Upload 9 files
Browse fileswhisper tiny finetuned on 10% of common voice Italian
- checkpoint-2385/config.json +61 -0
- checkpoint-2385/generation_config.json +248 -0
- checkpoint-2385/model.safetensors +3 -0
- checkpoint-2385/optimizer.pt +3 -0
- checkpoint-2385/preprocessor_config.json +14 -0
- checkpoint-2385/rng_state.pth +3 -0
- checkpoint-2385/scheduler.pt +3 -0
- checkpoint-2385/trainer_state.json +1739 -0
- checkpoint-2385/training_args.bin +3 -0
checkpoint-2385/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-tiny",
|
| 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": 384,
|
| 14 |
+
"decoder_attention_heads": 6,
|
| 15 |
+
"decoder_ffn_dim": 1536,
|
| 16 |
+
"decoder_layerdrop": 0.0,
|
| 17 |
+
"decoder_layers": 4,
|
| 18 |
+
"decoder_start_token_id": 50258,
|
| 19 |
+
"dropout": 0.0,
|
| 20 |
+
"encoder_attention_heads": 6,
|
| 21 |
+
"encoder_ffn_dim": 1536,
|
| 22 |
+
"encoder_layerdrop": 0.0,
|
| 23 |
+
"encoder_layers": 4,
|
| 24 |
+
"eos_token_id": 50257,
|
| 25 |
+
"forced_decoder_ids": [
|
| 26 |
+
[
|
| 27 |
+
1,
|
| 28 |
+
50274
|
| 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": 4,
|
| 53 |
+
"num_mel_bins": 80,
|
| 54 |
+
"pad_token_id": 50257,
|
| 55 |
+
"scale_embedding": false,
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.48.3",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"use_weighted_layer_sum": false,
|
| 60 |
+
"vocab_size": 51865
|
| 61 |
+
}
|
checkpoint-2385/generation_config.json
ADDED
|
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
2,
|
| 5 |
+
2
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
3,
|
| 9 |
+
0
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
3,
|
| 13 |
+
2
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
3,
|
| 17 |
+
3
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
3,
|
| 21 |
+
4
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
3,
|
| 25 |
+
5
|
| 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": "4.48.3"
|
| 248 |
+
}
|
checkpoint-2385/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ad64b9c5ea44d2284d3ae970552bc46e489f8702c67956abb196cd2f9b73dce
|
| 3 |
+
size 151061672
|
checkpoint-2385/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9a881644bf34dce16916622d4920a41f6d9bc992858b107c974da3e4cd85310
|
| 3 |
+
size 297616186
|
checkpoint-2385/preprocessor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 4 |
+
"feature_size": 80,
|
| 5 |
+
"hop_length": 160,
|
| 6 |
+
"n_fft": 400,
|
| 7 |
+
"n_samples": 480000,
|
| 8 |
+
"nb_max_frames": 3000,
|
| 9 |
+
"padding_side": "right",
|
| 10 |
+
"padding_value": 0.0,
|
| 11 |
+
"processor_class": "WhisperProcessor",
|
| 12 |
+
"return_attention_mask": false,
|
| 13 |
+
"sampling_rate": 16000
|
| 14 |
+
}
|
checkpoint-2385/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbb353e49063091e2970f0aeb14ab8a120ae2cca1852d84c476d38cb92ac2e00
|
| 3 |
+
size 14244
|
checkpoint-2385/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b56d351882ecfb811edd2cbfb9bbe6e2df2b21a05f965ade2e469bdd9b4de9f
|
| 3 |
+
size 1064
|
checkpoint-2385/trainer_state.json
ADDED
|
@@ -0,0 +1,1739 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2385,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.020964360587002098,
|
| 13 |
+
"grad_norm": 3.998500347137451,
|
| 14 |
+
"learning_rate": 9.958071278825997e-05,
|
| 15 |
+
"loss": 0.1821,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.041928721174004195,
|
| 20 |
+
"grad_norm": 4.23317813873291,
|
| 21 |
+
"learning_rate": 9.916142557651992e-05,
|
| 22 |
+
"loss": 0.1617,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06289308176100629,
|
| 27 |
+
"grad_norm": 4.348649024963379,
|
| 28 |
+
"learning_rate": 9.874213836477988e-05,
|
| 29 |
+
"loss": 0.1799,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08385744234800839,
|
| 34 |
+
"grad_norm": 4.8091020584106445,
|
| 35 |
+
"learning_rate": 9.832285115303984e-05,
|
| 36 |
+
"loss": 0.2127,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.10482180293501048,
|
| 41 |
+
"grad_norm": 4.523597240447998,
|
| 42 |
+
"learning_rate": 9.790356394129979e-05,
|
| 43 |
+
"loss": 0.2195,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12578616352201258,
|
| 48 |
+
"grad_norm": 6.083479404449463,
|
| 49 |
+
"learning_rate": 9.748427672955975e-05,
|
| 50 |
+
"loss": 0.2142,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.14675052410901468,
|
| 55 |
+
"grad_norm": 5.268312454223633,
|
| 56 |
+
"learning_rate": 9.706498951781971e-05,
|
| 57 |
+
"loss": 0.2293,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.16771488469601678,
|
| 62 |
+
"grad_norm": 5.908782482147217,
|
| 63 |
+
"learning_rate": 9.664570230607967e-05,
|
| 64 |
+
"loss": 0.2391,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.18867924528301888,
|
| 69 |
+
"grad_norm": 5.333123207092285,
|
| 70 |
+
"learning_rate": 9.622641509433963e-05,
|
| 71 |
+
"loss": 0.2519,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.20964360587002095,
|
| 76 |
+
"grad_norm": 4.541295051574707,
|
| 77 |
+
"learning_rate": 9.58071278825996e-05,
|
| 78 |
+
"loss": 0.241,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.23060796645702306,
|
| 83 |
+
"grad_norm": 5.367836952209473,
|
| 84 |
+
"learning_rate": 9.538784067085954e-05,
|
| 85 |
+
"loss": 0.2516,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.25157232704402516,
|
| 90 |
+
"grad_norm": 4.476315975189209,
|
| 91 |
+
"learning_rate": 9.496855345911951e-05,
|
| 92 |
+
"loss": 0.2581,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.27253668763102723,
|
| 97 |
+
"grad_norm": 4.104060173034668,
|
| 98 |
+
"learning_rate": 9.454926624737947e-05,
|
| 99 |
+
"loss": 0.2612,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.29350104821802936,
|
| 104 |
+
"grad_norm": 5.152798652648926,
|
| 105 |
+
"learning_rate": 9.412997903563942e-05,
|
| 106 |
+
"loss": 0.2736,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.31446540880503143,
|
| 111 |
+
"grad_norm": 4.785223960876465,
|
| 112 |
+
"learning_rate": 9.371069182389938e-05,
|
| 113 |
+
"loss": 0.267,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.33542976939203356,
|
| 118 |
+
"grad_norm": 4.769683837890625,
|
| 119 |
+
"learning_rate": 9.329140461215934e-05,
|
| 120 |
+
"loss": 0.2766,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.35639412997903563,
|
| 125 |
+
"grad_norm": 4.8373942375183105,
|
| 126 |
+
"learning_rate": 9.287211740041929e-05,
|
| 127 |
+
"loss": 0.2878,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.37735849056603776,
|
| 132 |
+
"grad_norm": 4.6672515869140625,
|
| 133 |
+
"learning_rate": 9.245283018867925e-05,
|
| 134 |
+
"loss": 0.2748,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.39832285115303984,
|
| 139 |
+
"grad_norm": 7.549396514892578,
|
| 140 |
+
"learning_rate": 9.203354297693921e-05,
|
| 141 |
+
