
|
| 249 |
+
47425,
|
| 250 |
+
49870,
|
| 251 |
+
50254,
|
| 252 |
+
50258,
|
| 253 |
+
50360,
|
| 254 |
+
50361,
|
| 255 |
+
50362
|
| 256 |
+
],
|
| 257 |
+
"task_to_id": {
|
| 258 |
+
"transcribe": 50359,
|
| 259 |
+
"translate": 50358
|
| 260 |
+
},
|
| 261 |
+
"transformers_version": "4.46.2"
|
| 262 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aebb6c271eff7ab1a6f9b4fd642cc2da021a40ac7f968073f46100535cd45e31
|
| 3 |
+
size 966995080
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19a4ad4631cc9c9db4d0d43292557063eb2b2b25d86b722ac42e7e2ecd835cb4
|
| 3 |
+
size 1925064044
|
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 sha256:32aaf049cc53791a5beae7383ac87c32e1779c488d893928dbedb1f93005bd7e
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bf6d6461f193b93f4eeb4df0f7a33d39520a76389b97b65c4e6112e16065f47
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.420545746388443,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04012841091492777,
|
| 13 |
+
"grad_norm": 86.5052261352539,
|
| 14 |
+
"learning_rate": 5.750000000000001e-07,
|
| 15 |
+
"loss": 2.891,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08025682182985554,
|
| 20 |
+
"grad_norm": 44.9648551940918,
|
| 21 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 22 |
+
"loss": 2.0127,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12038523274478331,
|
| 27 |
+
"grad_norm": 32.67415237426758,
|
| 28 |
+
"learning_rate": 1.825e-06,
|
| 29 |
+
"loss": 1.3251,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16051364365971107,
|
| 34 |
+
"grad_norm": 33.664764404296875,
|
| 35 |
+
"learning_rate": 2.4500000000000003e-06,
|
| 36 |
+
"loss": 1.139,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.20064205457463885,
|
| 41 |
+
"grad_norm": 38.86428451538086,
|
| 42 |
+
"learning_rate": 3.075e-06,
|
| 43 |
+
"loss": 0.9913,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24077046548956663,
|
| 48 |
+
"grad_norm": 38.11140441894531,
|
| 49 |
+
"learning_rate": 3.7e-06,
|
| 50 |
+
"loss": 0.9344,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2808988764044944,
|
| 55 |
+
"grad_norm": 39.1014518737793,
|
| 56 |
+
"learning_rate": 4.325e-06,
|
| 57 |
+
"loss": 0.8068,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.32102728731942215,
|
| 62 |
+
"grad_norm": 19.286678314208984,
|
| 63 |
+
"learning_rate": 4.95e-06,
|
| 64 |
+
"loss": 0.7104,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3611556982343499,
|
| 69 |
+
"grad_norm": 24.21994972229004,
|
| 70 |
+
"learning_rate": 5.575000000000001e-06,
|
| 71 |
+
"loss": 0.6199,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4012841091492777,
|
| 76 |
+
"grad_norm": 23.403148651123047,
|
| 77 |
+
"learning_rate": 6.200000000000001e-06,
|
| 78 |
+
"loss": 0.6139,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.44141252006420545,
|
| 83 |
+
"grad_norm": 21.166723251342773,
|
| 84 |
+
"learning_rate": 6.825000000000001e-06,
|
| 85 |
+
"loss": 0.5843,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.48154093097913325,
|
| 90 |
+
"grad_norm": 18.9536075592041,
|
| 91 |
+
"learning_rate": 7.450000000000001e-06,
|
| 92 |
+
"loss": 0.578,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.521669341894061,
|
| 97 |
+
"grad_norm": 21.438701629638672,
|
| 98 |
+
"learning_rate": 8.075000000000001e-06,
|
| 99 |
+
"loss": 0.5505,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5617977528089888,
|
| 104 |
+
"grad_norm": 25.26392364501953,
|
| 105 |
+
"learning_rate": 8.700000000000001e-06,
|
| 106 |
+
"loss": 0.5649,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6019261637239165,
|
| 111 |
+
"grad_norm": 19.77715492248535,
|
| 112 |
+
"learning_rate": 9.325000000000001e-06,
|
| 113 |
+
"loss": 0.5839,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6420545746388443,
|
| 118 |
+
"grad_norm": 20.142839431762695,
|
| 119 |
+
"learning_rate": 9.950000000000001e-06,
|
| 120 |
+
"loss": 0.5518,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6821829855537721,
|
| 125 |
+
"grad_norm": 20.156387329101562,
|
| 126 |
+
"learning_rate": 9.936111111111112e-06,
|
| 127 |
+
"loss": 0.5514,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.7223113964686998,
|
| 132 |
+
"grad_norm": 21.246883392333984,
|
| 133 |
+
"learning_rate": 9.866666666666668e-06,
|
| 134 |
+
"loss": 0.5125,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7624398073836276,
|
| 139 |
+
"grad_norm": 17.57798957824707,
|
| 140 |
+
"learning_rate": 9.797222222222223e-06,
|
| 141 |
+
"loss": 0.5129,
|
| 142 |
+
"step": 950
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8025682182985554,
