Training in progress, epoch 0
Browse files- adapter_config.json +6 -3
- adapter_model.safetensors +2 -2
- trainer_state.json +373 -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 sha256:422da69ac8725b4452a0e841a6f80fe1605c538ddf269d78c049d5cca514f1b3
|
| 3 |
+
size 39256704
|
trainer_state.json
ADDED
|
@@ -0,0 +1,373 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.949238578680204,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 490,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.20304568527918782,
|
| 13 |
+
"grad_norm": 0.2015380859375,
|
| 14 |
+
"learning_rate": 0.00019979453927503364,
|
| 15 |
+
"loss": 0.7307,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.40609137055837563,
|
| 20 |
+
"grad_norm": 0.255615234375,
|
| 21 |
+
"learning_rate": 0.0001991790013823246,
|
| 22 |
+
"loss": 0.7211,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6091370558375635,
|
| 27 |
+
"grad_norm": 0.306640625,
|
| 28 |
+
"learning_rate": 0.00019815591569910654,
|
| 29 |
+
"loss": 0.7372,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.8121827411167513,
|
| 34 |
+
"grad_norm": 0.359130859375,
|
| 35 |
+
"learning_rate": 0.00019672948630390294,
|
| 36 |
+
"loss": 0.7826,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.015228426395939,
|
| 41 |
+
"grad_norm": 0.385986328125,
|
| 42 |
+
"learning_rate": 0.00019490557470106686,
|
| 43 |
+
"loss": 0.8238,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.218274111675127,
|
| 48 |
+
"grad_norm": 0.359130859375,
|
| 49 |
+
"learning_rate": 0.0001926916757346022,
|
| 50 |
+
"loss": 0.7958,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.4213197969543148,
|
| 55 |
+
"grad_norm": 0.34912109375,
|
| 56 |
+
"learning_rate": 0.0001900968867902419,
|
| 57 |
+
"loss": 0.7704,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.6243654822335025,
|
| 62 |
+
"grad_norm": 0.378662109375,
|
| 63 |
+
"learning_rate": 0.00018713187041233896,
|
| 64 |
+
"loss": 0.7576,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.8274111675126905,
|
| 69 |
+
"grad_norm": 0.38818359375,
|
| 70 |
+
"learning_rate": 0.00018380881048918405,
|
| 71 |
+
"loss": 0.7895,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.030456852791878,
|
| 76 |
+
"grad_norm": 0.3798828125,
|
| 77 |
+
"learning_rate": 0.00018014136218679567,
|
| 78 |
+
"loss": 0.7953,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.233502538071066,
|
| 83 |
+
"grad_norm": 0.40869140625,
|
| 84 |
+
"learning_rate": 0.00017614459583691346,
|
| 85 |
+
"loss": 0.7621,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.436548223350254,
|
| 90 |
+
"grad_norm": 0.409912109375,
|
| 91 |
+
"learning_rate": 0.00017183493500977278,
|
| 92 |
+
"loss": 0.7806,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.6395939086294415,
|
| 97 |
+
"grad_norm": 0.41162109375,
|
| 98 |
+
"learning_rate": 0.0001672300890261317,
|
| 99 |
+
"loss": 0.7414,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.8426395939086295,
|
| 104 |
+
"grad_norm": 0.4326171875,
|
| 105 |
+
"learning_rate": 0.00016234898018587337,
|
| 106 |
+
"loss": 0.7326,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.045685279187817,
|
| 111 |
+
"grad_norm": 0.468994140625,
|
| 112 |
+
"learning_rate": 0.00015721166601221698,
|
| 113 |
+
"loss": 0.7233,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.248730964467005,
|
| 118 |
+
"grad_norm": 0.443359375,
|
| 119 |
+
"learning_rate": 0.00015183925683105254,
|
| 120 |
+
"loss": 0.7304,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 3.451776649746193,
