Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +259 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 315,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.15873015873015872,
|
| 13 |
+
"grad_norm": 5.117466449737549,
|
| 14 |
+
"learning_rate": 0.000125,
|
| 15 |
+
"loss": 1.112,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.31746031746031744,
|
| 20 |
+
"grad_norm": 3.9644668102264404,
|
| 21 |
+
"learning_rate": 0.00019991169537951468,
|
| 22 |
+
"loss": 0.4916,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.47619047619047616,
|
| 27 |
+
"grad_norm": 2.397569417953491,
|
| 28 |
+
"learning_rate": 0.00019892005856487878,
|
| 29 |
+
"loss": 0.3606,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.6349206349206349,
|
| 34 |
+
"grad_norm": 1.5157995223999023,
|
| 35 |
+
"learning_rate": 0.00019683737802329244,
|
| 36 |
+
"loss": 0.2953,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.7936507936507936,
|
| 41 |
+
"grad_norm": 2.1924238204956055,
|
| 42 |
+
"learning_rate": 0.00019368662478381799,
|
| 43 |
+
"loss": 0.2249,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.9523809523809523,
|
| 48 |
+
"grad_norm": 2.078732967376709,
|
| 49 |
+
"learning_rate": 0.00018950255023668876,
|
| 50 |
+
"loss": 0.2383,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.1111111111111112,
|
| 55 |
+
"grad_norm": 1.4331333637237549,
|
| 56 |
+
"learning_rate": 0.0001843313028411149,
|
| 57 |
+
"loss": 0.1957,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.2698412698412698,
|
| 62 |
+
"grad_norm": 0.9676660299301147,
|
| 63 |
+
"learning_rate": 0.00017822991912854713,
|
| 64 |
+
"loss": 0.1727,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.4285714285714286,
|
| 69 |
+
"grad_norm": 1.7661018371582031,
|
| 70 |
+
"learning_rate": 0.00017126569461540443,
|
| 71 |
+
"loss": 0.1687,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.5873015873015874,
|
| 76 |
+
"grad_norm": 1.013567328453064,
|
| 77 |
+
"learning_rate": 0.00016351544156381414,
|
| 78 |
+
"loss": 0.1581,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.746031746031746,
|
| 83 |
+
"grad_norm": 1.0763999223709106,
|
| 84 |
+
"learning_rate": 0.0001550646417769301,
|
| 85 |
+
"loss": 0.1281,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.9047619047619047,
|
| 90 |
+
"grad_norm": 0.9065868258476257,
|
| 91 |
+
"learning_rate": 0.00014600650377311522,
|
| 92 |
+
"loss": 0.1301,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.0634920634920633,
|
| 97 |
+
"grad_norm": 0.8975210785865784,
|
| 98 |
+
"learning_rate": 0.00013644093473793215,
|
| 99 |
+
"loss": 0.1131,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.2222222222222223,
|
| 104 |
+
"grad_norm": 0.7319889664649963,
|
| 105 |
+
"learning_rate": 0.00012647343859284997,
|
| 106 |
+
"loss": 0.0953,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.380952380952381,
|
| 111 |
+
"grad_norm": 0.849612832069397,
|
| 112 |
+
"learning_rate": 0.00011621395233447248,
|
| 113 |
+
"loss": 0.1131,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.5396825396825395,
|
| 118 |
+
"grad_norm": 0.8651995062828064,
|
| 119 |
+
"learning_rate": 0.00010577563347894285,
|
| 120 |
+
"loss": 0.1016,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.6984126984126986,
|
| 125 |
+
"grad_norm": 1.222275972366333,
|
| 126 |
+
"learning_rate": 9.527361198546714e-05,
|
| 127 |
+
"loss": 0.0894,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.857142857142857,
|
| 132 |
+
"grad_norm": 1.0224725008010864,
|
| 133 |
+
"learning_rate": 8.48237204246785e-05,
|
| 134 |
+
