Commit
·
be4e905
1
Parent(s):
f625d5e
Model save
Browse files- checkpoint-7000/config.json +0 -115
- checkpoint-7000/optimizer.pt +0 -3
- checkpoint-7000/preprocessor_config.json +0 -9
- checkpoint-7000/pytorch_model.bin +0 -3
- checkpoint-7000/rng_state.pth +0 -3
- checkpoint-7000/scaler.pt +0 -3
- checkpoint-7000/scheduler.pt +0 -3
- checkpoint-7000/trainer_state.json +0 -499
- checkpoint-7000/training_args.bin +0 -3
- pytorch_model.bin +1 -1
checkpoint-7000/config.json
DELETED
|
@@ -1,115 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "KBLab/wav2vec2-large-voxrex",
|
| 3 |
-
"activation_dropout": 0.15,
|
| 4 |
-
"adapter_kernel_size": 3,
|
| 5 |
-
"adapter_stride": 2,
|
| 6 |
-
"add_adapter": false,
|
| 7 |
-
"apply_spec_augment": true,
|
| 8 |
-
"architectures": [
|
| 9 |
-
"Wav2Vec2ForCTC"
|
| 10 |
-
],
|
| 11 |
-
"attention_dropout": 0.0,
|
| 12 |
-
"bos_token_id": 1,
|
| 13 |
-
"classifier_proj_size": 256,
|
| 14 |
-
"codevector_dim": 768,
|
| 15 |
-
"contrastive_logits_temperature": 0.1,
|
| 16 |
-
"conv_bias": true,
|
| 17 |
-
"conv_dim": [
|
| 18 |
-
512,
|
| 19 |
-
512,
|
| 20 |
-
512,
|
| 21 |
-
512,
|
| 22 |
-
512,
|
| 23 |
-
512,
|
| 24 |
-
512
|
| 25 |
-
],
|
| 26 |
-
"conv_kernel": [
|
| 27 |
-
10,
|
| 28 |
-
3,
|
| 29 |
-
3,
|
| 30 |
-
3,
|
| 31 |
-
3,
|
| 32 |
-
2,
|
| 33 |
-
2
|
| 34 |
-
],
|
| 35 |
-
"conv_stride": [
|
| 36 |
-
5,
|
| 37 |
-
2,
|
| 38 |
-
2,
|
| 39 |
-
2,
|
| 40 |
-
2,
|
| 41 |
-
2,
|
| 42 |
-
2
|
| 43 |
-
],
|
| 44 |
-
"ctc_loss_reduction": "mean",
|
| 45 |
-
"ctc_zero_infinity": false,
|
| 46 |
-
"diversity_loss_weight": 0.1,
|
| 47 |
-
"do_stable_layer_norm": true,
|
| 48 |
-
"eos_token_id": 2,
|
| 49 |
-
"feat_extract_activation": "gelu",
|
| 50 |
-
"feat_extract_dropout": 0.0,
|
| 51 |
-
"feat_extract_norm": "layer",
|
| 52 |
-
"feat_proj_dropout": 0.0,
|
| 53 |
-
"feat_quantizer_dropout": 0.0,
|
| 54 |
-
"final_dropout": 0.0,
|
| 55 |
-
"hidden_act": "gelu",
|
| 56 |
-
"hidden_dropout": 0.0,
|
| 57 |
-
"hidden_size": 1024,
|
| 58 |
-
"initializer_range": 0.02,
|
| 59 |
-
"intermediate_size": 4096,
|
| 60 |
-
"layer_norm_eps": 1e-05,
|
| 61 |
-
"layerdrop": 0.0,
|
| 62 |
-
"mask_channel_length": 10,
|
| 63 |
-
"mask_channel_min_space": 1,
|
| 64 |
-
"mask_channel_other": 0.0,
|
| 65 |
-
"mask_channel_prob": 0.0,
|
| 66 |
-
"mask_channel_selection": "static",
|
| 67 |
-
"mask_feature_length": 64,
|
| 68 |
-
"mask_feature_min_masks": 0,
|
| 69 |
-
"mask_feature_prob": 0.25,
|
| 70 |
-
"mask_time_length": 10,
|
| 71 |
-
"mask_time_min_masks": 2,
|
| 72 |
-
"mask_time_min_space": 1,
|
| 73 |
-
"mask_time_other": 0.0,
|
| 74 |
-
"mask_time_prob": 0.75,
|
| 75 |
-
"mask_time_selection": "static",
|
| 76 |
-
"model_type": "wav2vec2",
|
| 77 |
-
"num_adapter_layers": 3,
|
| 78 |
-
"num_attention_heads": 16,
|
| 79 |
-
"num_codevector_groups": 2,
|
| 80 |
-
"num_codevectors_per_group": 320,
|
| 81 |
-
"num_conv_pos_embedding_groups": 16,
|
| 82 |
-
"num_conv_pos_embeddings": 128,
|
| 83 |
-
"num_feat_extract_layers": 7,
|
| 84 |
-
"num_hidden_layers": 24,
|
| 85 |
-
"num_negatives": 100,
|
| 86 |
-
"output_hidden_size": 1024,
|
| 87 |
-
"pad_token_id": 31,
|
| 88 |
-
"proj_codevector_dim": 768,
|
| 89 |
-
"tdnn_dilation": [
|
| 90 |