"loss": 0.264,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4192872117400419,
|
| 146 |
+
"grad_norm": 6.70684289932251,
|
| 147 |
+
"learning_rate": 9.161425576519916e-05,
|
| 148 |
+
"loss": 0.2843,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.44025157232704404,
|
| 153 |
+
"grad_norm": 5.79678201675415,
|
| 154 |
+
"learning_rate": 9.119496855345912e-05,
|
| 155 |
+
"loss": 0.2907,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.4612159329140461,
|
| 160 |
+
"grad_norm": 6.699160575866699,
|
| 161 |
+
"learning_rate": 9.077568134171907e-05,
|
| 162 |
+
"loss": 0.2678,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.48218029350104824,
|
| 167 |
+
"grad_norm": 4.357872486114502,
|
| 168 |
+
"learning_rate": 9.035639412997903e-05,
|
| 169 |
+
"loss": 0.2965,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5031446540880503,
|
| 174 |
+
"grad_norm": 5.521259307861328,
|
| 175 |
+
"learning_rate": 8.9937106918239e-05,
|
| 176 |
+
"loss": 0.2876,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5241090146750524,
|
| 181 |
+
"grad_norm": 6.627674579620361,
|
| 182 |
+
"learning_rate": 8.951781970649896e-05,
|
| 183 |
+
"loss": 0.2825,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5450733752620545,
|
| 188 |
+
"grad_norm": 5.5945634841918945,
|
| 189 |
+
"learning_rate": 8.909853249475892e-05,
|
| 190 |
+
"loss": 0.2855,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5660377358490566,
|
| 195 |
+
"grad_norm": 4.596319198608398,
|
| 196 |
+
"learning_rate": 8.867924528301888e-05,
|
| 197 |
+
"loss": 0.2753,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5870020964360587,
|
| 202 |
+
"grad_norm": 5.92698860168457,
|
| 203 |
+
"learning_rate": 8.825995807127883e-05,
|
| 204 |
+
"loss": 0.3076,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6079664570230608,
|
| 209 |
+
"grad_norm": 4.971231937408447,
|
| 210 |
+
"learning_rate": 8.784067085953879e-05,
|
| 211 |
+
"loss": 0.2945,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6289308176100629,
|
| 216 |
+
"grad_norm": 5.803814888000488,
|
| 217 |
+
"learning_rate": 8.742138364779875e-05,
|
| 218 |
+
"loss": 0.3121,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.649895178197065,
|
| 223 |
+
"grad_norm": 4.640927314758301,
|
| 224 |
+
"learning_rate": 8.70020964360587e-05,
|
| 225 |
+
"loss": 0.2965,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6708595387840671,
|
| 230 |
+
"grad_norm": 4.943049430847168,
|
| 231 |
+
"learning_rate": 8.662473794549267e-05,
|
| 232 |
+
"loss": 0.2814,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6918238993710691,
|
| 237 |
+
"grad_norm": 18.59223175048828,
|
| 238 |
+
"learning_rate": 8.620545073375263e-05,
|
| 239 |
+
"loss": 0.2998,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7127882599580713,
|
| 244 |
+
"grad_norm": 4.966686725616455,
|
| 245 |
+
"learning_rate": 8.578616352201259e-05,
|
| 246 |
+
"loss": 0.282,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7337526205450734,
|
| 251 |
+
"grad_norm": 6.274560451507568,
|
| 252 |
+
"learning_rate": 8.536687631027254e-05,
|
| 253 |
+
"loss": 0.3123,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.7547169811320755,
|
| 258 |
+
"grad_norm": 5.680440902709961,
|
| 259 |
+
"learning_rate": 8.49475890985325e-05,
|
| 260 |
+
"loss": 0.2915,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.7756813417190775,
|
| 265 |
+
"grad_norm": 5.426858425140381,
|
| 266 |
+
"learning_rate": 8.452830188679246e-05,
|
| 267 |
+
"loss": 0.3192,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.7966457023060797,
|
| 272 |
+
"grad_norm": 5.293428421020508,
|
| 273 |
+
"learning_rate": 8.410901467505241e-05,
|
| 274 |
+
"loss": 0.3207,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8176100628930818,
|
| 279 |
+
"grad_norm": 5.778203964233398,
|
| 280 |
+
"learning_rate": 8.368972746331237e-05,
|
| 281 |
+
"loss": 0.3202,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.8385744234800838,
|
| 286 |
+
"grad_norm": 5.326625347137451,
|
| 287 |
+
"learning_rate": 8.327044025157233e-05,
|
| 288 |
+
"loss": 0.3088,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.859538784067086,
|
| 293 |
+
"grad_norm": 5.26389217376709,
|
| 294 |
+
"learning_rate": 8.285115303983228e-05,
|
| 295 |
+
"loss": 0.3084,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8805031446540881,
|
| 300 |
+
"grad_norm": 5.999328136444092,
|
| 301 |
+
"learning_rate": 8.243186582809224e-05,
|
| 302 |
+
"loss": 0.2822,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.9014675052410901,
|
| 307 |
+
"grad_norm": 5.0098958015441895,
|
| 308 |
+
"learning_rate": 8.20125786163522e-05,
|
| 309 |
+
"loss": 0.307,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.9224318658280922,
|
| 314 |
+
"grad_norm": 6.384605407714844,
|
| 315 |
+
"learning_rate": 8.159329140461215e-05,
|
| 316 |
+
"loss": 0.2976,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.9433962264150944,
|
| 321 |
+
"grad_norm": 9.32125186920166,
|
| 322 |
+
"learning_rate": 8.117400419287212e-05,
|
| 323 |
+
"loss": 0.3198,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.9643605870020965,
|
| 328 |
+
"grad_norm": 4.630229949951172,
|
| 329 |
+
"learning_rate": 8.075471698113208e-05,
|
| 330 |
+
"loss": 0.3031,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.9853249475890985,
|
| 335 |
+
"grad_norm": 4.775624752044678,
|
| 336 |
+
"learning_rate": 8.033542976939204e-05,
|
| 337 |
+
"loss": 0.2676,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.0,
|
| 342 |
+
"eval_loss": 0.6731473207473755,
|
| 343 |
+
"eval_runtime": 20.7096,
|
| 344 |
+
"eval_samples_per_second": 72.43,
|
| 345 |
+
"eval_steps_per_second": 9.078,
|
| 346 |
+
"step": 477
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.0062893081761006,
|
| 350 |
+
"grad_norm": 1.9550973176956177,
|
| 351 |
+
"learning_rate": 7.9916142557652e-05,
|
| 352 |
+
"loss": 0.2451,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.0272536687631026,
|
| 357 |
+
"grad_norm": 3.6781623363494873,
|
| 358 |
+
"learning_rate": 7.949685534591196e-05,
|
| 359 |
+
"loss": 0.1127,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.0482180293501049,
|
| 364 |
+
"grad_norm": 3.6007821559906006,
|
| 365 |
+
"learning_rate": 7.907756813417191e-05,
|
| 366 |
+
"loss": 0.1089,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.069182389937107,
|
| 371 |
+
"grad_norm": 3.0092623233795166,
|
| 372 |
+
"learning_rate": 7.865828092243187e-05,
|
| 373 |
+
"loss": 0.1203,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.090146750524109,
|
| 378 |
+
"grad_norm": 2.852006196975708,
|
| 379 |
+
"learning_rate": 7.823899371069184e-05,
|
| 380 |
+
"loss": 0.1126,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.1111111111111112,
|
| 385 |
+
"grad_norm": 3.5420737266540527,
|
| 386 |
+
"learning_rate": 7.781970649895178e-05,
|
| 387 |
+
