Training in progress, step 100, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +24 -549
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 735396724
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b22e0217267118dca0bb186fb6ddb3f40cd3c2d065091315aa84ec45aea3a33
|
| 3 |
size 735396724
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1470915147
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a7925037db11bfaa072cc80f6c10eb63176e60ef303fe04fa0d30ce249f9c65
|
| 3 |
size 1470915147
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fed020fdb6d6b5500be0a6eead260f74482d4c1474ab8cc7290f8f9619dd4ac
|
| 3 |
size 16325
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2705c0ca32529bae0fb089affa76d4dce9705acfa8f541b2a544941069e3db71
|
| 3 |
size 16325
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48a749eb4f5ab8e806c82216971fdad2787560a699a10f6d2ccd66912c7317af
|
| 3 |
size 16325
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dfb684812103d15f6dc7042290075535040430b9f6febc2cd99421aa5648aa1
|
| 3 |
size 16325
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9136b453501f394f496b323cd31d0975a95309b91c07dc6d7473972ce8ec2c4d
|
| 3 |
size 16325
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c84ad5edda3c8c35d3ee9ea282864235bc608f83b4ab25eb288b919dd16a202c
|
| 3 |
size 16325
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1741447250e85a165f537024a3f313aab0ce32476707e8da4e55fcb7fb6dc4da
|
| 3 |
size 16325
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b98d17759f78d0cd88d89d081d9aeb89e0ae6a1f94c0d583e0af00025837bef
|
| 3 |
size 16325
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:611c9771a7a4075f31b269b7d9a8dd87cc4cee9bf7528c5f80e13a8699c560c1
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,567 +1,42 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "model/checkpoint-
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 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.
|
| 14 |
-
"grad_norm":
|
| 15 |
-
"learning_rate":
|
| 16 |
-
"loss":
|
| 17 |
"step": 50
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"grad_norm": 0.
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 100
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"eval_entity_f1": 0.
|
| 29 |
-
"eval_entity_precision": 0.
|
| 30 |
-
"eval_entity_recall": 0.
|
| 31 |
-
"eval_loss": 0.
|
| 32 |
-
"eval_runtime":
|
| 33 |
-
"eval_samples_per_second":
|
| 34 |
-
"eval_steps_per_second":
|
| 35 |
"step": 100
|
| 36 |
-
},
|
| 37 |
-
{
|
| 38 |
-
"epoch": 0.0767656090071648,
|
| 39 |
-
"grad_norm": 0.37045082449913025,
|
| 40 |
-
"learning_rate": 2.116477272727273e-05,
|
| 41 |
-
"loss": 0.1816,
|
| 42 |
-
"step": 150
|
| 43 |
-
},
|
| 44 |
-
{
|
| 45 |
-
"epoch": 0.1023541453428864,
|
| 46 |
-
"grad_norm": 0.42604702711105347,
|
| 47 |
-
"learning_rate": 2.499899071021083e-05,
|
| 48 |
-
"loss": 0.1481,
|
| 49 |
-
"step": 200
|
| 50 |
-
},
|
| 51 |
-
{
|
| 52 |
-
"epoch": 0.1023541453428864,
|
| 53 |
-
"eval_entity_f1": 0.6918361384960318,
|
| 54 |
-
