Training in progress, epoch 0
Browse files- adapter_model.safetensors +1 -1
- trainer_state.json +429 -0
- training_args.bin +1 -1
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9034480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8abe3837e75f4c4bb6a56ae60b667ec33ab7d1e6ae87c70b54862aa786b20c0
|
| 3 |
size 9034480
|
trainer_state.json
ADDED
|
@@ -0,0 +1,429 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.87012987012987,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 570,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.17316017316017315,
|
| 13 |
+
"grad_norm": 0.73779296875,
|
| 14 |
+
"learning_rate": 0.00019984815164333163,
|
| 15 |
+
"loss": 1.5442,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.3463203463203463,
|
| 20 |
+
"grad_norm": 0.67529296875,
|
| 21 |
+
"learning_rate": 0.00019939306773179497,
|
| 22 |
+
"loss": 1.4059,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.5194805194805194,
|
| 27 |
+
"grad_norm": 0.67724609375,
|
| 28 |
+
"learning_rate": 0.00019863613034027224,
|
| 29 |
+
"loss": 1.3684,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.6926406926406926,
|
| 34 |
+
"grad_norm": 0.62744140625,
|
| 35 |
+
"learning_rate": 0.00019757963826274357,
|
| 36 |
+
"loss": 1.3543,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.8658008658008658,
|
| 41 |
+
"grad_norm": 0.5947265625,
|
| 42 |
+
"learning_rate": 0.00019622680003092503,
|
| 43 |
+
"loss": 1.3547,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0389610389610389,
|
| 48 |
+
"grad_norm": 0.5986328125,
|
| 49 |
+
"learning_rate": 0.00019458172417006347,
|
| 50 |
+
"loss": 1.3248,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.2121212121212122,
|
| 55 |
+
"grad_norm": 0.638671875,
|
| 56 |
+
"learning_rate": 0.00019264940672148018,
|
| 57 |
+
"loss": 1.2603,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.3852813852813852,
|
| 62 |
+
"grad_norm": 0.78857421875,
|
| 63 |
+
"learning_rate": 0.00019043571606975777,
|
| 64 |
+
"loss": 1.2683,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.5584415584415585,
|
| 69 |
+
"grad_norm": 0.7412109375,
|
| 70 |
+
"learning_rate": 0.0001879473751206489,
|
| 71 |
+
"loss": 1.2356,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.7316017316017316,
|
| 76 |
+
"grad_norm": 0.70458984375,
|
| 77 |
+
"learning_rate": 0.00018519194088383273,
|
| 78 |
+
"loss": 1.2849,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.9047619047619047,
|
| 83 |
+
"grad_norm": 0.748046875,
|
| 84 |
+
"learning_rate": 0.0001821777815225245,
|
| 85 |
+
"loss": 1.2618,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.0779220779220777,
|
| 90 |
+
"grad_norm": 0.68359375,
|
| 91 |
+
"learning_rate": 0.00017891405093963938,
|
| 92 |
+
"loss": 1.1707,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.2510822510822512,
|
| 97 |
+
"grad_norm": 0.83740234375,
|
| 98 |
+
"learning_rate": 0.00017541066097768963,
|
| 99 |
+
"loss": 1.1533,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.4242424242424243,
|
| 104 |
+
"grad_norm": 0.81005859375,
|
| 105 |
+
"learning_rate": 0.00017167825131684513,
|
| 106 |
+
"loss": 1.1604,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.5974025974025974,
|
| 111 |
+
"grad_norm": 0.99462890625,
|
| 112 |
+
"learning_rate": 0.00016772815716257412,
|
| 113 |
+
"loss": 1.1347,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.7705627705627704,
|
| 118 |
+
"grad_norm": 0.9736328125,
|
| 119 |
+
"learning_rate": 0.00016357237482099684,
|
| 120 |
+
"loss": 1.1071,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.9437229437229435,
|
| 125 |
+
"grad_norm": 0.89111328125,
|
| 126 |
+
"learning_rate": 0.00015922352526649803,
|
| 127 |
+
"loss": 1.1747,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.116883116883117,
|
| 132 |
+
"grad_norm": 1.0849609375,
|
| 133 |
+
"learning_rate": 0.00015469481581224272,
|
| 134 |
+
"loss": 1.0882,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.29004329004329,
|
| 139 |
+
"grad_norm": 1.0166015625,
|
| 140 |
+
"learning_rate": 0.00015000000000000001,
