RafatK/Whisper_AZ
Browse files- README.md +63 -0
- config.json +61 -0
- generation_config.json +233 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +14 -0
- trainer_state.json +1455 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: openai/whisper-large-v2
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: second2
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# second2
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- eval_loss: 0.3327
|
| 20 |
+
- eval_cer: 5.4203
|
| 21 |
+
- eval_wer: 20.4638
|
| 22 |
+
- eval_bleu: 0.6173
|
| 23 |
+
- eval_runtime: 1022.0953
|
| 24 |
+
- eval_samples_per_second: 0.898
|
| 25 |
+
- eval_steps_per_second: 0.225
|
| 26 |
+
- epoch: 0.2134
|
| 27 |
+
- step: 1000
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 1e-05
|
| 47 |
+
- train_batch_size: 8
|
| 48 |
+
- eval_batch_size: 4
|
| 49 |
+
- seed: 420
|
| 50 |
+
- gradient_accumulation_steps: 8
|
| 51 |
+
- total_train_batch_size: 64
|
| 52 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 53 |
+
- lr_scheduler_type: linear
|
| 54 |
+
- lr_scheduler_warmup_steps: 2
|
| 55 |
+
- training_steps: 9500
|
| 56 |
+
- mixed_precision_training: Native AMP
|
| 57 |
+
|
| 58 |
+
### Framework versions
|
| 59 |
+
|
| 60 |
+
- Transformers 4.48.0
|
| 61 |
+
- Pytorch 2.9.1+cu126
|
| 62 |
+
- Datasets 3.6.0
|
| 63 |
+
- Tokenizers 0.21.4
|
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-large-v2",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"apply_spec_augment": true,
|
| 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": 1280,
|
| 14 |
+
"decoder_attention_heads": 20,
|
| 15 |
+
"decoder_ffn_dim": 5120,
|
| 16 |
+
"decoder_layerdrop": 0.0,
|
| 17 |
+
"decoder_layers": 32,
|
| 18 |
+
"decoder_start_token_id": 50258,
|
| 19 |
+
"dropout": 0.1,
|
| 20 |
+
"encoder_attention_heads": 20,
|
| 21 |
+
"encoder_ffn_dim": 5120,
|
| 22 |
+
"encoder_layerdrop": 0.0,
|
| 23 |
+
"encoder_layers": 32,
|
| 24 |
+
"eos_token_id": 50257,
|
| 25 |
+
"forced_decoder_ids": [
|
| 26 |
+
[
|
| 27 |
+
1,
|
| 28 |
+
50304
|
| 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": 32,
|
| 53 |
+
"num_mel_bins": 80,
|
| 54 |
+
"pad_token_id": 50257,
|
| 55 |
+
"scale_embedding": false,
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.48.0",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"use_weighted_layer_sum": false,
|
| 60 |
+
"vocab_size": 51865
|
| 61 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,233 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
10,
|
| 5 |
+
12
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
13,
|
| 9 |
+
17
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
16,
|
| 13 |
+
11
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
16,
|
| 17 |
+
12
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
16,
|
| 21 |
+
13
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
17,
|
| 25 |
+
15
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
17,
|
| 29 |
+
16
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
18,
|
| 33 |
+
4
|
| 34 |
+
],
|
| 35 |
+
[
|
| 36 |
+
18,
|
| 37 |
+
11
|
| 38 |
+
],
|
| 39 |
+
[
|
| 40 |
+
18,
|
| 41 |
+
19
|
| 42 |
+
],
|
| 43 |
+
[
|
| 44 |
+
19,
|
| 45 |
+
11
|
| 46 |
+
],
|
| 47 |
+
[
|
| 48 |
+
21,
|
| 49 |
+
2
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
21,
|
| 53 |
+
3
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
22,
|
| 57 |
+
3
|
| 58 |
+
],
|
| 59 |
+
[
|
| 60 |
+
22,
|
| 61 |
+
9
|
| 62 |
+
],
|
| 63 |
+
[
|
| 64 |
+
22,
|
| 65 |
+
12
|
| 66 |
+
],
|
| 67 |
+
[
|
| 68 |
+
23,
|
| 69 |
+
5
|
| 70 |
+
],
|
| 71 |
+
[
|
| 72 |
+
23,
|
| 73 |
+
7
|
| 74 |
+
],
|
| 75 |
+
[
|
| 76 |
+
23,
|
| 77 |
+
13
|
| 78 |
+
],
|
| 79 |
+
[
|
| 80 |
+
25,
|
| 81 |
+
5
|
| 82 |
+
],
|
| 83 |
+
[
|
| 84 |
+
26,
|
| 85 |
+
1
|
| 86 |
+
],
|
| 87 |
+
[
|
| 88 |
+
26,
|
| 89 |
+
12
|
| 90 |
+
],
|
| 91 |
+
[
|
| 92 |
+
27,
|
| 93 |
+
15
|
| 94 |
+
]
|
| 95 |
+
],
|
| 96 |
+
"begin_suppress_tokens": [
|
| 97 |
+
220,
|
| 98 |
+
50257
|
| 99 |
+
],
|
| 100 |
+
"bos_token_id": 50257,
|
| 101 |
+
"decoder_start_token_id": 50258,
|
| 102 |
+
"eos_token_id": 50257,
|
| 103 |
+
"forced_decoder_ids": [
|
| 104 |
+
[
|
| 105 |
+
1,
|
| 106 |
+
50304
|
| 107 |
+
],
|
| 108 |
+
[
|
| 109 |
+
2,
|
| 110 |
+
50359
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
3,
|
| 114 |
+
50363
|
| 115 |
+
]
|
| 116 |
+
],
|
| 117 |
+
"is_multilingual": true,
|
| 118 |
+
"lang_to_id": {
|
| 119 |
+
"<|af|>": 50327,
|
| 120 |
+
"<|am|>": 50334,
|
| 121 |
+
"<|ar|>": 50272,
|
| 122 |
+
"<|as|>": 50350,
|
| 123 |
+
"<|az|>": 50304,
|
| 124 |
+
"<|ba|>": 50355,
|
| 125 |
+
"<|be|>": 50330,
|
| 126 |
+
"<|bg|>": 50292,
|
| 127 |
+
"<|bn|>": 50302,
|
| 128 |
+
"<|bo|>": 50347,
|
| 129 |
+
"<|br|>": 50309,
|
| 130 |
+
"<|bs|>": 50315,
|
| 131 |
+
"<|ca|>": 50270,
|
| 132 |
+
"<|cs|>": 50283,
|
| 133 |
+
"<|cy|>": 50297,
|
| 134 |
+
"<|da|>": 50285,
|
| 135 |
+
"<|de|>": 50261,
|
| 136 |
+
"<|el|>": 50281,
|
| 137 |
+
"<|en|>": 50259,
|
| 138 |
+
"<|es|>": 50262,
|
| 139 |
+
"<|et|>": 50307,
|
| 140 |
+
"<|eu|>": 50310,
|
| 141 |
+
"<|fa|>": 50300,
|
| 142 |
+
"<|fi|>": 50277,
|
| 143 |
+
"<|fo|>": 50338,
|
| 144 |
+
"<|fr|>": 50265,
|
| 145 |
+
"<|gl|>": 50319,
|
| 146 |
+
"<|gu|>": 50333,
|
| 147 |
+
"<|haw|>": 50352,
|
| 148 |
+
"<|ha|>": 50354,
|
| 149 |
+
"<|he|>": 50279,
|
| 150 |
+
"<|hi|>": 50276,
|
| 151 |
+
"<|hr|>": 50291,
|
| 152 |
+
"<|ht|>": 50339,
|
| 153 |
+
"<|hu|>": 50286,
|
| 154 |
+
"<|hy|>": 50312,
|
| 155 |
+
"<|id|>": 50275,
|
| 156 |
+
"<|is|>": 50311,
|
| 157 |
+
"<|it|>": 50274,
|
| 158 |
+
"<|ja|>": 50266,
|
| 159 |
+
"<|jw|>": 50356,
|
| 160 |
+
"<|ka|>": 50329,
|
| 161 |
+
"<|kk|>": 50316,
|
| 162 |
+
"<|km|>": 50323,
|
| 163 |
+
"<|kn|>": 50306,
|
| 164 |
+
"<|ko|>": 50264,
|
| 165 |
+
"<|la|>": 50294,
|
| 166 |
+
"<|lb|>": 50345,
|
| 167 |
+
"<|ln|>": 50353,
|
| 168 |
+
"<|lo|>": 50336,
|
| 169 |
+
"<|lt|>": 50293,
|
| 170 |
+
"<|lv|>": 50301,
|
| 171 |
+
"<|mg|>": 50349,
|
| 172 |
+
"<|mi|>": 50295,
|
| 173 |
+
"<|mk|>": 50308,
|
| 174 |
+
"<|ml|>": 50296,
|
| 175 |
+
"<|mn|>": 50314,
|
| 176 |
+
"<|mr|>": 50320,
|
| 177 |
+
"<|ms|>": 50282,
|
| 178 |
+
"<|mt|>": 50343,
|
| 179 |
+
"<|my|>": 50346,
|
| 180 |
+
"<|ne|>": 50313,
|
| 181 |
+
"<|nl|>": 50271,
|
| 182 |
+
"<|nn|>": 50342,
|
| 183 |
+
"<|no|>": 50288,
|
| 184 |
+
"<|oc|>": 50328,
|
| 185 |
+
"<|pa|>": 50321,
|
| 186 |
+
"<|pl|>": 50269,
|
| 187 |
+
"<|ps|>": 50340,
|
| 188 |
+
"<|pt|>": 50267,
|
| 189 |
+
"<|ro|>": 50284,
|
| 190 |
+
"<|ru|>": 50263,
|
| 191 |
