Training in progress, epoch 0
Browse files- adapter_config.json +4 -2
- adapter_model.safetensors +2 -2
- trainer_state.json +317 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -20,10 +20,12 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"k_proj",
|
| 24 |
"v_proj",
|
|
|
|
| 25 |
"q_proj",
|
| 26 |
-
"
|
|
|
|
|
|
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM",
|
| 29 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
| 23 |
"v_proj",
|
| 24 |
+
"fc1",
|
| 25 |
"q_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"fc2",
|
| 28 |
+
"dense"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM",
|
| 31 |
"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 sha256:261e0270c9dbf399b11e2fb87774b201c48297b789370c78af65f541e42ee3a4
|
| 3 |
+
size 47236352
|
trainer_state.json
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.820359281437126,
|
| 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": 0.23952095808383234,
|
| 13 |
+
"grad_norm": 2.16796875,
|
| 14 |
+
"learning_rate": 0.00019970658011837404,
|
| 15 |
+
"loss": 0.5442,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.47904191616766467,
|
| 20 |
+
"grad_norm": 2.02734375,
|
| 21 |
+
"learning_rate": 0.00019882804237803488,
|
| 22 |
+
"loss": 0.5445,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.718562874251497,
|
| 27 |
+
"grad_norm": 1.2587890625,
|
| 28 |
+
"learning_rate": 0.00019736954238777792,
|
| 29 |
+
"loss": 0.5499,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.9580838323353293,
|
| 34 |
+
"grad_norm": 1.3486328125,
|
| 35 |
+
"learning_rate": 0.00019533963920549306,
|
| 36 |
+
"loss": 0.5429,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.1976047904191618,
|
| 41 |
+
"grad_norm": 2.08984375,
|
| 42 |
+
"learning_rate": 0.0001927502451102095,
|
| 43 |
+
"loss": 0.5336,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.437125748502994,
|
| 48 |
+
"grad_norm": 1.7734375,
|
| 49 |
+
"learning_rate": 0.00018961655569610557,
|
| 50 |
+
"loss": 0.5333,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.6766467065868262,
|
| 55 |
+
"grad_norm": 2.63671875,
|
| 56 |
+
"learning_rate": 0.00018595696069872013,
|
| 57 |
+
"loss": 0.5401,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.9161676646706587,
|
| 62 |
+
"grad_norm": 2.19921875,
|
| 63 |
+
"learning_rate": 0.00018179293607667178,
|
| 64 |
+
"loss": 0.5414,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.155688622754491,
|
| 69 |
+
"grad_norm": 1.908203125,
|
| 70 |
+
"learning_rate": 0.0001771489179821943,
|
| 71 |
+
"loss": 0.5713,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.3952095808383236,
|
| 76 |
+
"grad_norm": 4.09765625,
|
| 77 |
+
"learning_rate": 0.0001720521593600787,
|
| 78 |
+
"loss": 0.538,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.6347305389221556,
|
| 83 |
+
"grad_norm": 2.0390625,
|
| 84 |
+
"learning_rate": 0.00016653257001655652,
|
| 85 |
+
"loss": 0.5199,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.874251497005988,
|
| 90 |
+
"grad_norm": 1.8154296875,
|
| 91 |
+
"learning_rate": 0.0001606225410966638,
|
| 92 |
+
"loss": 0.5204,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.1137724550898205,
|
| 97 |
+
"grad_norm": 1.9189453125,
|
| 98 |
+
"learning_rate": 0.00015435675500012212,
|
| 99 |
+
"loss": 0.5396,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 3.3532934131736525,
|
| 104 |
+
"grad_norm": 1.8896484375,
|
| 105 |
+
"learning_rate": 0.0001477719818512263,
|
| 106 |
+
"loss": 0.5294,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.592814371257485,
|
| 111 |
+
"grad_norm": 2.302734375,
|
| 112 |
+
"learning_rate": 0.00014090686371713402,
|
| 113 |
+
"loss": 0.5394,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.8323353293413174,
|
| 118 |
+
"grad_norm": 2.16796875,
|
| 119 |
+
"learning_rate": 0.00013380168784085027,
|
| 120 |
+
"loss": 0.5279,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.07185628742515,
|
| 125 |
+
"grad_norm": 2.11328125,
|
| 126 |
+
"learning_rate": 0.0001264981502196662,
|
| 127 |
+
"loss": 0.5182,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.311377245508982,
|
| 132 |
+
"grad_norm": 1.9189453125,
|
| 133 |
+
"learning_rate": 0.00011903911091646684,
|
| 134 |
+
"loss": 0.5304,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.550898203592815,
|
| 139 |
+
"grad_norm": 2.48046875,
|
| 140 |
+
"learning_rate": 0.00011146834253984006,
|
| 141 |
+
"loss": 0.5386,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 4.790419161676647,
|
| 146 |
+
"grad_norm": 2.62890625,
|
| 147 |
+