-
1,
|
| 91 |
-
2,
|
| 92 |
-
3,
|
| 93 |
-
1,
|
| 94 |
-
1
|
| 95 |
-
],
|
| 96 |
-
"tdnn_dim": [
|
| 97 |
-
512,
|
| 98 |
-
512,
|
| 99 |
-
512,
|
| 100 |
-
512,
|
| 101 |
-
1500
|
| 102 |
-
],
|
| 103 |
-
"tdnn_kernel": [
|
| 104 |
-
5,
|
| 105 |
-
3,
|
| 106 |
-
3,
|
| 107 |
-
1,
|
| 108 |
-
1
|
| 109 |
-
],
|
| 110 |
-
"torch_dtype": "float32",
|
| 111 |
-
"transformers_version": "4.17.0.dev0",
|
| 112 |
-
"use_weighted_layer_sum": false,
|
| 113 |
-
"vocab_size": 34,
|
| 114 |
-
"xvector_output_dim": 512
|
| 115 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-7000/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8149cd19098a48ee10ff74dee0cc2084d94a4c41fe150d746e1b5709140f44ea
|
| 3 |
-
size 2490337809
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-7000/preprocessor_config.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_normalize": true,
|
| 3 |
-
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
-
"feature_size": 1,
|
| 5 |
-
"padding_side": "right",
|
| 6 |
-
"padding_value": 0,
|
| 7 |
-
"return_attention_mask": true,
|
| 8 |
-
"sampling_rate": 16000
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-7000/pytorch_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e37627cfc478091e469aa3336008b88b7357fe78bf289ef0337ff080db2b580d
|
| 3 |
-
size 1262063089
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-7000/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0098bfe058c915bbbc841978f5eadb77f3664601fc66d811f09cf306ed86a3e2
|
| 3 |
-
size 14567
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-7000/scaler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:681e98dfadb561ae4866d369f1998b470f759d7fcd031000d9858bd09b56b85e
|
| 3 |
-
size 559
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-7000/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:574187f5c73b47275ae699804d39777465bf9ef54d00a758e6fa127b339126d6
|
| 3 |
-
size 623
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-7000/trainer_state.json
DELETED
|
@@ -1,499 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 72.91428571428571,
|
| 5 |
-
"global_step": 7000,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 1.04,
|
| 12 |
-
"learning_rate": 3.828125e-06,
|
| 13 |
-
"loss": 15.104,
|
| 14 |
-
"step": 100
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 2.08,
|
| 18 |
-
"learning_rate": 7.6953125e-06,
|
| 19 |
-
"loss": 12.2149,
|
| 20 |
-
"step": 200
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 3.12,
|
| 24 |
-
"learning_rate": 1.16015625e-05,
|
| 25 |
-
"loss": 4.9885,
|
| 26 |
-
"step": 300
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch": 4.17,
|
| 30 |
-
"learning_rate": 1.55078125e-05,
|
| 31 |
-
"loss": 3.3788,
|
| 32 |
-
"step": 400
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 5.21,
|
| 36 |
-
"learning_rate": 1.94140625e-05,
|
| 37 |
-
"loss": 3.1705,
|
| 38 |
-
"step": 500
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 6.25,
|
| 42 |
-
"learning_rate": 2.3320312499999995e-05,
|
| 43 |
-
"loss": 3.11,
|
| 44 |
-
"step": 600
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 7.29,
|
| 48 |
-
"learning_rate": 2.72265625e-05,
|
| 49 |
-
"loss": 3.0526,
|
| 50 |
-
"step": 700
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 8.33,