+
"<|sa|>": 50344,
|
| 192 |
+
"<|sd|>": 50332,
|
| 193 |
+
"<|si|>": 50322,
|
| 194 |
+
"<|sk|>": 50298,
|
| 195 |
+
"<|sl|>": 50305,
|
| 196 |
+
"<|sn|>": 50324,
|
| 197 |
+
"<|so|>": 50326,
|
| 198 |
+
"<|sq|>": 50317,
|
| 199 |
+
"<|sr|>": 50303,
|
| 200 |
+
"<|su|>": 50357,
|
| 201 |
+
"<|sv|>": 50273,
|
| 202 |
+
"<|sw|>": 50318,
|
| 203 |
+
"<|ta|>": 50287,
|
| 204 |
+
"<|te|>": 50299,
|
| 205 |
+
"<|tg|>": 50331,
|
| 206 |
+
"<|th|>": 50289,
|
| 207 |
+
"<|tk|>": 50341,
|
| 208 |
+
"<|tl|>": 50348,
|
| 209 |
+
"<|tr|>": 50268,
|
| 210 |
+
"<|tt|>": 50351,
|
| 211 |
+
"<|uk|>": 50280,
|
| 212 |
+
"<|ur|>": 50290,
|
| 213 |
+
"<|uz|>": 50337,
|
| 214 |
+
"<|vi|>": 50278,
|
| 215 |
+
"<|yi|>": 50335,
|
| 216 |
+
"<|yo|>": 50325,
|
| 217 |
+
"<|zh|>": 50260
|
| 218 |
+
},
|
| 219 |
+
"language": "azerbaijani",
|
| 220 |
+
"max_initial_timestamp_index": 50,
|
| 221 |
+
"max_length": 448,
|
| 222 |
+
"no_timestamps_token_id": 50363,
|
| 223 |
+
"pad_token_id": 50257,
|
| 224 |
+
"prev_sot_token_id": 50361,
|
| 225 |
+
"return_timestamps": false,
|
| 226 |
+
"suppress_tokens": [],
|
| 227 |
+
"task": "transcribe",
|
| 228 |
+
"task_to_id": {
|
| 229 |
+
"transcribe": 50359,
|
| 230 |
+
"translate": 50358
|
| 231 |
+
},
|
| 232 |
+
"transformers_version": "4.48.0"
|
| 233 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f4da568a59ac91b8552e6f3ea528ad37c777855838670fc3060f614befbe564
|
| 3 |
+
size 4992706480
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad925562bc89a272373ae30b8cecda8339794ff8bb9035d5dcdbdfc5e8927e3b
|
| 3 |
+
size 1180663192
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1455 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 22.283451007404857,
|
| 3 |
+
"best_model_checkpoint": "./whisper-large-v2/second2/checkpoint-500",
|
| 4 |
+
"epoch": 0.2133902373966391,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0010669511869831954,
|
| 13 |
+
"grad_norm": 19.418699264526367,
|
| 14 |
+
"learning_rate": 3.3333333333333334e-08,
|
| 15 |
+
"loss": 2.4187,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.002133902373966391,
|
| 20 |
+
"grad_norm": 21.75494956970215,
|
| 21 |
+
"learning_rate": 6.666666666666667e-08,
|
| 22 |
+
"loss": 2.3362,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0032008535609495867,
|
| 27 |
+
"grad_norm": 21.226938247680664,
|
| 28 |
+
"learning_rate": 1e-07,
|
| 29 |
+
"loss": 2.4288,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.004267804747932782,
|
| 34 |
+
"grad_norm": 27.21125602722168,
|
| 35 |
+
"learning_rate": 1.3333333333333334e-07,
|
| 36 |
+
"loss": 2.4004,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.005334755934915978,
|
| 41 |
+
"grad_norm": 13.559316635131836,
|
| 42 |
+
"learning_rate": 1.6666666666666665e-07,
|
| 43 |
+
"loss": 2.1607,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0064017071218991735,
|
| 48 |
+
"grad_norm": 13.044219970703125,
|
| 49 |
+
"learning_rate": 1.9333333333333332e-07,
|
| 50 |
+
"loss": 2.1591,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.007468658308882369,
|
| 55 |
+
"grad_norm": 13.89301872253418,
|
| 56 |
+
"learning_rate": 2.2666666666666663e-07,
|
| 57 |
+
"loss": 2.0855,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.008535609495865563,
|
| 62 |
+
"grad_norm": 14.154369354248047,
|
| 63 |
+
"learning_rate": 2.6e-07,
|
| 64 |
+
"loss": 1.9557,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.00960256068284876,
|
| 69 |
+
"grad_norm": 9.126311302185059,
|
| 70 |
+
"learning_rate": 2.933333333333333e-07,
|
| 71 |
+
"loss": 1.8661,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.010669511869831956,
|
| 76 |
+
"grad_norm": 13.619270324707031,
|
| 77 |
+
"learning_rate": 3.2666666666666663e-07,
|
| 78 |
+
"loss": 1.8424,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.01173646305681515,
|
| 83 |
+
"grad_norm": 9.875323295593262,
|
| 84 |
+
"learning_rate": 3.6e-07,
|
| 85 |
+
"loss": 1.6208,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.012803414243798347,
|
| 90 |
+
"grad_norm": 11.143688201904297,
|
| 91 |
+
"learning_rate": 3.933333333333333e-07,
|
| 92 |
+
"loss": 1.5396,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.013870365430781541,
|
| 97 |
+
"grad_norm": 10.829161643981934,
|
| 98 |
+
"learning_rate": 4.266666666666667e-07,
|
| 99 |
+
"loss": 1.4174,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.014937316617764738,
|
| 104 |
+
"grad_norm": 7.393435001373291,
|
| 105 |
+
"learning_rate": 4.6e-07,
|
| 106 |
+
"loss": 1.1693,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.016004267804747934,
|
| 111 |
+
"grad_norm": 4.182456016540527,
|
| 112 |
+
"learning_rate": 4.933333333333333e-07,
|
| 113 |
+
"loss": 1.1779,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.017071218991731127,
|
| 118 |
+
"grad_norm": 8.4662504196167,
|
| 119 |
+
"learning_rate": 5.266666666666666e-07,
|
| 120 |
+
"loss": 1.1281,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.018138170178714323,
|
| 125 |
+
"grad_norm": 4.043624401092529,
|
| 126 |
+
"learning_rate": 5.6e-07,
|
| 127 |
+
"loss": 1.0614,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.01920512136569752,
|
| 132 |
+
"grad_norm": 3.8517227172851562,
|
| 133 |
+
"learning_rate": 5.933333333333334e-07,
|
| 134 |
+
"loss": 1.0066,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.020272072552680716,
|
| 139 |
+
"grad_norm": 4.19964075088501,
|
| 140 |
+
"learning_rate": 6.266666666666667e-07,
|
| 141 |
+
"loss": 1.0659,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.021339023739663912,
|
| 146 |
+
"grad_norm": 4.7087178230285645,
|
| 147 |
+
"learning_rate": 6.6e-07,
|
| 148 |
+
"loss": 0.9793,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.022405974926647105,
|
| 153 |
+
"grad_norm": 4.864803314208984,
|
| 154 |
+
"learning_rate": 6.933333333333333e-07,
|
| 155 |
+
"loss": 0.9675,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.0234729261136303,
|
| 160 |
+
"grad_norm": 3.8939764499664307,
|
| 161 |
+
"learning_rate": 7.266666666666667e-07,
|
| 162 |
+
"loss": 0.9513,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.024539877300613498,
|
| 167 |
+
"grad_norm": 3.557497978210449,
|
| 168 |
+
"learning_rate": 7.599999999999999e-07,
|
| 169 |
+
"loss": 0.9164,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.025606828487596694,
|
| 174 |
+
"grad_norm": 4.033596038818359,
|
| 175 |
+
"learning_rate": 7.933333333333333e-07,
|
| 176 |
+
"loss": 0.9069,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.026673779674579887,
|
| 181 |
+
