Commit
•
2fbef78
1
Parent(s):
eb2a240
Upload folder using huggingface_hub
Browse files- config.json +163 -0
- preprocessor_config.json +14 -0
- pytorch_model.bin +3 -0
- trainer_state.json +727 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-base",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"apply_spec_augment": false,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"WhisperForAudioClassification"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"begin_suppress_tokens": [
|
| 11 |
+
220,
|
| 12 |
+
50257
|
| 13 |
+
],
|
| 14 |
+
"bos_token_id": 50257,
|
| 15 |
+
"classifier_proj_size": 256,
|
| 16 |
+
"d_model": 512,
|
| 17 |
+
"decoder_attention_heads": 8,
|
| 18 |
+
"decoder_ffn_dim": 2048,
|
| 19 |
+
"decoder_layerdrop": 0.0,
|
| 20 |
+
"decoder_layers": 6,
|
| 21 |
+
"decoder_start_token_id": 50258,
|
| 22 |
+
"dropout": 0.0,
|
| 23 |
+
"encoder_attention_heads": 8,
|
| 24 |
+
"encoder_ffn_dim": 2048,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 6,
|
| 27 |
+
"eos_token_id": 50257,
|
| 28 |
+
"finetuning_task": "audio-classification",
|
| 29 |
+
"forced_decoder_ids": [
|
| 30 |
+
[
|
| 31 |
+
1,
|
| 32 |
+
50259
|
| 33 |
+
],
|
| 34 |
+
[
|
| 35 |
+
2,
|
| 36 |
+
50359
|
| 37 |
+
],
|
| 38 |
+
[
|
| 39 |
+
3,
|
| 40 |
+
50363
|
| 41 |
+
]
|
| 42 |
+
],
|
| 43 |
+
"id2label": {
|
| 44 |
+
"0": "real",
|
| 45 |
+
"1": "fake"
|
| 46 |
+
},
|
| 47 |
+
"init_std": 0.02,
|
| 48 |
+
"is_encoder_decoder": true,
|
| 49 |
+
"label2id": {
|
| 50 |
+
"fake": "1",
|
| 51 |
+
"real": "0"
|
| 52 |
+
},
|
| 53 |
+
"mask_feature_length": 10,
|
| 54 |
+
"mask_feature_min_masks": 0,
|
| 55 |
+
"mask_feature_prob": 0.0,
|
| 56 |
+
"mask_time_length": 10,
|
| 57 |
+
"mask_time_min_masks": 2,
|
| 58 |
+
"mask_time_prob": 0.05,
|
| 59 |
+
"max_length": 448,
|
| 60 |
+
"max_source_positions": 1500,
|
| 61 |
+
"max_target_positions": 448,
|
| 62 |
+
"median_filter_width": 7,
|
| 63 |
+
"model_type": "whisper",
|
| 64 |
+
"num_hidden_layers": 6,
|
| 65 |
+
"num_mel_bins": 80,
|
| 66 |
+
"pad_token_id": 50257,
|
| 67 |
+
"scale_embedding": false,
|
| 68 |
+
"suppress_tokens": [
|
| 69 |
+
1,
|
| 70 |
+
2,
|
| 71 |
+
7,
|
| 72 |
+
8,
|
| 73 |
+
9,
|
| 74 |
+
10,
|
| 75 |
+
14,
|
| 76 |
+
25,
|
| 77 |
+
26,
|
| 78 |
+
27,
|
| 79 |
+
28,
|
| 80 |
+
29,
|
| 81 |
+
31,
|
| 82 |
+
58,
|
| 83 |
+
59,
|
| 84 |
+
60,
|
| 85 |
+
61,
|
| 86 |
+
62,
|
| 87 |
+
63,
|
| 88 |
+
90,
|
| 89 |
+
91,
|
| 90 |
+
92,
|
| 91 |
+
93,
|
| 92 |
+
359,
|
| 93 |
+
503,
|
| 94 |
+
522,
|
| 95 |
+
542,
|
| 96 |
+
873,
|
| 97 |
+
893,
|
| 98 |
+
902,
|
| 99 |
+
918,
|
| 100 |
+
922,
|
| 101 |
+
931,
|
| 102 |
+
1350,
|
| 103 |
+
1853,
|
| 104 |
+
1982,
|
| 105 |
+
2460,
|
| 106 |
+
2627,
|
| 107 |
+
3246,
|
| 108 |
+
3253,
|
| 109 |
+
3268,
|
| 110 |
+
3536,
|
| 111 |
+
3846,
|
| 112 |
+
3961,
|
| 113 |
+
4183,
|
| 114 |
+
4667,
|
| 115 |
+
6585,
|
| 116 |
+
6647,
|
| 117 |
+
7273,
|
| 118 |
+
9061,
|
| 119 |
+
9383,
|
| 120 |
+
10428,
|
| 121 |
+
10929,
|
| 122 |
+
11938,
|
| 123 |
+
12033,
|
| 124 |
+
12331,
|
| 125 |
+
12562,
|
| 126 |
+
13793,
|
| 127 |
+
14157,
|
| 128 |
+
14635,
|
| 129 |
+
15265,
|
| 130 |
+
15618,
|
| 131 |
+
16553,
|
| 132 |
+
16604,
|
| 133 |
+
18362,
|
| 134 |
+
18956,
|
| 135 |
+
20075,
|
| 136 |
+
21675,
|
| 137 |
+
22520,
|
| 138 |
+
26130,
|
| 139 |
+
26161,
|
| 140 |
+
26435,
|
| 141 |
+
28279,
|
| 142 |
+
29464,
|
| 143 |
+
31650,
|
| 144 |
+
32302,
|
| 145 |
+
32470,