|
| 54 |
-
"learning_rate": 3.11328125e-05,
|
| 55 |
-
"loss": 3.0113,
|
| 56 |
-
"step": 800
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 9.37,
|
| 60 |
-
"learning_rate": 3.5039062499999995e-05,
|
| 61 |
-
"loss": 2.9601,
|
| 62 |
-
"step": 900
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 10.42,
|
| 66 |
-
"learning_rate": 3.89453125e-05,
|
| 67 |
-
"loss": 2.9099,
|
| 68 |
-
"step": 1000
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 10.42,
|
| 72 |
-
"eval_loss": 2.8369038105010986,
|
| 73 |
-
"eval_runtime": 198.5866,
|
| 74 |
-
"eval_samples_per_second": 25.405,
|
| 75 |
-
"eval_steps_per_second": 0.796,
|
| 76 |
-
"eval_wer": 1.0,
|
| 77 |
-
"step": 1000
|
| 78 |
-
},
|
| 79 |
-
{
|
| 80 |
-
"epoch": 11.46,
|
| 81 |
-
"learning_rate": 4.28515625e-05,
|
| 82 |
-
"loss": 2.6653,
|
| 83 |
-
"step": 1100
|
| 84 |
-
},
|
| 85 |
-
{
|
| 86 |
-
"epoch": 12.5,
|
| 87 |
-
"learning_rate": 4.675781249999999e-05,
|
| 88 |
-
"loss": 1.8958,
|
| 89 |
-
"step": 1200
|
| 90 |
-
},
|
| 91 |
-
{
|
| 92 |
-
"epoch": 13.54,
|
| 93 |
-
"learning_rate": 5.0664062499999996e-05,
|
| 94 |
-
"loss": 1.4812,
|
| 95 |
-
"step": 1300
|
| 96 |
-
},
|
| 97 |
-
{
|
| 98 |
-
"epoch": 14.58,
|
| 99 |
-
"learning_rate": 5.45703125e-05,
|
| 100 |
-
"loss": 1.3358,
|
| 101 |
-
"step": 1400
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 15.62,
|
| 105 |
-
"learning_rate": 5.8476562499999996e-05,
|
| 106 |
-
"loss": 1.2522,
|
| 107 |
-
"step": 1500
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 16.66,
|
| 111 |
-
"learning_rate": 6.238281249999999e-05,
|
| 112 |
-
"loss": 1.1919,
|
| 113 |
-
"step": 1600
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 17.71,
|
| 117 |
-
"learning_rate": 6.62890625e-05,
|
| 118 |
-
"loss": 1.1663,
|
| 119 |
-
"step": 1700
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 18.75,
|
| 123 |
-
"learning_rate": 7.019531249999999e-05,
|
| 124 |
-
"loss": 1.1289,
|
| 125 |
-
"step": 1800
|
| 126 |
-
},
|
| 127 |
-
{
|
| 128 |
-
"epoch": 19.79,
|
| 129 |
-
"learning_rate": 7.410156249999999e-05,
|
| 130 |
-
"loss": 1.0902,
|
| 131 |
-
"step": 1900
|
| 132 |
-
},
|
| 133 |
-
{
|
| 134 |
-
"epoch": 20.83,
|
| 135 |
-
"learning_rate": 7.4248046875e-05,
|
| 136 |
-
"loss": 1.0745,
|
| 137 |
-
"step": 2000
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"epoch": 20.83,
|
| 141 |
-
"eval_loss": 0.19572903215885162,
|
| 142 |
-
"eval_runtime": 202.06,
|
| 143 |
-
"eval_samples_per_second": 24.968,
|
| 144 |
-
"eval_steps_per_second": 0.782,
|
| 145 |
-
"eval_wer": 0.16725371193237237,
|
| 146 |
-
"step": 2000
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 21.87,
|
| 150 |
-
"learning_rate": 7.327148437499999e-05,
|
| 151 |
-
"loss": 1.0485,
|
| 152 |
-
"step": 2100
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 22.91,
|
| 156 |
-
"learning_rate": 7.2294921875e-05,
|
| 157 |
-
"loss": 1.0291,
|
| 158 |
-
"step": 2200
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 23.96,
|
| 162 |
-
"learning_rate": 7.1318359375e-05,
|
| 163 |
-
"loss": 1.007,
|
| 164 |
-
"step": 2300
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 25.0,
|
| 168 |
-
"learning_rate": 7.0341796875e-05,
|
| 169 |
-