"loss": 0.1254,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.1320754716981132,
|
| 392 |
+
"grad_norm": 3.2206077575683594,
|
| 393 |
+
"learning_rate": 7.740041928721175e-05,
|
| 394 |
+
"loss": 0.1328,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.1530398322851152,
|
| 399 |
+
"grad_norm": 3.895273447036743,
|
| 400 |
+
"learning_rate": 7.698113207547171e-05,
|
| 401 |
+
"loss": 0.125,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.1740041928721174,
|
| 406 |
+
"grad_norm": 3.2703685760498047,
|
| 407 |
+
"learning_rate": 7.656184486373166e-05,
|
| 408 |
+
"loss": 0.1306,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.1949685534591195,
|
| 413 |
+
"grad_norm": 2.977438449859619,
|
| 414 |
+
"learning_rate": 7.614255765199162e-05,
|
| 415 |
+
"loss": 0.1261,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.2159329140461215,
|
| 420 |
+
"grad_norm": 3.917140007019043,
|
| 421 |
+
"learning_rate": 7.572327044025158e-05,
|
| 422 |
+
"loss": 0.1232,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.2368972746331237,
|
| 427 |
+
"grad_norm": 4.090723514556885,
|
| 428 |
+
"learning_rate": 7.530398322851153e-05,
|
| 429 |
+
"loss": 0.1374,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.2578616352201257,
|
| 434 |
+
"grad_norm": 3.666203737258911,
|
| 435 |
+
"learning_rate": 7.488469601677149e-05,
|
| 436 |
+
"loss": 0.1317,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.2788259958071277,
|
| 441 |
+
"grad_norm": 4.610381126403809,
|
| 442 |
+
"learning_rate": 7.446540880503144e-05,
|
| 443 |
+
"loss": 0.1276,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.29979035639413,
|
| 448 |
+
"grad_norm": 5.928828716278076,
|
| 449 |
+
"learning_rate": 7.40461215932914e-05,
|
| 450 |
+
"loss": 0.1258,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.320754716981132,
|
| 455 |
+
"grad_norm": 4.312713623046875,
|
| 456 |
+
"learning_rate": 7.362683438155136e-05,
|
| 457 |
+
"loss": 0.1318,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.3417190775681342,
|
| 462 |
+
"grad_norm": 3.831658363342285,
|
| 463 |
+
"learning_rate": 7.320754716981132e-05,
|
| 464 |
+
"loss": 0.1217,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.3626834381551363,
|
| 469 |
+
"grad_norm": 2.7465438842773438,
|
| 470 |
+
"learning_rate": 7.278825995807129e-05,
|
| 471 |
+
"loss": 0.1157,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.3836477987421385,
|
| 476 |
+
"grad_norm": 2.915738582611084,
|
| 477 |
+
"learning_rate": 7.236897274633125e-05,
|
| 478 |
+
"loss": 0.1414,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.4046121593291405,
|
| 483 |
+
"grad_norm": 3.2107832431793213,
|
| 484 |
+
"learning_rate": 7.19496855345912e-05,
|
| 485 |
+
"loss": 0.1253,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.4255765199161425,
|
| 490 |
+
"grad_norm": 3.7944188117980957,
|
| 491 |
+
"learning_rate": 7.153039832285116e-05,
|
| 492 |
+
"loss": 0.1249,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.4465408805031448,
|
| 497 |
+
"grad_norm": 3.0400636196136475,
|
| 498 |
+
"learning_rate": 7.111111111111112e-05,
|
| 499 |
+
"loss": 0.1323,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.4675052410901468,
|
| 504 |
+
"grad_norm": 3.911773443222046,
|
| 505 |
+
"learning_rate": 7.069182389937107e-05,
|
| 506 |
+
"loss": 0.1265,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.4884696016771488,
|
| 511 |
+
"grad_norm": 4.3404765129089355,
|
| 512 |
+
"learning_rate": 7.027253668763103e-05,
|
| 513 |
+
"loss": 0.1328,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.509433962264151,
|
| 518 |
+
"grad_norm": 3.5862231254577637,
|
| 519 |
+
"learning_rate": 6.985324947589099e-05,
|
| 520 |
+
"loss": 0.1336,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.530398322851153,
|
| 525 |
+
"grad_norm": 4.099681377410889,
|
| 526 |
+
"learning_rate": 6.943396226415094e-05,
|
| 527 |
+
"loss": 0.1345,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.551362683438155,
|
| 532 |
+
"grad_norm": 4.485490322113037,
|
| 533 |
+
"learning_rate": 6.90146750524109e-05,
|
| 534 |
+
"loss": 0.1368,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.5723270440251573,
|
| 539 |
+
"grad_norm": 3.4771294593811035,
|
| 540 |
+
"learning_rate": 6.859538784067086e-05,
|
| 541 |
+
"loss": 0.1197,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.5932914046121593,
|
| 546 |
+
"grad_norm": 3.602762460708618,
|
| 547 |
+
"learning_rate": 6.817610062893081e-05,
|
| 548 |
+
"loss": 0.125,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.6142557651991614,
|
| 553 |
+
"grad_norm": 3.6131410598754883,
|
| 554 |
+
"learning_rate": 6.775681341719077e-05,
|
| 555 |
+
"loss": 0.1363,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.6352201257861636,
|
| 560 |
+
"grad_norm": 4.117647647857666,
|
| 561 |
+
"learning_rate": 6.733752620545074e-05,
|
| 562 |
+
"loss": 0.1289,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.6561844863731656,
|
| 567 |
+
"grad_norm": 3.723130941390991,
|
| 568 |
+
"learning_rate": 6.691823899371068e-05,
|
| 569 |
+
"loss": 0.1319,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.6771488469601676,
|
| 574 |
+
"grad_norm": 3.42946195602417,
|
| 575 |
+
"learning_rate": 6.649895178197065e-05,
|
| 576 |
+
"loss": 0.1449,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.6981132075471699,
|
| 581 |
+
"grad_norm": 3.705895185470581,
|
| 582 |
+
"learning_rate": 6.607966457023061e-05,
|
| 583 |
+
"loss": 0.1446,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.719077568134172,
|
| 588 |
+
"grad_norm": 4.407285213470459,
|
| 589 |
+
"learning_rate": 6.566037735849057e-05,
|
| 590 |
+
"loss": 0.1417,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.740041928721174,
|
| 595 |
+
"grad_norm": 3.557760000228882,
|
| 596 |
+
"learning_rate": 6.524109014675053e-05,
|
| 597 |
+
"loss": 0.1338,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.7610062893081762,
|
| 602 |
+
"grad_norm": 3.342160224914551,
|
| 603 |
+
"learning_rate": 6.48218029350105e-05,
|
| 604 |
+
"loss": 0.1439,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.7819706498951782,
|
| 609 |
+
"grad_norm": 3.4098939895629883,
|
| 610 |
+
"learning_rate": 6.440251572327044e-05,
|
| 611 |
+
"loss": 0.1444,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.8029350104821802,
|
| 616 |
+
"grad_norm": 3.757795572280884,
|
| 617 |
+
"learning_rate": 6.39832285115304e-05,
|
| 618 |
+
"loss": 0.1327,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.8238993710691824,
|
| 623 |
+
"grad_norm": 3.3094663619995117,
|
| 624 |
+
"learning_rate": 6.356394129979037e-05,
|
| 625 |
+
"loss": 0.1338,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.8448637316561844,
|
| 630 |
+
"grad_norm": 3.925997495651245,
|
| 631 |
+
"learning_rate": 6.314465408805031e-05,
|
| 632 |
+