"eval_entity_precision": 0.5961861615992166,
|
| 55 |
-
"eval_entity_recall": 0.8690620722247572,
|
| 56 |
-
"eval_loss": 0.12863518297672272,
|
| 57 |
-
"eval_runtime": 218.582,
|
| 58 |
-
"eval_samples_per_second": 1829.977,
|
| 59 |
-
"eval_steps_per_second": 28.593,
|
| 60 |
-
"step": 200
|
| 61 |
-
},
|
| 62 |
-
{
|
| 63 |
-
"epoch": 0.12794268167860798,
|
| 64 |
-
"grad_norm": 0.36878466606140137,
|
| 65 |
-
"learning_rate": 2.4989833934677885e-05,
|
| 66 |
-
"loss": 0.1343,
|
| 67 |
-
"step": 250
|
| 68 |
-
},
|
| 69 |
-
{
|
| 70 |
-
"epoch": 0.1535312180143296,
|
| 71 |
-
"grad_norm": 0.5593751072883606,
|
| 72 |
-
"learning_rate": 2.4971145794455734e-05,
|
| 73 |
-
"loss": 0.1281,
|
| 74 |
-
"step": 300
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 0.1535312180143296,
|
| 78 |
-
"eval_entity_f1": 0.6996789378037388,
|
| 79 |
-
"eval_entity_precision": 0.6106036365741541,
|
| 80 |
-
"eval_entity_recall": 0.8724720520174696,
|
| 81 |
-
"eval_loss": 0.12191963195800781,
|
| 82 |
-
"eval_runtime": 217.8663,
|
| 83 |
-
"eval_samples_per_second": 1835.988,
|
| 84 |
-
"eval_steps_per_second": 28.687,
|
| 85 |
-
"step": 300
|
| 86 |
-
},
|
| 87 |
-
{
|
| 88 |
-
"epoch": 0.17911975435005117,
|
| 89 |
-
"grad_norm": 0.36381790041923523,
|
| 90 |
-
"learning_rate": 2.4942940551021408e-05,
|
| 91 |
-
"loss": 0.1244,
|
| 92 |
-
"step": 350
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"epoch": 0.2047082906857728,
|
| 96 |
-
"grad_norm": 0.44861096143722534,
|
| 97 |
-
"learning_rate": 2.4905239728637176e-05,
|
| 98 |
-
"loss": 0.1203,
|
| 99 |
-
"step": 400
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 0.2047082906857728,
|
| 103 |
-
"eval_entity_f1": 0.7212507498513367,
|
| 104 |
-
"eval_entity_precision": 0.6382543079453578,
|
| 105 |
-
"eval_entity_recall": 0.8747942604784564,
|
| 106 |
-
"eval_loss": 0.11121271550655365,
|
| 107 |
-
"eval_runtime": 216.5237,
|
| 108 |
-
"eval_samples_per_second": 1847.373,
|
| 109 |
-
"eval_steps_per_second": 28.865,
|
| 110 |
-
"step": 400
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 0.23029682702149437,
|
| 114 |
-
"grad_norm": 0.3033084273338318,
|
| 115 |
-
"learning_rate": 2.4858072097924742e-05,
|
| 116 |
-
"loss": 0.1163,
|
| 117 |
-
"step": 450
|
| 118 |
-
},
|
| 119 |
-
{
|
| 120 |
-
"epoch": 0.25588536335721596,
|
| 121 |
-
"grad_norm": 0.29682832956314087,
|
| 122 |
-
"learning_rate": 2.4801473653909512e-05,
|
| 123 |
-
"loss": 0.1162,
|
| 124 |
-
"step": 500
|
| 125 |
-
},
|
| 126 |
-
{
|
| 127 |
-
"epoch": 0.25588536335721596,
|
| 128 |
-
"eval_entity_f1": 0.7247694309446124,
|
| 129 |
-
"eval_entity_precision": 0.6445471431888633,
|
| 130 |
-
"eval_entity_recall": 0.8732909360537122,
|
| 131 |
-
"eval_loss": 0.10730964690446854,
|
| 132 |
-
"eval_runtime": 217.7466,
|
| 133 |
-
"eval_samples_per_second": 1836.998,
|
| 134 |
-
"eval_steps_per_second": 28.703,
|
| 135 |
-
"step": 500
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.28147389969293757,
|
| 139 |
-
"grad_norm": 0.29889968037605286,
|