"loss": 1.0008,
|
| 170 |
-
"step": 2400
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 26.04,
|
| 174 |
-
"learning_rate": 6.9365234375e-05,
|
| 175 |
-
"loss": 0.988,
|
| 176 |
-
"step": 2500
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"epoch": 27.08,
|
| 180 |
-
"learning_rate": 6.8388671875e-05,
|
| 181 |
-
"loss": 0.9766,
|
| 182 |
-
"step": 2600
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 28.12,
|
| 186 |
-
"learning_rate": 6.7412109375e-05,
|
| 187 |
-
"loss": 0.9663,
|
| 188 |
-
"step": 2700
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 29.17,
|
| 192 |
-
"learning_rate": 6.6435546875e-05,
|
| 193 |
-
"loss": 0.9539,
|
| 194 |
-
"step": 2800
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 30.21,
|
| 198 |
-
"learning_rate": 6.545898437499999e-05,
|
| 199 |
-
"loss": 0.9479,
|
| 200 |
-
"step": 2900
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 31.25,
|
| 204 |
-
"learning_rate": 6.448242187499999e-05,
|
| 205 |
-
"loss": 0.934,
|
| 206 |
-
"step": 3000
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 31.25,
|
| 210 |
-
"eval_loss": 0.1579357087612152,
|
| 211 |
-
"eval_runtime": 198.7733,
|
| 212 |
-
"eval_samples_per_second": 25.381,
|
| 213 |
-
"eval_steps_per_second": 0.795,
|
| 214 |
-
"eval_wer": 0.1388858784003468,
|
| 215 |
-
"step": 3000
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 32.29,
|
| 219 |
-
"learning_rate": 6.3505859375e-05,
|
| 220 |
-
"loss": 0.9285,
|
| 221 |
-
"step": 3100
|
| 222 |
-
},
|
| 223 |
-
{
|
| 224 |
-
"epoch": 33.33,
|
| 225 |
-
"learning_rate": 6.252929687499999e-05,
|
| 226 |
-
"loss": 0.9121,
|
| 227 |
-
"step": 3200
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 34.37,
|
| 231 |
-
"learning_rate": 6.155273437499999e-05,
|
| 232 |
-
"loss": 0.9016,
|
| 233 |
-
"step": 3300
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 35.42,
|
| 237 |
-
"learning_rate": 6.0576171875e-05,
|
| 238 |
-
"loss": 0.9023,
|
| 239 |
-
"step": 3400
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 36.46,
|
| 243 |
-
"learning_rate": 5.9599609374999994e-05,
|
| 244 |
-
"loss": 0.9004,
|
| 245 |
-
"step": 3500
|
| 246 |
-
},
|
| 247 |
-
{
|
| 248 |
-
"epoch": 37.5,
|
| 249 |
-
"learning_rate": 5.862304687499999e-05,
|
| 250 |
-
"loss": 0.8844,
|
| 251 |
-
"step": 3600
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 38.54,
|
| 255 |
-
"learning_rate": 5.7646484375e-05,
|
| 256 |
-
"loss": 0.8771,
|
| 257 |
-
"step": 3700
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"epoch": 39.58,
|
| 261 |
-
"learning_rate": 5.6669921875e-05,
|
| 262 |
-
"loss": 0.876,
|
| 263 |
-
"step": 3800
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 40.62,
|
| 267 |
-
"learning_rate": 5.569335937499999e-05,
|
| 268 |
-
"loss": 0.8708,
|
| 269 |
-
"step": 3900
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 41.66,
|
| 273 |
-
"learning_rate": 5.4716796874999997e-05,
|
| 274 |
-
"loss": 0.8691,
|
| 275 |
-
"step": 4000
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 41.66,
|
| 279 |
-
"eval_loss": 0.14571049809455872,
|
| 280 |
-
"eval_runtime": 195.237,
|
| 281 |
-
"eval_samples_per_second": 25.84,
|
| 282 |
-
"eval_steps_per_second": 0.809,
|
| 283 |
-
"eval_wer": 0.12899642353961202,