|
| 146 |
+
36865,
|
| 147 |
+
42863,
|
| 148 |
+
47425,
|
| 149 |
+
49870,
|
| 150 |
+
50254,
|
| 151 |
+
50258,
|
| 152 |
+
50358,
|
| 153 |
+
50359,
|
| 154 |
+
50360,
|
| 155 |
+
50361,
|
| 156 |
+
50362
|
| 157 |
+
],
|
| 158 |
+
"torch_dtype": "float32",
|
| 159 |
+
"transformers_version": "4.31.0",
|
| 160 |
+
"use_cache": true,
|
| 161 |
+
"use_weighted_layer_sum": false,
|
| 162 |
+
"vocab_size": 51865
|
| 163 |
+
}
|
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 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6371663d68bb05bf9829ed9b799ae100f211c15ed7346322b9200f5751bd9bff
|
| 3 |
+
size 82923230
|
trainer_state.json
ADDED
|
@@ -0,0 +1,727 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "whisper-base-ft/checkpoint-292",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
+
"global_step": 2628,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 8.561643835616439e-07,
|
| 13 |
+
"loss": 0.6917,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"learning_rate": 1.7123287671232877e-06,
|
| 19 |
+
"loss": 0.689,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.26,
|
| 24 |
+
"learning_rate": 2.568493150684932e-06,
|
| 25 |
+
"loss": 0.6774,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.34,
|
| 30 |
+
"learning_rate": 3.4246575342465754e-06,
|
| 31 |
+
"loss": 0.5974,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.43,
|
| 36 |
+
"learning_rate": 4.28082191780822e-06,
|
| 37 |
+
"loss": 0.3433,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.51,
|
| 42 |
+
"learning_rate": 5.136986301369864e-06,
|
| 43 |
+
"loss": 0.1137,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6,
|
| 48 |
+
"learning_rate": 5.993150684931507e-06,
|
| 49 |
+
"loss": 0.0302,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.68,
|
| 54 |
+
"learning_rate": 6.849315068493151e-06,
|
| 55 |
+
"loss": 0.0061,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.77,
|
| 60 |
+
"learning_rate": 7.705479452054794e-06,
|
| 61 |
+
"loss": 0.0086,
|
| 62 |
+
"step": 225
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.86,
|
| 66 |
+
"learning_rate": 8.56164383561644e-06,
|
| 67 |
+
"loss": 0.0025,
|
| 68 |
+
"step": 250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.94,
|
| 72 |
+
"learning_rate": 9.417808219178083e-06,
|
| 73 |
+
"loss": 0.0037,
|
| 74 |
+
"step": 275
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0,
|
| 78 |
+
"eval_accuracy": 1.0,
|
| 79 |
+
"eval_loss": 0.0018677616026252508,
|
| 80 |
+
"eval_runtime": 4.1932,
|
| 81 |
+
"eval_samples_per_second": 23.848,
|
| 82 |
+
"eval_steps_per_second": 1.669,
|
| 83 |
+
"step": 292
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.03,
|
| 87 |
+
"learning_rate": 9.969558599695586e-06,
|
| 88 |
+
"loss": 0.0024,
|
| 89 |
+
"step": 300
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.11,
|
| 93 |
+
"learning_rate": 9.874429223744293e-06,
|
| 94 |
+
"loss": 0.0017,
|
| 95 |
+
"step": 325
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.2,
|
| 99 |
+
"learning_rate": 9.779299847792999e-06,
|
| 100 |
+
"loss": 0.001,
|
| 101 |
+
"step": 350
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.28,
|
| 105 |
+
"learning_rate": 9.684170471841705e-06,
|
| 106 |
+
"loss": 0.0008,
|
| 107 |
+
"step": 375
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.37,
|
| 111 |
+
"learning_rate": 9.589041095890411e-06,
|
| 112 |
+
"loss": 0.006,
|
| 113 |
+
"step": 400
