Upload 7 files
Browse files- config.json +30 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +361 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "klue/roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 4096,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 16,
|
| 20 |
+
"num_hidden_layers": 24,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"problem_type": "single_label_classification",
|
| 24 |
+
"tokenizer_class": "BertTokenizer",
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.28.1",
|
| 27 |
+
"type_vocab_size": 1,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 32000
|
| 30 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7122436f15a481bd46f4f620b47b98dc4ddd57113b06a1a4ceaaa438e75585f
|
| 3 |
+
size 2693498373
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab8b22e6989ecd0e4085cf6e78663c0aeb0deadb1491c47c940eca73e4c30b2c
|
| 3 |
+
size 1346773749
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8860f3d222bcf225f8853687c04a2739ca14897cd42adbeab7f4c5ef9029a7b
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eef7f583b57edb4c200662e48b2c0103f0a458d3f91babb83378f6b746e9b233
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9956499952041198,
|
| 3 |
+
"best_model_checkpoint": "C:\\Users\\tm011\\PycharmProjects\\Custom_baseline\\sangsang_re\\checkpoint-5625",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 5625,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 1.9822222222222226e-05,
|
| 13 |
+
"loss": 0.0627,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 1.9644444444444447e-05,
|
| 19 |
+
"loss": 0.0274,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.05,
|
| 24 |
+
"learning_rate": 1.9466666666666668e-05,
|
| 25 |
+
"loss": 0.032,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.07,
|
| 30 |
+
"learning_rate": 1.928888888888889e-05,
|
| 31 |
+
"loss": 0.0335,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.09,
|
| 36 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 37 |
+
"loss": 0.0276,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11,
|
| 42 |
+
"learning_rate": 1.8933333333333334e-05,
|
| 43 |
+
"loss": 0.034,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12,
|
| 48 |
+
"learning_rate": 1.8755555555555558e-05,
|
| 49 |
+
"loss": 0.0292,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.14,
|
| 54 |
+
"learning_rate": 1.857777777777778e-05,
|
| 55 |
+
"loss": 0.0203,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.16,
|
| 60 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 61 |
+
"loss": 0.0303,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.18,
|
| 66 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 67 |
+
"loss": 0.0251,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.2,
|
| 72 |
+
"learning_rate": 1.8044444444444445e-05,
|
| 73 |
+
"loss": 0.0192,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.21,
|
| 78 |
+
"learning_rate": 1.7866666666666666e-05,
|
| 79 |
+
"loss": 0.02,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.23,
|
| 84 |
+
"learning_rate": 1.768888888888889e-05,
|
| 85 |
+
"loss": 0.0278,
|
| 86 |
+
"step": 1300
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.25,
|
| 90 |
+
"learning_rate": 1.751111111111111e-05,
|
| 91 |
+
"loss": 0.0217,
|
| 92 |
+
"step": 1400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.27,
|
| 96 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 97 |
+
"loss": 0.0125,
|
| 98 |
+
"step": 1500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.28,
|
| 102 |
+
"learning_rate": 1.7155555555555557e-05,
|
| 103 |
+
"loss": 0.0288,
|
| 104 |
+
"step": 1600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.3,
|
| 108 |
+
"learning_rate": 1.697777777777778e-05,
|
| 109 |
+
"loss": 0.0193,
|
| 110 |
+
"step": 1700
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.32,
|
| 114 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 115 |
+
"loss": 0.0208,
|
| 116 |
+
"step": 1800
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.34,
|
| 120 |
+
"learning_rate": 1.6622222222222223e-05,
|
| 121 |
+
"loss": 0.0183,
|
| 122 |
+
"step": 1900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.36,
|
| 126 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 127 |
+
"loss": 0.0171,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.37,
|
| 132 |
+
"learning_rate": 1.6266666666666668e-05,
|
| 133 |
+
"loss": 0.0179,
|
| 134 |
+
"step": 2100
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.39,
|
| 138 |
+
"learning_rate": 1.608888888888889e-05,
|
| 139 |
+
"loss": 0.0196,
|
| 140 |
+
"step": 2200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.41,
|
| 144 |
+
"learning_rate": 1.5911111111111113e-05,
|
| 145 |
+
"loss": 0.0215,
|
| 146 |
+
"step": 2300
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.43,
|
| 150 |
+
"learning_rate": 1.5733333333333334e-05,
|
| 151 |
+
"loss": 0.0249,
|
| 152 |
+
"step": 2400
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.44,
|
| 156 |
+
"learning_rate": 1.555555555555556e-05,
|
| 157 |
+
"loss": 0.0193,
|
| 158 |
+
"step": 2500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.46,
|
| 162 |
+
"learning_rate": 1.537777777777778e-05,
|
| 163 |
+
"loss": 0.0259,
|
| 164 |
+
"step": 2600
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.48,
|
| 168 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 169 |
+
"loss": 0.0237,
|
| 170 |
+
