Training in progress, epoch 1
Browse files- adapter_config.json +6 -3
- adapter_model.safetensors +2 -2
- trainer_state.json +317 -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 sha256:6b4e76984a3e1a558b51b12e9f33b601eed99f29ddeb03c9f0861577550188a9
|
| 3 |
+
size 39256704
|
trainer_state.json
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 410,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.24390243902439024,
|
| 13 |
+
"grad_norm": 7.625,
|
| 14 |
+
"learning_rate": 0.00019970658011837404,
|
| 15 |
+
"loss": 2.0086,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.4878048780487805,
|
| 20 |
+
"grad_norm": 0.59033203125,
|
| 21 |
+
"learning_rate": 0.00019882804237803488,
|
| 22 |
+
"loss": 1.1443,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.7317073170731707,
|
| 27 |
+
"grad_norm": 0.736328125,
|
| 28 |
+
"learning_rate": 0.00019736954238777792,
|
| 29 |
+
"loss": 0.985,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.975609756097561,
|
| 34 |
+
"grad_norm": 0.50048828125,
|
| 35 |
+
"learning_rate": 0.00019533963920549306,
|
| 36 |
+
"loss": 0.918,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.2195121951219512,
|
| 41 |
+
"grad_norm": 0.36083984375,
|
| 42 |
+
"learning_rate": 0.0001927502451102095,
|
| 43 |
+
"loss": 0.7771,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.4634146341463414,
|
| 48 |
+
"grad_norm": 0.376953125,
|
| 49 |
+
"learning_rate": 0.00018961655569610557,
|
| 50 |
+
"loss": 0.8079,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.7073170731707317,
|
| 55 |
+
"grad_norm": 0.314208984375,
|
| 56 |
+
"learning_rate": 0.00018595696069872013,
|
| 57 |
+
"loss": 0.7491,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.951219512195122,
|
| 62 |
+
"grad_norm": 0.3203125,
|
| 63 |
+
"learning_rate": 0.00018179293607667178,
|
| 64 |
+
"loss": 0.7349,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.1951219512195124,
|
| 69 |
+
"grad_norm": 0.331787109375,
|
| 70 |
+
"learning_rate": 0.0001771489179821943,
|
| 71 |
+
"loss": 0.7468,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.4390243902439024,
|
| 76 |
+
"grad_norm": 0.374755859375,
|
| 77 |
+
"learning_rate": 0.0001720521593600787,
|
| 78 |
+
"loss": 0.7582,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.682926829268293,
|
| 83 |
+
"grad_norm": 0.3662109375,
|
| 84 |
+
"learning_rate": 0.00016653257001655652,
|
| 85 |
+
"loss": 0.715,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.926829268292683,
|
| 90 |
+
"grad_norm": 0.413818359375,
|
| 91 |
+
"learning_rate": 0.0001606225410966638,
|
| 92 |
+
"loss": 0.7404,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.1707317073170733,
|
| 97 |
+
"grad_norm": 0.349609375,
|
| 98 |
+
"learning_rate": 0.00015435675500012212,
|
| 99 |
+
"loss": 0.6844,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 3.4146341463414633,
|
| 104 |
+
"grad_norm": 0.48095703125,
|
| 105 |
+
"learning_rate": 0.0001477719818512263,
|
| 106 |
+
"loss": 0.7568,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.658536585365854,
|
| 111 |
+
"grad_norm": 0.369384765625,
|
| 112 |
+
"learning_rate": 0.00014090686371713402,
|
| 113 |
+
"loss": 0.6647,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.902439024390244,
|
| 118 |
+
"grad_norm": 0.422607421875,
|
| 119 |
+
"learning_rate": 0.00013380168784085027,
|
| 120 |
+
"loss": 0.698,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.146341463414634,
|
| 125 |
+
"grad_norm": 0.38427734375,
|
| 126 |
+
"learning_rate": 0.0001264981502196662,
|
| 127 |
+
"loss": 0.6861,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.390243902439025,
|
| 132 |
+
"grad_norm": 0.38525390625,
|
| 133 |
+
"learning_rate": 0.00011903911091646684,
|
| 134 |
+
"loss": 0.6855,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.634146341463414,
|
| 139 |
+
"grad_norm": 0.384033203125,
|
| 140 |
+
"learning_rate": 0.00011146834253984006,
|
| 141 |
+
"loss": 0.6797,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 4.878048780487805,
|
| 146 |
+
"grad_norm": 0.365966796875,
|
| 147 |
+
"learning_rate": 0.00010383027336900355,
|
| 148 |
+
"loss": 0.6865,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.121951219512195,
|
| 153 |
+
"grad_norm": 0.39794921875,
|
| 154 |
+
"learning_rate": 9.616972663099647e-05,
|
| 155 |
+
"loss": 0.6859,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 5.365853658536586,
|
| 160 |
+
"grad_norm": 0.3837890625,
|
| 161 |
+