"loss": 0.092,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.015873015873016,
|
| 139 |
+
"grad_norm": 0.9545143246650696,
|
| 140 |
+
"learning_rate": 7.454121639751371e-05,
|
| 141 |
+
"loss": 0.0983,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 3.1746031746031744,
|
| 146 |
+
"grad_norm": 0.6206408143043518,
|
| 147 |
+
"learning_rate": 6.453951129574644e-05,
|
| 148 |
+
"loss": 0.0956,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 3.3333333333333335,
|
| 153 |
+
"grad_norm": 0.5555378198623657,
|
| 154 |
+
"learning_rate": 5.492891942537703e-05,
|
| 155 |
+
"loss": 0.0828,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.492063492063492,
|
| 160 |
+
"grad_norm": 0.5887261629104614,
|
| 161 |
+
"learning_rate": 4.581544128948413e-05,
|
| 162 |
+
"loss": 0.083,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 3.6507936507936507,
|
| 167 |
+
"grad_norm": 0.4162333011627197,
|
| 168 |
+
"learning_rate": 3.729959445038136e-05,
|
| 169 |
+
"loss": 0.0714,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.8095238095238093,
|
| 174 |
+
"grad_norm": 0.4157885015010834,
|
| 175 |
+
"learning_rate": 2.9475304866143027e-05,
|
| 176 |
+
"loss": 0.0688,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.9682539682539684,
|
| 181 |
+
"grad_norm": 0.4919394850730896,
|
| 182 |
+
"learning_rate": 2.242887092955801e-05,
|
| 183 |
+
"loss": 0.057,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 4.1269841269841265,
|
| 188 |
+
"grad_norm": 0.5343856811523438,
|
| 189 |
+
"learning_rate": 1.6238011635695848e-05,
|
| 190 |
+
"loss": 0.0651,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 4.285714285714286,
|
| 195 |
+
"grad_norm": 0.42693275213241577,
|
| 196 |
+
"learning_rate": 1.0971009376368612e-05,
|
| 197 |
+
"loss": 0.0531,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 4.444444444444445,
|
| 202 |
+
"grad_norm": 0.4508126676082611,
|
| 203 |
+
"learning_rate": 6.6859568160797525e-06,
|
| 204 |
+
"loss": 0.0644,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 4.603174603174603,
|
| 209 |
+
"grad_norm": 0.4287712872028351,
|
| 210 |
+
"learning_rate": 3.4301161560792774e-06,
|
| 211 |
+
"loss": 0.0467,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.761904761904762,
|
| 216 |
+
"grad_norm": 0.39040446281433105,
|
| 217 |
+
"learning_rate": 1.239397853554336e-06,
|
| 218 |
+
"loss": 0.0587,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.920634920634921,
|
| 223 |
+
"grad_norm": 0.39611175656318665,
|
| 224 |
+
"learning_rate": 1.379645454479661e-07,
|
| 225 |
+
"loss": 0.056,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 5.0,
|
| 230 |
+
"step": 315,
|
| 231 |
+
"total_flos": 5801722395569280.0,
|
| 232 |
+
"train_loss": 0.16537500326595608,
|
| 233 |
+
"train_runtime": 123.2447,
|
| 234 |
+
"train_samples_per_second": 40.894,
|
| 235 |
+
"train_steps_per_second": 2.556
|
| 236 |
+
}
|
| 237 |
+
],
|
| 238 |
+
"logging_steps": 10,
|
| 239 |
+
"max_steps": 315,
|
| 240 |
+
"num_input_tokens_seen": 0,
|
| 241 |
+
"num_train_epochs": 5,
|
| 242 |
+
"save_steps": 500,
|
| 243 |
+
"stateful_callbacks": {
|
| 244 |
+
"TrainerControl": {
|
| 245 |
+
"args": {
|
| 246 |
+
"should_epoch_stop": false,
|
| 247 |
+
"should_evaluate": false,
|
| 248 |
+
"should_log": false,
|
| 249 |
+
"should_save": true,
|
| 250 |
+
"should_training_stop": true
|
| 251 |
+
},
|
| 252 |
+
"attributes": {}
|
| 253 |
+
}
|
| 254 |
+
},
|
| 255 |
+
"total_flos": 5801722395569280.0,
|
| 256 |
+
"train_batch_size": 16,
|
| 257 |
+
"trial_name": null,
|
| 258 |
+
"trial_params": null
|
| 259 |
+
}
|