"loss": 0.1391,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.8658280922431865,
|
| 637 |
+
"grad_norm": 3.38191819190979,
|
| 638 |
+
"learning_rate": 6.272536687631028e-05,
|
| 639 |
+
"loss": 0.1396,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.8867924528301887,
|
| 644 |
+
"grad_norm": 3.194735288619995,
|
| 645 |
+
"learning_rate": 6.230607966457024e-05,
|
| 646 |
+
"loss": 0.1304,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.9077568134171907,
|
| 651 |
+
"grad_norm": 3.6266653537750244,
|
| 652 |
+
"learning_rate": 6.188679245283019e-05,
|
| 653 |
+
"loss": 0.1259,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.9287211740041927,
|
| 658 |
+
"grad_norm": 4.087035655975342,
|
| 659 |
+
"learning_rate": 6.146750524109015e-05,
|
| 660 |
+
"loss": 0.145,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.949685534591195,
|
| 665 |
+
"grad_norm": 3.725505828857422,
|
| 666 |
+
"learning_rate": 6.104821802935011e-05,
|
| 667 |
+
"loss": 0.1291,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.9706498951781972,
|
| 672 |
+
"grad_norm": 3.440652847290039,
|
| 673 |
+
"learning_rate": 6.0628930817610065e-05,
|
| 674 |
+
"loss": 0.1348,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.991614255765199,
|
| 679 |
+
"grad_norm": 3.5756237506866455,
|
| 680 |
+
"learning_rate": 6.020964360587003e-05,
|
| 681 |
+
"loss": 0.1535,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.0,
|
| 686 |
+
"eval_loss": 0.6702887415885925,
|
| 687 |
+
"eval_runtime": 20.8625,
|
| 688 |
+
"eval_samples_per_second": 71.9,
|
| 689 |
+
"eval_steps_per_second": 9.011,
|
| 690 |
+
"step": 954
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.0125786163522013,
|
| 694 |
+
"grad_norm": 1.9692338705062866,
|
| 695 |
+
"learning_rate": 5.979035639412999e-05,
|
| 696 |
+
"loss": 0.0812,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.0335429769392035,
|
| 701 |
+
"grad_norm": 2.1989524364471436,
|
| 702 |
+
"learning_rate": 5.937106918238994e-05,
|
| 703 |
+
"loss": 0.0489,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.0545073375262053,
|
| 708 |
+
"grad_norm": 1.9158607721328735,
|
| 709 |
+
"learning_rate": 5.89517819706499e-05,
|
| 710 |
+
"loss": 0.0465,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.0754716981132075,
|
| 715 |
+
"grad_norm": 1.7822378873825073,
|
| 716 |
+
"learning_rate": 5.853249475890986e-05,
|
| 717 |
+
"loss": 0.049,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.0964360587002098,
|
| 722 |
+
"grad_norm": 2.644869089126587,
|
| 723 |
+
"learning_rate": 5.811320754716981e-05,
|
| 724 |
+
"loss": 0.0545,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.1174004192872116,
|
| 729 |
+
"grad_norm": 2.888030529022217,
|
| 730 |
+
"learning_rate": 5.769392033542977e-05,
|
| 731 |
+
"loss": 0.0563,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.138364779874214,
|
| 736 |
+
"grad_norm": 2.034641742706299,
|
| 737 |
+
"learning_rate": 5.727463312368973e-05,
|
| 738 |
+
"loss": 0.0527,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.159329140461216,
|
| 743 |
+
"grad_norm": 1.8326114416122437,
|
| 744 |
+
"learning_rate": 5.685534591194969e-05,
|
| 745 |
+
"loss": 0.0509,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.180293501048218,
|
| 750 |
+
"grad_norm": 2.1253228187561035,
|
| 751 |
+
"learning_rate": 5.643605870020965e-05,
|
| 752 |
+
"loss": 0.0533,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.20125786163522,
|
| 757 |
+
"grad_norm": 2.369814872741699,
|
| 758 |
+
"learning_rate": 5.60167714884696e-05,
|
| 759 |
+
"loss": 0.0535,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.2222222222222223,
|
| 764 |
+
"grad_norm": 2.15043568611145,
|
| 765 |
+
"learning_rate": 5.559748427672956e-05,
|
| 766 |
+
"loss": 0.0525,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.243186582809224,
|
| 771 |
+
"grad_norm": 2.138932943344116,
|
| 772 |
+
"learning_rate": 5.517819706498952e-05,
|
| 773 |
+
"loss": 0.052,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.2641509433962264,
|
| 778 |
+
"grad_norm": 2.2840254306793213,
|
| 779 |
+
"learning_rate": 5.475890985324947e-05,
|
| 780 |
+
"loss": 0.0582,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.2851153039832286,
|
| 785 |
+
"grad_norm": 1.516945481300354,
|
| 786 |
+
"learning_rate": 5.433962264150943e-05,
|
| 787 |
+
"loss": 0.0557,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.3060796645702304,
|
| 792 |
+
"grad_norm": 2.2309811115264893,
|
| 793 |
+
"learning_rate": 5.3920335429769395e-05,
|
| 794 |
+
"loss": 0.0563,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.3270440251572326,
|
| 799 |
+
"grad_norm": 2.9257094860076904,
|
| 800 |
+
"learning_rate": 5.350104821802935e-05,
|
| 801 |
+
"loss": 0.056,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.348008385744235,
|
| 806 |
+
"grad_norm": 2.112194538116455,
|
| 807 |
+
"learning_rate": 5.308176100628931e-05,
|
| 808 |
+
"loss": 0.0567,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.368972746331237,
|
| 813 |
+
"grad_norm": 2.411298990249634,
|
| 814 |
+
"learning_rate": 5.2662473794549274e-05,
|
| 815 |
+
"loss": 0.0558,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.389937106918239,
|
| 820 |
+
"grad_norm": 2.410545825958252,
|
| 821 |
+
"learning_rate": 5.224318658280922e-05,
|
| 822 |
+
"loss": 0.0557,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.410901467505241,
|
| 827 |
+
"grad_norm": 2.1554999351501465,
|
| 828 |
+
"learning_rate": 5.1823899371069184e-05,
|
| 829 |
+
"loss": 0.0589,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.431865828092243,
|
| 834 |
+
"grad_norm": 2.1737091541290283,
|
| 835 |
+
"learning_rate": 5.1404612159329146e-05,
|
| 836 |
+
"loss": 0.0673,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.452830188679245,
|
| 841 |
+
"grad_norm": 3.798069477081299,
|
| 842 |
+
"learning_rate": 5.0985324947589094e-05,
|
| 843 |
+
"loss": 0.0546,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.4737945492662474,
|
| 848 |
+
"grad_norm": 2.5850603580474854,
|
| 849 |
+
"learning_rate": 5.0566037735849056e-05,
|
| 850 |
+
"loss": 0.0546,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.4947589098532497,
|
| 855 |
+
"grad_norm": 2.899369239807129,
|
| 856 |
+
"learning_rate": 5.014675052410902e-05,
|
| 857 |
+
"loss": 0.0576,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.5157232704402515,
|
| 862 |
+
"grad_norm": 2.534893035888672,
|
| 863 |
+
"learning_rate": 4.972746331236898e-05,
|
| 864 |
+
"loss": 0.0529,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.5366876310272537,
|
| 869 |
+
"grad_norm": 4.3690924644470215,
|
| 870 |
+
"learning_rate": 4.9308176100628935e-05,
|
| 871 |
+
"loss": 0.0494,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.5576519916142555,
|
| 876 |
+
"grad_norm": 1.8138058185577393,
|
| 877 |
+
"learning_rate": 4.888888888888889e-05,
|
| 878 |
+