|
| 284 |
-
"step": 4000
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 42.71,
|
| 288 |
-
"learning_rate": 5.3740234374999996e-05,
|
| 289 |
-
"loss": 0.8624,
|
| 290 |
-
"step": 4100
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 43.75,
|
| 294 |
-
"learning_rate": 5.2763671874999995e-05,
|
| 295 |
-
"loss": 0.8556,
|
| 296 |
-
"step": 4200
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 44.79,
|
| 300 |
-
"learning_rate": 5.1787109375e-05,
|
| 301 |
-
"loss": 0.8607,
|
| 302 |
-
"step": 4300
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 45.83,
|
| 306 |
-
"learning_rate": 5.0810546875e-05,
|
| 307 |
-
"loss": 0.8536,
|
| 308 |
-
"step": 4400
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 46.87,
|
| 312 |
-
"learning_rate": 4.983398437499999e-05,
|
| 313 |
-
"loss": 0.8493,
|
| 314 |
-
"step": 4500
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 47.91,
|
| 318 |
-
"learning_rate": 4.8857421875e-05,
|
| 319 |
-
"loss": 0.8456,
|
| 320 |
-
"step": 4600
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 48.96,
|
| 324 |
-
"learning_rate": 4.7880859375e-05,
|
| 325 |
-
"loss": 0.8333,
|
| 326 |
-
"step": 4700
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 50.0,
|
| 330 |
-
"learning_rate": 4.6904296874999996e-05,
|
| 331 |
-
"loss": 0.8346,
|
| 332 |
-
"step": 4800
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 51.04,
|
| 336 |
-
"learning_rate": 4.5927734375e-05,
|
| 337 |
-
"loss": 0.8403,
|
| 338 |
-
"step": 4900
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 52.08,
|
| 342 |
-
"learning_rate": 4.4951171874999995e-05,
|
| 343 |
-
"loss": 0.8328,
|
| 344 |
-
"step": 5000
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 52.08,
|
| 348 |
-
"eval_loss": 0.14348936080932617,
|
| 349 |
-
"eval_runtime": 197.7739,
|
| 350 |
-
"eval_samples_per_second": 25.509,
|
| 351 |
-
"eval_steps_per_second": 0.799,
|
| 352 |
-
"eval_wer": 0.12054297171344966,
|
| 353 |
-
"step": 5000
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 53.12,
|
| 357 |
-
"learning_rate": 4.3974609374999994e-05,
|
| 358 |
-
"loss": 0.8275,
|
| 359 |
-
"step": 5100
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 54.17,
|
| 363 |
-
"learning_rate": 4.2998046875e-05,
|
| 364 |
-
"loss": 0.8262,
|
| 365 |
-
"step": 5200
|
| 366 |
-
},
|
| 367 |
-
{
|
| 368 |
-
"epoch": 55.21,
|
| 369 |
-
"learning_rate": 4.2021484375e-05,
|
| 370 |
-
"loss": 0.8167,
|
| 371 |
-
"step": 5300
|
| 372 |
-
},
|
| 373 |
-
{
|
| 374 |
-
"epoch": 56.25,
|
| 375 |
-
"learning_rate": 4.1044921875e-05,
|
| 376 |
-
"loss": 0.8194,
|
| 377 |
-
"step": 5400
|
| 378 |
-
},
|
| 379 |
-
{
|
| 380 |
-
"epoch": 57.29,
|
| 381 |
-
"learning_rate": 4.0068359375e-05,
|
| 382 |
-
"loss": 0.8192,
|
| 383 |
-
"step": 5500
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 58.33,
|
| 387 |
-
"learning_rate": 3.9091796874999996e-05,
|
| 388 |
-
"loss": 0.8176,
|
| 389 |
-
"step": 5600
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 59.37,
|
| 393 |
-
"learning_rate": 3.8115234374999995e-05,
|
| 394 |
-
"loss": 0.8115,
|
| 395 |
-
"step": 5700
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 60.42,
|
| 399 |
-
"learning_rate": 3.7138671874999994e-05,