|
| 146 |
+
"grad_norm": 18.979021072387695,
|
| 147 |
+
"learning_rate": 9.727777777777777e-06,
|
| 148 |
+
"loss": 0.493,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8426966292134831,
|
| 153 |
+
"grad_norm": 20.188549041748047,
|
| 154 |
+
"learning_rate": 9.658333333333334e-06,
|
| 155 |
+
"loss": 0.5158,
|
| 156 |
+
"step": 1050
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8828250401284109,
|
| 160 |
+
"grad_norm": 17.60784149169922,
|
| 161 |
+
"learning_rate": 9.58888888888889e-06,
|
| 162 |
+
"loss": 0.4901,
|
| 163 |
+
"step": 1100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.9229534510433387,
|
| 167 |
+
"grad_norm": 38.89186477661133,
|
| 168 |
+
"learning_rate": 9.519444444444446e-06,
|
| 169 |
+
"loss": 0.493,
|
| 170 |
+
"step": 1150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9630818619582665,
|
| 174 |
+
"grad_norm": 20.224136352539062,
|
| 175 |
+
"learning_rate": 9.450000000000001e-06,
|
| 176 |
+
"loss": 0.4911,
|
| 177 |
+
"step": 1200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.0032102728731942,
|
| 181 |
+
"grad_norm": 13.886350631713867,
|
| 182 |
+
"learning_rate": 9.380555555555556e-06,
|
| 183 |
+
"loss": 0.4649,
|
| 184 |
+
"step": 1250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.043338683788122,
|
| 188 |
+
"grad_norm": 14.338887214660645,
|
| 189 |
+
"learning_rate": 9.311111111111112e-06,
|
| 190 |
+
"loss": 0.3867,
|
| 191 |
+
"step": 1300
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0834670947030498,
|
| 195 |
+
"grad_norm": 17.406949996948242,
|
| 196 |
+
"learning_rate": 9.241666666666668e-06,
|
| 197 |
+
"loss": 0.3609,
|
| 198 |
+
"step": 1350
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.1235955056179776,
|
| 202 |
+
"grad_norm": 19.521095275878906,
|
| 203 |
+
"learning_rate": 9.172222222222223e-06,
|
| 204 |
+
"loss": 0.354,
|
| 205 |
+
"step": 1400
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.1637239165329052,
|
| 209 |
+
"grad_norm": 14.558744430541992,
|
| 210 |
+
"learning_rate": 9.102777777777777e-06,
|
| 211 |
+
"loss": 0.357,
|
| 212 |
+
"step": 1450
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.203852327447833,
|
| 216 |
+
"grad_norm": 13.476064682006836,
|
| 217 |
+
"learning_rate": 9.033333333333334e-06,
|
| 218 |
+
"loss": 0.3593,
|
| 219 |
+
"step": 1500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.2439807383627608,
|
| 223 |
+
"grad_norm": 15.735109329223633,
|
| 224 |
+
"learning_rate": 8.96388888888889e-06,
|
| 225 |
+
"loss": 0.3567,
|
| 226 |
+
"step": 1550
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.2841091492776886,
|
| 230 |
+
"grad_norm": 17.4168758392334,
|
| 231 |
+
"learning_rate": 8.894444444444445e-06,
|
| 232 |
+
"loss": 0.3534,
|
| 233 |
+
"step": 1600
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.3242375601926164,
|
| 237 |
+
"grad_norm": 17.488101959228516,
|
| 238 |
+
"learning_rate": 8.825000000000001e-06,
|
| 239 |
+
"loss": 0.3481,
|
| 240 |
+
"step": 1650
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.3643659711075442,
|
| 244 |
+
"grad_norm": 14.388931274414062,
|
| 245 |
+
"learning_rate": 8.755555555555556e-06,
|
| 246 |
+
"loss": 0.3517,
|
| 247 |
+
"step": 1700
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.404494382022472,
|
| 251 |
+
"grad_norm": 14.942325592041016,
|
| 252 |
+
"learning_rate": 8.686111111111112e-06,
|
| 253 |
+
"loss": 0.3361,
|
| 254 |
+
"step": 1750
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.4446227929373996,
|
| 258 |
+
"grad_norm": 19.468101501464844,
|
| 259 |
+
"learning_rate": 8.616666666666668e-06,
|
| 260 |
+
"loss": 0.349,
|
| 261 |
+
"step": 1800
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.4847512038523274,
|
| 265 |
+
"grad_norm": 17.254077911376953,
|
| 266 |
+
"learning_rate": 8.547222222222223e-06,
|
| 267 |
+
"loss": 0.3593,
|
| 268 |
+
"step": 1850
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.5248796147672552,
|
| 272 |
+
"grad_norm": 14.908585548400879,
|
| 273 |
+
"learning_rate": 8.477777777777778e-06,
|
| 274 |
+
"loss": 0.3464,
|
| 275 |
+
"step": 1900
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.565008025682183,
|
| 279 |
+
"grad_norm": 14.53330135345459,
|
| 280 |
+
"learning_rate": 8.408333333333334e-06,
|
| 281 |
+
"loss": 0.3431,
|
| 282 |
+
"step": 1950
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.6051364365971108,
|
| 286 |
+
"grad_norm": 16.17108154296875,
|
| 287 |
+
"learning_rate": 8.33888888888889e-06,
|
| 288 |
+
"loss": 0.3272,
|
| 289 |
+
