Training in progress, epoch 0
Browse files- adapter_config.json +6 -3
- adapter_model.safetensors +2 -2
- trainer_state.json +352 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -20,10 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"k_proj",
|
| 24 |
-
"q_proj",
|
| 25 |
"o_proj",
|
| 26 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM",
|
| 29 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
| 23 |
"o_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bb78a4c33aeba5726052842a165757cd2c01ed69664ea7c0095de5149123214
|
| 3 |
+
size 39256704
|
trainer_state.json
ADDED
|
@@ -0,0 +1,352 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.945945945945946,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 460,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.21621621621621623,
|
| 13 |
+
"grad_norm": 0.1806640625,
|
| 14 |
+
"learning_rate": 0.00019976687691905393,
|
| 15 |
+
"loss": 0.7107,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.43243243243243246,
|
| 20 |
+
"grad_norm": 0.235595703125,
|
| 21 |
+
"learning_rate": 0.00019906859460363307,
|
| 22 |
+
"loss": 0.6952,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6486486486486487,
|
| 27 |
+
"grad_norm": 0.423583984375,
|
| 28 |
+
"learning_rate": 0.00019790840876823232,
|
| 29 |
+
"loss": 0.6967,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.8648648648648649,
|
| 34 |
+
"grad_norm": 0.3974609375,
|
| 35 |
+
"learning_rate": 0.00019629172873477995,
|
| 36 |
+
"loss": 0.7649,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0810810810810811,
|
| 41 |
+
"grad_norm": 0.327880859375,
|
| 42 |
+
"learning_rate": 0.00019422609221188207,
|
| 43 |
+
"loss": 0.7627,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.2972972972972974,
|
| 48 |
+
"grad_norm": 0.31689453125,
|
| 49 |
+
"learning_rate": 0.00019172113015054532,
|
| 50 |
+
"loss": 0.7527,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.5135135135135136,
|
| 55 |
+
"grad_norm": 0.4111328125,
|
| 56 |
+
"learning_rate": 0.0001887885218402375,
|
| 57 |
+
"loss": 0.7536,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.7297297297297298,
|
| 62 |
+
"grad_norm": 1.376953125,
|
| 63 |
+
"learning_rate": 0.00018544194045464886,
|
| 64 |
+
"loss": 0.7241,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.945945945945946,
|
| 69 |
+
"grad_norm": 0.387939453125,
|
| 70 |
+
"learning_rate": 0.0001816969893010442,
|
| 71 |
+
"loss": 0.757,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.1621621621621623,
|
| 76 |
+
"grad_norm": 0.366455078125,
|
| 77 |
+
"learning_rate": 0.000177571129070442,
|
| 78 |
+
"loss": 0.7339,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.3783783783783785,
|
| 83 |
+
"grad_norm": 0.419677734375,
|
| 84 |
+
"learning_rate": 0.00017308359642781242,
|
| 85 |
+
"loss": 0.7005,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.5945945945945947,
|
| 90 |
+
"grad_norm": 0.38818359375,
|
| 91 |
+
"learning_rate": 0.00016825531432186543,
|
| 92 |
+
"loss": 0.7167,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.810810810810811,
|
| 97 |
+
"grad_norm": 0.452880859375,
|
| 98 |
+
"learning_rate": 0.00016310879443260528,
|
| 99 |
+
"loss": 0.7403,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 3.027027027027027,
|
| 104 |
+
"grad_norm": 0.412841796875,
|
| 105 |
+
"learning_rate": 0.00015766803221148673,
|
| 106 |
+
"loss": 0.7248,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.2432432432432434,
|
| 111 |
+
"grad_norm": 0.410400390625,
|
| 112 |
+
"learning_rate": 0.00015195839500354335,
|
| 113 |
+
"loss": 0.7208,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.4594594594594597,
|
| 118 |
+
"grad_norm": 0.484619140625,
|
| 119 |
+
"learning_rate": 0.00014600650377311522,
|
| 120 |
+
"loss": 0.7079,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 3.6756756756756754,
|
| 125 |
+
"grad_norm": 0.429443359375,
|
| 126 |
+
"learning_rate": 0.00013984010898462416,
|
| 127 |
+
"loss": 0.6847,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.891891891891892,
|
| 132 |
+
"grad_norm": 0.437744140625,
|
| 133 |
+
"learning_rate": 0.00013348796121709862,
|
| 134 |
+
"loss": 0.7104,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.108108108108108,
|
| 139 |
+
"grad_norm": 0.4140625,
|
| 140 |
+
"learning_rate": 0.00012697967711570242,
|
| 141 |
+
"loss": 0.682,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 4.324324324324325,
|
| 146 |
+
"grad_norm": 0.484130859375,
|
| 147 |
+
"learning_rate": 0.0001203456013052634,
|
| 148 |
+
"loss": 0.6754,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.54054054054054,
|
| 153 |
+
"grad_norm": 0.474853515625,
|
| 154 |
+
"learning_rate": 0.00011361666490962468,
|
| 155 |
+
"loss": 0.6671,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.756756756756757,
|
| 160 |
+
"grad_norm": 0.474365234375,
|
| 161 |
+
"learning_rate": 0.0001068242413364671,
|
| 162 |
+
"loss": 0.6956,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 4.972972972972973,
|
| 167 |
+
"grad_norm": 0.484130859375,
|
| 168 |
+
"learning_rate": 0.0001,
|
| 169 |
+
"loss": 0.6679,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.1891891891891895,
