Training in progress, step 500
Browse files- checkpoint-500/config.json +42 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/preprocessor_config.json +0 -0
- checkpoint-500/pytorch_model.bin +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scaler.pt +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +366 -0
- checkpoint-500/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- runs/Dec20_20-28-50_129-146-32-172/events.out.tfevents.1671568135.129-146-32-172.151517.0 +2 -2
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-small",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"begin_suppress_tokens": [
|
| 10 |
+
220,
|
| 11 |
+
50257
|
| 12 |
+
],
|
| 13 |
+
"bos_token_id": 50257,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
+
"decoder_start_token_id": 50258,
|
| 20 |
+
"dropout": 0.0,
|
| 21 |
+
"encoder_attention_heads": 12,
|
| 22 |
+
"encoder_ffn_dim": 3072,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 12,
|
| 25 |
+
"eos_token_id": 50257,
|
| 26 |
+
"forced_decoder_ids": null,
|
| 27 |
+
"init_std": 0.02,
|
| 28 |
+
"is_encoder_decoder": true,
|
| 29 |
+
"max_length": 448,
|
| 30 |
+
"max_source_positions": 1500,
|
| 31 |
+
"max_target_positions": 448,
|
| 32 |
+
"model_type": "whisper",
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"num_mel_bins": 80,
|
| 35 |
+
"pad_token_id": 50257,
|
| 36 |
+
"scale_embedding": false,
|
| 37 |
+
"suppress_tokens": [],
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.26.0.dev0",
|
| 40 |
+
"use_cache": false,
|
| 41 |
+
"vocab_size": 51865
|
| 42 |
+
}
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fe2638751500814fa3c265bc551009d3713f92df095891cac6eb08cd082c521
|
| 3 |
+
size 1934161093
|
checkpoint-500/preprocessor_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-500/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebe17ada781704db4e86ac51bda39fc484951a47d25340f719dca6ce554aab2d
|
| 3 |
+
size 967102601
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:510e16a97bbd59cc378fcb2467e6f8970096a7729d5be8bf0c6e6d11d2058361
|
| 3 |
+
size 14575
|
checkpoint-500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac1412620d0199fc5b0c13848e4498b7cd4932f2b0be56702b47335e3f1226fc
|
| 3 |
+
size 557
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25988ef1426d99d319d7eebdab74ef540055ecbcf177b9d16e284f8c3b84a320
|
| 3 |
+
size 627
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,366 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 49.03147699757869,
|
| 3 |
+
"best_model_checkpoint": "./checkpoint-400",
|
| 4 |
+
"epoch": 11.894117647058824,
|
| 5 |
+
"global_step": 500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.24,
|
| 12 |
+
"learning_rate": 2.666666666666667e-06,
|
| 13 |
+
"loss": 4.3134,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.47,
|
| 18 |
+
"learning_rate": 6e-06,
|
| 19 |
+
"loss": 2.9329,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.71,
|
| 24 |
+
"learning_rate": 9.333333333333334e-06,
|
| 25 |
+
"loss": 2.0584,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.94,
|
| 30 |
+
"learning_rate": 9.829787234042554e-06,
|
| 31 |
+
"loss": 1.566,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.19,
|
| 36 |
+
"learning_rate": 9.617021276595745e-06,
|
| 37 |
+
"loss": 1.3777,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.42,
|
| 42 |
+
"learning_rate": 9.404255319148937e-06,
|
| 43 |
+
"loss": 1.1469,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.66,
|
| 48 |
+
"learning_rate": 9.191489361702128e-06,
|
| 49 |
+
"loss": 1.0638,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.89,
|
| 54 |
+
"learning_rate": 8.97872340425532e-06,
|
| 55 |
+
"loss": 0.9974,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.14,
|
| 60 |
+
"learning_rate": 8.765957446808512e-06,
|
| 61 |
+
"loss": 0.9615,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.38,
|
| 66 |
+
"learning_rate": 8.553191489361703e-06,
|
| 67 |
+
"loss": 0.8262,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.38,
|
| 72 |
+
"eval_cer": 149.33157314260887,
|
| 73 |
+
"eval_loss": 0.8188337683677673,
|
| 74 |
+
"eval_runtime": 459.9395,
|
| 75 |
+
"eval_samples_per_second": 1.113,
|
| 76 |
+
"eval_steps_per_second": 0.139,
|
| 77 |
+