"step": 2000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.6452648475120384,
|
| 293 |
+
"grad_norm": 17.363994598388672,
|
| 294 |
+
"learning_rate": 8.269444444444445e-06,
|
| 295 |
+
"loss": 0.354,
|
| 296 |
+
"step": 2050
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.6853932584269664,
|
| 300 |
+
"grad_norm": 15.006171226501465,
|
| 301 |
+
"learning_rate": 8.2e-06,
|
| 302 |
+
"loss": 0.3399,
|
| 303 |
+
"step": 2100
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.725521669341894,
|
| 307 |
+
"grad_norm": 19.402164459228516,
|
| 308 |
+
"learning_rate": 8.130555555555556e-06,
|
| 309 |
+
"loss": 0.3507,
|
| 310 |
+
"step": 2150
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.7656500802568218,
|
| 314 |
+
"grad_norm": 18.973295211791992,
|
| 315 |
+
"learning_rate": 8.061111111111112e-06,
|
| 316 |
+
"loss": 0.3384,
|
| 317 |
+
"step": 2200
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.8057784911717496,
|
| 321 |
+
"grad_norm": 16.426692962646484,
|
| 322 |
+
"learning_rate": 7.991666666666668e-06,
|
| 323 |
+
"loss": 0.3475,
|
| 324 |
+
"step": 2250
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.8459069020866774,
|
| 328 |
+
"grad_norm": 15.58637523651123,
|
| 329 |
+
"learning_rate": 7.922222222222223e-06,
|
| 330 |
+
"loss": 0.3392,
|
| 331 |
+
"step": 2300
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.8860353130016052,
|
| 335 |
+
"grad_norm": 22.870681762695312,
|
| 336 |
+
"learning_rate": 7.852777777777778e-06,
|
| 337 |
+
"loss": 0.3379,
|
| 338 |
+
"step": 2350
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.9261637239165328,
|
| 342 |
+
"grad_norm": 13.37627124786377,
|
| 343 |
+
"learning_rate": 7.783333333333334e-06,
|
| 344 |
+
"loss": 0.3397,
|
| 345 |
+
"step": 2400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.9662921348314608,
|
| 349 |
+
"grad_norm": 13.650712013244629,
|
| 350 |
+
"learning_rate": 7.71388888888889e-06,
|
| 351 |
+
"loss": 0.3325,
|
| 352 |
+
"step": 2450
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.0064205457463884,
|
| 356 |
+
"grad_norm": 11.761895179748535,
|
| 357 |
+
"learning_rate": 7.644444444444445e-06,
|
| 358 |
+
"loss": 0.3198,
|
| 359 |
+
"step": 2500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.0465489566613164,
|
| 363 |
+
"grad_norm": 10.545045852661133,
|
| 364 |
+
"learning_rate": 7.575e-06,
|
| 365 |
+
"loss": 0.2247,
|
| 366 |
+
"step": 2550
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.086677367576244,
|
| 370 |
+
"grad_norm": 14.525964736938477,
|
| 371 |
+
"learning_rate": 7.505555555555556e-06,
|
| 372 |
+
"loss": 0.2106,
|
| 373 |
+
"step": 2600
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.1268057784911716,
|
| 377 |
+
"grad_norm": 12.788507461547852,
|
| 378 |
+
"learning_rate": 7.436111111111112e-06,
|
| 379 |
+
"loss": 0.2179,
|
| 380 |
+
"step": 2650
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.1669341894060996,
|
| 384 |
+
"grad_norm": 15.106952667236328,
|
| 385 |
+
"learning_rate": 7.3666666666666676e-06,
|
| 386 |
+
"loss": 0.23,
|
| 387 |
+
"step": 2700
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.207062600321027,
|
| 391 |
+
"grad_norm": 14.04389762878418,
|
| 392 |
+
"learning_rate": 7.297222222222223e-06,
|
| 393 |
+
"loss": 0.2156,
|
| 394 |
+
"step": 2750
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.247191011235955,
|
| 398 |
+
"grad_norm": 17.352598190307617,
|
| 399 |
+
"learning_rate": 7.227777777777778e-06,
|
| 400 |
+
"loss": 0.2175,
|
| 401 |
+
"step": 2800
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.287319422150883,
|
| 405 |
+
"grad_norm": 11.569601058959961,
|
| 406 |
+
"learning_rate": 7.158333333333334e-06,
|
| 407 |
+
"loss": 0.2079,
|
| 408 |
+
"step": 2850
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.3274478330658104,
|
| 412 |
+
"grad_norm": 14.02609634399414,
|
| 413 |
+
"learning_rate": 7.0888888888888894e-06,
|
| 414 |
+
"loss": 0.2307,
|
| 415 |
+
"step": 2900
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.3675762439807384,
|
| 419 |
+
"grad_norm": 15.397391319274902,
|
| 420 |
+
"learning_rate": 7.019444444444446e-06,
|
| 421 |
+
"loss": 0.211,
|
| 422 |
+
"step": 2950
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.407704654895666,
|
| 426 |
+
"grad_norm": 13.850847244262695,
|
| 427 |
+
"learning_rate": 6.95e-06,
|
| 428 |
+
"loss": 0.2115,
|
| 429 |
+
"step": 3000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.447833065810594,
|
| 433 |
+
"grad_norm": 10.497112274169922,
|
| 434 |
+
"learning_rate": 6.880555555555556e-06,
|
| 435 |
+
"loss": 0.2071,
|
| 436 |
+