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.46,
|
| 117 |
+
"learning_rate": 9.493911719939119e-06,
|
| 118 |
+
"loss": 0.0007,
|
| 119 |
+
"step": 425
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.54,
|
| 123 |
+
"learning_rate": 9.398782343987825e-06,
|
| 124 |
+
"loss": 0.0006,
|
| 125 |
+
"step": 450
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.63,
|
| 129 |
+
"learning_rate": 9.303652968036531e-06,
|
| 130 |
+
"loss": 0.0005,
|
| 131 |
+
"step": 475
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.71,
|
| 135 |
+
"learning_rate": 9.208523592085237e-06,
|
| 136 |
+
"loss": 0.001,
|
| 137 |
+
"step": 500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.8,
|
| 141 |
+
"learning_rate": 9.113394216133943e-06,
|
| 142 |
+
"loss": 0.0005,
|
| 143 |
+
"step": 525
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.88,
|
| 147 |
+
"learning_rate": 9.01826484018265e-06,
|
| 148 |
+
"loss": 0.0004,
|
| 149 |
+
"step": 550
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.97,
|
| 153 |
+
"learning_rate": 8.923135464231355e-06,
|
| 154 |
+
"loss": 0.0059,
|
| 155 |
+
"step": 575
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.0,
|
| 159 |
+
"eval_accuracy": 1.0,
|
| 160 |
+
"eval_loss": 0.000401403900468722,
|
| 161 |
+
"eval_runtime": 4.2497,
|
| 162 |
+
"eval_samples_per_second": 23.531,
|
| 163 |
+
"eval_steps_per_second": 1.647,
|
| 164 |
+
"step": 584
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.05,
|
| 168 |
+
"learning_rate": 8.828006088280061e-06,
|
| 169 |
+
"loss": 0.0004,
|
| 170 |
+
"step": 600
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.14,
|
| 174 |
+
"learning_rate": 8.732876712328769e-06,
|
| 175 |
+
"loss": 0.001,
|
| 176 |
+
"step": 625
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.23,
|
| 180 |
+
"learning_rate": 8.637747336377475e-06,
|
| 181 |
+
"loss": 0.0004,
|
| 182 |
+
"step": 650
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.31,
|
| 186 |
+
"learning_rate": 8.542617960426181e-06,
|
| 187 |
+
"loss": 0.0004,
|
| 188 |
+
"step": 675
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.4,
|
| 192 |
+
"learning_rate": 8.447488584474887e-06,
|
| 193 |
+
"loss": 0.0003,
|
| 194 |
+
"step": 700
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.48,
|
| 198 |
+
"learning_rate": 8.352359208523594e-06,
|
| 199 |
+
"loss": 0.0002,
|
| 200 |
+
"step": 725
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.57,
|
| 204 |
+
"learning_rate": 8.2572298325723e-06,
|
| 205 |
+
"loss": 0.0002,
|
| 206 |
+
"step": 750
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.65,
|
| 210 |
+
"learning_rate": 8.162100456621006e-06,
|
| 211 |
+
"loss": 0.0002,
|
| 212 |
+
"step": 775
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.74,
|
| 216 |
+
"learning_rate": 8.066971080669712e-06,
|
| 217 |
+
"loss": 0.0007,
|
| 218 |
+
"step": 800
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.83,
|
| 222 |
+
"learning_rate": 7.971841704718418e-06,
|
| 223 |
+
"loss": 0.0028,
|
| 224 |
+
"step": 825
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.91,
|
| 228 |
+
"learning_rate": 7.876712328767124e-06,
|
| 229 |
+
"loss": 0.0091,
|
| 230 |
+
"step": 850
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.0,
|
| 234 |
+
"learning_rate": 7.78158295281583e-06,
|
| 235 |
+
"loss": 0.0005,
|
| 236 |
+
"step": 875
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.0,
|
| 240 |
+
"eval_accuracy": 1.0,
|
| 241 |
+
