Commit
•
19ab8f7
1
Parent(s):
36ac160
Add new model files
Browse files- config.json +28 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +421 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilroberta-base",
|
| 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 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 6,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"problem_type": "single_label_classification",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.18.0",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7ee71febf1301799b307434725e38e3bdd8a793c5e8b685b949b1f951bfa15c
|
| 3 |
+
size 657021061
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04cddaebd01116fa44a36a1cff517dda70c208c575f3dae160fc8e0b0e1d3cec
|
| 3 |
+
size 328519925
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d6fc1a43fa3d2407d3a19e0842bd9d81c7a8630d96ccd0e770c8514d620cf68
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1cdb33a4438d1ab9ec7a4d55ed897f9e042f7171be388f1182dd5943f71ebb8
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9254587155963303,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-6315",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 6315,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 1.9683293745051467e-05,
|
| 13 |
+
"loss": 0.5035,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.1,
|
| 18 |
+
"learning_rate": 1.936658749010293e-05,
|
| 19 |
+
"loss": 0.3283,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.14,
|
| 24 |
+
"learning_rate": 1.9049881235154395e-05,
|
| 25 |
+
"loss": 0.2999,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.19,
|
| 30 |
+
"learning_rate": 1.873317498020586e-05,
|
| 31 |
+
"loss": 0.2995,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.24,
|
| 36 |
+
"learning_rate": 1.8416468725257326e-05,
|
| 37 |
+
"loss": 0.2684,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.29,
|
| 42 |
+
"learning_rate": 1.809976247030879e-05,
|
| 43 |
+
"loss": 0.2604,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.33,
|
| 48 |
+
"learning_rate": 1.7783056215360253e-05,
|
| 49 |
+
"loss": 0.2505,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.38,
|
| 54 |
+
"learning_rate": 1.746634996041172e-05,
|
| 55 |
+
"loss": 0.275,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.43,
|
| 60 |
+
"learning_rate": 1.7149643705463184e-05,
|
| 61 |
+
"loss": 0.2649,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.48,
|
| 66 |
+
"learning_rate": 1.6832937450514647e-05,
|
| 67 |
+
"loss": 0.2449,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.52,
|
| 72 |
+
"learning_rate": 1.6516231195566115e-05,
|
| 73 |
+
"loss": 0.2219,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.57,
|
| 78 |
+
"learning_rate": 1.6199524940617578e-05,
|
| 79 |
+
"loss": 0.2454,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.62,
|
| 84 |
+
"learning_rate": 1.5882818685669043e-05,
|
| 85 |
+
"loss": 0.2174,
|
| 86 |
+
"step": 1300
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.67,
|
| 90 |
+
"learning_rate": 1.556611243072051e-05,
|
| 91 |
+
"loss": 0.2191,
|
| 92 |
+
"step": 1400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.71,
|
| 96 |
+
"learning_rate": 1.5249406175771972e-05,
|
| 97 |
+
"loss": 0.2085,
|
| 98 |
+
"step": 1500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.76,
|
| 102 |
+
"learning_rate": 1.4932699920823436e-05,
|
| 103 |
+
"loss": 0.2181,
|
| 104 |
+
"step": 1600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.81,
|
| 108 |
+
"learning_rate": 1.4615993665874902e-05,
|
| 109 |
+
"loss": 0.2157,
|
| 110 |
+
"step": 1700
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.86,
|
| 114 |
+
"learning_rate": 1.4299287410926367e-05,
|
| 115 |
+
"loss": 0.2152,
|
| 116 |
+
"step": 1800
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.9,
|
| 120 |
+
"learning_rate": 1.3982581155977833e-05,
|
| 121 |
+
"loss": 0.2021,
|
| 122 |
+
"step": 1900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.95,
|
| 126 |
+
"learning_rate": 1.3665874901029297e-05,
|
| 127 |
+
"loss": 0.2079,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0,