| 140 |
-
"learning_rate": 2.473548758855173e-05,
|
| 141 |
-
"loss": 0.1147,
|
| 142 |
-
"step": 550
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.3070624360286592,
|
| 146 |
-
"grad_norm": 0.33070290088653564,
|
| 147 |
-
"learning_rate": 2.4660164257785407e-05,
|
| 148 |
-
"loss": 0.1139,
|
| 149 |
-
"step": 600
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.3070624360286592,
|
| 153 |
-
"eval_entity_f1": 0.7246454221566335,
|
| 154 |
-
"eval_entity_precision": 0.6442261030859694,
|
| 155 |
-
"eval_entity_recall": 0.8747800013036959,
|
| 156 |
-
"eval_loss": 0.10540451109409332,
|
| 157 |
-
"eval_runtime": 215.57,
|
| 158 |
-
"eval_samples_per_second": 1855.546,
|
| 159 |
-
"eval_steps_per_second": 28.993,
|
| 160 |
-
"step": 600
|
| 161 |
-
},
|
| 162 |
-
{
|
| 163 |
-
"epoch": 0.33265097236438074,
|
| 164 |
-
"grad_norm": 0.3055472671985626,
|
| 165 |
-
"learning_rate": 2.4575561143090183e-05,
|
| 166 |
-
"loss": 0.1107,
|
| 167 |
-
"step": 650
|
| 168 |
-
},
|
| 169 |
-
{
|
| 170 |
-
"epoch": 0.35823950870010235,
|
| 171 |
-
"grad_norm": 0.2586459815502167,
|
| 172 |
-
"learning_rate": 2.448174280762552e-05,
|
| 173 |
-
"loss": 0.1095,
|
| 174 |
-
"step": 700
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 0.35823950870010235,
|
| 178 |
-
"eval_entity_f1": 0.7284125931431864,
|
| 179 |
-
"eval_entity_precision": 0.6474090741872752,
|
| 180 |
-
"eval_entity_recall": 0.8761570301805619,
|
| 181 |
-
"eval_loss": 0.10319036990404129,
|
| 182 |
-
"eval_runtime": 218.0048,
|
| 183 |
-
"eval_samples_per_second": 1834.822,
|
| 184 |
-
"eval_steps_per_second": 28.669,
|
| 185 |
-
"step": 700
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 0.38382804503582396,
|
| 189 |
-
"grad_norm": 0.33241644501686096,
|
| 190 |
-
"learning_rate": 2.437878084696063e-05,
|
| 191 |
-
"loss": 0.1135,
|
| 192 |
-
"step": 750
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 0.4094165813715456,
|
| 196 |
-
"grad_norm": 0.25659117102622986,
|
| 197 |
-
"learning_rate": 2.426675383443775e-05,
|
| 198 |
-
"loss": 0.1096,
|
| 199 |
-
"step": 800
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 0.4094165813715456,
|
| 203 |
-
"eval_entity_f1": 0.7338641401753581,
|
| 204 |
-
"eval_entity_precision": 0.6539984330176954,
|
| 205 |
-
"eval_entity_recall": 0.8741016719900919,
|
| 206 |
-
"eval_loss": 0.10057927668094635,
|
| 207 |
-
"eval_runtime": 216.7356,
|
| 208 |
-
"eval_samples_per_second": 1845.567,
|
| 209 |
-
"eval_steps_per_second": 28.837,
|
| 210 |
-
"step": 800
|
| 211 |
-
},
|
| 212 |
-
{
|
| 213 |
-
"epoch": 0.43500511770726713,
|
| 214 |
-
"grad_norm": 0.33531299233436584,
|
| 215 |
-
"learning_rate": 2.4145747261210484e-05,
|
| 216 |
-
"loss": 0.1077,
|
| 217 |
-
"step": 850
|
| 218 |
-
},
|
| 219 |
-
{
|
| 220 |
-
"epoch": 0.46059365404298874,
|
| 221 |
-
"grad_norm": 0.22903941571712494,
|
| 222 |
-
"learning_rate": 2.4015853471002953e-05,
|
| 223 |
-
"loss": 0.1068,
|
| 224 |
-
"step": 900
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 0.46059365404298874,
