Training in progress, epoch 0
Browse files- adapter_config.json +4 -2
- adapter_model.safetensors +2 -2
- trainer_state.json +408 -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:fb2b1ef06c08cccfeb118cb9baf41ef34483c9da2358271c436a9606eb621177
|
| 3 |
+
size 47236352
|
trainer_state.json
ADDED
|
@@ -0,0 +1,408 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.953917050691244,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 540,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.18433179723502305,
|
| 13 |
+
"grad_norm": 15.2578125,
|
| 14 |
+
"learning_rate": 0.00019983081582712685,
|
| 15 |
+
"loss": 1.1335,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.3686635944700461,
|
| 20 |
+
"grad_norm": 15.1484375,
|
| 21 |
+
"learning_rate": 0.00019932383577419432,
|
| 22 |
+
"loss": 1.0389,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.5529953917050692,
|
| 27 |
+
"grad_norm": 16.21875,
|
| 28 |
+
"learning_rate": 0.00019848077530122083,
|
| 29 |
+
"loss": 1.0017,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.7373271889400922,
|
| 34 |
+
"grad_norm": 13.3359375,
|
| 35 |
+
"learning_rate": 0.00019730448705798239,
|
| 36 |
+
"loss": 0.9937,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.9216589861751152,
|
| 41 |
+
"grad_norm": 13.1171875,
|
| 42 |
+
"learning_rate": 0.0001957989512315489,
|
| 43 |
+
"loss": 0.9773,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.1059907834101383,
|
| 48 |
+
"grad_norm": 11.2578125,
|
| 49 |
+
"learning_rate": 0.00019396926207859084,
|
| 50 |
+
"loss": 0.9484,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.2903225806451613,
|
| 55 |
+
"grad_norm": 13.71875,
|
| 56 |
+
"learning_rate": 0.00019182161068802741,
|
| 57 |
+
"loss": 0.9577,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.4746543778801844,
|
| 62 |
+
"grad_norm": 10.65625,
|
| 63 |
+
"learning_rate": 0.00018936326403234125,
|
| 64 |
+
"loss": 0.9277,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.6589861751152073,
|
| 69 |
+
"grad_norm": 12.90625,
|
| 70 |
+
"learning_rate": 0.00018660254037844388,
|
| 71 |
+
"loss": 0.9301,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.8433179723502304,
|
| 76 |
+
"grad_norm": 13.7578125,
|
| 77 |
+
"learning_rate": 0.00018354878114129367,
|
| 78 |
+
"loss": 0.9212,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.0276497695852536,
|
| 83 |
+
"grad_norm": 10.140625,
|
| 84 |
+
"learning_rate": 0.0001802123192755044,
|
| 85 |
+
"loss": 0.8985,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.2119815668202767,
|
| 90 |
+
"grad_norm": 9.6015625,
|
| 91 |
+
"learning_rate": 0.0001766044443118978,
|
| 92 |
+
"loss": 0.8939,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.3963133640552994,
|
| 97 |
+
"grad_norm": 11.921875,
|
| 98 |
+
"learning_rate": 0.00017273736415730488,
|
| 99 |
+
"loss": 0.8935,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.5806451612903225,
|
| 104 |
+
"grad_norm": 10.8203125,
|
| 105 |
+
"learning_rate": 0.0001686241637868734,
|
| 106 |
+
"loss": 0.8973,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.7649769585253456,
|
| 111 |
+
"grad_norm": 11.7421875,
|
| 112 |
+
"learning_rate": 0.00016427876096865394,
|
| 113 |
+
"loss": 0.9522,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.9493087557603688,
|
| 118 |
+
"grad_norm": 11.5234375,
|
| 119 |
+
"learning_rate": 0.00015971585917027862,
|
| 120 |
+
"loss": 0.9124,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 3.133640552995392,
|
| 125 |
+
"grad_norm": 10.25,
|
| 126 |
+
"learning_rate": 0.0001549508978070806,
|
| 127 |
+
"loss": 0.899,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.3179723502304146,
|
| 132 |
+
"grad_norm": 10.4609375,
|
| 133 |
+
"learning_rate": 0.00015000000000000001,
|
| 134 |
+