"loss": 0.0559,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.5786163522012577,
|
| 883 |
+
"grad_norm": 1.9707310199737549,
|
| 884 |
+
"learning_rate": 4.846960167714885e-05,
|
| 885 |
+
"loss": 0.0544,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.59958071278826,
|
| 890 |
+
"grad_norm": 2.480036973953247,
|
| 891 |
+
"learning_rate": 4.805031446540881e-05,
|
| 892 |
+
"loss": 0.0591,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.620545073375262,
|
| 897 |
+
"grad_norm": 3.3198599815368652,
|
| 898 |
+
"learning_rate": 4.763102725366876e-05,
|
| 899 |
+
"loss": 0.0519,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.641509433962264,
|
| 904 |
+
"grad_norm": 4.302845478057861,
|
| 905 |
+
"learning_rate": 4.7211740041928724e-05,
|
| 906 |
+
"loss": 0.0588,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.6624737945492662,
|
| 911 |
+
"grad_norm": 2.769380807876587,
|
| 912 |
+
"learning_rate": 4.679245283018868e-05,
|
| 913 |
+
"loss": 0.0561,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.6834381551362685,
|
| 918 |
+
"grad_norm": 2.0273640155792236,
|
| 919 |
+
"learning_rate": 4.637316561844864e-05,
|
| 920 |
+
"loss": 0.0531,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.7044025157232703,
|
| 925 |
+
"grad_norm": 3.1066033840179443,
|
| 926 |
+
"learning_rate": 4.59538784067086e-05,
|
| 927 |
+
"loss": 0.0547,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.7253668763102725,
|
| 932 |
+
"grad_norm": 3.7857868671417236,
|
| 933 |
+
"learning_rate": 4.553459119496856e-05,
|
| 934 |
+
"loss": 0.0552,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.7463312368972748,
|
| 939 |
+
"grad_norm": 2.8125133514404297,
|
| 940 |
+
"learning_rate": 4.511530398322851e-05,
|
| 941 |
+
"loss": 0.0592,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.767295597484277,
|
| 946 |
+
"grad_norm": 1.8335483074188232,
|
| 947 |
+
"learning_rate": 4.469601677148847e-05,
|
| 948 |
+
"loss": 0.0576,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.788259958071279,
|
| 953 |
+
"grad_norm": 2.8290367126464844,
|
| 954 |
+
"learning_rate": 4.427672955974843e-05,
|
| 955 |
+
"loss": 0.0566,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.809224318658281,
|
| 960 |
+
"grad_norm": 2.31840443611145,
|
| 961 |
+
"learning_rate": 4.3857442348008385e-05,
|
| 962 |
+
"loss": 0.0504,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.830188679245283,
|
| 967 |
+
"grad_norm": 2.372063159942627,
|
| 968 |
+
"learning_rate": 4.343815513626835e-05,
|
| 969 |
+
"loss": 0.0591,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.851153039832285,
|
| 974 |
+
"grad_norm": 2.2945821285247803,
|
| 975 |
+
"learning_rate": 4.301886792452831e-05,
|
| 976 |
+
"loss": 0.0571,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.8721174004192873,
|
| 981 |
+
"grad_norm": 1.8437625169754028,
|
| 982 |
+
"learning_rate": 4.2599580712788264e-05,
|
| 983 |
+
"loss": 0.0544,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.8930817610062896,
|
| 988 |
+
"grad_norm": 2.612316608428955,
|
| 989 |
+
"learning_rate": 4.218029350104822e-05,
|
| 990 |
+
"loss": 0.0517,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.9140461215932913,
|
| 995 |
+
"grad_norm": 2.7713685035705566,
|
| 996 |
+
"learning_rate": 4.176100628930818e-05,
|
| 997 |
+
"loss": 0.0565,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.9350104821802936,
|
| 1002 |
+
"grad_norm": 2.0892138481140137,
|
| 1003 |
+
"learning_rate": 4.1341719077568136e-05,
|
| 1004 |
+
"loss": 0.0591,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.9559748427672954,
|
| 1009 |
+
"grad_norm": 1.9455903768539429,
|
| 1010 |
+
"learning_rate": 4.092243186582809e-05,
|
| 1011 |
+
"loss": 0.0494,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.9769392033542976,
|
| 1016 |
+
"grad_norm": 3.191281318664551,
|
| 1017 |
+
"learning_rate": 4.050314465408805e-05,
|
| 1018 |
+
"loss": 0.0562,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.9979035639413,
|
| 1023 |
+
"grad_norm": 2.252624034881592,
|
| 1024 |
+
"learning_rate": 4.008385744234801e-05,
|
| 1025 |
+
"loss": 0.053,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 3.0,
|
| 1030 |
+
"eval_loss": 0.667631983757019,
|
| 1031 |
+
"eval_runtime": 22.0522,
|
| 1032 |
+
"eval_samples_per_second": 68.02,
|
| 1033 |
+
"eval_steps_per_second": 8.525,
|
| 1034 |
+
"step": 1431
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 3.018867924528302,
|
| 1038 |
+
"grad_norm": 1.2633923292160034,
|
| 1039 |
+
"learning_rate": 3.966457023060797e-05,
|
| 1040 |
+
"loss": 0.025,
|
| 1041 |
+
"step": 1440
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 3.039832285115304,
|
| 1045 |
+
"grad_norm": 1.2608442306518555,
|
| 1046 |
+
"learning_rate": 3.924528301886793e-05,
|
| 1047 |
+
"loss": 0.0191,
|
| 1048 |
+
"step": 1450
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 3.060796645702306,
|
| 1052 |
+
"grad_norm": 3.670048475265503,
|
| 1053 |
+
"learning_rate": 3.882599580712789e-05,
|
| 1054 |
+
"loss": 0.0231,
|
| 1055 |
+
"step": 1460
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 3.0817610062893084,
|
| 1059 |
+
"grad_norm": 3.2211225032806396,
|
| 1060 |
+
"learning_rate": 3.840670859538784e-05,
|
| 1061 |
+
"loss": 0.0225,
|
| 1062 |
+
"step": 1470
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 3.10272536687631,
|
| 1066 |
+
"grad_norm": 1.0529983043670654,
|
| 1067 |
+
"learning_rate": 3.7987421383647804e-05,
|
| 1068 |
+
"loss": 0.0242,
|
| 1069 |
+
"step": 1480
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 3.1236897274633124,
|
| 1073 |
+
"grad_norm": 1.5843929052352905,
|
| 1074 |
+
"learning_rate": 3.756813417190776e-05,
|
| 1075 |
+
"loss": 0.0199,
|
| 1076 |
+
"step": 1490
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 3.1446540880503147,
|
| 1080 |
+
"grad_norm": 1.28718900680542,
|
| 1081 |
+
"learning_rate": 3.7148846960167714e-05,
|
| 1082 |
+
"loss": 0.022,
|
| 1083 |
+
"step": 1500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 3.1656184486373165,
|
| 1087 |
+
"grad_norm": 1.1010375022888184,
|
| 1088 |
+
"learning_rate": 3.672955974842767e-05,
|
| 1089 |
+
"loss": 0.0185,
|
| 1090 |
+
"step": 1510
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 3.1865828092243187,
|
| 1094 |
+
"grad_norm": 1.0108301639556885,
|
| 1095 |
+
"learning_rate": 3.631027253668763e-05,
|
| 1096 |
+
"loss": 0.0203,
|
| 1097 |
+
"step": 1520
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 3.207547169811321,
|
| 1101 |
+
"grad_norm": 1.856557846069336,
|
| 1102 |
+
"learning_rate": 3.589098532494759e-05,
|
| 1103 |
+
"loss": 0.0188,
|
| 1104 |
+
"step": 1530
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 3.2285115303983227,
|
| 1108 |
+
"grad_norm": 1.2554458379745483,
|
| 1109 |
+
"learning_rate": 3.547169811320755e-05,
|
| 1110 |
+
"loss": 0.0217,
|
| 1111 |