"grad_norm": 4.726081371307373,
|
| 182 |
+
"learning_rate": 8.266666666666667e-07,
|
| 183 |
+
"loss": 0.8976,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.027740730861563083,
|
| 188 |
+
"grad_norm": 18.711572647094727,
|
| 189 |
+
"learning_rate": 8.599999999999999e-07,
|
| 190 |
+
"loss": 0.9157,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.02880768204854628,
|
| 195 |
+
"grad_norm": 4.13236141204834,
|
| 196 |
+
"learning_rate": 8.933333333333333e-07,
|
| 197 |
+
"loss": 0.8808,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.029874633235529476,
|
| 202 |
+
"grad_norm": 3.7335939407348633,
|
| 203 |
+
"learning_rate": 9.266666666666665e-07,
|
| 204 |
+
"loss": 0.7707,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.03094158442251267,
|
| 209 |
+
"grad_norm": 4.5814313888549805,
|
| 210 |
+
"learning_rate": 9.6e-07,
|
| 211 |
+
"loss": 0.8349,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.03200853560949587,
|
| 216 |
+
"grad_norm": 4.993039608001709,
|
| 217 |
+
"learning_rate": 9.933333333333333e-07,
|
| 218 |
+
"loss": 0.7002,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.033075486796479064,
|
| 223 |
+
"grad_norm": 5.326510906219482,
|
| 224 |
+
"learning_rate": 9.996791443850267e-07,
|
| 225 |
+
"loss": 0.6418,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.034142437983462254,
|
| 230 |
+
"grad_norm": 4.4001994132995605,
|
| 231 |
+
"learning_rate": 9.99144385026738e-07,
|
| 232 |
+
"loss": 0.5632,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.03520938917044545,
|
| 237 |
+
"grad_norm": 71.39772033691406,
|
| 238 |
+
"learning_rate": 9.98716577540107e-07,
|
| 239 |
+
"loss": 0.6374,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.036276340357428646,
|
| 244 |
+
"grad_norm": 9.561308860778809,
|
| 245 |
+
"learning_rate": 9.98288770053476e-07,
|
| 246 |
+
"loss": 0.5493,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.03734329154441184,
|
| 251 |
+
"grad_norm": 2.866039991378784,
|
| 252 |
+
"learning_rate": 9.97754010695187e-07,
|
| 253 |
+
"loss": 0.473,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.03841024273139504,
|
| 258 |
+
"grad_norm": 3.0788004398345947,
|
| 259 |
+
"learning_rate": 9.972192513368983e-07,
|
| 260 |
+
"loss": 0.4903,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.039477193918378235,
|
| 265 |
+
"grad_norm": 3.4059643745422363,
|
| 266 |
+
"learning_rate": 9.966844919786097e-07,
|
| 267 |
+
"loss": 0.5017,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.04054414510536143,
|
| 272 |
+
"grad_norm": 2.9747097492218018,
|
| 273 |
+
"learning_rate": 9.961497326203208e-07,
|
| 274 |
+
"loss": 0.4269,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.04161109629234463,
|
| 279 |
+
"grad_norm": 3.476583242416382,
|
| 280 |
+
"learning_rate": 9.95614973262032e-07,
|
| 281 |
+
"loss": 0.4214,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.042678047479327824,
|
| 286 |
+
"grad_norm": 3.0810964107513428,
|
| 287 |
+
"learning_rate": 9.950802139037432e-07,
|
| 288 |
+
"loss": 0.4291,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.043744998666311014,
|
| 293 |
+
"grad_norm": 87.03646850585938,
|
| 294 |
+
"learning_rate": 9.945454545454544e-07,
|
| 295 |
+
"loss": 0.4035,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.04481194985329421,
|
| 300 |
+
"grad_norm": 2.6879165172576904,
|
| 301 |
+
"learning_rate": 9.940106951871658e-07,
|
| 302 |
+
"loss": 0.428,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.045878901040277406,
|
| 307 |
+
"grad_norm": 3.602217197418213,
|
| 308 |
+
"learning_rate": 9.93475935828877e-07,
|
| 309 |
+
"loss": 0.4534,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.0469458522272606,
|
| 314 |
+
"grad_norm": 2.9568989276885986,
|
| 315 |
+
"learning_rate": 9.929411764705881e-07,
|
| 316 |
+
"loss": 0.42,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.0480128034142438,
|
| 321 |
+
"grad_norm": 2.7602076530456543,
|
| 322 |
+
"learning_rate": 9.924064171122995e-07,
|
| 323 |
+
"loss": 0.448,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.049079754601226995,
|
| 328 |
+
"grad_norm": 2.7191200256347656,
|
| 329 |
+
"learning_rate": 9.918716577540107e-07,
|
| 330 |
+
"loss": 0.4046,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.05014670578821019,
|
| 335 |
+
"grad_norm": 2.7233424186706543,
|
| 336 |
+
"learning_rate": 9.913368983957219e-07,
|
| 337 |
+
"loss": 0.4028,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.05121365697519339,
|
| 342 |
+
"grad_norm": 2.730400323867798,
|
| 343 |
+
"learning_rate": 9.90802139037433e-07,
|
| 344 |
+
"loss": 0.4361,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.05228060816217658,
|
| 349 |
+
"grad_norm": 4.667561054229736,
|
| 350 |
+
"learning_rate": 9.902673796791442e-07,
|
| 351 |
+
"loss": 0.4183,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.05334755934915977,
|
| 356 |
+
"grad_norm": 2.981497049331665,
|
| 357 |
+
"learning_rate": 9.897326203208556e-07,
|
| 358 |
+
"loss": 0.4148,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.05441451053614297,
|
| 363 |
+
"grad_norm": 9.336112976074219,
|
| 364 |
+
"learning_rate": 9.891978609625668e-07,
|
| 365 |
+
"loss": 0.4386,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.055481461723126166,
|
| 370 |
+
"grad_norm": 4.434041500091553,
|
| 371 |
+
"learning_rate": 9.88663101604278e-07,
|
| 372 |
+
"loss": 0.4235,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.05654841291010936,
|
| 377 |
+
"grad_norm": 2.695866346359253,
|
| 378 |
+
"learning_rate": 9.881283422459892e-07,
|
| 379 |
+
"loss": 0.4424,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.05761536409709256,
|
| 384 |
+
"grad_norm": 2.8247873783111572,
|
| 385 |
+
"learning_rate": 9.875935828877004e-07,
|
| 386 |
+
"loss": 0.387,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.058682315284075755,
|
| 391 |
+
"grad_norm": 3.4680376052856445,
|
| 392 |
+
"learning_rate": 9.870588235294118e-07,
|
| 393 |
+
"loss": 0.4294,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.05974926647105895,
|
| 398 |
+
"grad_norm": 2.6994473934173584,
|
| 399 |
+
"learning_rate": 9.86524064171123e-07,
|
| 400 |
+
"loss": 0.4043,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.06081621765804215,
|
| 405 |
+
"grad_norm": 2.6048827171325684,
|
| 406 |
+
"learning_rate": 9.859893048128341e-07,
|
| 407 |
+
"loss": 0.4064,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.06188316884502534,
|
| 412 |
+
"grad_norm": 3.028503179550171,
|
| 413 |
+
"learning_rate": 9.854545454545455e-07,
|
