first commit
Browse files- config.json +76 -0
- preprocessor_config.json +8 -0
- pytorch_model.bin +3 -0
- trainer_state.json +324 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"apply_spec_augment": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"CustomClassificationModel"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.01,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"conv_bias": true,
|
| 11 |
+
"conv_dim": [
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512
|
| 19 |
+
],
|
| 20 |
+
"conv_kernel": [
|
| 21 |
+
10,
|
| 22 |
+
3,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
2,
|
| 27 |
+
2
|
| 28 |
+
],
|
| 29 |
+
"conv_stride": [
|
| 30 |
+
5,
|
| 31 |
+
2,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2
|
| 37 |
+
],
|
| 38 |
+
"ctc_loss_reduction": "sum",
|
| 39 |
+
"ctc_zero_infinity": false,
|
| 40 |
+
"do_stable_layer_norm": true,
|
| 41 |
+
"eos_token_id": 2,
|
| 42 |
+
"feat_extract_activation": "gelu",
|
| 43 |
+
"feat_extract_dropout": 0.0,
|
| 44 |
+
"feat_extract_norm": "layer",
|
| 45 |
+
"feat_proj_dropout": 0.0,
|
| 46 |
+
"final_dropout": 0.0,
|
| 47 |
+
"gradient_checkpointing": true,
|
| 48 |
+
"hidden_act": "gelu",
|
| 49 |
+
"hidden_dropout": 0.01,
|
| 50 |
+
"hidden_size": 1024,
|
| 51 |
+
"initializer_range": 0.02,
|
| 52 |
+
"intermediate_size": 4096,
|
| 53 |
+
"layer_norm_eps": 1e-05,
|
| 54 |
+
"layerdrop": 0.01,
|
| 55 |
+
"mask_channel_length": 10,
|
| 56 |
+
"mask_channel_min_space": 1,
|
| 57 |
+
"mask_channel_other": 0.0,
|
| 58 |
+
"mask_channel_prob": 0.0,
|
| 59 |
+
"mask_channel_selection": "static",
|
| 60 |
+
"mask_feature_length": 10,
|
| 61 |
+
"mask_feature_prob": 0.0,
|
| 62 |
+
"mask_time_length": 10,
|
| 63 |
+
"mask_time_min_space": 1,
|
| 64 |
+
"mask_time_other": 0.0,
|
| 65 |
+
"mask_time_prob": 0.05,
|
| 66 |
+
"mask_time_selection": "static",
|
| 67 |
+
"model_type": "wav2vec2",
|
| 68 |
+
"num_attention_heads": 16,
|
| 69 |
+
"num_conv_pos_embedding_groups": 16,
|
| 70 |
+
"num_conv_pos_embeddings": 128,
|
| 71 |
+
"num_feat_extract_layers": 7,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"pad_token_id": 0,
|
| 74 |
+
"transformers_version": "4.4.2",
|
| 75 |
+
"vocab_size": 32
|
| 76 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_size": 1,
|
| 4 |
+
"padding_side": "right",
|
| 5 |
+
"padding_value": 0.0,
|
| 6 |
+
"return_attention_mask": true,
|
| 7 |
+
"sampling_rate": 16000
|
| 8 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f64da00b3a836544cfce6c19393da385760943de3f28c8ce89db05aa7953464a
|
| 3 |
+
size 1265016809
|
trainer_state.json
ADDED
|
@@ -0,0 +1,324 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.412280701754386,
|
| 5 |
+
"global_step": 2200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 2.973626373626374e-05,
|
| 13 |
+
"loss": 1.622,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"eval_accuracy": 0.24010217113665389,
|
| 19 |
+
"eval_loss": 1.6581733226776123,
|
| 20 |
+
"eval_runtime": 381.1384,
|
| 21 |
+
"eval_samples_per_second": 4.109,
|
| 22 |
+
"step": 100
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.22,
|
| 26 |
+
"learning_rate": 2.9406593406593407e-05,
|
| 27 |
+
"loss": 1.3721,
|
| 28 |
+
"step": 200
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.22,
|
| 32 |
+
"eval_accuracy": 0.2835249042145594,
|
| 33 |
+
"eval_loss": 1.9170576333999634,
|
| 34 |
+
"eval_runtime": 378.5115,
|
| 35 |
+
"eval_samples_per_second": 4.137,
|
| 36 |
+
"step": 200
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.33,
|
| 40 |
+
"learning_rate": 2.907692307692308e-05,
|
| 41 |
+
"loss": 1.1269,
|
| 42 |
+
"step": 300
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.33,
|
| 46 |
+
"eval_accuracy": 0.36845466155810985,
|
| 47 |
+
"eval_loss": 1.7032861709594727,
|
| 48 |
+
"eval_runtime": 385.3173,
|
| 49 |
+
"eval_samples_per_second": 4.064,
|
| 50 |
+
"step": 300
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.44,
|
| 54 |
+
"learning_rate": 2.8747252747252748e-05,
|
| 55 |
+
"loss": 0.9152,
|
| 56 |
+
"step": 400
