Upload 6 files
Browse files- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +356 -0
- training_args.bin +3 -0
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eff0e5f975449ebfc26f4c043bf066004853938657ac47af9f39173a76d3ce0e
|
| 3 |
+
size 409920
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:818797a818802e6185a5ed19a2a6227253263064d355385e3a6f5944c61c2450
|
| 3 |
+
size 862202
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c1d7b0e6cb33788a2ae4d68550e727c394f543791abd725cf64234b6e83db98
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd62f7f784258a36cb676118c39a9a016facd6bd49a0868982b48a8d5fe2eb1c
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,356 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4690,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.10660980810234541,
|
| 14 |
+
"grad_norm": 1.512649655342102,
|
| 15 |
+
"learning_rate": 7.021276595744681e-05,
|
| 16 |
+
"loss": 0.8783621978759766,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.21321961620469082,
|
| 21 |
+
"grad_norm": 0.41342806816101074,
|
| 22 |
+
"learning_rate": 9.872499450428666e-05,
|
| 23 |
+
"loss": 0.3635389709472656,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.31982942430703626,
|
| 28 |
+
"grad_norm": 0.2897585332393646,
|
| 29 |
+
"learning_rate": 9.652670916684985e-05,
|
| 30 |
+
"loss": 0.18652456283569335,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.42643923240938164,
|
| 35 |
+
"grad_norm": 0.39718756079673767,
|
| 36 |
+
"learning_rate": 9.432842382941306e-05,
|
| 37 |
+
"loss": 0.13982501983642578,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.5330490405117271,
|
| 42 |
+
"grad_norm": 0.22674299776554108,
|
| 43 |
+
"learning_rate": 9.213013849197626e-05,
|
| 44 |
+
"loss": 0.12051151275634765,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.6396588486140725,
|
| 49 |
+
"grad_norm": 0.27016663551330566,
|
| 50 |
+
"learning_rate": 8.993185315453946e-05,
|
| 51 |
+
"loss": 0.10687240600585937,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.746268656716418,
|
| 56 |
+
"grad_norm": 0.27923911809921265,
|
| 57 |
+
"learning_rate": 8.773356781710267e-05,
|
| 58 |
+
"loss": 0.0931793212890625,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.8528784648187633,
|
| 63 |
+
"grad_norm": 0.48017603158950806,
|
| 64 |
+
"learning_rate": 8.553528247966587e-05,
|
| 65 |
+
"loss": 0.08681591987609863,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.9594882729211087,
|
| 70 |
+
"grad_norm": 0.25462451577186584,
|
| 71 |
+
"learning_rate": 8.333699714222907e-05,
|
| 72 |
+
"loss": 0.08227352142333984,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.0660980810234542,
|
| 77 |
+
"grad_norm": 0.25555577874183655,
|
| 78 |
+
"learning_rate": 8.113871180479227e-05,
|
| 79 |
+
"loss": 0.07781341552734375,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.1727078891257996,
|
| 84 |
+
"grad_norm": 0.2868955433368683,
|
| 85 |
+
"learning_rate": 7.894042646735546e-05,
|
| 86 |
+
"loss": 0.07137668609619141,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.279317697228145,
|
| 91 |
+
"grad_norm": 0.7258135080337524,
|
| 92 |
+
"learning_rate": 7.674214112991867e-05,
|
| 93 |
+
"loss": 0.06982158660888672,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.3859275053304905,
|
| 98 |
+
"grad_norm": 0.21467193961143494,
|
| 99 |
+
"learning_rate": 7.454385579248186e-05,
|
| 100 |
+
"loss": 0.06995021343231202,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.4925373134328357,
|
| 105 |
+
"grad_norm": 0.2582932412624359,
|
| 106 |
+
"learning_rate": 7.234557045504506e-05,
|
| 107 |
+
"loss": 0.06500450611114501,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.5991471215351813,
|
| 112 |
+
"grad_norm": 0.6736129522323608,
|
| 113 |
+
"learning_rate": 7.014728511760827e-05,
|
| 114 |
+