|
| 174 |
+
"grad_norm": 0.47265625,
|
| 175 |
+
"learning_rate": 9.317575866353292e-05,
|
| 176 |
+
"loss": 0.6496,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.405405405405405,
|
| 181 |
+
"grad_norm": 0.44482421875,
|
| 182 |
+
"learning_rate": 8.638333509037536e-05,
|
| 183 |
+
"loss": 0.6547,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 5.621621621621622,
|
| 188 |
+
"grad_norm": 0.488037109375,
|
| 189 |
+
"learning_rate": 7.965439869473664e-05,
|
| 190 |
+
"loss": 0.6739,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 5.837837837837838,
|
| 195 |
+
"grad_norm": 0.4658203125,
|
| 196 |
+
"learning_rate": 7.302032288429756e-05,
|
| 197 |
+
"loss": 0.6501,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 6.054054054054054,
|
| 202 |
+
"grad_norm": 0.48974609375,
|
| 203 |
+
"learning_rate": 6.651203878290139e-05,
|
| 204 |
+
"loss": 0.6773,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 6.27027027027027,
|
| 209 |
+
"grad_norm": 0.4775390625,
|
| 210 |
+
"learning_rate": 6.015989101537586e-05,
|
| 211 |
+
"loss": 0.6298,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.486486486486487,
|
| 216 |
+
"grad_norm": 0.521484375,
|
| 217 |
+
"learning_rate": 5.399349622688479e-05,
|
| 218 |
+
"loss": 0.6464,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 6.702702702702703,
|
| 223 |
+
"grad_norm": 0.5234375,
|
| 224 |
+
"learning_rate": 4.804160499645667e-05,
|
| 225 |
+
"loss": 0.6369,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 6.918918918918919,
|
| 230 |
+
"grad_norm": 0.59765625,
|
| 231 |
+
"learning_rate": 4.2331967788513295e-05,
|
| 232 |
+
"loss": 0.6734,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 7.135135135135135,
|
| 237 |
+
"grad_norm": 0.54736328125,
|
| 238 |
+
"learning_rate": 3.689120556739475e-05,
|
| 239 |
+
"loss": 0.6321,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 7.351351351351352,
|
| 244 |
+
"grad_norm": 0.57080078125,
|
| 245 |
+
"learning_rate": 3.174468567813461e-05,
|
| 246 |
+
"loss": 0.6261,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 7.5675675675675675,
|
| 251 |
+
"grad_norm": 0.47705078125,
|
| 252 |
+
"learning_rate": 2.691640357218759e-05,
|
| 253 |
+
"loss": 0.6196,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 7.783783783783784,
|
| 258 |
+
"grad_norm": 0.5712890625,
|
| 259 |
+
"learning_rate": 2.242887092955801e-05,
|
| 260 |
+
"loss": 0.6505,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.0,
|
| 265 |
+
"grad_norm": 0.50732421875,
|
| 266 |
+
"learning_rate": 1.8303010698955804e-05,
|
| 267 |
+
"loss": 0.6331,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 8.216216216216216,
|
| 272 |
+
"grad_norm": 0.48046875,
|
| 273 |
+
"learning_rate": 1.4558059545351143e-05,
|
| 274 |
+
"loss": 0.6366,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 8.432432432432432,
|
| 279 |
+
"grad_norm": 0.49951171875,
|
| 280 |
+
"learning_rate": 1.1211478159762478e-05,
|
| 281 |
+
"loss": 0.641,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 8.64864864864865,
|
| 286 |
+
"grad_norm": 0.5078125,
|
| 287 |
+
"learning_rate": 8.278869849454718e-06,
|
| 288 |
+
"loss": 0.6233,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 8.864864864864865,
|
| 293 |
+
"grad_norm": 0.50634765625,
|
| 294 |
+
"learning_rate": 5.77390778811796e-06,
|
| 295 |
+
"loss": 0.6185,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 9.08108108108108,
|
| 300 |
+
"grad_norm": 0.53125,
|
| 301 |
+
"learning_rate": 3.7082712652200867e-06,
|
| 302 |
+
"loss": 0.6224,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 9.297297297297296,
|
| 307 |
+
"grad_norm": 0.487548828125,
|
| 308 |
+
"learning_rate": 2.091591231767709e-06,
|
| 309 |
+
"loss": 0.6054,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 9.513513513513514,
|
| 314 |
+
"grad_norm": 0.5166015625,
|
| 315 |
+
"learning_rate": 9.314053963669245e-07,
|
| 316 |
+
"loss": 0.6299,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 9.72972972972973,
|
| 321 |
+
"grad_norm": 0.4990234375,
|
| 322 |
+
"learning_rate": 2.3312308094607382e-07,
|
| 323 |
+
"loss": 0.6193,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 9.945945945945946,
|
| 328 |
+
"grad_norm": 0.53271484375,
|
| 329 |
+
"learning_rate": 0.0,
|
| 330 |
+
"loss": 0.6231,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 9.945945945945946,
|
| 335 |
+
"step": 460,
|
| 336 |
+
"total_flos": 2.244679865204736e+16,
|
| 337 |
+
"train_loss": 0.6764944273492565,
|
| 338 |
+
"train_runtime": 411.2593,
|
| 339 |
+
"train_samples_per_second": 4.498,
|
| 340 |
+
"train_steps_per_second": 1.119
|
| 341 |
+
}
|
| 342 |
+
],
|
| 343 |
+
"logging_steps": 10,
|
| 344 |
+
"max_steps": 460,
|
| 345 |
+
"num_input_tokens_seen": 0,
|
| 346 |
+
"num_train_epochs": 10,
|
| 347 |
+
"save_steps": 500,
|
| 348 |
+
"total_flos": 2.244679865204736e+16,
|
| 349 |
+
"train_batch_size": 1,
|
| 350 |
+
"trial_name": null,
|
| 351 |
+
"trial_params": null
|
| 352 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60b2e50b0db935bb0604b66e2a7853b590ec15a47d606cca8dfedff57b9791c0
|
| 3 |
size 4984
|