"step": 3050
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.4879614767255216,
|
| 440 |
+
"grad_norm": 13.437689781188965,
|
| 441 |
+
"learning_rate": 6.811111111111111e-06,
|
| 442 |
+
"loss": 0.2085,
|
| 443 |
+
"step": 3100
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.5280898876404496,
|
| 447 |
+
"grad_norm": 17.070728302001953,
|
| 448 |
+
"learning_rate": 6.741666666666668e-06,
|
| 449 |
+
"loss": 0.2022,
|
| 450 |
+
"step": 3150
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.568218298555377,
|
| 454 |
+
"grad_norm": 14.102376937866211,
|
| 455 |
+
"learning_rate": 6.672222222222223e-06,
|
| 456 |
+
"loss": 0.2014,
|
| 457 |
+
"step": 3200
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.608346709470305,
|
| 461 |
+
"grad_norm": 12.899041175842285,
|
| 462 |
+
"learning_rate": 6.602777777777778e-06,
|
| 463 |
+
"loss": 0.2172,
|
| 464 |
+
"step": 3250
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.648475120385233,
|
| 468 |
+
"grad_norm": 15.379789352416992,
|
| 469 |
+
"learning_rate": 6.533333333333334e-06,
|
| 470 |
+
"loss": 0.2096,
|
| 471 |
+
"step": 3300
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.6886035313001604,
|
| 475 |
+
"grad_norm": 12.808381080627441,
|
| 476 |
+
"learning_rate": 6.4638888888888895e-06,
|
| 477 |
+
"loss": 0.2154,
|
| 478 |
+
"step": 3350
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.7287319422150884,
|
| 482 |
+
"grad_norm": 13.826408386230469,
|
| 483 |
+
"learning_rate": 6.394444444444445e-06,
|
| 484 |
+
"loss": 0.2176,
|
| 485 |
+
"step": 3400
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.768860353130016,
|
| 489 |
+
"grad_norm": 14.112689971923828,
|
| 490 |
+
"learning_rate": 6.3250000000000004e-06,
|
| 491 |
+
"loss": 0.2079,
|
| 492 |
+
"step": 3450
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.808988764044944,
|
| 496 |
+
"grad_norm": 11.431640625,
|
| 497 |
+
"learning_rate": 6.255555555555556e-06,
|
| 498 |
+
"loss": 0.2152,
|
| 499 |
+
"step": 3500
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.8491171749598716,
|
| 503 |
+
"grad_norm": 17.434322357177734,
|
| 504 |
+
"learning_rate": 6.186111111111111e-06,
|
| 505 |
+
"loss": 0.189,
|
| 506 |
+
"step": 3550
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.889245585874799,
|
| 510 |
+
"grad_norm": 15.394646644592285,
|
| 511 |
+
"learning_rate": 6.116666666666668e-06,
|
| 512 |
+
"loss": 0.2078,
|
| 513 |
+
"step": 3600
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.929373996789727,
|
| 517 |
+
"grad_norm": 19.227445602416992,
|
| 518 |
+
"learning_rate": 6.047222222222223e-06,
|
| 519 |
+
"loss": 0.2104,
|
| 520 |
+
"step": 3650
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.969502407704655,
|
| 524 |
+
"grad_norm": 14.099166870117188,
|
| 525 |
+
"learning_rate": 5.977777777777778e-06,
|
| 526 |
+
"loss": 0.2252,
|
| 527 |
+
"step": 3700
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 3.009630818619583,
|
| 531 |
+
"grad_norm": 11.261530876159668,
|
| 532 |
+
"learning_rate": 5.908333333333334e-06,
|
| 533 |
+
"loss": 0.1895,
|
| 534 |
+
"step": 3750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 3.0497592295345104,
|
| 538 |
+
"grad_norm": 8.676029205322266,
|
| 539 |
+
"learning_rate": 5.8388888888888895e-06,
|
| 540 |
+
"loss": 0.133,
|
| 541 |
+
"step": 3800
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 3.0898876404494384,
|
| 545 |
+
"grad_norm": 8.65832233428955,
|
| 546 |
+
"learning_rate": 5.769444444444445e-06,
|
| 547 |
+
"loss": 0.1152,
|
| 548 |
+
"step": 3850
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.130016051364366,
|
| 552 |
+
"grad_norm": 9.719037055969238,
|
| 553 |
+
"learning_rate": 5.7e-06,
|
| 554 |
+
"loss": 0.1261,
|
| 555 |
+
"step": 3900
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.1701444622792936,
|
| 559 |
+
"grad_norm": 12.145017623901367,
|
| 560 |
+
"learning_rate": 5.630555555555556e-06,
|
| 561 |
+
"loss": 0.1216,
|
| 562 |
+
"step": 3950
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 3.2102728731942216,
|
| 566 |
+
"grad_norm": 10.67035961151123,
|
| 567 |
+
"learning_rate": 5.561111111111111e-06,
|
| 568 |
+
"loss": 0.1341,
|
| 569 |
+
"step": 4000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.250401284109149,
|
| 573 |
+
"grad_norm": 13.00109577178955,
|
| 574 |
+
"learning_rate": 5.491666666666668e-06,
|
| 575 |
+
"loss": 0.1294,
|
| 576 |
+
"step": 4050
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.290529695024077,
|
| 580 |
+
"grad_norm": 34.79175567626953,
|
| 581 |
+
"learning_rate": 5.422222222222223e-06,