| 414 |
+
"loss": 0.4269,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.06295012003200853,
|
| 419 |
+
"grad_norm": 3.3406739234924316,
|
| 420 |
+
"learning_rate": 9.849197860962567e-07,
|
| 421 |
+
"loss": 0.4339,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.06401707121899174,
|
| 426 |
+
"grad_norm": 3.1800878047943115,
|
| 427 |
+
"learning_rate": 9.843850267379679e-07,
|
| 428 |
+
"loss": 0.3972,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.06508402240597493,
|
| 433 |
+
"grad_norm": 2.818852424621582,
|
| 434 |
+
"learning_rate": 9.83850267379679e-07,
|
| 435 |
+
"loss": 0.3898,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.06615097359295813,
|
| 440 |
+
"grad_norm": 3.256840705871582,
|
| 441 |
+
"learning_rate": 9.833155080213902e-07,
|
| 442 |
+
"loss": 0.4377,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.06721792477994132,
|
| 447 |
+
"grad_norm": 3.388472318649292,
|
| 448 |
+
"learning_rate": 9.827807486631016e-07,
|
| 449 |
+
"loss": 0.4187,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.06828487596692451,
|
| 454 |
+
"grad_norm": 4.434413909912109,
|
| 455 |
+
"learning_rate": 9.822459893048128e-07,
|
| 456 |
+
"loss": 0.4009,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.06935182715390771,
|
| 461 |
+
"grad_norm": 3.08677077293396,
|
| 462 |
+
"learning_rate": 9.81711229946524e-07,
|
| 463 |
+
"loss": 0.3837,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.0704187783408909,
|
| 468 |
+
"grad_norm": 3.7852623462677,
|
| 469 |
+
"learning_rate": 9.811764705882352e-07,
|
| 470 |
+
"loss": 0.3999,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.0714857295278741,
|
| 475 |
+
"grad_norm": 2.947720766067505,
|
| 476 |
+
"learning_rate": 9.806417112299463e-07,
|
| 477 |
+
"loss": 0.3677,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.07255268071485729,
|
| 482 |
+
"grad_norm": 3.1685659885406494,
|
| 483 |
+
"learning_rate": 9.801069518716577e-07,
|
| 484 |
+
"loss": 0.4035,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.0736196319018405,
|
| 489 |
+
"grad_norm": 2.661599636077881,
|
| 490 |
+
"learning_rate": 9.79572192513369e-07,
|
| 491 |
+
"loss": 0.3658,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.07468658308882369,
|
| 496 |
+
"grad_norm": 2.6443653106689453,
|
| 497 |
+
"learning_rate": 9.7903743315508e-07,
|
| 498 |
+
"loss": 0.3805,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.07575353427580689,
|
| 503 |
+
"grad_norm": 3.653778314590454,
|
| 504 |
+
"learning_rate": 9.785026737967915e-07,
|
| 505 |
+
"loss": 0.407,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.07682048546279008,
|
| 510 |
+
"grad_norm": 2.991504430770874,
|
| 511 |
+
"learning_rate": 9.779679144385027e-07,
|
| 512 |
+
"loss": 0.4135,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.07788743664977327,
|
| 517 |
+
"grad_norm": 2.7770955562591553,
|
| 518 |
+
"learning_rate": 9.774331550802139e-07,
|
| 519 |
+
"loss": 0.3934,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.07895438783675647,
|
| 524 |
+
"grad_norm": 2.686368703842163,
|
| 525 |
+
"learning_rate": 9.76898395721925e-07,
|
| 526 |
+
"loss": 0.409,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.08002133902373966,
|
| 531 |
+
"grad_norm": 3.307638168334961,
|
| 532 |
+
"learning_rate": 9.763636363636362e-07,
|
| 533 |
+
"loss": 0.3872,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.08108829021072286,
|
| 538 |
+
"grad_norm": 8.76164722442627,
|
| 539 |
+
"learning_rate": 9.758288770053476e-07,
|
| 540 |
+
"loss": 0.3882,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.08215524139770605,
|
| 545 |
+
"grad_norm": 2.868077039718628,
|
| 546 |
+
"learning_rate": 9.752941176470588e-07,
|
| 547 |
+
"loss": 0.4123,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.08322219258468926,
|
| 552 |
+
"grad_norm": 4.677827835083008,
|
| 553 |
+
"learning_rate": 9.7475935828877e-07,
|
| 554 |
+
"loss": 0.362,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.08428914377167245,
|
| 559 |
+
"grad_norm": 3.836914539337158,
|
| 560 |
+
"learning_rate": 9.742245989304812e-07,
|
| 561 |
+
"loss": 0.4023,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.08535609495865565,
|
| 566 |
+
"grad_norm": 2.7120203971862793,
|
| 567 |
+
"learning_rate": 9.736898395721923e-07,
|
| 568 |
+
"loss": 0.419,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.08642304614563884,
|
| 573 |
+
"grad_norm": 3.1341233253479004,
|
| 574 |
+
"learning_rate": 9.731550802139037e-07,
|
| 575 |
+
"loss": 0.4275,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.08748999733262203,
|
| 580 |
+
"grad_norm": 3.0901923179626465,
|
| 581 |
+
"learning_rate": 9.72620320855615e-07,
|
| 582 |
+
"loss": 0.3799,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.08855694851960523,
|
| 587 |
+
"grad_norm": 2.7124781608581543,
|
| 588 |
+
"learning_rate": 9.72085561497326e-07,
|
| 589 |
+
"loss": 0.3788,
|
| 590 |
+
"step": 415
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.08962389970658842,
|
| 594 |
+
"grad_norm": 2.8177292346954346,
|
| 595 |
+
"learning_rate": 9.715508021390375e-07,
|
| 596 |
+
"loss": 0.3436,
|
| 597 |
+
"step": 420
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.09069085089357162,
|
| 601 |
+
"grad_norm": 3.063669204711914,
|
| 602 |
+
"learning_rate": 9.710160427807487e-07,
|
| 603 |
+
"loss": 0.4312,
|
| 604 |
+
"step": 425
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.09175780208055481,
|
| 608 |
+
"grad_norm": 2.78320574760437,
|
| 609 |
+
"learning_rate": 9.704812834224598e-07,
|
| 610 |
+
"loss": 0.4122,
|
| 611 |
+
"step": 430
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.09282475326753802,
|
| 615 |
+
"grad_norm": 3.080400228500366,
|
| 616 |
+
"learning_rate": 9.69946524064171e-07,
|
| 617 |
+
"loss": 0.3917,
|
| 618 |
+
"step": 435
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.0938917044545212,
|
| 622 |
+
"grad_norm": 3.02703857421875,
|
| 623 |
+
"learning_rate": 9.694117647058822e-07,
|
| 624 |
+
"loss": 0.3546,
|
| 625 |
+
"step": 440
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.09495865564150441,
|
| 629 |
+
"grad_norm": 2.6559834480285645,
|
| 630 |
+
"learning_rate": 9.688770053475936e-07,
|
| 631 |
+
"loss": 0.3536,
|
| 632 |
+
"step": 445
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.0960256068284876,
|
| 636 |
+
"grad_norm": 3.939589738845825,
|
| 637 |
+
"learning_rate": 9.683422459893048e-07,
|
| 638 |
+
"loss": 0.3729,
|
| 639 |
+
"step": 450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.09709255801547079,