|
| 228 |
-
"eval_entity_f1": 0.7275735384662312,
|
| 229 |
-
"eval_entity_precision": 0.6474825783025171,
|
| 230 |
-
"eval_entity_recall": 0.8750162961997262,
|
| 231 |
-
"eval_loss": 0.10151632875204086,
|
| 232 |
-
"eval_runtime": 217.3217,
|
| 233 |
-
"eval_samples_per_second": 1840.589,
|
| 234 |
-
"eval_steps_per_second": 28.759,
|
| 235 |
-
"step": 900
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 0.48618219037871035,
|
| 239 |
-
"grad_norm": 0.2852090895175934,
|
| 240 |
-
"learning_rate": 2.387717158963955e-05,
|
| 241 |
-
"loss": 0.1071,
|
| 242 |
-
"step": 950
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 0.5117707267144319,
|
| 246 |
-
"grad_norm": 0.2822493314743042,
|
| 247 |
-
"learning_rate": 2.3729807449399073e-05,
|
| 248 |
-
"loss": 0.1029,
|
| 249 |
-
"step": 1000
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.5117707267144319,
|
| 253 |
-
"eval_entity_f1": 0.7221577453080383,
|
| 254 |
-
"eval_entity_precision": 0.6427698580390063,
|
| 255 |
-
"eval_entity_recall": 0.8804612639332507,
|
| 256 |
-
"eval_loss": 0.10289132595062256,
|
| 257 |
-
"eval_runtime": 217.3919,
|
| 258 |
-
"eval_samples_per_second": 1839.995,
|
| 259 |
-
"eval_steps_per_second": 28.75,
|
| 260 |
-
"step": 1000
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"epoch": 0.5373592630501536,
|
| 264 |
-
"grad_norm": 0.2739166021347046,
|
| 265 |
-
"learning_rate": 2.3573873508250943e-05,
|
| 266 |
-
"loss": 0.106,
|
| 267 |
-
"step": 1050
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 0.5629477993858751,
|
| 271 |
-
"grad_norm": 0.2460411638021469,
|
| 272 |
-
"learning_rate": 2.340948876403519e-05,
|
| 273 |
-
"loss": 0.1061,
|
| 274 |
-
"step": 1100
|
| 275 |
-
},
|
| 276 |
-
{
|
| 277 |
-
"epoch": 0.5629477993858751,
|
| 278 |
-
"eval_entity_f1": 0.71621057747755,
|
| 279 |
-
"eval_entity_precision": 0.6257511574094254,
|
| 280 |
-
"eval_entity_recall": 0.8857575288442735,
|
| 281 |
-
"eval_loss": 0.10222392529249191,
|
| 282 |
-
"eval_runtime": 217.2994,
|
| 283 |
-
"eval_samples_per_second": 1840.778,
|
| 284 |
-
"eval_steps_per_second": 28.762,
|
| 285 |
-
"step": 1100
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 0.5885363357215967,
|
| 289 |
-
"grad_norm": 0.261122465133667,
|
| 290 |
-
"learning_rate": 2.323677866365164e-05,
|
| 291 |
-
"loss": 0.1031,
|
| 292 |
-
"step": 1150
|
| 293 |
-
},
|
| 294 |
-
{
|
| 295 |
-
"epoch": 0.6141248720573184,
|
| 296 |
-
"grad_norm": 0.5882133841514587,
|
| 297 |
-
"learning_rate": 2.3055875007327647e-05,
|
| 298 |
-
"loss": 0.1053,
|
| 299 |
-
"step": 1200
|
| 300 |
-
},
|
| 301 |
-
{
|
| 302 |
-
"epoch": 0.6141248720573184,
|
| 303 |
-
"eval_entity_f1": 0.7285411257555304,
|
| 304 |
-
"eval_entity_precision": 0.6473905842385259,
|
| 305 |
-
"eval_entity_recall": 0.8782123883710319,
|
| 306 |
-
"eval_loss": 0.09962841868400574,
|
| 307 |
-
"eval_runtime": 217.0704,
|
| 308 |
-
"eval_samples_per_second": 1842.72,
|
| 309 |
-
"eval_steps_per_second": 28.793,
|
| 310 |
-
"step": 1200