|
| 132 |
+
"learning_rate": 1.3349168646080762e-05,
|
| 133 |
+
"loss": 0.2149,
|
| 134 |
+
"step": 2100
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.0,
|
| 138 |
+
"eval_accuracy": 0.9197247706422018,
|
| 139 |
+
"eval_loss": 0.25181546807289124,
|
| 140 |
+
"eval_runtime": 0.5786,
|
| 141 |
+
"eval_samples_per_second": 1507.048,
|
| 142 |
+
"eval_steps_per_second": 24.196,
|
| 143 |
+
"step": 2105
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.05,
|
| 147 |
+
"learning_rate": 1.3032462391132226e-05,
|
| 148 |
+
"loss": 0.1549,
|
| 149 |
+
"step": 2200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.09,
|
| 153 |
+
"learning_rate": 1.271575613618369e-05,
|
| 154 |
+
"loss": 0.1544,
|
| 155 |
+
"step": 2300
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.14,
|
| 159 |
+
"learning_rate": 1.2399049881235155e-05,
|
| 160 |
+
"loss": 0.1603,
|
| 161 |
+
"step": 2400
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.19,
|
| 165 |
+
"learning_rate": 1.208234362628662e-05,
|
| 166 |
+
"loss": 0.1552,
|
| 167 |
+
"step": 2500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.24,
|
| 171 |
+
"learning_rate": 1.1765637371338086e-05,
|
| 172 |
+
"loss": 0.1694,
|
| 173 |
+
"step": 2600
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.28,
|
| 177 |
+
"learning_rate": 1.144893111638955e-05,
|
| 178 |
+
"loss": 0.1448,
|
| 179 |
+
"step": 2700
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.33,
|
| 183 |
+
"learning_rate": 1.1132224861441014e-05,
|
| 184 |
+
"loss": 0.15,
|
| 185 |
+
"step": 2800
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.38,
|
| 189 |
+
"learning_rate": 1.081551860649248e-05,
|
| 190 |
+
"loss": 0.1641,
|
| 191 |
+
"step": 2900
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.43,
|
| 195 |
+
"learning_rate": 1.0498812351543943e-05,
|
| 196 |
+
"loss": 0.1598,
|
| 197 |
+
"step": 3000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.47,
|
| 201 |
+
"learning_rate": 1.0182106096595407e-05,
|
| 202 |
+
"loss": 0.1587,
|
| 203 |
+
"step": 3100
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.52,
|
| 207 |
+
"learning_rate": 9.865399841646872e-06,
|
| 208 |
+
"loss": 0.1562,
|
| 209 |
+
"step": 3200
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.57,
|
| 213 |
+
"learning_rate": 9.548693586698338e-06,
|
| 214 |
+
"loss": 0.1486,
|
| 215 |
+
"step": 3300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.62,
|
| 219 |
+
"learning_rate": 9.231987331749803e-06,
|
| 220 |
+
"loss": 0.1493,
|
| 221 |
+
"step": 3400
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.66,
|
| 225 |
+
"learning_rate": 8.915281076801267e-06,
|
| 226 |
+
"loss": 0.1477,
|
| 227 |
+
"step": 3500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.71,
|
| 231 |
+
"learning_rate": 8.598574821852733e-06,
|
| 232 |
+
"loss": 0.1482,
|
| 233 |
+
"step": 3600
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.76,
|
| 237 |
+
"learning_rate": 8.281868566904197e-06,
|
| 238 |
+
"loss": 0.143,
|
| 239 |
+
"step": 3700
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.81,
|
| 243 |
+
"learning_rate": 7.965162311955662e-06,
|
| 244 |
+
"loss": 0.1574,
|
| 245 |
+
"step": 3800
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.85,
|
| 249 |
+
"learning_rate": 7.648456057007126e-06,
|
| 250 |
+
"loss": 0.1496,
|
| 251 |
+
"step": 3900
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.9,
|
| 255 |
+
"learning_rate": 7.331749802058591e-06,
|
| 256 |
+
"loss": 0.1514,
|
| 257 |
+
"step": 4000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.95,
|
| 261 |
+
"learning_rate": 7.015043547110056e-06,
|
| 262 |
+
"loss": 0.144,
|
| 263 |
+
"step": 4100
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.0,
|
| 267 |
+
"learning_rate": 6.698337292161521e-06,
|
| 268 |
+
"loss": 0.1472,
|
| 269 |
+
"step": 4200
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.0,
|
| 273 |
+
"eval_accuracy": 0.9185779816513762,
|
| 274 |
+
"eval_loss": 0.2679901719093323,
|
| 275 |
+
"eval_runtime": 0.5778,
|
| 276 |
+
"eval_samples_per_second": 1509.287,