|
| 643 |
+
"grad_norm": 2.419799327850342,
|
| 644 |
+
"learning_rate": 9.67807486631016e-07,
|
| 645 |
+
"loss": 0.3474,
|
| 646 |
+
"step": 455
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.09815950920245399,
|
| 650 |
+
"grad_norm": 2.237165927886963,
|
| 651 |
+
"learning_rate": 9.672727272727271e-07,
|
| 652 |
+
"loss": 0.3387,
|
| 653 |
+
"step": 460
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.09922646038943718,
|
| 657 |
+
"grad_norm": 2.6400506496429443,
|
| 658 |
+
"learning_rate": 9.667379679144385e-07,
|
| 659 |
+
"loss": 0.3462,
|
| 660 |
+
"step": 465
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.10029341157642038,
|
| 664 |
+
"grad_norm": 3.294222354888916,
|
| 665 |
+
"learning_rate": 9.662032085561497e-07,
|
| 666 |
+
"loss": 0.3724,
|
| 667 |
+
"step": 470
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.10136036276340357,
|
| 671 |
+
"grad_norm": 2.5825111865997314,
|
| 672 |
+
"learning_rate": 9.656684491978609e-07,
|
| 673 |
+
"loss": 0.3652,
|
| 674 |
+
"step": 475
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.10242731395038678,
|
| 678 |
+
"grad_norm": 2.6807165145874023,
|
| 679 |
+
"learning_rate": 9.65133689839572e-07,
|
| 680 |
+
"loss": 0.3824,
|
| 681 |
+
"step": 480
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.10349426513736996,
|
| 685 |
+
"grad_norm": 2.541398048400879,
|
| 686 |
+
"learning_rate": 9.645989304812835e-07,
|
| 687 |
+
"loss": 0.3509,
|
| 688 |
+
"step": 485
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.10456121632435315,
|
| 692 |
+
"grad_norm": 3.071420192718506,
|
| 693 |
+
"learning_rate": 9.640641711229946e-07,
|
| 694 |
+
"loss": 0.3511,
|
| 695 |
+
"step": 490
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.10562816751133636,
|
| 699 |
+
"grad_norm": 3.117623805999756,
|
| 700 |
+
"learning_rate": 9.635294117647058e-07,
|
| 701 |
+
"loss": 0.3823,
|
| 702 |
+
"step": 495
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.10669511869831955,
|
| 706 |
+
"grad_norm": 2.9759390354156494,
|
| 707 |
+
"learning_rate": 9.62994652406417e-07,
|
| 708 |
+
"loss": 0.3595,
|
| 709 |
+
"step": 500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.10669511869831955,
|
| 713 |
+
"eval_bleu": 0.5858525890811711,
|
| 714 |
+
"eval_cer": 5.81035140115651,
|
| 715 |
+
"eval_loss": 0.35532379150390625,
|
| 716 |
+
"eval_runtime": 1038.2775,
|
| 717 |
+
"eval_samples_per_second": 0.884,
|
| 718 |
+
"eval_steps_per_second": 0.222,
|
| 719 |
+
"eval_wer": 22.283451007404857,
|
| 720 |
+
"step": 500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.10776206988530275,
|
| 724 |
+
"grad_norm": 2.9231984615325928,
|
| 725 |
+
"learning_rate": 9.475679090334807e-07,
|
| 726 |
+
"loss": 0.3783,
|
| 727 |
+
"step": 505
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.10882902107228594,
|
| 731 |
+
"grad_norm": 2.2739880084991455,
|
| 732 |
+
"learning_rate": 9.470414824173509e-07,
|
| 733 |
+
"loss": 0.3238,
|
| 734 |
+
"step": 510
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.10989597225926914,
|
| 738 |
+
"grad_norm": 2.603306531906128,
|
| 739 |
+
"learning_rate": 9.465150558012212e-07,
|
| 740 |
+
"loss": 0.3538,
|
| 741 |
+
"step": 515
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.11096292344625233,
|
| 745 |
+
"grad_norm": 2.871011972427368,
|
| 746 |
+
"learning_rate": 9.459886291850916e-07,
|
| 747 |
+
"loss": 0.3955,
|
| 748 |
+
"step": 520
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.11202987463323553,
|
| 752 |
+
"grad_norm": 3.134646415710449,
|
| 753 |
+
"learning_rate": 9.454622025689618e-07,
|
| 754 |
+
"loss": 0.3508,
|
| 755 |
+
"step": 525
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.11309682582021872,
|
| 759 |
+
"grad_norm": 3.014796733856201,
|
| 760 |
+
"learning_rate": 9.449357759528321e-07,
|
| 761 |
+
"loss": 0.3664,
|
| 762 |
+
"step": 530
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.11416377700720191,
|
| 766 |
+
"grad_norm": 3.0675926208496094,
|
| 767 |
+
"learning_rate": 9.444093493367024e-07,
|
| 768 |
+
"loss": 0.3497,
|
| 769 |
+
"step": 535
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.11523072819418512,
|
| 773 |
+
"grad_norm": 4.508389472961426,
|
| 774 |
+
"learning_rate": 9.438829227205727e-07,
|
| 775 |
+
"loss": 0.3172,
|
| 776 |
+
"step": 540
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.1162976793811683,
|
| 780 |
+
"grad_norm": 2.528317451477051,
|
| 781 |
+
"learning_rate": 9.43356496104443e-07,
|
| 782 |
+
"loss": 0.3495,
|
| 783 |
+
"step": 545
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.11736463056815151,
|
| 787 |
+
"grad_norm": 2.759575843811035,
|
| 788 |
+
"learning_rate": 9.428300694883133e-07,
|
| 789 |
+
"loss": 0.3326,
|
| 790 |
+
"step": 550
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.1184315817551347,
|
| 794 |
+
"grad_norm": 6.699812889099121,
|
| 795 |
+
"learning_rate": 9.423036428721835e-07,
|
| 796 |
+
"loss": 0.4124,
|
| 797 |
+
"step": 555
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.1194985329421179,
|
| 801 |
+
"grad_norm": 2.358922243118286,
|
| 802 |
+
"learning_rate": 9.417772162560539e-07,
|
| 803 |
+
"loss": 0.3292,
|
| 804 |
+
"step": 560
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.12056548412910109,
|
| 808 |
+
"grad_norm": 2.3635692596435547,
|
| 809 |
+
"learning_rate": 9.412507896399241e-07,
|
| 810 |
+
"loss": 0.3715,
|
| 811 |
+
"step": 565
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.1216324353160843,
|
| 815 |
+
"grad_norm": 2.8696706295013428,
|
| 816 |
+
"learning_rate": 9.407243630237944e-07,
|
| 817 |
+
"loss": 0.3348,
|
| 818 |
+
"step": 570
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.12269938650306748,
|
| 822 |
+
"grad_norm": 3.717510223388672,
|
| 823 |
+
"learning_rate": 9.401979364076647e-07,
|
| 824 |
+
"loss": 0.355,
|
| 825 |
+
"step": 575
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.12376633769005067,
|
| 829 |
+
"grad_norm": 3.9285202026367188,
|
| 830 |
+
"learning_rate": 9.39671509791535e-07,
|
| 831 |
+
"loss": 0.3752,
|
| 832 |
+
"step": 580
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.12483328887703388,
|
| 836 |
+
"grad_norm": 3.560582399368286,
|
| 837 |
+
"learning_rate": 9.391450831754053e-07,
|
| 838 |
+
"loss": 0.3422,
|
| 839 |
+
"step": 585
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.12590024006401707,
|
| 843 |
+
"grad_norm": 6.333406925201416,
|
| 844 |
+
"learning_rate": 9.386186565592757e-07,
|
| 845 |
+
"loss": 0.3436,
|
| 846 |
+
"step": 590