+
"step": 1540
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 3.249475890985325,
|
| 1115 |
+
"grad_norm": 1.5458911657333374,
|
| 1116 |
+
"learning_rate": 3.505241090146751e-05,
|
| 1117 |
+
"loss": 0.0217,
|
| 1118 |
+
"step": 1550
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 3.270440251572327,
|
| 1122 |
+
"grad_norm": 1.8719966411590576,
|
| 1123 |
+
"learning_rate": 3.4633123689727465e-05,
|
| 1124 |
+
"loss": 0.0239,
|
| 1125 |
+
"step": 1560
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 3.291404612159329,
|
| 1129 |
+
"grad_norm": 0.8294363617897034,
|
| 1130 |
+
"learning_rate": 3.421383647798742e-05,
|
| 1131 |
+
"loss": 0.0174,
|
| 1132 |
+
"step": 1570
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 3.3123689727463312,
|
| 1136 |
+
"grad_norm": 1.013922095298767,
|
| 1137 |
+
"learning_rate": 3.379454926624738e-05,
|
| 1138 |
+
"loss": 0.0191,
|
| 1139 |
+
"step": 1580
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 3.3333333333333335,
|
| 1143 |
+
"grad_norm": 2.7998366355895996,
|
| 1144 |
+
"learning_rate": 3.337526205450734e-05,
|
| 1145 |
+
"loss": 0.0211,
|
| 1146 |
+
"step": 1590
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 3.3542976939203353,
|
| 1150 |
+
"grad_norm": 1.3313286304473877,
|
| 1151 |
+
"learning_rate": 3.295597484276729e-05,
|
| 1152 |
+
"loss": 0.0214,
|
| 1153 |
+
"step": 1600
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 3.3752620545073375,
|
| 1157 |
+
"grad_norm": 1.3300907611846924,
|
| 1158 |
+
"learning_rate": 3.2536687631027254e-05,
|
| 1159 |
+
"loss": 0.0229,
|
| 1160 |
+
"step": 1610
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 3.3962264150943398,
|
| 1164 |
+
"grad_norm": 1.3926533460617065,
|
| 1165 |
+
"learning_rate": 3.2117400419287216e-05,
|
| 1166 |
+
"loss": 0.0192,
|
| 1167 |
+
"step": 1620
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 3.4171907756813416,
|
| 1171 |
+
"grad_norm": 1.8201309442520142,
|
| 1172 |
+
"learning_rate": 3.169811320754717e-05,
|
| 1173 |
+
"loss": 0.0194,
|
| 1174 |
+
"step": 1630
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 3.438155136268344,
|
| 1178 |
+
"grad_norm": 1.1363880634307861,
|
| 1179 |
+
"learning_rate": 3.127882599580713e-05,
|
| 1180 |
+
"loss": 0.0196,
|
| 1181 |
+
"step": 1640
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 3.459119496855346,
|
| 1185 |
+
"grad_norm": 1.1997497081756592,
|
| 1186 |
+
"learning_rate": 3.085953878406709e-05,
|
| 1187 |
+
"loss": 0.0192,
|
| 1188 |
+
"step": 1650
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 3.480083857442348,
|
| 1192 |
+
"grad_norm": 1.1632133722305298,
|
| 1193 |
+
"learning_rate": 3.0440251572327043e-05,
|
| 1194 |
+
"loss": 0.0165,
|
| 1195 |
+
"step": 1660
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 3.50104821802935,
|
| 1199 |
+
"grad_norm": 1.141566514968872,
|
| 1200 |
+
"learning_rate": 3.0020964360587005e-05,
|
| 1201 |
+
"loss": 0.0182,
|
| 1202 |
+
"step": 1670
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 3.5220125786163523,
|
| 1206 |
+
"grad_norm": 1.4071044921875,
|
| 1207 |
+
"learning_rate": 2.9601677148846964e-05,
|
| 1208 |
+
"loss": 0.0177,
|
| 1209 |
+
"step": 1680
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 3.5429769392033545,
|
| 1213 |
+
"grad_norm": 0.6424669623374939,
|
| 1214 |
+
"learning_rate": 2.918238993710692e-05,
|
| 1215 |
+
"loss": 0.018,
|
| 1216 |
+
"step": 1690
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 3.5639412997903563,
|
| 1220 |
+
"grad_norm": 1.240339756011963,
|
| 1221 |
+
"learning_rate": 2.8763102725366874e-05,
|
| 1222 |
+
"loss": 0.0181,
|
| 1223 |
+
"step": 1700
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 3.5849056603773586,
|
| 1227 |
+
"grad_norm": 1.8148901462554932,
|
| 1228 |
+
"learning_rate": 2.8343815513626836e-05,
|
| 1229 |
+
"loss": 0.0203,
|
| 1230 |
+
"step": 1710
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 3.6058700209643604,
|
| 1234 |
+
"grad_norm": 2.1308140754699707,
|
| 1235 |
+
"learning_rate": 2.7924528301886794e-05,
|
| 1236 |
+
"loss": 0.0208,
|
| 1237 |
+
"step": 1720
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 3.6268343815513626,
|
| 1241 |
+
"grad_norm": 1.0319384336471558,
|
| 1242 |
+
"learning_rate": 2.750524109014675e-05,
|
| 1243 |
+
"loss": 0.0171,
|
| 1244 |
+
"step": 1730
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 3.647798742138365,
|
| 1248 |
+
"grad_norm": 1.056301236152649,
|
| 1249 |
+
"learning_rate": 2.708595387840671e-05,
|
| 1250 |
+
"loss": 0.0193,
|
| 1251 |
+
"step": 1740
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 3.668763102725367,
|
| 1255 |
+
"grad_norm": 1.0502632856369019,
|
| 1256 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 1257 |
+
"loss": 0.0181,
|
| 1258 |
+
"step": 1750
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 3.689727463312369,
|
| 1262 |
+
"grad_norm": 1.5024515390396118,
|
| 1263 |
+
"learning_rate": 2.6247379454926625e-05,
|
| 1264 |
+
"loss": 0.0194,
|
| 1265 |
+
"step": 1760
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 3.710691823899371,
|
| 1269 |
+
"grad_norm": 1.1332629919052124,
|
| 1270 |
+
"learning_rate": 2.5828092243186587e-05,
|
| 1271 |
+
"loss": 0.0154,
|
| 1272 |
+
"step": 1770
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 3.731656184486373,
|
| 1276 |
+
"grad_norm": 1.3538895845413208,
|
| 1277 |
+
"learning_rate": 2.5408805031446542e-05,
|
| 1278 |
+
"loss": 0.0174,
|
| 1279 |
+
"step": 1780
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 3.752620545073375,
|
| 1283 |
+
"grad_norm": 3.9446728229522705,
|
| 1284 |
+
"learning_rate": 2.49895178197065e-05,
|
| 1285 |
+
"loss": 0.0174,
|
| 1286 |
+
"step": 1790
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 3.7735849056603774,
|
| 1290 |
+
"grad_norm": 1.6350576877593994,
|
| 1291 |
+
"learning_rate": 2.4570230607966456e-05,
|
| 1292 |
+
"loss": 0.0211,
|
| 1293 |
+
"step": 1800
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 3.7945492662473796,
|
| 1297 |
+
"grad_norm": 0.998974621295929,
|
| 1298 |
+
"learning_rate": 2.4150943396226418e-05,
|
| 1299 |
+
"loss": 0.0185,
|
| 1300 |
+
"step": 1810
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 3.8155136268343814,
|
| 1304 |
+
"grad_norm": 1.1701918840408325,
|
| 1305 |
+
"learning_rate": 2.3731656184486376e-05,
|
| 1306 |
+
"loss": 0.019,
|
| 1307 |
+
"step": 1820
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 3.8364779874213837,
|
| 1311 |
+
"grad_norm": 1.005288004875183,
|
| 1312 |
+
"learning_rate": 2.331236897274633e-05,
|
| 1313 |
+
"loss": 0.0169,
|
| 1314 |
+
"step": 1830
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 3.8574423480083855,
|
| 1318 |
+
"grad_norm": 1.4519301652908325,
|
| 1319 |
+
"learning_rate": 2.289308176100629e-05,
|
| 1320 |
+
"loss": 0.0191,
|
| 1321 |
+
"step": 1840