"learning_rate": 0.00010383027336900355,
|
| 148 |
+
"loss": 0.5276,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.029940119760479,
|
| 153 |
+
"grad_norm": 3.021484375,
|
| 154 |
+
"learning_rate": 9.616972663099647e-05,
|
| 155 |
+
"loss": 0.5229,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 5.269461077844311,
|
| 160 |
+
"grad_norm": 3.259765625,
|
| 161 |
+
"learning_rate": 8.853165746015997e-05,
|
| 162 |
+
"loss": 0.5243,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 5.508982035928144,
|
| 167 |
+
"grad_norm": 2.876953125,
|
| 168 |
+
"learning_rate": 8.096088908353315e-05,
|
| 169 |
+
"loss": 0.5206,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.748502994011976,
|
| 174 |
+
"grad_norm": 3.349609375,
|
| 175 |
+
"learning_rate": 7.350184978033386e-05,
|
| 176 |
+
"loss": 0.5374,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.9880239520958085,
|
| 181 |
+
"grad_norm": 3.791015625,
|
| 182 |
+
"learning_rate": 6.619831215914974e-05,
|
| 183 |
+
"loss": 0.5258,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 6.227544910179641,
|
| 188 |
+
"grad_norm": 3.240234375,
|
| 189 |
+
"learning_rate": 5.909313628286601e-05,
|
| 190 |
+
"loss": 0.5166,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 6.467065868263473,
|
| 195 |
+
"grad_norm": 3.248046875,
|
| 196 |
+
"learning_rate": 5.222801814877369e-05,
|
| 197 |
+
"loss": 0.5329,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 6.706586826347305,
|
| 202 |
+
"grad_norm": 2.83984375,
|
| 203 |
+
"learning_rate": 4.56432449998779e-05,
|
| 204 |
+
"loss": 0.5117,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 6.946107784431137,
|
| 209 |
+
"grad_norm": 4.03515625,
|
| 210 |
+
"learning_rate": 3.937745890333623e-05,
|
| 211 |
+
"loss": 0.5269,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.18562874251497,
|
| 216 |
+
"grad_norm": 4.08203125,
|
| 217 |
+
"learning_rate": 3.346742998344348e-05,
|
| 218 |
+
"loss": 0.5299,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.425149700598802,
|
| 223 |
+
"grad_norm": 3.03125,
|
| 224 |
+
"learning_rate": 2.794784063992131e-05,
|
| 225 |
+
"loss": 0.5217,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.664670658682635,
|
| 230 |
+
"grad_norm": 3.00390625,
|
| 231 |
+
"learning_rate": 2.2851082017805703e-05,
|
| 232 |
+
"loss": 0.5241,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 7.904191616766467,
|
| 237 |
+
"grad_norm": 3.27734375,
|
| 238 |
+
"learning_rate": 1.8207063923328237e-05,
|
| 239 |
+
"loss": 0.5066,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 8.1437125748503,
|
| 244 |
+
"grad_norm": 2.927734375,
|
| 245 |
+
"learning_rate": 1.4043039301279903e-05,
|
| 246 |
+
"loss": 0.5111,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 8.383233532934131,
|
| 251 |
+
"grad_norm": 3.3984375,
|
| 252 |
+
"learning_rate": 1.0383444303894452e-05,
|
| 253 |
+
"loss": 0.5137,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.622754491017965,
|
| 258 |
+
"grad_norm": 3.4375,
|
| 259 |
+
"learning_rate": 7.249754889790539e-06,
|
| 260 |
+
"loss": 0.5279,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.862275449101796,
|
| 265 |
+
"grad_norm": 3.19140625,
|
| 266 |
+
"learning_rate": 4.660360794506946e-06,
|
| 267 |
+
"loss": 0.5125,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 9.10179640718563,
|
| 272 |
+
"grad_norm": 4.23046875,
|
| 273 |
+
"learning_rate": 2.6304576122221035e-06,
|
| 274 |
+
"loss": 0.5141,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 9.341317365269461,
|
| 279 |
+
"grad_norm": 2.779296875,
|
| 280 |
+
"learning_rate": 1.1719576219651585e-06,
|
| 281 |
+
"loss": 0.5172,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 9.580838323353294,
|
| 286 |
+
"grad_norm": 3.619140625,
|
| 287 |
+
"learning_rate": 2.934198816259559e-07,
|
| 288 |
+
"loss": 0.5389,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 9.820359281437126,
|
| 293 |
+
"grad_norm": 4.30078125,
|
| 294 |
+
"learning_rate": 0.0,
|
| 295 |
+
"loss": 0.5024,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 9.820359281437126,
|
| 300 |
+
"step": 410,
|
| 301 |
+
"total_flos": 2.67670788243456e+16,
|
| 302 |
+
"train_loss": 0.5285330202521348,
|
| 303 |
+
"train_runtime": 355.5253,
|
| 304 |
+
"train_samples_per_second": 4.697,
|
| 305 |
+
"train_steps_per_second": 1.153
|
| 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": 2.67670788243456e+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 4984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c06099d4eb235513a1439a552237439d2e6e7a121a8c6162b02c3f4b29f578e8
|
| 3 |
size 4984
|