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"epoch": 0.6397134083930399,
|
| 314 |
-
"grad_norm": 0.24729904532432556,
|
| 315 |
-
"learning_rate": 2.286691584803743e-05,
|
| 316 |
-
"loss": 0.1026,
|
| 317 |
-
"step": 1250
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"epoch": 0.6653019447287615,
|
| 321 |
-
"grad_norm": 0.22042767703533173,
|
| 322 |
-
"learning_rate": 2.267004538614969e-05,
|
| 323 |
-
"loss": 0.1016,
|
| 324 |
-
"step": 1300
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 0.6653019447287615,
|
| 328 |
-
"eval_entity_f1": 0.7348005576281786,
|
| 329 |
-
"eval_entity_precision": 0.6562706240432347,
|
| 330 |
-
"eval_entity_recall": 0.8809745942246269,
|
| 331 |
-
"eval_loss": 0.097366563975811,
|
| 332 |
-
"eval_runtime": 216.5805,
|
| 333 |
-
"eval_samples_per_second": 1846.888,
|
| 334 |
-
"eval_steps_per_second": 28.858,
|
| 335 |
-
"step": 1300
|
| 336 |
-
},
|
| 337 |
-
{
|
| 338 |
-
"epoch": 0.6908904810644831,
|
| 339 |
-
"grad_norm": 0.3312689960002899,
|
| 340 |
-
"learning_rate": 2.2465413859384055e-05,
|
| 341 |
-
"loss": 0.1038,
|
| 342 |
-
"step": 1350
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 0.7164790174002047,
|
| 346 |
-
"grad_norm": 0.2452154904603958,
|
| 347 |
-
"learning_rate": 2.2253177428160162e-05,
|
| 348 |
-
"loss": 0.1015,
|
| 349 |
-
"step": 1400
|
| 350 |
-
},
|
| 351 |
-
{
|
| 352 |
-
"epoch": 0.7164790174002047,
|
| 353 |
-
"eval_entity_f1": 0.7398759871996227,
|
| 354 |
-
"eval_entity_precision": 0.6658170752171122,
|
| 355 |
-
"eval_entity_recall": 0.8744744475588293,
|
| 356 |
-
"eval_loss": 0.09488771855831146,
|
| 357 |
-
"eval_runtime": 216.5515,
|
| 358 |
-
"eval_samples_per_second": 1847.135,
|
| 359 |
-
"eval_steps_per_second": 28.861,
|
| 360 |
-
"step": 1400
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 0.7420675537359263,
|
| 364 |
-
"grad_norm": 0.20783787965774536,
|
| 365 |
-
"learning_rate": 2.2033498056427014e-05,
|
| 366 |
-
"loss": 0.1022,
|
| 367 |
-
"step": 1450
|
| 368 |
-
},
|
| 369 |
-
{
|
| 370 |
-
"epoch": 0.7676560900716479,
|
| 371 |
-
"grad_norm": 0.29527485370635986,
|
| 372 |
-
"learning_rate": 2.1806543388063425e-05,
|
| 373 |
-
"loss": 0.1018,
|
| 374 |
-
"step": 1500
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 0.7676560900716479,
|
| 378 |
-
"eval_entity_f1": 0.7417511032149782,
|
| 379 |
-
"eval_entity_precision": 0.6634728873135575,
|
| 380 |
-
"eval_entity_recall": 0.8743400039110879,
|
| 381 |
-
"eval_loss": 0.09429246187210083,
|
| 382 |
-
"eval_runtime": 216.2683,
|
| 383 |
-
"eval_samples_per_second": 1849.554,
|
| 384 |
-
"eval_steps_per_second": 28.899,
|
| 385 |
-
"step": 1500
|
| 386 |
-
},
|
| 387 |
-
{
|
| 388 |
-
"epoch": 0.7932446264073695,
|
| 389 |
-
"grad_norm": 0.2353503704071045,
|
| 390 |
-
"learning_rate": 2.1572486618944016e-05,
|
| 391 |
-
"loss": 0.1011,
|
| 392 |
-
"step": 1550
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 0.8188331627430911,
|
| 396 |
-
"grad_norm": 0.2825823724269867,
|
| 397 |
-
"learning_rate": 2.133150636476825e-05,