"eval_loss": 0.00028352142544463277,
|
| 242 |
+
"eval_runtime": 4.4612,
|
| 243 |
+
"eval_samples_per_second": 22.416,
|
| 244 |
+
"eval_steps_per_second": 1.569,
|
| 245 |
+
"step": 876
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.08,
|
| 249 |
+
"learning_rate": 7.686453576864536e-06,
|
| 250 |
+
"loss": 0.0019,
|
| 251 |
+
"step": 900
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.17,
|
| 255 |
+
"learning_rate": 7.591324200913242e-06,
|
| 256 |
+
"loss": 0.0013,
|
| 257 |
+
"step": 925
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.25,
|
| 261 |
+
"learning_rate": 7.496194824961948e-06,
|
| 262 |
+
"loss": 0.0008,
|
| 263 |
+
"step": 950
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.34,
|
| 267 |
+
"learning_rate": 7.4010654490106545e-06,
|
| 268 |
+
"loss": 0.0009,
|
| 269 |
+
"step": 975
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.42,
|
| 273 |
+
"learning_rate": 7.305936073059361e-06,
|
| 274 |
+
"loss": 0.0002,
|
| 275 |
+
"step": 1000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.51,
|
| 279 |
+
"learning_rate": 7.210806697108067e-06,
|
| 280 |
+
"loss": 0.0002,
|
| 281 |
+
"step": 1025
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.6,
|
| 285 |
+
"learning_rate": 7.1156773211567745e-06,
|
| 286 |
+
"loss": 0.0002,
|
| 287 |
+
"step": 1050
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.68,
|
| 291 |
+
"learning_rate": 7.020547945205481e-06,
|
| 292 |
+
"loss": 0.0001,
|
| 293 |
+
"step": 1075
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.77,
|
| 297 |
+
"learning_rate": 6.925418569254187e-06,
|
| 298 |
+
"loss": 0.0001,
|
| 299 |
+
"step": 1100
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.85,
|
| 303 |
+
"learning_rate": 6.830289193302893e-06,
|
| 304 |
+
"loss": 0.0007,
|
| 305 |
+
"step": 1125
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 3.94,
|
| 309 |
+
"learning_rate": 6.735159817351599e-06,
|
| 310 |
+
"loss": 0.0003,
|
| 311 |
+
"step": 1150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 4.0,
|
| 315 |
+
"eval_accuracy": 1.0,
|
| 316 |
+
"eval_loss": 0.0001292741362703964,
|
| 317 |
+
"eval_runtime": 4.3055,
|
| 318 |
+
"eval_samples_per_second": 23.226,
|
| 319 |
+
"eval_steps_per_second": 1.626,
|
| 320 |
+
"step": 1168
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.02,
|
| 324 |
+
"learning_rate": 6.640030441400305e-06,
|
| 325 |
+
"loss": 0.0001,
|
| 326 |
+
"step": 1175
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.11,
|
| 330 |
+
"learning_rate": 6.544901065449011e-06,
|
| 331 |
+
"loss": 0.0005,
|
| 332 |
+
"step": 1200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.2,
|
| 336 |
+
"learning_rate": 6.449771689497717e-06,
|
| 337 |
+
"loss": 0.005,
|
| 338 |
+
"step": 1225
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.28,
|
| 342 |
+
"learning_rate": 6.354642313546424e-06,
|
| 343 |
+
"loss": 0.0002,
|
| 344 |
+
"step": 1250
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.37,
|
| 348 |
+
"learning_rate": 6.25951293759513e-06,
|
| 349 |
+
"loss": 0.004,
|
| 350 |
+
"step": 1275
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.45,
|
| 354 |
+
"learning_rate": 6.168188736681888e-06,
|
| 355 |
+
"loss": 0.0029,
|
| 356 |
+
"step": 1300
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.54,
|
| 360 |
+
"learning_rate": 6.073059360730594e-06,
|
| 361 |
+
"loss": 0.0001,
|
| 362 |
+
"step": 1325
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.62,