|
| 125 |
+
"grad_norm": 0.47705078125,
|
| 126 |
+
"learning_rate": 0.00014625382902408356,
|
| 127 |
+
"loss": 0.7311,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.6548223350253806,
|
| 132 |
+
"grad_norm": 0.44287109375,
|
| 133 |
+
"learning_rate": 0.00014047833431223938,
|
| 134 |
+
"loss": 0.7204,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.8578680203045685,
|
| 139 |
+
"grad_norm": 0.490478515625,
|
| 140 |
+
"learning_rate": 0.00013453650544213076,
|
| 141 |
+
"loss": 0.6965,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 4.060913705583756,
|
| 146 |
+
"grad_norm": 0.42578125,
|
| 147 |
+
"learning_rate": 0.00012845275866310324,
|
| 148 |
+
"loss": 0.7102,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.2639593908629445,
|
| 153 |
+
"grad_norm": 0.46240234375,
|
| 154 |
+
"learning_rate": 0.00012225209339563145,
|
| 155 |
+
"loss": 0.7164,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.467005076142132,
|
| 160 |
+
"grad_norm": 0.449951171875,
|
| 161 |
+
"learning_rate": 0.00011595998950333793,
|
| 162 |
+
"loss": 0.7068,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 4.67005076142132,
|
| 167 |
+
"grad_norm": 0.54296875,
|
| 168 |
+
"learning_rate": 0.00010960230259076818,
|
| 169 |
+
"loss": 0.7092,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.873096446700508,
|
| 174 |
+
"grad_norm": 0.5244140625,
|
| 175 |
+
"learning_rate": 0.00010320515775716555,
|
| 176 |
+
"loss": 0.6712,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.0761421319796955,
|
| 181 |
+
"grad_norm": 0.47705078125,
|
| 182 |
+
"learning_rate": 9.679484224283449e-05,
|
| 183 |
+
"loss": 0.6593,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 5.279187817258883,
|
| 188 |
+
"grad_norm": 0.50830078125,
|
| 189 |
+
"learning_rate": 9.039769740923183e-05,
|
| 190 |
+
"loss": 0.6991,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 5.482233502538071,
|
| 195 |
+
"grad_norm": 0.51318359375,
|
| 196 |
+
"learning_rate": 8.404001049666211e-05,
|
| 197 |
+
"loss": 0.6612,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 5.685279187817259,
|
| 202 |
+
"grad_norm": 0.50341796875,
|
| 203 |
+
"learning_rate": 7.774790660436858e-05,
|
| 204 |
+
"loss": 0.6829,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 5.888324873096447,
|
| 209 |
+
"grad_norm": 0.513671875,
|
| 210 |
+
"learning_rate": 7.154724133689677e-05,
|
| 211 |
+
"loss": 0.6576,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.091370558375634,
|
| 216 |
+
"grad_norm": 0.471435546875,
|
| 217 |
+
"learning_rate": 6.546349455786926e-05,
|
| 218 |
+
"loss": 0.6669,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 6.2944162436548226,
|
| 223 |
+
"grad_norm": 0.55224609375,
|
| 224 |
+
"learning_rate": 5.952166568776062e-05,
|
| 225 |
+
"loss": 0.6569,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 6.49746192893401,
|
| 230 |
+
"grad_norm": 0.5986328125,
|
| 231 |
+
"learning_rate": 5.37461709759165e-05,
|
| 232 |
+
"loss": 0.6517,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 6.700507614213198,
|
| 237 |
+
"grad_norm": 0.5849609375,
|
| 238 |
+
"learning_rate": 4.8160743168947496e-05,
|
| 239 |
+
"loss": 0.6627,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 6.903553299492386,
|
| 244 |
+
"grad_norm": 0.54345703125,
|
| 245 |
+
"learning_rate": 4.278833398778306e-05,
|
| 246 |
+
"loss": 0.6526,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 7.106598984771574,
|
| 251 |
+
"grad_norm": 0.53125,
|
| 252 |
+
"learning_rate": 3.7651019814126654e-05,