"loss": 0.8893,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.5023041474654377,
|
| 139 |
+
"grad_norm": 9.0078125,
|
| 140 |
+
"learning_rate": 0.00014487991802004623,
|
| 141 |
+
"loss": 0.8878,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 3.686635944700461,
|
| 146 |
+
"grad_norm": 10.21875,
|
| 147 |
+
"learning_rate": 0.0001396079766039157,
|
| 148 |
+
"loss": 0.8656,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 3.870967741935484,
|
| 153 |
+
"grad_norm": 7.875,
|
| 154 |
+
"learning_rate": 0.00013420201433256689,
|
| 155 |
+
"loss": 0.8897,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.055299539170507,
|
| 160 |
+
"grad_norm": 9.4921875,
|
| 161 |
+
"learning_rate": 0.00012868032327110904,
|
| 162 |
+
"loss": 0.8549,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 4.23963133640553,
|
| 167 |
+
"grad_norm": 9.2421875,
|
| 168 |
+
"learning_rate": 0.00012306158707424403,
|
| 169 |
+
"loss": 0.8577,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.423963133640553,
|
| 174 |
+
"grad_norm": 7.875,
|
| 175 |
+
"learning_rate": 0.00011736481776669306,
|
| 176 |
+
"loss": 0.8579,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.6082949308755765,
|
| 181 |
+
"grad_norm": 8.1328125,
|
| 182 |
+
"learning_rate": 0.00011160929141252303,
|
| 183 |
+
"loss": 0.8278,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 4.792626728110599,
|
| 188 |
+
"grad_norm": 7.01171875,
|
| 189 |
+
"learning_rate": 0.00010581448289104758,
|
| 190 |
+
"loss": 0.8458,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 4.976958525345622,
|
| 195 |
+
"grad_norm": 6.92578125,
|
| 196 |
+
"learning_rate": 0.0001,
|
| 197 |
+
"loss": 0.874,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 5.161290322580645,
|
| 202 |
+
"grad_norm": 8.1796875,
|
| 203 |
+
"learning_rate": 9.418551710895243e-05,
|
| 204 |
+
"loss": 0.8455,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 5.345622119815668,
|
| 209 |
+
"grad_norm": 7.21484375,
|
| 210 |
+
"learning_rate": 8.839070858747697e-05,
|
| 211 |
+
"loss": 0.8316,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 5.529953917050691,
|
| 216 |
+
"grad_norm": 9.9375,
|
| 217 |
+
"learning_rate": 8.263518223330697e-05,
|
| 218 |
+
"loss": 0.8555,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.714285714285714,
|
| 223 |
+
"grad_norm": 7.5390625,
|
| 224 |
+
"learning_rate": 7.693841292575598e-05,
|
| 225 |
+
"loss": 0.8385,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 5.8986175115207375,
|
| 230 |
+
"grad_norm": 6.8515625,
|
| 231 |
+
"learning_rate": 7.131967672889101e-05,
|
| 232 |
+
"loss": 0.8339,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 6.082949308755761,
|
| 237 |
+
"grad_norm": 7.38671875,
|
| 238 |
+
"learning_rate": 6.579798566743314e-05,
|
| 239 |
+
"loss": 0.8497,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 6.267281105990784,
|
| 244 |
+
"grad_norm": 7.21875,
|
| 245 |
+
"learning_rate": 6.039202339608432e-05,
|
| 246 |
+
"loss": 0.836,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 6.451612903225806,
|
| 251 |
+
"grad_norm": 8.515625,
|
| 252 |
+
"learning_rate": 5.5120081979953785e-05,
|
| 253 |
+
"loss": 0.8411,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 6.635944700460829,
|
| 258 |
+
"grad_norm": 8.515625,
|
| 259 |
+
"learning_rate": 5.000000000000002e-05,
|
| 260 |
+
"loss": 0.822,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 6.820276497695852,
|
| 265 |
+
"grad_norm": 7.73828125,
|
| 266 |
+
"learning_rate": 4.50491021929194e-05,
|
| 267 |
+
"loss": 0.8298,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 7.0046082949308754,
|
| 272 |
+
"grad_norm": 7.15625,
|
| 273 |
+
"learning_rate": 4.028414082972141e-05,
|
| 274 |
+
"loss": 0.8366,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 7.188940092165899,