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.12696719125100026,
|
| 850 |
+
"grad_norm": 2.94331431388855,
|
| 851 |
+
"learning_rate": 9.380922299431458e-07,
|
| 852 |
+
"loss": 0.3346,
|
| 853 |
+
"step": 595
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.12803414243798347,
|
| 857 |
+
"grad_norm": 2.933142900466919,
|
| 858 |
+
"learning_rate": 9.375658033270162e-07,
|
| 859 |
+
"loss": 0.3414,
|
| 860 |
+
"step": 600
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.12910109362496666,
|
| 864 |
+
"grad_norm": 3.2017970085144043,
|
| 865 |
+
"learning_rate": 9.370393767108865e-07,
|
| 866 |
+
"loss": 0.3731,
|
| 867 |
+
"step": 605
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.13016804481194985,
|
| 871 |
+
"grad_norm": 3.2127702236175537,
|
| 872 |
+
"learning_rate": 9.365129500947567e-07,
|
| 873 |
+
"loss": 0.3399,
|
| 874 |
+
"step": 610
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.13123499599893304,
|
| 878 |
+
"grad_norm": 3.1433818340301514,
|
| 879 |
+
"learning_rate": 9.35986523478627e-07,
|
| 880 |
+
"loss": 0.342,
|
| 881 |
+
"step": 615
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.13230194718591626,
|
| 885 |
+
"grad_norm": 3.0913007259368896,
|
| 886 |
+
"learning_rate": 9.354600968624973e-07,
|
| 887 |
+
"loss": 0.3543,
|
| 888 |
+
"step": 620
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 0.13336889837289945,
|
| 892 |
+
"grad_norm": 3.459428310394287,
|
| 893 |
+
"learning_rate": 9.349336702463676e-07,
|
| 894 |
+
"loss": 0.292,
|
| 895 |
+
"step": 625
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 0.13443584955988264,
|
| 899 |
+
"grad_norm": 2.965162754058838,
|
| 900 |
+
"learning_rate": 9.34407243630238e-07,
|
| 901 |
+
"loss": 0.3591,
|
| 902 |
+
"step": 630
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.13550280074686583,
|
| 906 |
+
"grad_norm": 2.476099967956543,
|
| 907 |
+
"learning_rate": 9.338808170141081e-07,
|
| 908 |
+
"loss": 0.3351,
|
| 909 |
+
"step": 635
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.13656975193384902,
|
| 913 |
+
"grad_norm": 2.853848695755005,
|
| 914 |
+
"learning_rate": 9.333543903979785e-07,
|
| 915 |
+
"loss": 0.3828,
|
| 916 |
+
"step": 640
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.13763670312083223,
|
| 920 |
+
"grad_norm": 2.560877561569214,
|
| 921 |
+
"learning_rate": 9.328279637818488e-07,
|
| 922 |
+
"loss": 0.3183,
|
| 923 |
+
"step": 645
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.13870365430781542,
|
| 927 |
+
"grad_norm": 2.7191262245178223,
|
| 928 |
+
"learning_rate": 9.32301537165719e-07,
|
| 929 |
+
"loss": 0.3572,
|
| 930 |
+
"step": 650
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.1397706054947986,
|
| 934 |
+
"grad_norm": 3.388456106185913,
|
| 935 |
+
"learning_rate": 9.317751105495893e-07,
|
| 936 |
+
"loss": 0.3207,
|
| 937 |
+
"step": 655
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.1408375566817818,
|
| 941 |
+
"grad_norm": 2.827470302581787,
|
| 942 |
+
"learning_rate": 9.312486839334597e-07,
|
| 943 |
+
"loss": 0.3576,
|
| 944 |
+
"step": 660
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.14190450786876502,
|
| 948 |
+
"grad_norm": 2.630094528198242,
|
| 949 |
+
"learning_rate": 9.307222573173299e-07,
|
| 950 |
+
"loss": 0.3616,
|
| 951 |
+
"step": 665
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.1429714590557482,
|
| 955 |
+
"grad_norm": 2.7217891216278076,
|
| 956 |
+
"learning_rate": 9.301958307012003e-07,
|
| 957 |
+
"loss": 0.3434,
|
| 958 |
+
"step": 670
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 0.1440384102427314,
|
| 962 |
+
"grad_norm": 2.558335065841675,
|
| 963 |
+
"learning_rate": 9.296694040850705e-07,
|
| 964 |
+
"loss": 0.3516,
|
| 965 |
+
"step": 675
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 0.14510536142971459,
|
| 969 |
+
"grad_norm": 3.1991679668426514,
|
| 970 |
+
"learning_rate": 9.291429774689408e-07,
|
| 971 |
+
"loss": 0.338,
|
| 972 |
+
"step": 680
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 0.14617231261669777,
|
| 976 |
+
"grad_norm": 4.686666011810303,
|
| 977 |
+
"learning_rate": 9.286165508528111e-07,
|
| 978 |
+
"loss": 0.3539,
|
| 979 |
+
"step": 685
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 0.147239263803681,
|
| 983 |
+
"grad_norm": 3.0826447010040283,
|
| 984 |
+
"learning_rate": 9.280901242366814e-07,
|
| 985 |
+
"loss": 0.3313,
|
| 986 |
+
"step": 690
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.14830621499066418,
|
| 990 |
+
"grad_norm": 2.656141757965088,
|
| 991 |
+
"learning_rate": 9.275636976205516e-07,
|
| 992 |
+
"loss": 0.3454,
|
| 993 |
+
"step": 695
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.14937316617764737,
|
| 997 |
+
"grad_norm": 4.859818935394287,
|
| 998 |
+
"learning_rate": 9.27037271004422e-07,
|
| 999 |
+
"loss": 0.3331,
|
| 1000 |
+
"step": 700
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.15044011736463056,
|
| 1004 |
+
"grad_norm": 5.376903057098389,
|
| 1005 |
+
"learning_rate": 9.265108443882922e-07,
|
| 1006 |
+
"loss": 0.3377,
|
| 1007 |
+
"step": 705
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.15150706855161378,
|
| 1011 |
+
"grad_norm": 2.7976577281951904,
|
| 1012 |
+
"learning_rate": 9.259844177721626e-07,
|
| 1013 |
+
"loss": 0.3768,
|
| 1014 |
+
"step": 710
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.15257401973859697,
|
| 1018 |
+
"grad_norm": 2.993427038192749,
|
| 1019 |
+
"learning_rate": 9.254579911560328e-07,
|
| 1020 |
+
"loss": 0.3509,
|
| 1021 |
+
"step": 715
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.15364097092558016,
|
| 1025 |
+
"grad_norm": 2.8581597805023193,
|
| 1026 |
+
"learning_rate": 9.249315645399031e-07,
|
| 1027 |
+
"loss": 0.3338,
|
| 1028 |
+
"step": 720
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.15470792211256335,
|
| 1032 |
+
"grad_norm": 2.8063721656799316,
|
| 1033 |
+
"learning_rate": 9.244051379237734e-07,
|
| 1034 |
+
"loss": 0.3597,
|
| 1035 |
+
"step": 725
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.15577487329954653,
|
| 1039 |
+
"grad_norm": 2.7333686351776123,
|
| 1040 |
+
"learning_rate": 9.238787113076438e-07,
|
| 1041 |
+
"loss": 0.3563,
|
| 1042 |
+
"step": 730
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.15684182448652975,
|
| 1046 |
+
"grad_norm": 3.4143598079681396,
|
| 1047 |
+
"learning_rate": 9.233522846915139e-07,
|
| 1048 |
+
"loss": 0.336,
|
| 1049 |
+
"step": 735
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.15790877567351294,
|
| 1053 |
+
"grad_norm": 2.84298038482666,