|
| 253 |
+
"loss": 0.652,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 7.309644670050761,
|
| 258 |
+
"grad_norm": 0.51611328125,
|
| 259 |
+
"learning_rate": 3.276991097386831e-05,
|
| 260 |
+
"loss": 0.6237,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 7.5126903553299496,
|
| 265 |
+
"grad_norm": 0.5654296875,
|
| 266 |
+
"learning_rate": 2.8165064990227252e-05,
|
| 267 |
+
"loss": 0.6313,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 7.715736040609137,
|
| 272 |
+
"grad_norm": 0.5810546875,
|
| 273 |
+
"learning_rate": 2.3855404163086558e-05,
|
| 274 |
+
"loss": 0.6452,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 7.918781725888325,
|
| 279 |
+
"grad_norm": 0.59423828125,
|
| 280 |
+
"learning_rate": 1.985863781320435e-05,
|
| 281 |
+
"loss": 0.6412,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 8.121827411167512,
|
| 286 |
+
"grad_norm": 0.55712890625,
|
| 287 |
+
"learning_rate": 1.619118951081594e-05,
|
| 288 |
+
"loss": 0.6532,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 8.3248730964467,
|
| 293 |
+
"grad_norm": 0.60595703125,
|
| 294 |
+
"learning_rate": 1.286812958766106e-05,
|
| 295 |
+
"loss": 0.6271,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 8.527918781725889,
|
| 300 |
+
"grad_norm": 0.580078125,
|
| 301 |
+
"learning_rate": 9.903113209758096e-06,
|
| 302 |
+
"loss": 0.6202,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 8.730964467005077,
|
| 307 |
+
"grad_norm": 0.54833984375,
|
| 308 |
+
"learning_rate": 7.308324265397836e-06,
|
| 309 |
+
"loss": 0.6382,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 8.934010152284264,
|
| 314 |
+
"grad_norm": 0.53759765625,
|
| 315 |
+
"learning_rate": 5.094425298933136e-06,
|
| 316 |
+
"loss": 0.6374,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 9.137055837563452,
|
| 321 |
+
"grad_norm": 0.591796875,
|
| 322 |
+
"learning_rate": 3.270513696097055e-06,
|
| 323 |
+
"loss": 0.6319,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 9.34010152284264,
|
| 328 |
+
"grad_norm": 0.54638671875,
|
| 329 |
+
"learning_rate": 1.8440843008934561e-06,
|
| 330 |
+
"loss": 0.6336,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 9.543147208121827,
|
| 335 |
+
"grad_norm": 0.56494140625,
|
| 336 |
+
"learning_rate": 8.209986176753948e-07,
|
| 337 |
+
"loss": 0.6319,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 9.746192893401016,
|
| 342 |
+
"grad_norm": 0.55029296875,
|
| 343 |
+
"learning_rate": 2.054607249663665e-07,
|
| 344 |
+
"loss": 0.6295,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 9.949238578680204,
|
| 349 |
+
"grad_norm": 0.5234375,
|
| 350 |
+
"learning_rate": 0.0,
|
| 351 |
+
"loss": 0.6314,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 9.949238578680204,
|
| 356 |
+
"step": 490,
|
| 357 |
+
"total_flos": 2.391072030326784e+16,
|
| 358 |
+
"train_loss": 0.6941771516994554,
|
| 359 |
+
"train_runtime": 436.887,
|
| 360 |
+
"train_samples_per_second": 4.509,
|
| 361 |
+
"train_steps_per_second": 1.122
|
| 362 |
+
}
|
| 363 |
+
],
|
| 364 |
+
"logging_steps": 10,
|
| 365 |
+
"max_steps": 490,
|
| 366 |
+
"num_input_tokens_seen": 0,
|
| 367 |
+
"num_train_epochs": 10,
|
| 368 |
+
"save_steps": 500,
|
| 369 |
+
"total_flos": 2.391072030326784e+16,
|
| 370 |
+
"train_batch_size": 1,
|
| 371 |
+
"trial_name": null,
|
| 372 |
+
"trial_params": null
|
| 373 |
+
}
|
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 sha256:9676af07377700635b8594d97cc1183bc996d8c9418d3671d744dcd922b07c4a
|
| 3 |
size 4984
|