|
| 279 |
+
"grad_norm": 7.45703125,
|
| 280 |
+
"learning_rate": 3.5721239031346066e-05,
|
| 281 |
+
"loss": 0.8222,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 7.373271889400922,
|
| 286 |
+
"grad_norm": 7.94921875,
|
| 287 |
+
"learning_rate": 3.137583621312665e-05,
|
| 288 |
+
"loss": 0.8294,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 7.557603686635945,
|
| 293 |
+
"grad_norm": 7.80078125,
|
| 294 |
+
"learning_rate": 2.7262635842695127e-05,
|
| 295 |
+
"loss": 0.8189,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.741935483870968,
|
| 300 |
+
"grad_norm": 7.33984375,
|
| 301 |
+
"learning_rate": 2.339555568810221e-05,
|
| 302 |
+
"loss": 0.8279,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 7.926267281105991,
|
| 307 |
+
"grad_norm": 10.0390625,
|
| 308 |
+
"learning_rate": 1.9787680724495617e-05,
|
| 309 |
+
"loss": 0.8299,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 8.110599078341014,
|
| 314 |
+
"grad_norm": 8.34375,
|
| 315 |
+
"learning_rate": 1.6451218858706374e-05,
|
| 316 |
+
"loss": 0.8408,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 8.294930875576037,
|
| 321 |
+
"grad_norm": 7.22265625,
|
| 322 |
+
"learning_rate": 1.339745962155613e-05,
|
| 323 |
+
"loss": 0.819,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 8.47926267281106,
|
| 328 |
+
"grad_norm": 7.890625,
|
| 329 |
+
"learning_rate": 1.0636735967658784e-05,
|
| 330 |
+
"loss": 0.8087,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 8.663594470046084,
|
| 335 |
+
"grad_norm": 8.9296875,
|
| 336 |
+
"learning_rate": 8.178389311972612e-06,
|
| 337 |
+
"loss": 0.8218,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 8.847926267281107,
|
| 342 |
+
"grad_norm": 9.421875,
|
| 343 |
+
"learning_rate": 6.030737921409169e-06,
|
| 344 |
+
"loss": 0.8213,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 9.03225806451613,
|
| 349 |
+
"grad_norm": 7.0078125,
|
| 350 |
+
"learning_rate": 4.20104876845111e-06,
|
| 351 |
+
"loss": 0.8259,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 9.216589861751151,
|
| 356 |
+
"grad_norm": 7.5546875,
|
| 357 |
+
"learning_rate": 2.6955129420176196e-06,
|
| 358 |
+
"loss": 0.8463,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 9.400921658986174,
|
| 363 |
+
"grad_norm": 8.0546875,
|
| 364 |
+
"learning_rate": 1.5192246987791981e-06,
|
| 365 |
+
"loss": 0.7932,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 9.585253456221198,
|
| 370 |
+
"grad_norm": 8.109375,
|
| 371 |
+
"learning_rate": 6.761642258056978e-07,
|
| 372 |
+
"loss": 0.8172,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 9.76958525345622,
|
| 377 |
+
"grad_norm": 7.5859375,
|
| 378 |
+
"learning_rate": 1.6918417287318245e-07,
|
| 379 |
+
"loss": 0.8263,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 9.953917050691244,
|
| 384 |
+
"grad_norm": 8.59375,
|
| 385 |
+
"learning_rate": 0.0,
|
| 386 |
+
"loss": 0.8372,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 9.953917050691244,
|
| 391 |
+
"step": 540,
|
| 392 |
+
"total_flos": 3.52542013784064e+16,
|
| 393 |
+
"train_loss": 0.8746989762341535,
|
| 394 |
+
"train_runtime": 468.0964,
|
| 395 |
+
"train_samples_per_second": 4.636,
|
| 396 |
+
"train_steps_per_second": 1.154
|
| 397 |
+
}
|
| 398 |
+
],
|
| 399 |
+
"logging_steps": 10,
|
| 400 |
+
"max_steps": 540,
|
| 401 |
+
"num_input_tokens_seen": 0,
|
| 402 |
+
"num_train_epochs": 10,
|
| 403 |
+
"save_steps": 500,
|
| 404 |
+
"total_flos": 3.52542013784064e+16,
|
| 405 |
+
"train_batch_size": 1,
|
| 406 |
+
"trial_name": null,
|
| 407 |
+
"trial_params": null
|
| 408 |
+
}
|
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 sha256:4318c3473e8d964da0c3b8be9515815da9824e38824919aeb2ca5d12ce479c59
|
| 3 |
size 4984
|