|
| 582 |
+
"loss": 0.1287,
|
| 583 |
+
"step": 4100
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 3.330658105939005,
|
| 587 |
+
"grad_norm": 8.047740936279297,
|
| 588 |
+
"learning_rate": 5.352777777777778e-06,
|
| 589 |
+
"loss": 0.1282,
|
| 590 |
+
"step": 4150
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.370786516853933,
|
| 594 |
+
"grad_norm": 10.46933364868164,
|
| 595 |
+
"learning_rate": 5.283333333333333e-06,
|
| 596 |
+
"loss": 0.126,
|
| 597 |
+
"step": 4200
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.4109149277688604,
|
| 601 |
+
"grad_norm": 9.083063125610352,
|
| 602 |
+
"learning_rate": 5.21388888888889e-06,
|
| 603 |
+
"loss": 0.1322,
|
| 604 |
+
"step": 4250
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.451043338683788,
|
| 608 |
+
"grad_norm": 10.835976600646973,
|
| 609 |
+
"learning_rate": 5.144444444444445e-06,
|
| 610 |
+
"loss": 0.1393,
|
| 611 |
+
"step": 4300
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.491171749598716,
|
| 615 |
+
"grad_norm": 9.417113304138184,
|
| 616 |
+
"learning_rate": 5.075e-06,
|
| 617 |
+
"loss": 0.1322,
|
| 618 |
+
"step": 4350
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 3.5313001605136436,
|
| 622 |
+
"grad_norm": 11.396635055541992,
|
| 623 |
+
"learning_rate": 5.005555555555556e-06,
|
| 624 |
+
"loss": 0.1369,
|
| 625 |
+
"step": 4400
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 3.571428571428571,
|
| 629 |
+
"grad_norm": 16.883840560913086,
|
| 630 |
+
"learning_rate": 4.9361111111111115e-06,
|
| 631 |
+
"loss": 0.1301,
|
| 632 |
+
"step": 4450
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.611556982343499,
|
| 636 |
+
"grad_norm": 16.863872528076172,
|
| 637 |
+
"learning_rate": 4.866666666666667e-06,
|
| 638 |
+
"loss": 0.1383,
|
| 639 |
+
"step": 4500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.6516853932584272,
|
| 643 |
+
"grad_norm": 11.84510612487793,
|
| 644 |
+
"learning_rate": 4.797222222222222e-06,
|
| 645 |
+
"loss": 0.1288,
|
| 646 |
+
"step": 4550
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.691813804173355,
|
| 650 |
+
"grad_norm": 10.211877822875977,
|
| 651 |
+
"learning_rate": 4.727777777777779e-06,
|
| 652 |
+
"loss": 0.1327,
|
| 653 |
+
"step": 4600
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.7319422150882824,
|
| 657 |
+
"grad_norm": 11.919416427612305,
|
| 658 |
+
"learning_rate": 4.658333333333333e-06,
|
| 659 |
+
"loss": 0.1306,
|
| 660 |
+
"step": 4650
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.7720706260032104,
|
| 664 |
+
"grad_norm": 10.668038368225098,
|
| 665 |
+
"learning_rate": 4.58888888888889e-06,
|
| 666 |
+
"loss": 0.1432,
|
| 667 |
+
"step": 4700
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.812199036918138,
|
| 671 |
+
"grad_norm": 9.114903450012207,
|
| 672 |
+
"learning_rate": 4.519444444444444e-06,
|
| 673 |
+
"loss": 0.1313,
|
| 674 |
+
"step": 4750
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.8523274478330656,
|
| 678 |
+
"grad_norm": 9.845243453979492,
|
| 679 |
+
"learning_rate": 4.450000000000001e-06,
|
| 680 |
+
"loss": 0.1351,
|
| 681 |
+
"step": 4800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.8924558587479936,
|
| 685 |
+
"grad_norm": 10.04245376586914,
|
| 686 |
+
"learning_rate": 4.380555555555556e-06,
|
| 687 |
+
"loss": 0.1242,
|
| 688 |
+
"step": 4850
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 3.932584269662921,
|
| 692 |
+
"grad_norm": 11.454913139343262,
|
| 693 |
+
"learning_rate": 4.3111111111111115e-06,
|
| 694 |
+
"loss": 0.1327,
|
| 695 |
+
"step": 4900
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.972712680577849,
|
| 699 |
+
"grad_norm": 9.704380989074707,
|
| 700 |
+
"learning_rate": 4.241666666666667e-06,
|
| 701 |
+
"loss": 0.136,
|
| 702 |
+
"step": 4950
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 4.012841091492777,
|
| 706 |
+
"grad_norm": 8.607508659362793,
|
| 707 |
+
"learning_rate": 4.1722222222222225e-06,
|
| 708 |
+
"loss": 0.1057,
|
| 709 |
+
"step": 5000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 4.052969502407705,
|
| 713 |
+
"grad_norm": 9.908164024353027,
|
| 714 |
+
"learning_rate": 4.102777777777778e-06,
|
| 715 |
+
"loss": 0.0793,
|
| 716 |
+
"step": 5050
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 4.093097913322633,
|
| 720 |
+
"grad_norm": 9.310582160949707,
|
| 721 |
+
"learning_rate": 4.033333333333333e-06,
|
| 722 |
+
"loss": 0.0819,
|
| 723 |
+
"step": 5100
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 4.13322632423756,
|
| 727 |
+
"grad_norm": 8.358500480651855,