|
| 366 |
+
"learning_rate": 5.9779299847793e-06,
|
| 367 |
+
"loss": 0.0001,
|
| 368 |
+
"step": 1350
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.71,
|
| 372 |
+
"learning_rate": 5.882800608828006e-06,
|
| 373 |
+
"loss": 0.0019,
|
| 374 |
+
"step": 1375
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.79,
|
| 378 |
+
"learning_rate": 5.7876712328767125e-06,
|
| 379 |
+
"loss": 0.0001,
|
| 380 |
+
"step": 1400
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.88,
|
| 384 |
+
"learning_rate": 5.6925418569254186e-06,
|
| 385 |
+
"loss": 0.0001,
|
| 386 |
+
"step": 1425
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.97,
|
| 390 |
+
"learning_rate": 5.597412480974125e-06,
|
| 391 |
+
"loss": 0.0001,
|
| 392 |
+
"step": 1450
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 5.0,
|
| 396 |
+
"eval_accuracy": 1.0,
|
| 397 |
+
"eval_loss": 0.0001045739627443254,
|
| 398 |
+
"eval_runtime": 4.1825,
|
| 399 |
+
"eval_samples_per_second": 23.909,
|
| 400 |
+
"eval_steps_per_second": 1.674,
|
| 401 |
+
"step": 1460
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.05,
|
| 405 |
+
"learning_rate": 5.502283105022832e-06,
|
| 406 |
+
"loss": 0.0001,
|
| 407 |
+
"step": 1475
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 5.14,
|
| 411 |
+
"learning_rate": 5.407153729071538e-06,
|
| 412 |
+
"loss": 0.0003,
|
| 413 |
+
"step": 1500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 5.22,
|
| 417 |
+
"learning_rate": 5.312024353120245e-06,
|
| 418 |
+
"loss": 0.0001,
|
| 419 |
+
"step": 1525
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.31,
|
| 423 |
+
"learning_rate": 5.216894977168951e-06,
|
| 424 |
+
"loss": 0.0001,
|
| 425 |
+
"step": 1550
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 5.39,
|
| 429 |
+
"learning_rate": 5.121765601217657e-06,
|
| 430 |
+
"loss": 0.0002,
|
| 431 |
+
"step": 1575
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 5.48,
|
| 435 |
+
"learning_rate": 5.026636225266363e-06,
|
| 436 |
+
"loss": 0.0002,
|
| 437 |
+
"step": 1600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 5.57,
|
| 441 |
+
"learning_rate": 4.931506849315069e-06,
|
| 442 |
+
"loss": 0.0009,
|
| 443 |
+
"step": 1625
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 5.65,
|
| 447 |
+
"learning_rate": 4.836377473363775e-06,
|
| 448 |
+
"loss": 0.0029,
|
| 449 |
+
"step": 1650
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 5.74,
|
| 453 |
+
"learning_rate": 4.741248097412481e-06,
|
| 454 |
+
"loss": 0.0001,
|
| 455 |
+
"step": 1675
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 5.82,
|
| 459 |
+
"learning_rate": 4.646118721461187e-06,
|
| 460 |
+
"loss": 0.0001,
|
| 461 |
+
"step": 1700
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 5.91,
|
| 465 |
+
"learning_rate": 4.550989345509893e-06,
|
| 466 |
+
"loss": 0.0001,
|
| 467 |
+
"step": 1725
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.99,
|
| 471 |
+
"learning_rate": 4.4558599695586e-06,
|
| 472 |
+
"loss": 0.0001,
|
| 473 |
+
"step": 1750
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 6.0,
|
| 477 |
+
"eval_accuracy": 1.0,
|
| 478 |
+
"eval_loss": 8.005261770449579e-05,
|
| 479 |
+
"eval_runtime": 4.4258,
|
| 480 |
+
"eval_samples_per_second": 22.595,
|
| 481 |
+
"eval_steps_per_second": 1.582,
|
| 482 |
+
"step": 1752
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 6.08,
|
| 486 |
+
"learning_rate": 4.3607305936073065e-06,