|
| 141 |
+
"loss": 1.0027,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 3.463203463203463,
|
| 146 |
+
"grad_norm": 1.0068359375,
|
| 147 |
+
"learning_rate": 0.00014515333583108896,
|
| 148 |
+
"loss": 1.059,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 3.6363636363636362,
|
| 153 |
+
"grad_norm": 0.9970703125,
|
| 154 |
+
"learning_rate": 0.00014016954246529696,
|
| 155 |
+
"loss": 1.0374,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.8095238095238093,
|
| 160 |
+
"grad_norm": 1.0283203125,
|
| 161 |
+
"learning_rate": 0.00013506375551927547,
|
| 162 |
+
"loss": 0.9911,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 3.982683982683983,
|
| 167 |
+
"grad_norm": 1.0732421875,
|
| 168 |
+
"learning_rate": 0.00012985148110016947,
|
| 169 |
+
"loss": 1.089,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.1558441558441555,
|
| 174 |
+
"grad_norm": 2.0078125,
|
| 175 |
+
"learning_rate": 0.00012454854871407994,
|
| 176 |
+
"loss": 0.9512,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.329004329004329,
|
| 181 |
+
"grad_norm": 1.2607421875,
|
| 182 |
+
"learning_rate": 0.00011917106319237386,
|
| 183 |
+
"loss": 0.9437,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 4.5021645021645025,
|
| 188 |
+
"grad_norm": 1.21875,
|
| 189 |
+
"learning_rate": 0.00011373535578184082,
|
| 190 |
+
"loss": 0.9019,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 4.675324675324675,
|
| 195 |
+
"grad_norm": 1.3486328125,
|
| 196 |
+
"learning_rate": 0.00010825793454723325,
|
| 197 |
+
"loss": 0.9206,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 4.848484848484849,
|
| 202 |
+
"grad_norm": 1.1474609375,
|
| 203 |
+
"learning_rate": 0.00010275543423681621,
|
| 204 |
+
"loss": 0.9218,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 5.021645021645021,
|
| 209 |
+
"grad_norm": 1.119140625,
|
| 210 |
+
"learning_rate": 9.724456576318381e-05,
|
| 211 |
+
"loss": 0.8835,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 5.194805194805195,
|
| 216 |
+
"grad_norm": 1.25390625,
|
| 217 |
+
"learning_rate": 9.174206545276677e-05,
|
| 218 |
+
"loss": 0.8657,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.367965367965368,
|
| 223 |
+
"grad_norm": 1.2841796875,
|
| 224 |
+
"learning_rate": 8.626464421815919e-05,
|
| 225 |
+
"loss": 0.8135,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 5.541125541125541,
|
| 230 |
+
"grad_norm": 1.302734375,
|
| 231 |
+
"learning_rate": 8.082893680762619e-05,
|
| 232 |
+
"loss": 0.828,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 5.714285714285714,
|
| 237 |
+
"grad_norm": 1.255859375,
|
| 238 |
+
"learning_rate": 7.54514512859201e-05,
|
| 239 |
+
"loss": 0.8363,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.887445887445887,
|
| 244 |
+
"grad_norm": 1.2783203125,
|
| 245 |
+
"learning_rate": 7.014851889983057e-05,
|
| 246 |
+
"loss": 0.8205,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 6.0606060606060606,
|
| 251 |
+
"grad_norm": 1.15234375,
|
| 252 |
+
"learning_rate": 6.493624448072457e-05,
|
| 253 |
+
"loss": 0.8129,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 6.233766233766234,
|
| 258 |
+
"grad_norm": 1.314453125,
|
| 259 |
+
"learning_rate": 5.983045753470308e-05,
|
| 260 |
+
"loss": 0.7766,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 6.406926406926407,
|
| 265 |
+
"grad_norm": 1.556640625,
|
| 266 |
+
"learning_rate": 5.484666416891109e-05,
|
| 267 |
+
"loss": 0.7152,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 6.58008658008658,
|
| 272 |
+
"grad_norm": 1.3330078125,
|
| 273 |
+
"learning_rate": 5.000000000000002e-05,
|
| 274 |
+
"loss": 0.7112,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 6.753246753246753,
|
| 279 |
+
"grad_norm": 1.3564453125,
|
| 280 |
+
"learning_rate": 4.530518418775733e-05,
|
| 281 |
+
"loss": 0.7955,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 6.926406926406926,
|
| 286 |
+
"grad_norm": 1.31640625,
|
| 287 |
+
"learning_rate": 4.077647473350201e-05,
|
| 288 |
+
"loss": 0.8241,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 7.0995670995671,