"loss": 0.06558525085449218,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.7057569296375266,
|
| 119 |
+
"grad_norm": 0.347025603055954,
|
| 120 |
+
"learning_rate": 6.794899978017147e-05,
|
| 121 |
+
"loss": 0.06201983451843262,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.8123667377398722,
|
| 126 |
+
"grad_norm": 0.14061450958251953,
|
| 127 |
+
"learning_rate": 6.575071444273467e-05,
|
| 128 |
+
"loss": 0.06188218116760254,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.9189765458422174,
|
| 133 |
+
"grad_norm": 0.671807587146759,
|
| 134 |
+
"learning_rate": 6.355242910529788e-05,
|
| 135 |
+
"loss": 0.06162861347198487,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.025586353944563,
|
| 140 |
+
"grad_norm": 0.23481066524982452,
|
| 141 |
+
"learning_rate": 6.135414376786107e-05,
|
| 142 |
+
"loss": 0.059541940689086914,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.1321961620469083,
|
| 147 |
+
"grad_norm": 0.37396782636642456,
|
| 148 |
+
"learning_rate": 5.915585843042427e-05,
|
| 149 |
+
"loss": 0.05958046913146973,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.2388059701492535,
|
| 154 |
+
"grad_norm": 0.3006986975669861,
|
| 155 |
+
"learning_rate": 5.695757309298747e-05,
|
| 156 |
+
"loss": 0.058162903785705565,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 2.345415778251599,
|
| 161 |
+
"grad_norm": 0.512683629989624,
|
| 162 |
+
"learning_rate": 5.475928775555067e-05,
|
| 163 |
+
"loss": 0.05590470790863037,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.4520255863539444,
|
| 168 |
+
"grad_norm": 0.6538902521133423,
|
| 169 |
+
"learning_rate": 5.2561002418113866e-05,
|
| 170 |
+
"loss": 0.056855697631835934,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.55863539445629,
|
| 175 |
+
"grad_norm": 0.384748250246048,
|
| 176 |
+
"learning_rate": 5.036271708067708e-05,
|
| 177 |
+
"loss": 0.0553256368637085,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.6652452025586353,
|
| 182 |
+
"grad_norm": 0.2743995785713196,
|
| 183 |
+
"learning_rate": 4.8164431743240275e-05,
|
| 184 |
+
"loss": 0.055201725959777834,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.771855010660981,
|
| 189 |
+
"grad_norm": 0.3086058497428894,
|
| 190 |
+
"learning_rate": 4.5966146405803476e-05,
|
| 191 |
+
"loss": 0.05579360485076904,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.878464818763326,
|
| 196 |
+
"grad_norm": 0.20562346279621124,
|
| 197 |
+
"learning_rate": 4.376786106836668e-05,
|
| 198 |
+
"loss": 0.053631467819213866,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 2.9850746268656714,
|
| 203 |
+
"grad_norm": 0.17855797708034515,
|
| 204 |
+
"learning_rate": 4.156957573092988e-05,
|
| 205 |
+
"loss": 0.05369348526000976,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.091684434968017,
|
| 210 |
+
"grad_norm": 0.21947342157363892,
|
| 211 |
+
"learning_rate": 3.937129039349308e-05,
|
| 212 |
+
"loss": 0.05297693252563476,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 3.1982942430703627,
|
| 217 |
+
"grad_norm": 0.1905689537525177,
|
| 218 |
+
"learning_rate": 3.717300505605627e-05,
|
| 219 |
+
"loss": 0.05208170413970947,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.304904051172708,
|
| 224 |
+
"grad_norm": 0.4524707496166229,
|
| 225 |
+
"learning_rate": 3.497471971861948e-05,
|
| 226 |
+
"loss": 0.053418731689453124,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 3.411513859275053,
|
| 231 |
+
"grad_norm": 0.3877377510070801,
|
| 232 |
+
"learning_rate": 3.277643438118268e-05,
|
| 233 |
+
"loss": 0.05178478240966797,
|
| 234 |
+
"step": 3200
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 3.518123667377399,
|
| 238 |
+
"grad_norm": 0.38067901134490967,
|
| 239 |
+
"learning_rate": 3.057814904374588e-05,
|
| 240 |
+
"loss": 0.05265708446502686,
|
| 241 |
+
"step": 3300
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 3.624733475479744,