"step": 2700
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5,
|
| 174 |
+
"learning_rate": 1.5022222222222223e-05,
|
| 175 |
+
"loss": 0.0272,
|
| 176 |
+
"step": 2800
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.52,
|
| 180 |
+
"learning_rate": 1.4844444444444445e-05,
|
| 181 |
+
"loss": 0.013,
|
| 182 |
+
"step": 2900
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.53,
|
| 186 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 187 |
+
"loss": 0.0257,
|
| 188 |
+
"step": 3000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.55,
|
| 192 |
+
"learning_rate": 1.448888888888889e-05,
|
| 193 |
+
"loss": 0.0219,
|
| 194 |
+
"step": 3100
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.57,
|
| 198 |
+
"learning_rate": 1.4311111111111111e-05,
|
| 199 |
+
"loss": 0.0139,
|
| 200 |
+
"step": 3200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.59,
|
| 204 |
+
"learning_rate": 1.4133333333333334e-05,
|
| 205 |
+
"loss": 0.019,
|
| 206 |
+
"step": 3300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6,
|
| 210 |
+
"learning_rate": 1.3955555555555558e-05,
|
| 211 |
+
"loss": 0.0181,
|
| 212 |
+
"step": 3400
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.62,
|
| 216 |
+
"learning_rate": 1.377777777777778e-05,
|
| 217 |
+
"loss": 0.0078,
|
| 218 |
+
"step": 3500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.64,
|
| 222 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 223 |
+
"loss": 0.0233,
|
| 224 |
+
"step": 3600
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.66,
|
| 228 |
+
"learning_rate": 1.3422222222222223e-05,
|
| 229 |
+
"loss": 0.021,
|
| 230 |
+
"step": 3700
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.68,
|
| 234 |
+
"learning_rate": 1.3244444444444447e-05,
|
| 235 |
+
"loss": 0.0201,
|
| 236 |
+
"step": 3800
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.69,
|
| 240 |
+
"learning_rate": 1.3066666666666668e-05,
|
| 241 |
+
"loss": 0.0222,
|
| 242 |
+
"step": 3900
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.71,
|
| 246 |
+
"learning_rate": 1.288888888888889e-05,
|
| 247 |
+
"loss": 0.0216,
|
| 248 |
+
"step": 4000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.73,
|
| 252 |
+
"learning_rate": 1.2711111111111112e-05,
|
| 253 |
+
"loss": 0.0206,
|
| 254 |
+
"step": 4100
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.75,
|
| 258 |
+
"learning_rate": 1.2533333333333336e-05,
|
| 259 |
+
"loss": 0.0113,
|
| 260 |
+
"step": 4200
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.76,
|
| 264 |
+
"learning_rate": 1.2355555555555557e-05,
|
| 265 |
+
"loss": 0.0161,
|
| 266 |
+
"step": 4300
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.78,
|
| 270 |
+
"learning_rate": 1.217777777777778e-05,
|
| 271 |
+
"loss": 0.025,
|
| 272 |
+
"step": 4400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.8,
|
| 276 |
+
"learning_rate": 1.2e-05,
|
| 277 |
+
"loss": 0.0097,
|
| 278 |
+
"step": 4500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.82,
|
| 282 |
+
"learning_rate": 1.1822222222222225e-05,
|
| 283 |
+
"loss": 0.0219,
|
| 284 |
+
"step": 4600
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.84,
|
| 288 |
+
"learning_rate": 1.1644444444444446e-05,
|
| 289 |
+
"loss": 0.0294,
|
| 290 |
+
"step": 4700
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.85,
|
| 294 |
+
"learning_rate": 1.1466666666666668e-05,
|
| 295 |
+
"loss": 0.017,
|
| 296 |
+
"step": 4800
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.87,
|
| 300 |
+
"learning_rate": 1.1288888888888889e-05,
|
| 301 |
+
"loss": 0.0198,
|
| 302 |
+
"step": 4900
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.89,
|
| 306 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 307 |
+
"loss": 0.0189,
|
| 308 |
+
"step": 5000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.91,
|
| 312 |
+
"learning_rate": 1.0933333333333334e-05,
|
| 313 |
+
"loss": 0.0161,
|
| 314 |
+
"step": 5100
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.92,
|
| 318 |
+
"learning_rate": 1.0755555555555557e-05,
|
| 319 |
+
"loss": 0.0167,
|
| 320 |
+
"step": 5200
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.94,
|
| 324 |
+
"learning_rate": 1.0577777777777778e-05,
|
| 325 |
+
"loss": 0.0236,
|
| 326 |
+
"step": 5300
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.96,
|
| 330 |
+
"learning_rate": 1.04e-05,
|
| 331 |
+
"loss": 0.0147,
|
| 332 |
+
"step": 5400
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.98,
|
| 336 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 337 |
+
"loss": 0.0324,
|
| 338 |
+
"step": 5500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.0,
|
| 342 |
+
"learning_rate": 1.0044444444444446e-05,
|
| 343 |
+
"loss": 0.0209,
|
| 344 |
+
"step": 5600
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.0,
|
| 348 |
+
"eval_f1": 0.9956499952041198,
|
| 349 |
+
"eval_loss": 0.016555603593587875,
|
| 350 |
+
"eval_runtime": 53.6078,
|
| 351 |
+
"eval_samples_per_second": 373.08,
|
| 352 |
+
"eval_steps_per_second": 11.659,
|
| 353 |
+
"step": 5625
|
| 354 |
+
}
|
| 355 |
+
],
|
| 356 |
+
"max_steps": 11250,
|
| 357 |
+
"num_train_epochs": 2,
|
| 358 |
+
"total_flos": 4.193691134976e+16,
|
| 359 |
+
"trial_name": null,
|
| 360 |
+
"trial_params": null
|
| 361 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5d9654bacee0a0bf61f656ca7fa21da0c58252897b3a6d37a3846620b8a65b3
|
| 3 |
+
size 3707
|