|
| 1054 |
+
"learning_rate": 9.228258580753843e-07,
|
| 1055 |
+
"loss": 0.3651,
|
| 1056 |
+
"step": 740
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.15897572686049613,
|
| 1060 |
+
"grad_norm": 5.912104606628418,
|
| 1061 |
+
"learning_rate": 9.222994314592545e-07,
|
| 1062 |
+
"loss": 0.3531,
|
| 1063 |
+
"step": 745
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 0.16004267804747932,
|
| 1067 |
+
"grad_norm": 3.0039525032043457,
|
| 1068 |
+
"learning_rate": 9.217730048431249e-07,
|
| 1069 |
+
"loss": 0.3212,
|
| 1070 |
+
"step": 750
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.16110962923446254,
|
| 1074 |
+
"grad_norm": 3.2109341621398926,
|
| 1075 |
+
"learning_rate": 9.212465782269951e-07,
|
| 1076 |
+
"loss": 0.3206,
|
| 1077 |
+
"step": 755
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.16217658042144573,
|
| 1081 |
+
"grad_norm": 2.7238008975982666,
|
| 1082 |
+
"learning_rate": 9.207201516108654e-07,
|
| 1083 |
+
"loss": 0.3696,
|
| 1084 |
+
"step": 760
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.16324353160842892,
|
| 1088 |
+
"grad_norm": 2.6420886516571045,
|
| 1089 |
+
"learning_rate": 9.201937249947357e-07,
|
| 1090 |
+
"loss": 0.3339,
|
| 1091 |
+
"step": 765
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.1643104827954121,
|
| 1095 |
+
"grad_norm": 2.8822038173675537,
|
| 1096 |
+
"learning_rate": 9.196672983786061e-07,
|
| 1097 |
+
"loss": 0.3611,
|
| 1098 |
+
"step": 770
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.1653774339823953,
|
| 1102 |
+
"grad_norm": 2.558979034423828,
|
| 1103 |
+
"learning_rate": 9.191408717624762e-07,
|
| 1104 |
+
"loss": 0.3247,
|
| 1105 |
+
"step": 775
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.1664443851693785,
|
| 1109 |
+
"grad_norm": 2.649867057800293,
|
| 1110 |
+
"learning_rate": 9.186144451463465e-07,
|
| 1111 |
+
"loss": 0.3146,
|
| 1112 |
+
"step": 780
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.1675113363563617,
|
| 1116 |
+
"grad_norm": 2.6174542903900146,
|
| 1117 |
+
"learning_rate": 9.180880185302169e-07,
|
| 1118 |
+
"loss": 0.3319,
|
| 1119 |
+
"step": 785
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.1685782875433449,
|
| 1123 |
+
"grad_norm": 2.65977144241333,
|
| 1124 |
+
"learning_rate": 9.175615919140871e-07,
|
| 1125 |
+
"loss": 0.3643,
|
| 1126 |
+
"step": 790
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.16964523873032808,
|
| 1130 |
+
"grad_norm": 3.2722222805023193,
|
| 1131 |
+
"learning_rate": 9.170351652979574e-07,
|
| 1132 |
+
"loss": 0.3349,
|
| 1133 |
+
"step": 795
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.1707121899173113,
|
| 1137 |
+
"grad_norm": 2.346200466156006,
|
| 1138 |
+
"learning_rate": 9.165087386818277e-07,
|
| 1139 |
+
"loss": 0.3028,
|
| 1140 |
+
"step": 800
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.17177914110429449,
|
| 1144 |
+
"grad_norm": 2.675050735473633,
|
| 1145 |
+
"learning_rate": 9.15982312065698e-07,
|
| 1146 |
+
"loss": 0.3256,
|
| 1147 |
+
"step": 805
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.17284609229127768,
|
| 1151 |
+
"grad_norm": 2.4576005935668945,
|
| 1152 |
+
"learning_rate": 9.154558854495683e-07,
|
| 1153 |
+
"loss": 0.3127,
|
| 1154 |
+
"step": 810
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.17391304347826086,
|
| 1158 |
+
"grad_norm": 2.73311710357666,
|
| 1159 |
+
"learning_rate": 9.150347441566645e-07,
|
| 1160 |
+
"loss": 0.3508,
|
| 1161 |
+
"step": 815
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.17497999466524405,
|
| 1165 |
+
"grad_norm": 2.6573374271392822,
|
| 1166 |
+
"learning_rate": 9.145083175405348e-07,
|
| 1167 |
+
"loss": 0.3643,
|
| 1168 |
+
"step": 820
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.17604694585222727,
|
| 1172 |
+
"grad_norm": 2.7585701942443848,
|
| 1173 |
+
"learning_rate": 9.139818909244052e-07,
|
| 1174 |
+
"loss": 0.3321,
|
| 1175 |
+
"step": 825
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.17711389703921046,
|
| 1179 |
+
"grad_norm": 2.8242616653442383,
|
| 1180 |
+
"learning_rate": 9.134554643082753e-07,
|
| 1181 |
+
"loss": 0.3175,
|
| 1182 |
+
"step": 830
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.17818084822619365,
|
| 1186 |
+
"grad_norm": 3.1244609355926514,
|
| 1187 |
+
"learning_rate": 9.129290376921457e-07,
|
| 1188 |
+
"loss": 0.3641,
|
| 1189 |
+
"step": 835
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.17924779941317684,
|
| 1193 |
+
"grad_norm": 2.4807212352752686,
|
| 1194 |
+
"learning_rate": 9.12402611076016e-07,
|
| 1195 |
+
"loss": 0.3464,
|
| 1196 |
+
"step": 840
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.18031475060016006,
|
| 1200 |
+
"grad_norm": 4.587203502655029,
|
| 1201 |
+
"learning_rate": 9.118761844598863e-07,
|
| 1202 |
+
"loss": 0.3199,
|
| 1203 |
+
"step": 845
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.18138170178714325,
|
| 1207 |
+
"grad_norm": 3.1150426864624023,
|
| 1208 |
+
"learning_rate": 9.113497578437566e-07,
|
| 1209 |
+
"loss": 0.3129,
|
| 1210 |
+
"step": 850
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.18244865297412644,
|
| 1214 |
+
"grad_norm": 2.80098557472229,
|
| 1215 |
+
"learning_rate": 9.108233312276268e-07,
|
| 1216 |
+
"loss": 0.3296,
|
| 1217 |
+
"step": 855
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.18351560416110962,
|
| 1221 |
+
"grad_norm": 2.6048800945281982,
|
| 1222 |
+
"learning_rate": 9.102969046114971e-07,
|
| 1223 |
+
"loss": 0.3426,
|
| 1224 |
+
"step": 860
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.1845825553480928,
|
| 1228 |
+
"grad_norm": 2.4776954650878906,
|
| 1229 |
+
"learning_rate": 9.097704779953675e-07,
|
| 1230 |
+
"loss": 0.3389,
|
| 1231 |
+
"step": 865
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.18564950653507603,
|
| 1235 |
+
"grad_norm": 3.662856101989746,
|
| 1236 |
+
"learning_rate": 9.092440513792377e-07,
|
| 1237 |
+
"loss": 0.3191,
|
| 1238 |
+
"step": 870
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.18671645772205922,
|
| 1242 |
+
"grad_norm": 5.855990886688232,
|
| 1243 |
+
"learning_rate": 9.08717624763108e-07,
|
| 1244 |
+
"loss": 0.3491,
|
| 1245 |
+
"step": 875
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.1877834089090424,
|
| 1249 |
+
"grad_norm": 2.6081950664520264,
|
| 1250 |
+
"learning_rate": 9.081911981469783e-07,
|
| 1251 |
+
"loss": 0.3256,
|
| 1252 |
+
"step": 880
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.1888503600960256,
|
| 1256 |
+
"grad_norm": 3.206470251083374,
|
| 1257 |