|
| 293 |
+
"grad_norm": 1.4013671875,
|
| 294 |
+
"learning_rate": 3.642762517900322e-05,
|
| 295 |
+
"loss": 0.7759,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.2727272727272725,
|
| 300 |
+
"grad_norm": 1.4345703125,
|
| 301 |
+
"learning_rate": 3.227184283742591e-05,
|
| 302 |
+
"loss": 0.747,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 7.445887445887446,
|
| 307 |
+
"grad_norm": 1.4423828125,
|
| 308 |
+
"learning_rate": 2.8321748683154893e-05,
|
| 309 |
+
"loss": 0.7206,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 7.619047619047619,
|
| 314 |
+
"grad_norm": 1.599609375,
|
| 315 |
+
"learning_rate": 2.4589339022310386e-05,
|
| 316 |
+
"loss": 0.6764,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 7.792207792207792,
|
| 321 |
+
"grad_norm": 1.3486328125,
|
| 322 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 323 |
+
"loss": 0.7336,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.965367965367966,
|
| 328 |
+
"grad_norm": 1.576171875,
|
| 329 |
+
"learning_rate": 1.7822218477475494e-05,
|
| 330 |
+
"loss": 0.6992,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 8.13852813852814,
|
| 335 |
+
"grad_norm": 1.560546875,
|
| 336 |
+
"learning_rate": 1.4808059116167305e-05,
|
| 337 |
+
"loss": 0.6818,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 8.311688311688311,
|
| 342 |
+
"grad_norm": 1.6240234375,
|
| 343 |
+
"learning_rate": 1.2052624879351104e-05,
|
| 344 |
+
"loss": 0.7221,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 8.484848484848484,
|
| 349 |
+
"grad_norm": 1.431640625,
|
| 350 |
+
"learning_rate": 9.564283930242257e-06,
|
| 351 |
+
"loss": 0.6785,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 8.658008658008658,
|
| 356 |
+
"grad_norm": 1.4521484375,
|
| 357 |
+
"learning_rate": 7.350593278519824e-06,
|
| 358 |
+
"loss": 0.6701,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 8.831168831168831,
|
| 363 |
+
"grad_norm": 1.46484375,
|
| 364 |
+
"learning_rate": 5.418275829936537e-06,
|
| 365 |
+
"loss": 0.695,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 9.004329004329005,
|
| 370 |
+
"grad_norm": 1.3701171875,
|
| 371 |
+
"learning_rate": 3.7731999690749585e-06,
|
| 372 |
+
"loss": 0.6976,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 9.177489177489177,
|
| 377 |
+
"grad_norm": 1.3154296875,
|
| 378 |
+
"learning_rate": 2.420361737256438e-06,
|
| 379 |
+
"loss": 0.6386,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 9.35064935064935,
|
| 384 |
+
"grad_norm": 1.5068359375,
|
| 385 |
+
"learning_rate": 1.3638696597277679e-06,
|
| 386 |
+
"loss": 0.706,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 9.523809523809524,
|
| 391 |
+
"grad_norm": 1.5166015625,
|
| 392 |
+
"learning_rate": 6.069322682050516e-07,
|
| 393 |
+
"loss": 0.6972,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 9.696969696969697,
|
| 398 |
+
"grad_norm": 1.2392578125,
|
| 399 |
+
"learning_rate": 1.518483566683826e-07,
|
| 400 |
+
"loss": 0.6888,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 9.87012987012987,
|
| 405 |
+
"grad_norm": 1.4599609375,
|
| 406 |
+
"learning_rate": 0.0,
|
| 407 |
+
"loss": 0.6703,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 9.87012987012987,
|
| 412 |
+
"step": 570,
|
| 413 |
+
"total_flos": 1.455489640562688e+16,
|
| 414 |
+
"train_loss": 0.9482885511297928,
|
| 415 |
+
"train_runtime": 548.5236,
|
| 416 |
+
"train_samples_per_second": 4.211,
|
| 417 |
+
"train_steps_per_second": 1.039
|
| 418 |
+
}
|
| 419 |
+
],
|
| 420 |
+
"logging_steps": 10,
|
| 421 |
+
"max_steps": 570,
|
| 422 |
+
"num_input_tokens_seen": 0,
|
| 423 |
+
"num_train_epochs": 10,
|
| 424 |
+
"save_steps": 500,
|
| 425 |
+
"total_flos": 1.455489640562688e+16,
|
| 426 |
+
"train_batch_size": 1,
|
| 427 |
+
"trial_name": null,
|
| 428 |
+
"trial_params": null
|
| 429 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4539
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1273e270b14d56ea307a3f8cd43046a55903043c7fd9040e99bcaeaff1026887
|
| 3 |
size 4539
|