|
| 728 |
+
"learning_rate": 3.96388888888889e-06,
|
| 729 |
+
"loss": 0.0713,
|
| 730 |
+
"step": 5150
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 4.173354735152488,
|
| 734 |
+
"grad_norm": 10.421764373779297,
|
| 735 |
+
"learning_rate": 3.894444444444444e-06,
|
| 736 |
+
"loss": 0.0882,
|
| 737 |
+
"step": 5200
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 4.213483146067416,
|
| 741 |
+
"grad_norm": 9.101556777954102,
|
| 742 |
+
"learning_rate": 3.825000000000001e-06,
|
| 743 |
+
"loss": 0.0795,
|
| 744 |
+
"step": 5250
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 4.253611556982343,
|
| 748 |
+
"grad_norm": 8.120292663574219,
|
| 749 |
+
"learning_rate": 3.7555555555555557e-06,
|
| 750 |
+
"loss": 0.0837,
|
| 751 |
+
"step": 5300
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 4.293739967897271,
|
| 755 |
+
"grad_norm": 7.72833251953125,
|
| 756 |
+
"learning_rate": 3.6861111111111116e-06,
|
| 757 |
+
"loss": 0.0834,
|
| 758 |
+
"step": 5350
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 4.333868378812199,
|
| 762 |
+
"grad_norm": 8.289836883544922,
|
| 763 |
+
"learning_rate": 3.616666666666667e-06,
|
| 764 |
+
"loss": 0.0787,
|
| 765 |
+
"step": 5400
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 4.373996789727126,
|
| 769 |
+
"grad_norm": 11.09408950805664,
|
| 770 |
+
"learning_rate": 3.5472222222222225e-06,
|
| 771 |
+
"loss": 0.0838,
|
| 772 |
+
"step": 5450
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 4.414125200642054,
|
| 776 |
+
"grad_norm": 5.381303310394287,
|
| 777 |
+
"learning_rate": 3.4777777777777784e-06,
|
| 778 |
+
"loss": 0.08,
|
| 779 |
+
"step": 5500
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 4.454253611556982,
|
| 783 |
+
"grad_norm": 7.058831214904785,
|
| 784 |
+
"learning_rate": 3.4083333333333335e-06,
|
| 785 |
+
"loss": 0.0811,
|
| 786 |
+
"step": 5550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 4.49438202247191,
|
| 790 |
+
"grad_norm": 7.9168620109558105,
|
| 791 |
+
"learning_rate": 3.3388888888888893e-06,
|
| 792 |
+
"loss": 0.0796,
|
| 793 |
+
"step": 5600
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 4.534510433386838,
|
| 797 |
+
"grad_norm": 8.293107032775879,
|
| 798 |
+
"learning_rate": 3.2694444444444444e-06,
|
| 799 |
+
"loss": 0.0765,
|
| 800 |
+
"step": 5650
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 4.574638844301766,
|
| 804 |
+
"grad_norm": 14.970193862915039,
|
| 805 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 806 |
+
"loss": 0.0786,
|
| 807 |
+
"step": 5700
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 4.614767255216694,
|
| 811 |
+
"grad_norm": 7.619186878204346,
|
| 812 |
+
"learning_rate": 3.1305555555555557e-06,
|
| 813 |
+
"loss": 0.079,
|
| 814 |
+
"step": 5750
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 4.654895666131621,
|
| 818 |
+
"grad_norm": 7.955104827880859,
|
| 819 |
+
"learning_rate": 3.0611111111111112e-06,
|
| 820 |
+
"loss": 0.0814,
|
| 821 |
+
"step": 5800
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 4.695024077046549,
|
| 825 |
+
"grad_norm": 6.463953971862793,
|
| 826 |
+
"learning_rate": 2.991666666666667e-06,
|
| 827 |
+
"loss": 0.0846,
|
| 828 |
+
"step": 5850
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 4.735152487961477,
|
| 832 |
+
"grad_norm": 7.264988422393799,
|
| 833 |
+
"learning_rate": 2.9222222222222226e-06,
|
| 834 |
+
"loss": 0.0846,
|
| 835 |
+
"step": 5900
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 4.775280898876405,
|
| 839 |
+
"grad_norm": 9.477662086486816,
|
| 840 |
+
"learning_rate": 2.852777777777778e-06,
|
| 841 |
+
"loss": 0.0737,
|
| 842 |
+
"step": 5950
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 4.815409309791332,
|
| 846 |
+
"grad_norm": 7.392651557922363,
|
| 847 |
+
"learning_rate": 2.7833333333333335e-06,
|
| 848 |
+
"loss": 0.0819,
|
| 849 |
+
"step": 6000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 4.85553772070626,
|
| 853 |
+
"grad_norm": 7.89952278137207,
|
| 854 |
+
"learning_rate": 2.7138888888888894e-06,
|
| 855 |
+
"loss": 0.0733,
|
| 856 |
+
"step": 6050
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 4.895666131621188,
|
| 860 |
+
"grad_norm": 9.701936721801758,
|
| 861 |
+
"learning_rate": 2.6444444444444444e-06,
|
| 862 |
+
"loss": 0.0766,
|
| 863 |
+
"step": 6100
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 4.935794542536115,
|
| 867 |
+
"grad_norm": 9.0658540725708,
|
| 868 |
+
"learning_rate": 2.5750000000000003e-06,
|
| 869 |
+
"loss": 0.0719,
|
| 870 |
+
"step": 6150