"eval_wer": 146.85230024213075,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.61,
|
| 82 |
+
"learning_rate": 8.340425531914894e-06,
|
| 83 |
+
"loss": 0.7986,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.85,
|
| 88 |
+
"learning_rate": 8.127659574468085e-06,
|
| 89 |
+
"loss": 0.7707,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 3.09,
|
| 94 |
+
"learning_rate": 7.914893617021278e-06,
|
| 95 |
+
"loss": 0.7623,
|
| 96 |
+
"step": 130
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.33,
|
| 100 |
+
"learning_rate": 7.702127659574469e-06,
|
| 101 |
+
"loss": 0.6451,
|
| 102 |
+
"step": 140
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 3.56,
|
| 106 |
+
"learning_rate": 7.48936170212766e-06,
|
| 107 |
+
"loss": 0.6205,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.8,
|
| 112 |
+
"learning_rate": 7.2765957446808524e-06,
|
| 113 |
+
"loss": 0.6097,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.05,
|
| 118 |
+
"learning_rate": 7.0638297872340434e-06,
|
| 119 |
+
"loss": 0.6217,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 4.28,
|
| 124 |
+
"learning_rate": 6.8510638297872344e-06,
|
| 125 |
+
"loss": 0.4584,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 4.52,
|
| 130 |
+
"learning_rate": 6.6382978723404254e-06,
|
| 131 |
+
"loss": 0.4929,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.75,
|
| 136 |
+
"learning_rate": 6.425531914893618e-06,
|
| 137 |
+
"loss": 0.4843,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.75,
|
| 142 |
+
"eval_cer": 22.099862972494236,
|
| 143 |
+
"eval_loss": 0.6699215173721313,
|
| 144 |
+
"eval_runtime": 1062.3991,
|
| 145 |
+
"eval_samples_per_second": 0.482,
|
| 146 |
+
"eval_steps_per_second": 0.06,
|
| 147 |
+
"eval_wer": 52.66343825665859,
|
| 148 |
+
"step": 200
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 4.99,
|
| 152 |
+
"learning_rate": 6.212765957446809e-06,
|
| 153 |
+
"loss": 0.4678,
|
| 154 |
+
"step": 210
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.24,
|
| 158 |
+
"learning_rate": 6e-06,
|
| 159 |
+
"loss": 0.4014,
|
| 160 |
+
"step": 220
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 5.47,
|
| 164 |
+
"learning_rate": 5.787234042553191e-06,
|
| 165 |
+
"loss": 0.3926,
|
| 166 |
+
"step": 230
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 5.71,
|
| 170 |
+
"learning_rate": 5.574468085106384e-06,
|
| 171 |
+
"loss": 0.3806,
|
| 172 |
+
"step": 240
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 5.94,
|
| 176 |
+
"learning_rate": 5.361702127659575e-06,
|
| 177 |
+
"loss": 0.3855,
|
| 178 |
+
"step": 250
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 6.19,
|
| 182 |
+
"learning_rate": 5.148936170212766e-06,
|
| 183 |
+
"loss": 0.3478,
|
| 184 |
+
"step": 260
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 6.42,
|
| 188 |
+
"learning_rate": 4.936170212765958e-06,
|
| 189 |
+
"loss": 0.3078,
|
| 190 |
+
"step": 270
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 6.66,
|
| 194 |
+
"learning_rate": 4.7234042553191496e-06,
|
| 195 |
+
"loss": 0.3147,
|
| 196 |
+
"step": 280
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 6.89,
|
| 200 |
+
"learning_rate": 4.5106382978723406e-06,
|
| 201 |
+
"loss": 0.3213,
|
| 202 |
+
"step": 290
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 7.14,
|
| 206 |
+
"learning_rate": 4.297872340425532e-06,
|
| 207 |
+
"loss": 0.287,
|
| 208 |
+
"step": 300
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 7.14,
|
| 212 |
+
"eval_cer": 20.677784833394604,
|
| 213 |
+
"eval_loss": 0.6913720369338989,
|
| 214 |
+
"eval_runtime": 1003.603,
|
| 215 |
+
"eval_samples_per_second": 0.51,
|
| 216 |
+
"eval_steps_per_second": 0.064,
|
| 217 |
+
"eval_wer": 50.13619854721549,
|
| 218 |
+
"step": 300
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 7.38,
|
| 222 |
+
"learning_rate": 4.085106382978723e-06,
|
| 223 |
+
"loss": 0.2602,
|
| 224 |
+
"step": 310
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 7.61,
|
| 228 |
+
"learning_rate": 3.872340425531915e-06,
|
| 229 |
+
"loss": 0.2612,
|
| 230 |
+
"step": 320
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 7.85,
|
| 234 |
+
"learning_rate": 3.6595744680851063e-06,
|
| 235 |
+
"loss": 0.2618,
|
| 236 |
+
"step": 330