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 3.8784067085953877,
|
| 1325 |
+
"grad_norm": 0.8834218382835388,
|
| 1326 |
+
"learning_rate": 2.2473794549266248e-05,
|
| 1327 |
+
"loss": 0.0171,
|
| 1328 |
+
"step": 1850
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 3.89937106918239,
|
| 1332 |
+
"grad_norm": 1.3449293375015259,
|
| 1333 |
+
"learning_rate": 2.2054507337526207e-05,
|
| 1334 |
+
"loss": 0.0149,
|
| 1335 |
+
"step": 1860
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 3.920335429769392,
|
| 1339 |
+
"grad_norm": 1.1032202243804932,
|
| 1340 |
+
"learning_rate": 2.1635220125786165e-05,
|
| 1341 |
+
"loss": 0.0175,
|
| 1342 |
+
"step": 1870
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 3.941299790356394,
|
| 1346 |
+
"grad_norm": 0.9004182815551758,
|
| 1347 |
+
"learning_rate": 2.121593291404612e-05,
|
| 1348 |
+
"loss": 0.0152,
|
| 1349 |
+
"step": 1880
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 3.9622641509433962,
|
| 1353 |
+
"grad_norm": 1.1716896295547485,
|
| 1354 |
+
"learning_rate": 2.0796645702306082e-05,
|
| 1355 |
+
"loss": 0.0189,
|
| 1356 |
+
"step": 1890
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 3.9832285115303985,
|
| 1360 |
+
"grad_norm": 1.6147270202636719,
|
| 1361 |
+
"learning_rate": 2.037735849056604e-05,
|
| 1362 |
+
"loss": 0.0183,
|
| 1363 |
+
"step": 1900
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 4.0,
|
| 1367 |
+
"eval_loss": 0.6632634401321411,
|
| 1368 |
+
"eval_runtime": 22.7298,
|
| 1369 |
+
"eval_samples_per_second": 65.993,
|
| 1370 |
+
"eval_steps_per_second": 8.271,
|
| 1371 |
+
"step": 1908
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 4.0041928721174,
|
| 1375 |
+
"grad_norm": 0.37951168417930603,
|
| 1376 |
+
"learning_rate": 1.9958071278825996e-05,
|
| 1377 |
+
"loss": 0.0163,
|
| 1378 |
+
"step": 1910
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 4.0251572327044025,
|
| 1382 |
+
"grad_norm": 0.3050394654273987,
|
| 1383 |
+
"learning_rate": 1.9538784067085954e-05,
|
| 1384 |
+
"loss": 0.007,
|
| 1385 |
+
"step": 1920
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 4.046121593291405,
|
| 1389 |
+
"grad_norm": 0.34913668036460876,
|
| 1390 |
+
"learning_rate": 1.9119496855345913e-05,
|
| 1391 |
+
"loss": 0.0064,
|
| 1392 |
+
"step": 1930
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 4.067085953878407,
|
| 1396 |
+
"grad_norm": 0.36414623260498047,
|
| 1397 |
+
"learning_rate": 1.870020964360587e-05,
|
| 1398 |
+
"loss": 0.0067,
|
| 1399 |
+
"step": 1940
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 4.088050314465409,
|
| 1403 |
+
"grad_norm": 0.5772935152053833,
|
| 1404 |
+
"learning_rate": 1.828092243186583e-05,
|
| 1405 |
+
"loss": 0.0061,
|
| 1406 |
+
"step": 1950
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 4.109014675052411,
|
| 1410 |
+
"grad_norm": 0.2230810970067978,
|
| 1411 |
+
"learning_rate": 1.7861635220125785e-05,
|
| 1412 |
+
"loss": 0.0059,
|
| 1413 |
+
"step": 1960
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 4.129979035639413,
|
| 1417 |
+
"grad_norm": 0.46709367632865906,
|
| 1418 |
+
"learning_rate": 1.7442348008385743e-05,
|
| 1419 |
+
"loss": 0.0063,
|
| 1420 |
+
"step": 1970
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 4.150943396226415,
|
| 1424 |
+
"grad_norm": 0.40340206027030945,
|
| 1425 |
+
"learning_rate": 1.7023060796645705e-05,
|
| 1426 |
+
"loss": 0.006,
|
| 1427 |
+
"step": 1980
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 4.171907756813417,
|
| 1431 |
+
"grad_norm": 0.22066733241081238,
|
| 1432 |
+
"learning_rate": 1.660377358490566e-05,
|
| 1433 |
+
"loss": 0.0055,
|
| 1434 |
+
"step": 1990
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 4.1928721174004195,
|
| 1438 |
+
"grad_norm": 0.22712306678295135,
|
| 1439 |
+
"learning_rate": 1.618448637316562e-05,
|
| 1440 |
+
"loss": 0.0075,
|
| 1441 |
+
"step": 2000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 4.213836477987422,
|
| 1445 |
+
"grad_norm": 0.3246201276779175,
|
| 1446 |
+
"learning_rate": 1.5765199161425577e-05,
|
| 1447 |
+
"loss": 0.0059,
|
| 1448 |
+
"step": 2010
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 4.234800838574423,
|
| 1452 |
+
"grad_norm": 0.6034521460533142,
|
| 1453 |
+
"learning_rate": 1.5345911949685536e-05,
|
| 1454 |
+
"loss": 0.0058,
|
| 1455 |
+
"step": 2020
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 4.255765199161425,
|
| 1459 |
+
"grad_norm": 0.3003758490085602,
|
| 1460 |
+
"learning_rate": 1.4926624737945494e-05,
|
| 1461 |
+
"loss": 0.0059,
|
| 1462 |
+
"step": 2030
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 4.276729559748428,
|
| 1466 |
+
"grad_norm": 0.38291364908218384,
|
| 1467 |
+
"learning_rate": 1.450733752620545e-05,
|
| 1468 |
+
"loss": 0.0053,
|
| 1469 |
+
"step": 2040
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 4.29769392033543,
|
| 1473 |
+
"grad_norm": 0.24918225407600403,
|
| 1474 |
+
"learning_rate": 1.408805031446541e-05,
|
| 1475 |
+
"loss": 0.0055,
|
| 1476 |
+
"step": 2050
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 4.318658280922432,
|
| 1480 |
+
"grad_norm": 0.29115813970565796,
|
| 1481 |
+
"learning_rate": 1.3668763102725368e-05,
|
| 1482 |
+
"loss": 0.0057,
|
| 1483 |
+
"step": 2060
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 4.339622641509434,
|
| 1487 |
+
"grad_norm": 0.6018015146255493,
|
| 1488 |
+
"learning_rate": 1.3249475890985325e-05,
|
| 1489 |
+
"loss": 0.0056,
|
| 1490 |
+
"step": 2070
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 4.360587002096436,
|
| 1494 |
+
"grad_norm": 0.4561573565006256,
|
| 1495 |
+
"learning_rate": 1.2830188679245283e-05,
|
| 1496 |
+
"loss": 0.0053,
|
| 1497 |
+
"step": 2080
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 4.381551362683438,
|
| 1501 |
+
"grad_norm": 0.2961859703063965,
|
| 1502 |
+
"learning_rate": 1.2410901467505242e-05,
|
| 1503 |
+
"loss": 0.0058,
|
| 1504 |
+
"step": 2090
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 4.40251572327044,
|
| 1508 |
+
"grad_norm": 0.7806200385093689,
|
| 1509 |
+
"learning_rate": 1.19916142557652e-05,
|
| 1510 |
+
"loss": 0.0051,
|
| 1511 |
+
"step": 2100
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 4.423480083857442,
|
| 1515 |
+
"grad_norm": 0.2288259118795395,
|
| 1516 |
+
"learning_rate": 1.1572327044025157e-05,
|
| 1517 |
+
"loss": 0.0062,
|
| 1518 |
+
"step": 2110
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 4.444444444444445,
|
| 1522 |
+
"grad_norm": 0.5480152368545532,
|
| 1523 |
+
"learning_rate": 1.1153039832285116e-05,
|
| 1524 |
+
"loss": 0.0054,
|
| 1525 |
+
"step": 2120
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 4.465408805031447,
|
| 1529 |
+
"grad_norm": 0.3903510272502899,
|
| 1530 |
+
"learning_rate": 1.0733752620545073e-05,
|
| 1531 |
+
"loss": 0.0068,
|