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.44,
|
| 60 |
+
"eval_accuracy": 0.388250319284802,
|
| 61 |
+
"eval_loss": 1.7423878908157349,
|
| 62 |
+
"eval_runtime": 388.0594,
|
| 63 |
+
"eval_samples_per_second": 4.035,
|
| 64 |
+
"step": 400
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.55,
|
| 68 |
+
"learning_rate": 2.8417582417582416e-05,
|
| 69 |
+
"loss": 0.732,
|
| 70 |
+
"step": 500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.55,
|
| 74 |
+
"eval_accuracy": 0.4616858237547893,
|
| 75 |
+
"eval_loss": 1.5253428220748901,
|
| 76 |
+
"eval_runtime": 386.9842,
|
| 77 |
+
"eval_samples_per_second": 4.047,
|
| 78 |
+
"step": 500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.66,
|
| 82 |
+
"learning_rate": 2.8087912087912088e-05,
|
| 83 |
+
"loss": 0.684,
|
| 84 |
+
"step": 600
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.66,
|
| 88 |
+
"eval_accuracy": 0.4367816091954023,
|
| 89 |
+
"eval_loss": 1.6441736221313477,
|
| 90 |
+
"eval_runtime": 388.1257,
|
| 91 |
+
"eval_samples_per_second": 4.035,
|
| 92 |
+
"step": 600
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.77,
|
| 96 |
+
"learning_rate": 2.775824175824176e-05,
|
| 97 |
+
"loss": 0.5538,
|
| 98 |
+
"step": 700
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.77,
|
| 102 |
+
"eval_accuracy": 0.5108556832694764,
|
| 103 |
+
"eval_loss": 1.450364351272583,
|
| 104 |
+
"eval_runtime": 389.4611,
|
| 105 |
+
"eval_samples_per_second": 4.021,
|
| 106 |
+
"step": 700
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.88,
|
| 110 |
+
"learning_rate": 2.7428571428571428e-05,
|
| 111 |
+
"loss": 0.5425,
|
| 112 |
+
"step": 800
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.88,
|
| 116 |
+
"eval_accuracy": 0.49936143039591313,
|
| 117 |
+
"eval_loss": 1.4108269214630127,
|
| 118 |
+
"eval_runtime": 389.7612,
|
| 119 |
+
"eval_samples_per_second": 4.018,
|
| 120 |
+
"step": 800
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.99,
|
| 124 |
+
"learning_rate": 2.70989010989011e-05,
|
| 125 |
+
"loss": 0.514,
|
| 126 |
+
"step": 900
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.99,
|
| 130 |
+
"eval_accuracy": 0.5057471264367817,
|
| 131 |
+
"eval_loss": 1.4206087589263916,
|
| 132 |
+
"eval_runtime": 396.4756,
|
| 133 |
+
"eval_samples_per_second": 3.95,
|
| 134 |
+
"step": 900
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.1,
|
| 138 |
+
"learning_rate": 2.6769230769230772e-05,
|
| 139 |
+
"loss": 0.3068,
|
| 140 |
+
"step": 1000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.1,
|
| 144 |
+
"eval_accuracy": 0.5159642401021711,
|
| 145 |
+
"eval_loss": 1.6294729709625244,
|
| 146 |
+
"eval_runtime": 394.6782,
|
| 147 |
+
"eval_samples_per_second": 3.968,
|
| 148 |
+
"step": 1000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.21,
|
| 152 |
+
"learning_rate": 2.643956043956044e-05,
|
| 153 |
+
"loss": 0.2865,
|
| 154 |
+
"step": 1100
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.21,
|
| 158 |
+
"eval_accuracy": 0.5076628352490421,
|
| 159 |
+
"eval_loss": 1.733625888824463,
|
| 160 |
+
"eval_runtime": 393.6145,
|
| 161 |
+
"eval_samples_per_second": 3.979,
|
| 162 |
+
"step": 1100
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.32,
|
| 166 |
+
"learning_rate": 2.6109890109890112e-05,
|
| 167 |
+
"loss": 0.301,
|
| 168 |
+
"step": 1200
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.32,
|
| 172 |
+
"eval_accuracy": 0.6277139208173691,
|
| 173 |
+
"eval_loss": 1.2089332342147827,
|
| 174 |
+
"eval_runtime": 389.8374,
|
| 175 |
+
"eval_samples_per_second": 4.017,
|
| 176 |
+
"step": 1200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.43,
|
| 180 |
+
"learning_rate": 2.578021978021978e-05,
|
| 181 |
+
"loss": 0.2517,
|
| 182 |
+
"step": 1300
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.43,
|
| 186 |
+
"eval_accuracy": 0.5983397190293742,
|
| 187 |
+
"eval_loss": 1.3427765369415283,
|
| 188 |
+
"eval_runtime": 388.9975,
|
| 189 |
+
"eval_samples_per_second": 4.026,
|
| 190 |
+
"step": 1300
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.54,
|
| 194 |
+