|
| 245 |
+
"grad_norm": 0.220926433801651,
|
| 246 |
+
"learning_rate": 2.837986370630908e-05,
|
| 247 |
+
"loss": 0.051145505905151364,
|
| 248 |
+
"step": 3400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.7313432835820897,
|
| 252 |
+
"grad_norm": 0.24693001806735992,
|
| 253 |
+
"learning_rate": 2.6181578368872278e-05,
|
| 254 |
+
"loss": 0.05244531154632568,
|
| 255 |
+
"step": 3500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 3.837953091684435,
|
| 259 |
+
"grad_norm": 0.16234378516674042,
|
| 260 |
+
"learning_rate": 2.3983293031435482e-05,
|
| 261 |
+
"loss": 0.05159466743469238,
|
| 262 |
+
"step": 3600
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 3.9445628997867805,
|
| 266 |
+
"grad_norm": 0.25106945633888245,
|
| 267 |
+
"learning_rate": 2.1785007693998683e-05,
|
| 268 |
+
"loss": 0.050518522262573244,
|
| 269 |
+
"step": 3700
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 4.051172707889126,
|
| 273 |
+
"grad_norm": 0.15427334606647491,
|
| 274 |
+
"learning_rate": 1.958672235656188e-05,
|
| 275 |
+
"loss": 0.05148844242095947,
|
| 276 |
+
"step": 3800
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 4.157782515991471,
|
| 280 |
+
"grad_norm": 0.2565928101539612,
|
| 281 |
+
"learning_rate": 1.7388437019125085e-05,
|
| 282 |
+
"loss": 0.05278157234191894,
|
| 283 |
+
"step": 3900
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 4.264392324093817,
|
| 287 |
+
"grad_norm": 0.23209957778453827,
|
| 288 |
+
"learning_rate": 1.5190151681688284e-05,
|
| 289 |
+
"loss": 0.05116010189056396,
|
| 290 |
+
"step": 4000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.371002132196162,
|
| 294 |
+
"grad_norm": 0.2657167613506317,
|
| 295 |
+
"learning_rate": 1.2991866344251485e-05,
|
| 296 |
+
"loss": 0.050900754928588865,
|
| 297 |
+
"step": 4100
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.477611940298507,
|
| 301 |
+
"grad_norm": 0.1503467857837677,
|
| 302 |
+
"learning_rate": 1.0793581006814684e-05,
|
| 303 |
+
"loss": 0.05005928516387939,
|
| 304 |
+
"step": 4200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.584221748400853,
|
| 308 |
+
"grad_norm": 0.22385095059871674,
|
| 309 |
+
"learning_rate": 8.595295669377885e-06,
|
| 310 |
+
"loss": 0.04985287666320801,
|
| 311 |
+
"step": 4300
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 4.690831556503198,
|
| 315 |
+
"grad_norm": 0.2489224523305893,
|
| 316 |
+
"learning_rate": 6.397010331941086e-06,
|
| 317 |
+
"loss": 0.05140969753265381,
|
| 318 |
+
"step": 4400
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 4.797441364605544,
|
| 322 |
+
"grad_norm": 0.14599594473838806,
|
| 323 |
+
"learning_rate": 4.198724994504287e-06,
|
| 324 |
+
"loss": 0.05068167209625244,
|
| 325 |
+
"step": 4500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 4.904051172707889,
|
| 329 |
+
"grad_norm": 0.2004062831401825,
|
| 330 |
+
"learning_rate": 2.0004396570674875e-06,
|
| 331 |
+
"loss": 0.050402441024780274,
|
| 332 |
+
"step": 4600
|
| 333 |
+
}
|
| 334 |
+
],
|
| 335 |
+
"logging_steps": 100,
|
| 336 |
+
"max_steps": 4690,
|
| 337 |
+
"num_input_tokens_seen": 0,
|
| 338 |
+
"num_train_epochs": 5,
|
| 339 |
+
"save_steps": 100,
|
| 340 |
+
"stateful_callbacks": {
|
| 341 |
+
"TrainerControl": {
|
| 342 |
+
"args": {
|
| 343 |
+
"should_epoch_stop": false,
|
| 344 |
+
"should_evaluate": false,
|
| 345 |
+
"should_log": false,
|
| 346 |
+
"should_save": true,
|
| 347 |
+
"should_training_stop": true
|
| 348 |
+
},
|
| 349 |
+
"attributes": {}
|
| 350 |
+
}
|
| 351 |
+
},
|
| 352 |
+
"total_flos": 0.0,
|
| 353 |
+
"train_batch_size": 64,
|
| 354 |
+
"trial_name": null,
|
| 355 |
+
"trial_params": null
|
| 356 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:178013532957002c570b66876a3075db5487e9ca63159ad81f2aac8948120ffe
|
| 3 |
+
size 4792
|