|
| 487 |
+
"loss": 0.0001,
|
| 488 |
+
"step": 1775
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 6.16,
|
| 492 |
+
"learning_rate": 4.2656012176560126e-06,
|
| 493 |
+
"loss": 0.0006,
|
| 494 |
+
"step": 1800
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 6.25,
|
| 498 |
+
"learning_rate": 4.170471841704719e-06,
|
| 499 |
+
"loss": 0.0004,
|
| 500 |
+
"step": 1825
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 6.34,
|
| 504 |
+
"learning_rate": 4.075342465753426e-06,
|
| 505 |
+
"loss": 0.0001,
|
| 506 |
+
"step": 1850
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 6.42,
|
| 510 |
+
"learning_rate": 3.980213089802132e-06,
|
| 511 |
+
"loss": 0.0001,
|
| 512 |
+
"step": 1875
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 6.51,
|
| 516 |
+
"learning_rate": 3.885083713850838e-06,
|
| 517 |
+
"loss": 0.0004,
|
| 518 |
+
"step": 1900
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.59,
|
| 522 |
+
"learning_rate": 3.7899543378995435e-06,
|
| 523 |
+
"loss": 0.0001,
|
| 524 |
+
"step": 1925
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 6.68,
|
| 528 |
+
"learning_rate": 3.69482496194825e-06,
|
| 529 |
+
"loss": 0.0001,
|
| 530 |
+
"step": 1950
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.76,
|
| 534 |
+
"learning_rate": 3.599695585996956e-06,
|
| 535 |
+
"loss": 0.0001,
|
| 536 |
+
"step": 1975
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 6.85,
|
| 540 |
+
"learning_rate": 3.504566210045662e-06,
|
| 541 |
+
"loss": 0.0001,
|
| 542 |
+
"step": 2000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 6.93,
|
| 546 |
+
"learning_rate": 3.4094368340943683e-06,
|
| 547 |
+
"loss": 0.0001,
|
| 548 |
+
"step": 2025
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 7.0,
|
| 552 |
+
"eval_accuracy": 1.0,
|
| 553 |
+
"eval_loss": 6.137609307188541e-05,
|
| 554 |
+
"eval_runtime": 4.0915,
|
| 555 |
+
"eval_samples_per_second": 24.441,
|
| 556 |
+
"eval_steps_per_second": 1.711,
|
| 557 |
+
"step": 2044
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 7.02,
|
| 561 |
+
"learning_rate": 3.3143074581430752e-06,
|
| 562 |
+
"loss": 0.0001,
|
| 563 |
+
"step": 2050
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 7.11,
|
| 567 |
+
"learning_rate": 3.2191780821917813e-06,
|
| 568 |
+
"loss": 0.0001,
|
| 569 |
+
"step": 2075
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 7.19,
|
| 573 |
+
"learning_rate": 3.1240487062404874e-06,
|
| 574 |
+
"loss": 0.0001,
|
| 575 |
+
"step": 2100
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 7.28,
|
| 579 |
+
"learning_rate": 3.0289193302891935e-06,
|
| 580 |
+
"loss": 0.0002,
|
| 581 |
+
"step": 2125
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 7.36,
|
| 585 |
+
"learning_rate": 2.9337899543379e-06,
|
| 586 |
+
"loss": 0.0001,
|
| 587 |
+
"step": 2150
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 7.45,
|
| 591 |
+
"learning_rate": 2.838660578386606e-06,
|
| 592 |
+
"loss": 0.0001,
|
| 593 |
+
"step": 2175
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 7.53,
|
| 597 |
+
"learning_rate": 2.7435312024353122e-06,
|
| 598 |
+
"loss": 0.0001,
|
| 599 |
+
"step": 2200
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 7.62,
|
| 603 |
+
"learning_rate": 2.6484018264840183e-06,
|
| 604 |
+
"loss": 0.0001,
|
| 605 |
+
"step": 2225
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 7.71,
|
| 609 |
+
"learning_rate": 2.553272450532725e-06,
|
| 610 |