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 4.975922953451043,
|
| 874 |
+
"grad_norm": 8.084450721740723,
|
| 875 |
+
"learning_rate": 2.5055555555555554e-06,
|
| 876 |
+
"loss": 0.0797,
|
| 877 |
+
"step": 6200
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 5.016051364365971,
|
| 881 |
+
"grad_norm": 9.634577751159668,
|
| 882 |
+
"learning_rate": 2.4361111111111113e-06,
|
| 883 |
+
"loss": 0.0728,
|
| 884 |
+
"step": 6250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 5.056179775280899,
|
| 888 |
+
"grad_norm": 6.3712921142578125,
|
| 889 |
+
"learning_rate": 2.3666666666666667e-06,
|
| 890 |
+
"loss": 0.0492,
|
| 891 |
+
"step": 6300
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 5.096308186195826,
|
| 895 |
+
"grad_norm": 5.370436191558838,
|
| 896 |
+
"learning_rate": 2.297222222222222e-06,
|
| 897 |
+
"loss": 0.0462,
|
| 898 |
+
"step": 6350
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 5.136436597110754,
|
| 902 |
+
"grad_norm": 5.955212116241455,
|
| 903 |
+
"learning_rate": 2.2277777777777777e-06,
|
| 904 |
+
"loss": 0.0458,
|
| 905 |
+
"step": 6400
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 5.176565008025682,
|
| 909 |
+
"grad_norm": 5.898159503936768,
|
| 910 |
+
"learning_rate": 2.1583333333333336e-06,
|
| 911 |
+
"loss": 0.0521,
|
| 912 |
+
"step": 6450
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 5.21669341894061,
|
| 916 |
+
"grad_norm": 4.376798152923584,
|
| 917 |
+
"learning_rate": 2.088888888888889e-06,
|
| 918 |
+
"loss": 0.0539,
|
| 919 |
+
"step": 6500
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 5.256821829855538,
|
| 923 |
+
"grad_norm": 8.122651100158691,
|
| 924 |
+
"learning_rate": 2.0194444444444445e-06,
|
| 925 |
+
"loss": 0.0532,
|
| 926 |
+
"step": 6550
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 5.296950240770466,
|
| 930 |
+
"grad_norm": 6.136049270629883,
|
| 931 |
+
"learning_rate": 1.9500000000000004e-06,
|
| 932 |
+
"loss": 0.049,
|
| 933 |
+
"step": 6600
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 5.337078651685394,
|
| 937 |
+
"grad_norm": 4.084792613983154,
|
| 938 |
+
"learning_rate": 1.8805555555555556e-06,
|
| 939 |
+
"loss": 0.0606,
|
| 940 |
+
"step": 6650
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 5.377207062600321,
|
| 944 |
+
"grad_norm": 10.023465156555176,
|
| 945 |
+
"learning_rate": 1.8111111111111113e-06,
|
| 946 |
+
"loss": 0.0528,
|
| 947 |
+
"step": 6700
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 5.417335473515249,
|
| 951 |
+
"grad_norm": 7.965837478637695,
|
| 952 |
+
"learning_rate": 1.7416666666666668e-06,
|
| 953 |
+
"loss": 0.0495,
|
| 954 |
+
"step": 6750
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 5.457463884430177,
|
| 958 |
+
"grad_norm": 4.469130516052246,
|
| 959 |
+
"learning_rate": 1.6722222222222223e-06,
|
| 960 |
+
"loss": 0.0498,
|
| 961 |
+
"step": 6800
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 5.497592295345104,
|
| 965 |
+
"grad_norm": 7.078831672668457,
|
| 966 |
+
"learning_rate": 1.6027777777777777e-06,
|
| 967 |
+
"loss": 0.0553,
|
| 968 |
+
"step": 6850
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 5.537720706260032,
|
| 972 |
+
"grad_norm": 6.6740336418151855,
|
| 973 |
+
"learning_rate": 1.5333333333333334e-06,
|
| 974 |
+
"loss": 0.0476,
|
| 975 |
+
"step": 6900
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 5.57784911717496,
|
| 979 |
+
"grad_norm": 4.432163715362549,
|
| 980 |
+
"learning_rate": 1.463888888888889e-06,
|
| 981 |
+
"loss": 0.0482,
|
| 982 |
+
"step": 6950
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 5.617977528089888,
|
| 986 |
+
"grad_norm": 7.402093410491943,
|
| 987 |
+
"learning_rate": 1.3944444444444446e-06,
|
| 988 |
+
"loss": 0.043,
|
| 989 |
+
"step": 7000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 5.658105939004815,
|
| 993 |
+
"grad_norm": 5.417418003082275,
|
| 994 |
+
"learning_rate": 1.3250000000000002e-06,
|
| 995 |
+
"loss": 0.0438,
|
| 996 |
+
"step": 7050
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 5.698234349919743,
|
| 1000 |
+
"grad_norm": 5.910097599029541,
|
| 1001 |
+
"learning_rate": 1.2555555555555557e-06,
|
| 1002 |
+
"loss": 0.0456,
|
| 1003 |
+
"step": 7100
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 5.738362760834671,
|
| 1007 |
+
"grad_norm": 7.781131744384766,
|
| 1008 |
+
"learning_rate": 1.1861111111111112e-06,
|
| 1009 |
+
"loss": 0.0504,
|
| 1010 |
+
"step": 7150
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 5.778491171749598,
|
| 1014 |
+
"grad_norm": 7.682769298553467,
|
| 1015 |