+
"learning_rate": 9.076647715308485e-07,
|
| 1258 |
+
"loss": 0.3419,
|
| 1259 |
+
"step": 885
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.18991731128300882,
|
| 1263 |
+
"grad_norm": 3.7217066287994385,
|
| 1264 |
+
"learning_rate": 9.071383449147189e-07,
|
| 1265 |
+
"loss": 0.3369,
|
| 1266 |
+
"step": 890
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.190984262469992,
|
| 1270 |
+
"grad_norm": 4.7247633934021,
|
| 1271 |
+
"learning_rate": 9.066119182985891e-07,
|
| 1272 |
+
"loss": 0.3664,
|
| 1273 |
+
"step": 895
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.1920512136569752,
|
| 1277 |
+
"grad_norm": 3.455446481704712,
|
| 1278 |
+
"learning_rate": 9.060854916824594e-07,
|
| 1279 |
+
"loss": 0.3171,
|
| 1280 |
+
"step": 900
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.19311816484395838,
|
| 1284 |
+
"grad_norm": 2.6066224575042725,
|
| 1285 |
+
"learning_rate": 9.055590650663297e-07,
|
| 1286 |
+
"loss": 0.3266,
|
| 1287 |
+
"step": 905
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.19418511603094157,
|
| 1291 |
+
"grad_norm": 3.2545228004455566,
|
| 1292 |
+
"learning_rate": 9.050326384502e-07,
|
| 1293 |
+
"loss": 0.3201,
|
| 1294 |
+
"step": 910
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.1952520672179248,
|
| 1298 |
+
"grad_norm": 3.8174829483032227,
|
| 1299 |
+
"learning_rate": 9.045062118340702e-07,
|
| 1300 |
+
"loss": 0.3537,
|
| 1301 |
+
"step": 915
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.19631901840490798,
|
| 1305 |
+
"grad_norm": 3.725991725921631,
|
| 1306 |
+
"learning_rate": 9.039797852179406e-07,
|
| 1307 |
+
"loss": 0.3373,
|
| 1308 |
+
"step": 920
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.19738596959189117,
|
| 1312 |
+
"grad_norm": 2.5402047634124756,
|
| 1313 |
+
"learning_rate": 9.034533586018108e-07,
|
| 1314 |
+
"loss": 0.3107,
|
| 1315 |
+
"step": 925
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.19845292077887436,
|
| 1319 |
+
"grad_norm": 2.3887853622436523,
|
| 1320 |
+
"learning_rate": 9.029269319856812e-07,
|
| 1321 |
+
"loss": 0.3255,
|
| 1322 |
+
"step": 930
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.19951987196585758,
|
| 1326 |
+
"grad_norm": 2.83178973197937,
|
| 1327 |
+
"learning_rate": 9.024005053695514e-07,
|
| 1328 |
+
"loss": 0.3192,
|
| 1329 |
+
"step": 935
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.20058682315284077,
|
| 1333 |
+
"grad_norm": 2.540933132171631,
|
| 1334 |
+
"learning_rate": 9.018740787534217e-07,
|
| 1335 |
+
"loss": 0.3414,
|
| 1336 |
+
"step": 940
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.20165377433982395,
|
| 1340 |
+
"grad_norm": 2.799577474594116,
|
| 1341 |
+
"learning_rate": 9.01347652137292e-07,
|
| 1342 |
+
"loss": 0.3383,
|
| 1343 |
+
"step": 945
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.20272072552680714,
|
| 1347 |
+
"grad_norm": 2.5945661067962646,
|
| 1348 |
+
"learning_rate": 9.008212255211624e-07,
|
| 1349 |
+
"loss": 0.3414,
|
| 1350 |
+
"step": 950
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.20378767671379033,
|
| 1354 |
+
"grad_norm": 3.102372407913208,
|
| 1355 |
+
"learning_rate": 9.002947989050325e-07,
|
| 1356 |
+
"loss": 0.33,
|
| 1357 |
+
"step": 955
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.20485462790077355,
|
| 1361 |
+
"grad_norm": 3.1992921829223633,
|
| 1362 |
+
"learning_rate": 8.997683722889029e-07,
|
| 1363 |
+
"loss": 0.3719,
|
| 1364 |
+
"step": 960
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.20592157908775674,
|
| 1368 |
+
"grad_norm": 3.082578420639038,
|
| 1369 |
+
"learning_rate": 8.992419456727732e-07,
|
| 1370 |
+
"loss": 0.3412,
|
| 1371 |
+
"step": 965
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.20698853027473993,
|
| 1375 |
+
"grad_norm": 2.406475067138672,
|
| 1376 |
+
"learning_rate": 8.987155190566435e-07,
|
| 1377 |
+
"loss": 0.3069,
|
| 1378 |
+
"step": 970
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.20805548146172312,
|
| 1382 |
+
"grad_norm": 3.033055067062378,
|
| 1383 |
+
"learning_rate": 8.981890924405137e-07,
|
| 1384 |
+
"loss": 0.3683,
|
| 1385 |
+
"step": 975
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.2091224326487063,
|
| 1389 |
+
"grad_norm": 2.807874917984009,
|
| 1390 |
+
"learning_rate": 8.97662665824384e-07,
|
| 1391 |
+
"loss": 0.3024,
|
| 1392 |
+
"step": 980
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.21018938383568952,
|
| 1396 |
+
"grad_norm": 2.6849870681762695,
|
| 1397 |
+
"learning_rate": 8.971362392082543e-07,
|
| 1398 |
+
"loss": 0.3248,
|
| 1399 |
+
"step": 985
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.21125633502267271,
|
| 1403 |
+
"grad_norm": 3.144150495529175,
|
| 1404 |
+
"learning_rate": 8.966098125921247e-07,
|
| 1405 |
+
"loss": 0.3158,
|
| 1406 |
+
"step": 990
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.2123232862096559,
|
| 1410 |
+
"grad_norm": 2.495368003845215,
|
| 1411 |
+
"learning_rate": 8.960833859759948e-07,
|
| 1412 |
+
"loss": 0.312,
|
| 1413 |
+
"step": 995
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.2133902373966391,
|
| 1417 |
+
"grad_norm": 2.2597124576568604,
|
| 1418 |
+
"learning_rate": 8.955569593598652e-07,
|
| 1419 |
+
"loss": 0.3053,
|
| 1420 |
+
"step": 1000
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.2133902373966391,
|
| 1424 |
+
"eval_bleu": 0.6173395426659279,
|
| 1425 |
+
"eval_cer": 5.420346953040605,
|
| 1426 |
+
"eval_loss": 0.3327235281467438,
|
| 1427 |
+
"eval_runtime": 1022.0953,
|
| 1428 |
+
"eval_samples_per_second": 0.898,
|
| 1429 |
+
"eval_steps_per_second": 0.225,
|
| 1430 |
+
"eval_wer": 20.46380804775845,
|
| 1431 |
+
"step": 1000
|
| 1432 |
+
}
|
| 1433 |
+
],
|
| 1434 |
+
"logging_steps": 5,
|
| 1435 |
+
"max_steps": 9500,
|
| 1436 |
+
"num_input_tokens_seen": 0,
|
| 1437 |
+
"num_train_epochs": 3,
|
| 1438 |
+
"save_steps": 500,
|
| 1439 |
+
"stateful_callbacks": {
|
| 1440 |
+
"TrainerControl": {
|
| 1441 |
+
"args": {
|
| 1442 |
+
"should_epoch_stop": false,
|
| 1443 |
+
"should_evaluate": false,
|
| 1444 |
+
"should_log": false,
|
| 1445 |
+
"should_save": true,
|
| 1446 |
+
"should_training_stop": false
|
| 1447 |
+
},
|
| 1448 |
+
"attributes": {}
|
| 1449 |
+
}
|
| 1450 |
+
},
|
| 1451 |
+
"total_flos": 1.358829453312e+20,
|
| 1452 |
+
"train_batch_size": 8,
|
| 1453 |
+
"trial_name": null,
|
| 1454 |
+
"trial_params": null
|
| 1455 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20adc179b6f798df62ecd414b871514d9da075bfe8a22514841288c4b0d3adc4
|
| 3 |
+
size 5841
|