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 8.09,
|
| 240 |
+
"learning_rate": 3.446808510638298e-06,
|
| 241 |
+
"loss": 0.2494,
|
| 242 |
+
"step": 340
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 8.33,
|
| 246 |
+
"learning_rate": 3.23404255319149e-06,
|
| 247 |
+
"loss": 0.2123,
|
| 248 |
+
"step": 350
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.56,
|
| 252 |
+
"learning_rate": 3.021276595744681e-06,
|
| 253 |
+
"loss": 0.2173,
|
| 254 |
+
"step": 360
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.8,
|
| 258 |
+
"learning_rate": 2.808510638297873e-06,
|
| 259 |
+
"loss": 0.2093,
|
| 260 |
+
"step": 370
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 9.05,
|
| 264 |
+
"learning_rate": 2.595744680851064e-06,
|
| 265 |
+
"loss": 0.2209,
|
| 266 |
+
"step": 380
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 9.28,
|
| 270 |
+
"learning_rate": 2.3829787234042557e-06,
|
| 271 |
+
"loss": 0.1742,
|
| 272 |
+
"step": 390
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 9.52,
|
| 276 |
+
"learning_rate": 2.170212765957447e-06,
|
| 277 |
+
"loss": 0.1828,
|
| 278 |
+
"step": 400
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 9.52,
|
| 282 |
+
"eval_cer": 20.460546104742487,
|
| 283 |
+
"eval_loss": 0.7369570136070251,
|
| 284 |
+
"eval_runtime": 1004.0546,
|
| 285 |
+
"eval_samples_per_second": 0.51,
|
| 286 |
+
"eval_steps_per_second": 0.064,
|
| 287 |
+
"eval_wer": 49.03147699757869,
|
| 288 |
+
"step": 400
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 9.75,
|
| 292 |
+
"learning_rate": 1.9574468085106385e-06,
|
| 293 |
+
"loss": 0.1902,
|
| 294 |
+
"step": 410
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 9.99,
|
| 298 |
+
"learning_rate": 1.74468085106383e-06,
|
| 299 |
+
"loss": 0.1809,
|
| 300 |
+
"step": 420
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 10.24,
|
| 304 |
+
"learning_rate": 1.5319148936170214e-06,
|
| 305 |
+
"loss": 0.1705,
|
| 306 |
+
"step": 430
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 10.47,
|
| 310 |
+
"learning_rate": 1.3191489361702128e-06,
|
| 311 |
+
"loss": 0.1593,
|
| 312 |
+
"step": 440
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 10.71,
|
| 316 |
+
"learning_rate": 1.1063829787234042e-06,
|
| 317 |
+
"loss": 0.1596,
|
| 318 |
+
"step": 450
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 10.94,
|
| 322 |
+
"learning_rate": 8.936170212765959e-07,
|
| 323 |
+
"loss": 0.161,
|
| 324 |
+
"step": 460
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 11.19,
|
| 328 |
+
"learning_rate": 6.808510638297873e-07,
|
| 329 |
+
"loss": 0.1594,
|
| 330 |
+
"step": 470
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 11.42,
|
| 334 |
+
"learning_rate": 4.6808510638297873e-07,
|
| 335 |
+
"loss": 0.1436,
|
| 336 |
+
"step": 480
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 11.66,
|
| 340 |
+
"learning_rate": 2.553191489361702e-07,
|
| 341 |
+
"loss": 0.1517,
|
| 342 |
+
"step": 490
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 11.89,
|
| 346 |
+
"learning_rate": 4.2553191489361707e-08,
|
| 347 |
+
"loss": 0.1493,
|
| 348 |
+
"step": 500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 11.89,
|
| 352 |
+
"eval_cer": 20.8064570034424,
|
| 353 |
+
"eval_loss": 0.7532366514205933,
|
| 354 |
+
"eval_runtime": 925.6199,
|
| 355 |
+
"eval_samples_per_second": 0.553,
|
| 356 |
+
"eval_steps_per_second": 0.069,
|
| 357 |
+
"eval_wer": 49.583837772397096,
|
| 358 |
+
"step": 500
|
| 359 |
+
}
|
| 360 |
+
],
|
| 361 |
+
"max_steps": 500,
|
| 362 |
+
"num_train_epochs": 12,
|
| 363 |
+
"total_flos": 9.30774491652096e+18,
|
| 364 |
+
"trial_name": null,
|
| 365 |
+
"trial_params": null
|
| 366 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5518cd575512706c66c89476ae9c64328c1bcac98ec06151bdc9afebf6c503fb
|
| 3 |
+
size 3643
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 967102601
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebe17ada781704db4e86ac51bda39fc484951a47d25340f719dca6ce554aab2d
|
| 3 |
size 967102601
|
runs/Dec20_20-28-50_129-146-32-172/events.out.tfevents.1671568135.129-146-32-172.151517.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2fa5e3071fe814ed1a0bdcaa151a7b328f57e40c21ff2f2665c2317d14e86fe
|
| 3 |
+
size 13919
|