|
| 277 |
+
"eval_steps_per_second": 24.232,
|
| 278 |
+
"step": 4210
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.04,
|
| 282 |
+
"learning_rate": 6.3816310372129854e-06,
|
| 283 |
+
"loss": 0.1153,
|
| 284 |
+
"step": 4300
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.09,
|
| 288 |
+
"learning_rate": 6.06492478226445e-06,
|
| 289 |
+
"loss": 0.1184,
|
| 290 |
+
"step": 4400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.14,
|
| 294 |
+
"learning_rate": 5.748218527315916e-06,
|
| 295 |
+
"loss": 0.1096,
|
| 296 |
+
"step": 4500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.19,
|
| 300 |
+
"learning_rate": 5.431512272367379e-06,
|
| 301 |
+
"loss": 0.1196,
|
| 302 |
+
"step": 4600
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.23,
|
| 306 |
+
"learning_rate": 5.114806017418844e-06,
|
| 307 |
+
"loss": 0.1246,
|
| 308 |
+
"step": 4700
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.28,
|
| 312 |
+
"learning_rate": 4.798099762470309e-06,
|
| 313 |
+
"loss": 0.0929,
|
| 314 |
+
"step": 4800
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.33,
|
| 318 |
+
"learning_rate": 4.481393507521774e-06,
|
| 319 |
+
"loss": 0.1204,
|
| 320 |
+
"step": 4900
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.38,
|
| 324 |
+
"learning_rate": 4.164687252573238e-06,
|
| 325 |
+
"loss": 0.1113,
|
| 326 |
+
"step": 5000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.42,
|
| 330 |
+
"learning_rate": 3.8479809976247036e-06,
|
| 331 |
+
"loss": 0.1169,
|
| 332 |
+
"step": 5100
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.47,
|
| 336 |
+
"learning_rate": 3.531274742676168e-06,
|
| 337 |
+
"loss": 0.1144,
|
| 338 |
+
"step": 5200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.52,
|
| 342 |
+
"learning_rate": 3.214568487727633e-06,
|
| 343 |
+
"loss": 0.1171,
|
| 344 |
+
"step": 5300
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.57,
|
| 348 |
+
"learning_rate": 2.897862232779098e-06,
|
| 349 |
+
"loss": 0.1031,
|
| 350 |
+
"step": 5400
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.61,
|
| 354 |
+
"learning_rate": 2.581155977830562e-06,
|
| 355 |
+
"loss": 0.1287,
|
| 356 |
+
"step": 5500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.66,
|
| 360 |
+
"learning_rate": 2.264449722882027e-06,
|
| 361 |
+
"loss": 0.12,
|
| 362 |
+
"step": 5600
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.71,
|
| 366 |
+
"learning_rate": 1.947743467933492e-06,
|
| 367 |
+
"loss": 0.1019,
|
| 368 |
+
"step": 5700
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.76,
|
| 372 |
+
"learning_rate": 1.6310372129849566e-06,
|
| 373 |
+
"loss": 0.1264,
|
| 374 |
+
"step": 5800
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.8,
|
| 378 |
+
"learning_rate": 1.3143309580364213e-06,
|
| 379 |
+
"loss": 0.1066,
|
| 380 |
+
"step": 5900
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.85,
|
| 384 |
+
"learning_rate": 9.976247030878861e-07,
|
| 385 |
+
"loss": 0.1226,
|
| 386 |
+
"step": 6000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.9,
|
| 390 |
+
"learning_rate": 6.809184481393508e-07,
|
| 391 |
+
"loss": 0.1027,
|
| 392 |
+
"step": 6100
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.95,
|
| 396 |
+
"learning_rate": 3.642121931908155e-07,
|
| 397 |
+
"loss": 0.1201,
|
| 398 |
+
"step": 6200
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.99,
|
| 402 |
+
"learning_rate": 4.750593824228029e-08,
|
| 403 |
+
"loss": 0.1071,
|
| 404 |
+
"step": 6300
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.0,
|
| 408 |
+
"eval_accuracy": 0.9254587155963303,
|
| 409 |
+
"eval_loss": 0.29632261395454407,
|
| 410 |
+
"eval_runtime": 0.5786,
|
| 411 |
+
"eval_samples_per_second": 1507.184,
|
| 412 |
+
"eval_steps_per_second": 24.198,
|
| 413 |
+
"step": 6315
|
| 414 |
+
}
|
| 415 |
+
],
|
| 416 |
+
"max_steps": 6315,
|
| 417 |
+
"num_train_epochs": 3,
|
| 418 |
+
"total_flos": 3345580062031104.0,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:590eaf893da3d87a9aa244d3f5203caf977ea10bba3d92868b42001d45b3888f
|
| 3 |
+
size 3003
|