"learning_rate": 8.853165746015997e-05,
|
| 162 |
+
"loss": 0.6636,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 5.609756097560975,
|
| 167 |
+
"grad_norm": 0.445068359375,
|
| 168 |
+
"learning_rate": 8.096088908353315e-05,
|
| 169 |
+
"loss": 0.6883,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.853658536585366,
|
| 174 |
+
"grad_norm": 0.4130859375,
|
| 175 |
+
"learning_rate": 7.350184978033386e-05,
|
| 176 |
+
"loss": 0.6432,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 6.097560975609756,
|
| 181 |
+
"grad_norm": 0.380859375,
|
| 182 |
+
"learning_rate": 6.619831215914974e-05,
|
| 183 |
+
"loss": 0.6597,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 6.341463414634147,
|
| 188 |
+
"grad_norm": 0.407958984375,
|
| 189 |
+
"learning_rate": 5.909313628286601e-05,
|
| 190 |
+
"loss": 0.6574,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 6.585365853658536,
|
| 195 |
+
"grad_norm": 0.3974609375,
|
| 196 |
+
"learning_rate": 5.222801814877369e-05,
|
| 197 |
+
"loss": 0.6499,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 6.829268292682927,
|
| 202 |
+
"grad_norm": 0.40625,
|
| 203 |
+
"learning_rate": 4.56432449998779e-05,
|
| 204 |
+
"loss": 0.6436,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 7.073170731707317,
|
| 209 |
+
"grad_norm": 0.3994140625,
|
| 210 |
+
"learning_rate": 3.937745890333623e-05,
|
| 211 |
+
"loss": 0.6644,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.317073170731708,
|
| 216 |
+
"grad_norm": 0.40673828125,
|
| 217 |
+
"learning_rate": 3.346742998344348e-05,
|
| 218 |
+
"loss": 0.656,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.560975609756097,
|
| 223 |
+
"grad_norm": 0.408447265625,
|
| 224 |
+
"learning_rate": 2.794784063992131e-05,
|
| 225 |
+
"loss": 0.6244,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.804878048780488,
|
| 230 |
+
"grad_norm": 0.41015625,
|
| 231 |
+
"learning_rate": 2.2851082017805703e-05,
|
| 232 |
+
"loss": 0.6594,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.048780487804878,
|
| 237 |
+
"grad_norm": 0.437744140625,
|
| 238 |
+
"learning_rate": 1.8207063923328237e-05,
|
| 239 |
+
"loss": 0.6423,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 8.292682926829269,
|
| 244 |
+
"grad_norm": 0.43212890625,
|
| 245 |
+
"learning_rate": 1.4043039301279903e-05,
|
| 246 |
+
"loss": 0.635,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 8.536585365853659,
|
| 251 |
+
"grad_norm": 0.4013671875,
|
| 252 |
+
"learning_rate": 1.0383444303894452e-05,
|
| 253 |
+
"loss": 0.6408,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.78048780487805,
|
| 258 |
+
"grad_norm": 0.40869140625,
|
| 259 |
+
"learning_rate": 7.249754889790539e-06,
|
| 260 |
+
"loss": 0.6438,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 9.024390243902438,
|
| 265 |
+
"grad_norm": 0.3857421875,
|
| 266 |
+
"learning_rate": 4.660360794506946e-06,
|
| 267 |
+
"loss": 0.6282,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 9.268292682926829,
|
| 272 |
+
"grad_norm": 0.400634765625,
|
| 273 |
+
"learning_rate": 2.6304576122221035e-06,
|
| 274 |
+
"loss": 0.6359,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 9.512195121951219,
|
| 279 |
+
"grad_norm": 0.3935546875,
|
| 280 |
+
"learning_rate": 1.1719576219651585e-06,
|
| 281 |
+
"loss": 0.6467,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 9.75609756097561,
|
| 286 |
+
"grad_norm": 0.4140625,
|
| 287 |
+
"learning_rate": 2.934198816259559e-07,
|
| 288 |
+
"loss": 0.6479,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 10.0,
|
| 293 |
+
"grad_norm": 0.400390625,
|
| 294 |
+
"learning_rate": 0.0,
|
| 295 |
+
"loss": 0.6203,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 10.0,
|
| 300 |
+
"step": 410,
|
| 301 |
+
"total_flos": 2.000692923334656e+16,
|
| 302 |
+
"train_loss": 0.7381390141277778,
|
| 303 |
+
"train_runtime": 366.1191,
|
| 304 |
+
"train_samples_per_second": 4.479,
|
| 305 |
+
"train_steps_per_second": 1.12
|
| 306 |
+
}
|
| 307 |
+
],
|
| 308 |
+
"logging_steps": 10,
|
| 309 |
+
"max_steps": 410,
|
| 310 |
+
"num_input_tokens_seen": 0,
|
| 311 |
+
"num_train_epochs": 10,
|
| 312 |
+
"save_steps": 500,
|
| 313 |
+
"total_flos": 2.000692923334656e+16,
|
| 314 |
+
"train_batch_size": 1,
|
| 315 |
+
"trial_name": null,
|
| 316 |
+
"trial_params": null
|
| 317 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4efee21f229df2d1d33be74e3b8c2ff4958f5d456ec8d17ee1d29d524be5c3ee
|
| 3 |
size 5048
|