Correctly upload
Browse files- adapter_model.bin +2 -2
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +259 -0
- training_args.bin +3 -0
adapter_model.bin
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:ff4a20cf8e48a4f35239f86504be1badcbbb838f6e08b267f096cc8aa948a1af
|
| 3 |
+
size 18898161
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa4e3dc87b0d15031e8e9c12e11aa82ac10a3fb9ef5bbd055bc4479647f88859
|
| 3 |
+
size 9530501
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d5c280437d3174a2eab070b5212281a5a2d99fc1deee390c4502efc782c370c
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d8a6dcb25d0de6c2845ff6853809ed78717b24f0ebcf428d186ba8370a93d15
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9979978438318189,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 405,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 9.523809523809524e-05,
|
| 14 |
+
"loss": 2.2532,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"learning_rate": 0.00019047619047619048,
|
| 20 |
+
"loss": 2.0208,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.07,
|
| 25 |
+
"learning_rate": 0.00019972904566786903,
|
| 26 |
+
"loss": 1.4376,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.1,
|
| 31 |
+
"learning_rate": 0.00019879429836063226,
|
| 32 |
+
"loss": 1.1412,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.12,
|
| 37 |
+
"learning_rate": 0.00019719866448212795,
|
| 38 |
+
"loss": 1.0641,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.15,
|
| 43 |
+
"learning_rate": 0.00019495281805930367,
|
| 44 |
+
"loss": 1.0379,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.17,
|
| 49 |
+
"learning_rate": 0.0001920717827298248,
|
| 50 |
+
"loss": 1.0215,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2,
|
| 55 |
+
"learning_rate": 0.00018857483124112907,
|
| 56 |
+
"loss": 1.0256,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.22,
|
| 61 |
+
"learning_rate": 0.00018448535652497073,
|
| 62 |
+
"loss": 1.016,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.25,
|
| 67 |
+
"learning_rate": 0.00017983071520990315,
|
| 68 |
+
"loss": 0.9956,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.27,
|
| 73 |
+
"learning_rate": 0.00017464204461852738,
|
| 74 |
+
"loss": 0.9963,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.3,
|
| 79 |
+
"learning_rate": 0.0001689540544737067,
|
| 80 |
+
"loss": 1.0188,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.32,
|
| 85 |
+
"learning_rate": 0.00016280479470713344,
|
| 86 |
+
"loss": 0.9989,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.34,
|
| 91 |
+
"learning_rate": 0.00015623540092349732,
|
| 92 |
+
"loss": 0.9916,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.37,
|
| 97 |
+
"learning_rate": 0.00014928981922297842,
|
| 98 |
+
"loss": 0.9849,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.39,
|
| 103 |
+
"learning_rate": 0.00014201451222287025,
|
| 104 |
+
"loss": 0.9778,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.42,
|
| 109 |
+
"learning_rate": 0.00013445814824490805,
|
| 110 |
+
"loss": 0.9728,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.44,
|
| 115 |
+
"learning_rate": 0.00012667127574748986,
|
| 116 |
+
"loss": 0.9669,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.47,
|
| 121 |
+
"learning_rate": 0.0001187059851806832,
|
| 122 |
+
"loss": 0.9786,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.49,
|
| 127 |
+
"learning_rate": 0.00011061556052604578,
|
| 128 |
+
"loss": 0.9766,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.52,
|
| 133 |
+
"learning_rate": 0.00010245412285229124,
|
| 134 |
+
"loss": 0.9884,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.54,
|
| 139 |
+
"learning_rate": 9.427626827124317e-05,
|
| 140 |
+
"loss": 0.9762,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.57,
|
| 145 |
+
"learning_rate": 8.613670271597733e-05,
|
| 146 |
+
"loss": 0.9811,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.59,
|
| 151 |
+
"learning_rate": 7.808987598431303e-05,
|
| 152 |
+
"loss": 0.9803,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.62,
|
| 157 |
+
"learning_rate": 7.018961749572604e-05,
|
| 158 |
+
"loss": 0.9752,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.64,
|
| 163 |
+
"learning_rate": 6.248877619829619e-05,
|
| 164 |
+
"loss": 0.9642,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.67,
|
| 169 |
+
"learning_rate": 5.503886703453933e-05,
|
| 170 |
+
"loss": 0.9635,
|
| 171 |
+
"step": 270
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.69,
|
| 175 |
+
"learning_rate": 4.7889726331097686e-05,
|
| 176 |
+
"loss": 0.9708,
|
| 177 |
+
"step": 280
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.71,
|
| 181 |
+
"learning_rate": 4.1089178417567164e-05,
|
| 182 |
+
"loss": 0.9692,
|
| 183 |
+
"step": 290
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.74,
|
| 187 |
+
"learning_rate": 3.468271570462235e-05,
|
| 188 |
+
"loss": 0.9752,
|
| 189 |
+
"step": 300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.76,
|
| 193 |
+
"learning_rate": 2.8713194361562036e-05,
|
| 194 |
+
"loss": 0.9734,
|
| 195 |
+
"step": 310
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.79,
|
| 199 |
+
"learning_rate": 2.3220547629048796e-05,
|
| 200 |
+
"loss": 0.9758,
|
| 201 |
+
"step": 320
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.81,
|
| 205 |
+
"learning_rate": 1.824151868484164e-05,
|
| 206 |
+
"loss": 0.9668,
|
| 207 |
+
"step": 330
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.84,
|
| 211 |
+
"learning_rate": 1.3809414849522584e-05,
|
| 212 |
+
"loss": 0.9736,
|
| 213 |
+
"step": 340
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.86,
|
| 217 |
+
"learning_rate": 9.953884776463652e-06,
|
| 218 |
+
"loss": 0.9818,
|
| 219 |
+
"step": 350
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.89,
|
| 223 |
+
"learning_rate": 6.700720116526116e-06,
|
| 224 |
+
"loss": 0.9776,
|
| 225 |
+
"step": 360
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.91,
|
| 229 |
+
"learning_rate": 4.071682984260638e-06,
|
| 230 |
+
"loss": 0.9626,
|
| 231 |
+
"step": 370
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.94,
|
| 235 |
+
"learning_rate": 2.0843603797766287e-06,
|
| 236 |
+
"loss": 0.9745,
|
| 237 |
+
"step": 380
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.96,
|
| 241 |
+
"learning_rate": 7.520465401290033e-07,
|
| 242 |
+
"loss": 0.9609,
|
| 243 |
+
"step": 390
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.99,
|
| 247 |
+
"learning_rate": 8.365400723512328e-08,
|
| 248 |
+
"loss": 0.9675,
|
| 249 |
+
"step": 400
|
| 250 |
+
}
|
| 251 |
+
],
|
| 252 |
+
"logging_steps": 10,
|
| 253 |
+
"max_steps": 405,
|
| 254 |
+
"num_train_epochs": 1,
|
| 255 |
+
"save_steps": 50,
|
| 256 |
+
"total_flos": 2.0624848885598822e+18,
|
| 257 |
+
"trial_name": null,
|
| 258 |
+
"trial_params": null
|
| 259 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63b371e07bba6300fcedd84cc9f5808549466467640f60b693f8d19d3526371e
|
| 3 |
+
size 4091
|