+
"loss": 0.0001,
|
| 611 |
+
"step": 2250
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 7.79,
|
| 615 |
+
"learning_rate": 2.458143074581431e-06,
|
| 616 |
+
"loss": 0.0001,
|
| 617 |
+
"step": 2275
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 7.88,
|
| 621 |
+
"learning_rate": 2.363013698630137e-06,
|
| 622 |
+
"loss": 0.0001,
|
| 623 |
+
"step": 2300
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 7.96,
|
| 627 |
+
"learning_rate": 2.267884322678843e-06,
|
| 628 |
+
"loss": 0.0,
|
| 629 |
+
"step": 2325
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 8.0,
|
| 633 |
+
"eval_accuracy": 1.0,
|
| 634 |
+
"eval_loss": 5.370378494262695e-05,
|
| 635 |
+
"eval_runtime": 4.28,
|
| 636 |
+
"eval_samples_per_second": 23.364,
|
| 637 |
+
"eval_steps_per_second": 1.636,
|
| 638 |
+
"step": 2336
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 8.05,
|
| 642 |
+
"learning_rate": 2.1727549467275497e-06,
|
| 643 |
+
"loss": 0.0002,
|
| 644 |
+
"step": 2350
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 8.13,
|
| 648 |
+
"learning_rate": 2.0776255707762557e-06,
|
| 649 |
+
"loss": 0.0,
|
| 650 |
+
"step": 2375
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 8.22,
|
| 654 |
+
"learning_rate": 1.9824961948249623e-06,
|
| 655 |
+
"loss": 0.0,
|
| 656 |
+
"step": 2400
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 8.3,
|
| 660 |
+
"learning_rate": 1.8873668188736682e-06,
|
| 661 |
+
"loss": 0.0,
|
| 662 |
+
"step": 2425
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 8.39,
|
| 666 |
+
"learning_rate": 1.7922374429223747e-06,
|
| 667 |
+
"loss": 0.0,
|
| 668 |
+
"step": 2450
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 8.48,
|
| 672 |
+
"learning_rate": 1.6971080669710808e-06,
|
| 673 |
+
"loss": 0.0001,
|
| 674 |
+
"step": 2475
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 8.56,
|
| 678 |
+
"learning_rate": 1.601978691019787e-06,
|
| 679 |
+
"loss": 0.0001,
|
| 680 |
+
"step": 2500
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 8.65,
|
| 684 |
+
"learning_rate": 1.5068493150684932e-06,
|
| 685 |
+
"loss": 0.0,
|
| 686 |
+
"step": 2525
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 8.73,
|
| 690 |
+
"learning_rate": 1.4117199391171995e-06,
|
| 691 |
+
"loss": 0.0001,
|
| 692 |
+
"step": 2550
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 8.82,
|
| 696 |
+
"learning_rate": 1.3165905631659056e-06,
|
| 697 |
+
"loss": 0.0001,
|
| 698 |
+
"step": 2575
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 8.9,
|
| 702 |
+
"learning_rate": 1.2214611872146119e-06,
|
| 703 |
+
"loss": 0.0,
|
| 704 |
+
"step": 2600
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 8.99,
|
| 708 |
+
"learning_rate": 1.1263318112633182e-06,
|
| 709 |
+
"loss": 0.0,
|
| 710 |
+
"step": 2625
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 9.0,
|
| 714 |
+
"eval_accuracy": 1.0,
|
| 715 |
+
"eval_loss": 4.9449205107521266e-05,
|
| 716 |
+
"eval_runtime": 4.2858,
|
| 717 |
+
"eval_samples_per_second": 23.333,
|
| 718 |
+
"eval_steps_per_second": 1.633,
|
| 719 |
+
"step": 2628
|
| 720 |
+
}
|
| 721 |
+
],
|
| 722 |
+
"max_steps": 2920,
|
| 723 |
+
"num_train_epochs": 10,
|
| 724 |
+
"total_flos": 2.41644683759616e+18,
|
| 725 |
+
"trial_name": null,
|
| 726 |
+
"trial_params": null
|
| 727 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ff292b8c055d5538ae8eb2340e23965e022b2966609237ea1bb45714cf654f5
|
| 3 |
+
size 4408
|