+
"learning_rate": 1.1166666666666666e-06,
|
| 1016 |
+
"loss": 0.0543,
|
| 1017 |
+
"step": 7200
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 5.818619582664526,
|
| 1021 |
+
"grad_norm": 5.041004657745361,
|
| 1022 |
+
"learning_rate": 1.0472222222222223e-06,
|
| 1023 |
+
"loss": 0.0477,
|
| 1024 |
+
"step": 7250
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 5.858747993579454,
|
| 1028 |
+
"grad_norm": 5.9667158126831055,
|
| 1029 |
+
"learning_rate": 9.77777777777778e-07,
|
| 1030 |
+
"loss": 0.0472,
|
| 1031 |
+
"step": 7300
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 5.898876404494382,
|
| 1035 |
+
"grad_norm": 7.793878555297852,
|
| 1036 |
+
"learning_rate": 9.083333333333335e-07,
|
| 1037 |
+
"loss": 0.0507,
|
| 1038 |
+
"step": 7350
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 5.93900481540931,
|
| 1042 |
+
"grad_norm": 7.589353561401367,
|
| 1043 |
+
"learning_rate": 8.388888888888889e-07,
|
| 1044 |
+
"loss": 0.0588,
|
| 1045 |
+
"step": 7400
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 5.979133226324238,
|
| 1049 |
+
"grad_norm": 6.20251989364624,
|
| 1050 |
+
"learning_rate": 7.694444444444445e-07,
|
| 1051 |
+
"loss": 0.0499,
|
| 1052 |
+
"step": 7450
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 6.019261637239166,
|
| 1056 |
+
"grad_norm": 6.208334445953369,
|
| 1057 |
+
"learning_rate": 7.000000000000001e-07,
|
| 1058 |
+
"loss": 0.0441,
|
| 1059 |
+
"step": 7500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 6.059390048154093,
|
| 1063 |
+
"grad_norm": 4.3427324295043945,
|
| 1064 |
+
"learning_rate": 6.305555555555556e-07,
|
| 1065 |
+
"loss": 0.0404,
|
| 1066 |
+
"step": 7550
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 6.099518459069021,
|
| 1070 |
+
"grad_norm": 5.3076581954956055,
|
| 1071 |
+
"learning_rate": 5.611111111111111e-07,
|
| 1072 |
+
"loss": 0.0363,
|
| 1073 |
+
"step": 7600
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 6.139646869983949,
|
| 1077 |
+
"grad_norm": 3.9682233333587646,
|
| 1078 |
+
"learning_rate": 4.916666666666667e-07,
|
| 1079 |
+
"loss": 0.0382,
|
| 1080 |
+
"step": 7650
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 6.179775280898877,
|
| 1084 |
+
"grad_norm": 5.612052917480469,
|
| 1085 |
+
"learning_rate": 4.2222222222222226e-07,
|
| 1086 |
+
"loss": 0.0411,
|
| 1087 |
+
"step": 7700
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 6.219903691813804,
|
| 1091 |
+
"grad_norm": 4.144915580749512,
|
| 1092 |
+
"learning_rate": 3.527777777777778e-07,
|
| 1093 |
+
"loss": 0.0358,
|
| 1094 |
+
"step": 7750
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 6.260032102728732,
|
| 1098 |
+
"grad_norm": 7.28611946105957,
|
| 1099 |
+
"learning_rate": 2.8333333333333336e-07,
|
| 1100 |
+
"loss": 0.035,
|
| 1101 |
+
"step": 7800
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 6.30016051364366,
|
| 1105 |
+
"grad_norm": 4.628722667694092,
|
| 1106 |
+
"learning_rate": 2.138888888888889e-07,
|
| 1107 |
+
"loss": 0.0371,
|
| 1108 |
+
"step": 7850
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 6.340288924558587,
|
| 1112 |
+
"grad_norm": 5.527387619018555,
|
| 1113 |
+
"learning_rate": 1.4444444444444445e-07,
|
| 1114 |
+
"loss": 0.0377,
|
| 1115 |
+
"step": 7900
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 6.380417335473515,
|
| 1119 |
+
"grad_norm": 4.704113006591797,
|
| 1120 |
+
"learning_rate": 7.500000000000001e-08,
|
| 1121 |
+
"loss": 0.0352,
|
| 1122 |
+
"step": 7950
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 6.420545746388443,
|
| 1126 |
+
"grad_norm": 4.203430652618408,
|
| 1127 |
+
"learning_rate": 5.555555555555556e-09,
|
| 1128 |
+
"loss": 0.0341,
|
| 1129 |
+
"step": 8000
|
| 1130 |
+
}
|
| 1131 |
+
],
|
| 1132 |
+
"logging_steps": 50,
|
| 1133 |
+
"max_steps": 8000,
|
| 1134 |
+
"num_input_tokens_seen": 0,
|
| 1135 |
+
"num_train_epochs": 7,
|
| 1136 |
+
"save_steps": 500,
|
| 1137 |
+
"stateful_callbacks": {
|
| 1138 |
+
"TrainerControl": {
|
| 1139 |
+
"args": {
|
| 1140 |
+
"should_epoch_stop": false,
|
| 1141 |
+
"should_evaluate": false,
|
| 1142 |
+
"should_log": false,
|
| 1143 |
+
"should_save": true,
|
| 1144 |
+
"should_training_stop": true
|
| 1145 |
+
},
|
| 1146 |
+
"attributes": {}
|
| 1147 |
+
}
|
| 1148 |
+
},
|
| 1149 |
+
"total_flos": 7.38692049199104e+19,
|
| 1150 |
+
"train_batch_size": 8,
|
| 1151 |
+
"trial_name": null,
|
| 1152 |
+
"trial_params": null
|
| 1153 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f451e135413b22d7c470c5a165d3327f71dbe79015c7034177bd13b9330b8edc
|
| 3 |
+
size 5432
|