| 1532 |
+
"step": 2130
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 4.486373165618448,
|
| 1536 |
+
"grad_norm": 0.26396581530570984,
|
| 1537 |
+
"learning_rate": 1.0314465408805033e-05,
|
| 1538 |
+
"loss": 0.0051,
|
| 1539 |
+
"step": 2140
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 4.5073375262054505,
|
| 1543 |
+
"grad_norm": 0.3533041477203369,
|
| 1544 |
+
"learning_rate": 9.89517819706499e-06,
|
| 1545 |
+
"loss": 0.0062,
|
| 1546 |
+
"step": 2150
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 4.528301886792453,
|
| 1550 |
+
"grad_norm": 0.23736946284770966,
|
| 1551 |
+
"learning_rate": 9.475890985324948e-06,
|
| 1552 |
+
"loss": 0.0056,
|
| 1553 |
+
"step": 2160
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 4.549266247379455,
|
| 1557 |
+
"grad_norm": 0.7073323726654053,
|
| 1558 |
+
"learning_rate": 9.056603773584905e-06,
|
| 1559 |
+
"loss": 0.0054,
|
| 1560 |
+
"step": 2170
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 4.570230607966457,
|
| 1564 |
+
"grad_norm": 0.22164012491703033,
|
| 1565 |
+
"learning_rate": 8.637316561844865e-06,
|
| 1566 |
+
"loss": 0.0055,
|
| 1567 |
+
"step": 2180
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 4.591194968553459,
|
| 1571 |
+
"grad_norm": 0.27965155243873596,
|
| 1572 |
+
"learning_rate": 8.218029350104822e-06,
|
| 1573 |
+
"loss": 0.0048,
|
| 1574 |
+
"step": 2190
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 4.612159329140461,
|
| 1578 |
+
"grad_norm": 0.7329670786857605,
|
| 1579 |
+
"learning_rate": 7.79874213836478e-06,
|
| 1580 |
+
"loss": 0.0057,
|
| 1581 |
+
"step": 2200
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 4.633123689727463,
|
| 1585 |
+
"grad_norm": 0.310923308134079,
|
| 1586 |
+
"learning_rate": 7.379454926624739e-06,
|
| 1587 |
+
"loss": 0.0054,
|
| 1588 |
+
"step": 2210
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 4.654088050314465,
|
| 1592 |
+
"grad_norm": 0.19455011188983917,
|
| 1593 |
+
"learning_rate": 6.9601677148846965e-06,
|
| 1594 |
+
"loss": 0.0072,
|
| 1595 |
+
"step": 2220
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 4.6750524109014675,
|
| 1599 |
+
"grad_norm": 0.257545530796051,
|
| 1600 |
+
"learning_rate": 6.540880503144654e-06,
|
| 1601 |
+
"loss": 0.0057,
|
| 1602 |
+
"step": 2230
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 4.69601677148847,
|
| 1606 |
+
"grad_norm": 1.0093029737472534,
|
| 1607 |
+
"learning_rate": 6.121593291404613e-06,
|
| 1608 |
+
"loss": 0.006,
|
| 1609 |
+
"step": 2240
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 4.716981132075472,
|
| 1613 |
+
"grad_norm": 0.4301735758781433,
|
| 1614 |
+
"learning_rate": 5.70230607966457e-06,
|
| 1615 |
+
"loss": 0.0056,
|
| 1616 |
+
"step": 2250
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 4.737945492662474,
|
| 1620 |
+
"grad_norm": 0.18497976660728455,
|
| 1621 |
+
"learning_rate": 5.283018867924529e-06,
|
| 1622 |
+
"loss": 0.0052,
|
| 1623 |
+
"step": 2260
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 4.758909853249476,
|
| 1627 |
+
"grad_norm": 0.21521350741386414,
|
| 1628 |
+
"learning_rate": 4.8637316561844865e-06,
|
| 1629 |
+
"loss": 0.0055,
|
| 1630 |
+
"step": 2270
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 4.779874213836478,
|
| 1634 |
+
"grad_norm": 0.20319782197475433,
|
| 1635 |
+
"learning_rate": 4.444444444444445e-06,
|
| 1636 |
+
"loss": 0.0058,
|
| 1637 |
+
"step": 2280
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 4.80083857442348,
|
| 1641 |
+
"grad_norm": 0.2288380116224289,
|
| 1642 |
+
"learning_rate": 4.025157232704403e-06,
|
| 1643 |
+
"loss": 0.005,
|
| 1644 |
+
"step": 2290
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 4.821802935010482,
|
| 1648 |
+
"grad_norm": 1.407477855682373,
|
| 1649 |
+
"learning_rate": 3.6058700209643607e-06,
|
| 1650 |
+
"loss": 0.0073,
|
| 1651 |
+
"step": 2300
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 4.8427672955974845,
|
| 1655 |
+
"grad_norm": 0.26325657963752747,
|
| 1656 |
+
"learning_rate": 3.1865828092243184e-06,
|
| 1657 |
+
"loss": 0.0057,
|
| 1658 |
+
"step": 2310
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 4.863731656184486,
|
| 1662 |
+
"grad_norm": 0.4354378283023834,
|
| 1663 |
+
"learning_rate": 2.767295597484277e-06,
|
| 1664 |
+
"loss": 0.006,
|
| 1665 |
+
"step": 2320
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 4.884696016771488,
|
| 1669 |
+
"grad_norm": 0.7161938548088074,
|
| 1670 |
+
"learning_rate": 2.348008385744235e-06,
|
| 1671 |
+
"loss": 0.0055,
|
| 1672 |
+
"step": 2330
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 4.90566037735849,
|
| 1676 |
+
"grad_norm": 1.1639270782470703,
|
| 1677 |
+
"learning_rate": 1.928721174004193e-06,
|
| 1678 |
+
"loss": 0.0056,
|
| 1679 |
+
"step": 2340
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 4.926624737945493,
|
| 1683 |
+
"grad_norm": 0.3333396017551422,
|
| 1684 |
+
"learning_rate": 1.509433962264151e-06,
|
| 1685 |
+
"loss": 0.0061,
|
| 1686 |
+
"step": 2350
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 4.947589098532495,
|
| 1690 |
+
"grad_norm": 0.3744851052761078,
|
| 1691 |
+
"learning_rate": 1.090146750524109e-06,
|
| 1692 |
+
"loss": 0.0056,
|
| 1693 |
+
"step": 2360
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 4.968553459119497,
|
| 1697 |
+
"grad_norm": 0.1569022685289383,
|
| 1698 |
+
"learning_rate": 6.70859538784067e-07,
|
| 1699 |
+
"loss": 0.0052,
|
| 1700 |
+
"step": 2370
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 4.989517819706499,
|
| 1704 |
+
"grad_norm": 0.30756279826164246,
|
| 1705 |
+
"learning_rate": 2.5157232704402517e-07,
|
| 1706 |
+
"loss": 0.0056,
|
| 1707 |
+
"step": 2380
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 5.0,
|
| 1711 |
+
"eval_loss": 0.6631835699081421,
|
| 1712 |
+
"eval_runtime": 22.601,
|
| 1713 |
+
"eval_samples_per_second": 66.369,
|
| 1714 |
+
"eval_steps_per_second": 8.318,
|
| 1715 |
+
"step": 2385
|
| 1716 |
+
}
|
| 1717 |
+
],
|
| 1718 |
+
"logging_steps": 10,
|
| 1719 |
+
"max_steps": 2385,
|
| 1720 |
+
"num_input_tokens_seen": 0,
|
| 1721 |
+
"num_train_epochs": 5,
|
| 1722 |
+
"save_steps": 500,
|
| 1723 |
+
"stateful_callbacks": {
|
| 1724 |
+
"TrainerControl": {
|
| 1725 |
+
"args": {
|
| 1726 |
+
"should_epoch_stop": false,
|
| 1727 |
+
"should_evaluate": false,
|
| 1728 |
+
"should_log": false,
|
| 1729 |
+
"should_save": true,
|
| 1730 |
+
"should_training_stop": true
|
| 1731 |
+
},
|
| 1732 |
+
"attributes": {}
|
| 1733 |
+
}
|
| 1734 |
+
},
|
| 1735 |
+
"total_flos": 1.8785440290816e+18,
|
| 1736 |
+
"train_batch_size": 8,
|
| 1737 |
+
"trial_name": null,
|
| 1738 |
+
"trial_params": null
|
| 1739 |
+
}
|
checkpoint-2385/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be638db66b2b30e7c25564e6984f988fcb84a168005a82bfc7f80a22c063a433
|
| 3 |
+
size 5368
|