"learning_rate": 2.545054945054945e-05,
|
| 195 |
+
"loss": 0.2819,
|
| 196 |
+
"step": 1400
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.54,
|
| 200 |
+
"eval_accuracy": 0.5600255427841635,
|
| 201 |
+
"eval_loss": 1.5083413124084473,
|
| 202 |
+
"eval_runtime": 390.3746,
|
| 203 |
+
"eval_samples_per_second": 4.012,
|
| 204 |
+
"step": 1400
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.64,
|
| 208 |
+
"learning_rate": 2.512087912087912e-05,
|
| 209 |
+
"loss": 0.2706,
|
| 210 |
+
"step": 1500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.64,
|
| 214 |
+
"eval_accuracy": 0.6047254150702427,
|
| 215 |
+
"eval_loss": 1.5413047075271606,
|
| 216 |
+
"eval_runtime": 389.1952,
|
| 217 |
+
"eval_samples_per_second": 4.024,
|
| 218 |
+
"step": 1500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.75,
|
| 222 |
+
"learning_rate": 2.479120879120879e-05,
|
| 223 |
+
"loss": 0.1991,
|
| 224 |
+
"step": 1600
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.75,
|
| 228 |
+
"eval_accuracy": 0.598978288633461,
|
| 229 |
+
"eval_loss": 1.5572402477264404,
|
| 230 |
+
"eval_runtime": 389.1243,
|
| 231 |
+
"eval_samples_per_second": 4.024,
|
| 232 |
+
"step": 1600
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.86,
|
| 236 |
+
"learning_rate": 2.446153846153846e-05,
|
| 237 |
+
"loss": 0.2726,
|
| 238 |
+
"step": 1700
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.86,
|
| 242 |
+
"eval_accuracy": 0.6021711366538953,
|
| 243 |
+
"eval_loss": 1.4013671875,
|
| 244 |
+
"eval_runtime": 392.7301,
|
| 245 |
+
"eval_samples_per_second": 3.987,
|
| 246 |
+
"step": 1700
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.97,
|
| 250 |
+
"learning_rate": 2.4131868131868133e-05,
|
| 251 |
+
"loss": 0.2015,
|
| 252 |
+
"step": 1800
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.97,
|
| 256 |
+
"eval_accuracy": 0.5676883780332056,
|
| 257 |
+
"eval_loss": 2.248255729675293,
|
| 258 |
+
"eval_runtime": 389.7999,
|
| 259 |
+
"eval_samples_per_second": 4.017,
|
| 260 |
+
"step": 1800
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.08,
|
| 264 |
+
"learning_rate": 2.38021978021978e-05,
|
| 265 |
+
"loss": 0.173,
|
| 266 |
+
"step": 1900
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.08,
|
| 270 |
+
"eval_accuracy": 0.644316730523627,
|
| 271 |
+
"eval_loss": 1.5393086671829224,
|
| 272 |
+
"eval_runtime": 390.3149,
|
| 273 |
+
"eval_samples_per_second": 4.012,
|
| 274 |
+
"step": 1900
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.19,
|
| 278 |
+
"learning_rate": 2.3472527472527474e-05,
|
| 279 |
+
"loss": 0.1177,
|
| 280 |
+
"step": 2000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.19,
|
| 284 |
+
"eval_accuracy": 0.6028097062579821,
|
| 285 |
+
"eval_loss": 1.9018601179122925,
|
| 286 |
+
"eval_runtime": 390.5708,
|
| 287 |
+
"eval_samples_per_second": 4.01,
|
| 288 |
+
"step": 2000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.3,
|
| 292 |
+
"learning_rate": 2.3142857142857145e-05,
|
| 293 |
+
"loss": 0.0907,
|
| 294 |
+
"step": 2100
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.3,
|
| 298 |
+
"eval_accuracy": 0.6194125159642401,
|
| 299 |
+
"eval_loss": 1.8655920028686523,
|
| 300 |
+
"eval_runtime": 392.1244,
|
| 301 |
+
"eval_samples_per_second": 3.994,
|
| 302 |
+
"step": 2100
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.41,
|
| 306 |
+
"learning_rate": 2.2813186813186814e-05,
|
| 307 |
+
"loss": 0.1878,
|
| 308 |
+
"step": 2200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.41,
|
| 312 |
+
"eval_accuracy": 0.6296296296296297,
|
| 313 |
+
"eval_loss": 1.998379111289978,
|
| 314 |
+
"eval_runtime": 390.0846,
|
| 315 |
+
"eval_samples_per_second": 4.015,
|
| 316 |
+
"step": 2200
|
| 317 |
+
}
|
| 318 |
+
],
|
| 319 |
+
"max_steps": 9120,
|
| 320 |
+
"num_train_epochs": 10,
|
| 321 |
+
"total_flos": 2.137068831744e+19,
|
| 322 |
+
"trial_name": null,
|
| 323 |
+
"trial_params": null
|
| 324 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75111b63f66ceef5558bccfa756b147f9bb7703645a7b27ee22101f1a5addd97
|
| 3 |
+
size 2287
|