|
| 400 |
-
"loss": 0.8129,
|
| 401 |
-
"step": 5800
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 61.46,
|
| 405 |
-
"learning_rate": 3.6162109375e-05,
|
| 406 |
-
"loss": 0.8052,
|
| 407 |
-
"step": 5900
|
| 408 |
-
},
|
| 409 |
-
{
|
| 410 |
-
"epoch": 62.5,
|
| 411 |
-
"learning_rate": 3.518554687499999e-05,
|
| 412 |
-
"loss": 0.8068,
|
| 413 |
-
"step": 6000
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 62.5,
|
| 417 |
-
"eval_loss": 0.13501569628715515,
|
| 418 |
-
"eval_runtime": 207.5786,
|
| 419 |
-
"eval_samples_per_second": 24.304,
|
| 420 |
-
"eval_steps_per_second": 0.761,
|
| 421 |
-
"eval_wer": 0.11913406307575593,
|
| 422 |
-
"step": 6000
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 63.54,
|
| 426 |
-
"learning_rate": 3.4208984375e-05,
|
| 427 |
-
"loss": 0.8004,
|
| 428 |
-
"step": 6100
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 64.58,
|
| 432 |
-
"learning_rate": 3.32421875e-05,
|
| 433 |
-
"loss": 0.7904,
|
| 434 |
-
"step": 6200
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 65.62,
|
| 438 |
-
"learning_rate": 3.2265625e-05,
|
| 439 |
-
"loss": 0.7947,
|
| 440 |
-
"step": 6300
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"epoch": 66.66,
|
| 444 |
-
"learning_rate": 3.12890625e-05,
|
| 445 |
-
"loss": 0.7981,
|
| 446 |
-
"step": 6400
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 67.71,
|
| 450 |
-
"learning_rate": 3.0312499999999998e-05,
|
| 451 |
-
"loss": 0.8018,
|
| 452 |
-
"step": 6500
|
| 453 |
-
},
|
| 454 |
-
{
|
| 455 |
-
"epoch": 68.75,
|
| 456 |
-
"learning_rate": 2.93359375e-05,
|
| 457 |
-
"loss": 0.7922,
|
| 458 |
-
"step": 6600
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 69.79,
|
| 462 |
-
"learning_rate": 2.8359374999999996e-05,
|
| 463 |
-
"loss": 0.796,
|
| 464 |
-
"step": 6700
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 70.83,
|
| 468 |
-
"learning_rate": 2.73828125e-05,
|
| 469 |
-
"loss": 0.7887,
|
| 470 |
-
"step": 6800
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 71.87,
|
| 474 |
-
"learning_rate": 2.6406249999999998e-05,
|
| 475 |
-
"loss": 0.7796,
|
| 476 |
-
"step": 6900
|
| 477 |
-
},
|
| 478 |
-
{
|
| 479 |
-
"epoch": 72.91,
|
| 480 |
-
"learning_rate": 2.5429687499999997e-05,
|
| 481 |
-
"loss": 0.7822,
|
| 482 |
-
"step": 7000
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 72.91,
|
| 486 |
-
"eval_loss": 0.1346774846315384,
|
| 487 |
-
"eval_runtime": 195.6804,
|
| 488 |
-
"eval_samples_per_second": 25.782,
|
| 489 |
-
"eval_steps_per_second": 0.807,
|
| 490 |
-
"eval_wer": 0.11550341389400672,
|
| 491 |
-
"step": 7000
|
| 492 |
-
}
|
| 493 |
-
],
|
| 494 |
-
"max_steps": 9600,
|
| 495 |
-
"num_train_epochs": 100,
|
| 496 |
-
"total_flos": 1.0876707707200464e+20,
|
| 497 |
-
"trial_name": null,
|
| 498 |
-
"trial_params": null
|
| 499 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-7000/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:28f8dab6838e0cc8a253bbc1fb16c34a7a36619cf3b9e2bd9c1e4027635a3b2b
|
| 3 |
-
size 3055
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262063089
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b01787364b33d07001b8b531ba393865dac319e3812bd53b7d9bdd904124e6c2
|
| 3 |
size 1262063089
|