|
| 398 |
-
"loss": 0.1019,
|
| 399 |
-
"step": 1600
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 0.8188331627430911,
|
| 403 |
-
"eval_entity_f1": 0.729570467525232,
|
| 404 |
-
"eval_entity_precision": 0.6470378701094908,
|
| 405 |
-
"eval_entity_recall": 0.8827081024705039,
|
| 406 |
-
"eval_loss": 0.09685087949037552,
|
| 407 |
-
"eval_runtime": 216.9111,
|
| 408 |
-
"eval_samples_per_second": 1844.073,
|
| 409 |
-
"eval_steps_per_second": 28.814,
|
| 410 |
-
"step": 1600
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 0.8444216990788127,
|
| 414 |
-
"grad_norm": 0.275238573551178,
|
| 415 |
-
"learning_rate": 2.108378652475348e-05,
|
| 416 |
-
"loss": 0.1024,
|
| 417 |
-
"step": 1650
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 0.8700102354145343,
|
| 421 |
-
"grad_norm": 0.2800333797931671,
|
| 422 |
-
"learning_rate": 2.082951614129597e-05,
|
| 423 |
-
"loss": 0.101,
|
| 424 |
-
"step": 1700
|
| 425 |
-
},
|
| 426 |
-
{
|
| 427 |
-
"epoch": 0.8700102354145343,
|
| 428 |
-
"eval_entity_f1": 0.7353454057986332,
|
| 429 |
-
"eval_entity_precision": 0.652794317591099,
|
| 430 |
-
"eval_entity_recall": 0.8812129261456229,
|
| 431 |
-
"eval_loss": 0.09363909065723419,
|
| 432 |
-
"eval_runtime": 216.9988,
|
| 433 |
-
"eval_samples_per_second": 1843.329,
|
| 434 |
-
"eval_steps_per_second": 28.802,
|
| 435 |
-
"step": 1700
|
| 436 |
-
},
|
| 437 |
-
{
|
| 438 |
-
"epoch": 0.8955987717502559,
|
| 439 |
-
"grad_norm": 0.2639468312263489,
|
| 440 |
-
"learning_rate": 2.0568889255706997e-05,
|
| 441 |
-
"loss": 0.1002,
|
| 442 |
-
"step": 1750
|
| 443 |
-
},
|
| 444 |
-
{
|
| 445 |
-
"epoch": 0.9211873080859775,
|
| 446 |
-
"grad_norm": 0.20764870941638947,
|
| 447 |
-
"learning_rate": 2.030210476013416e-05,
|
| 448 |
-
"loss": 0.0954,
|
| 449 |
-
"step": 1800
|
| 450 |
-
},
|
| 451 |
-
{
|
| 452 |
-
"epoch": 0.9211873080859775,
|
| 453 |
-
"eval_entity_f1": 0.7371102233664769,
|
| 454 |
-
"eval_entity_precision": 0.6580770648318734,
|
| 455 |
-
"eval_entity_recall": 0.8760388827325468,
|
| 456 |
-
"eval_loss": 0.0933997854590416,
|
| 457 |
-
"eval_runtime": 216.2115,
|
| 458 |
-
"eval_samples_per_second": 1850.04,
|
| 459 |
-
"eval_steps_per_second": 28.907,
|
| 460 |
-
"step": 1800
|
| 461 |
-
},
|
| 462 |
-
{
|
| 463 |
-
"epoch": 0.946775844421699,
|
| 464 |
-
"grad_norm": 0.26750797033309937,
|
| 465 |
-
"learning_rate": 2.002936624578084e-05,
|
| 466 |
-
"loss": 0.097,
|
| 467 |
-
"step": 1850
|
| 468 |
-
},
|
| 469 |
-
{
|
| 470 |
-
"epoch": 0.9723643807574207,
|
| 471 |
-
"grad_norm": 0.2236221879720688,
|
| 472 |
-
"learning_rate": 1.9750881847539672e-05,
|
| 473 |
-
"loss": 0.0996,
|
| 474 |
-
"step": 1900
|
| 475 |
-
},
|
| 476 |
-
{
|
| 477 |
-
"epoch": 0.9723643807574207,
|
| 478 |
-
"eval_entity_f1": 0.7403290961259323,
|
| 479 |
-
"eval_entity_precision": 0.6670676615171398,
|
| 480 |
-
"eval_entity_recall": 0.8754053679681898,
|
| 481 |
-
"eval_loss": 0.0930691733956337,
|
| 482 |
-
"eval_runtime": 217.201,
|
| 483 |
-
"eval_samples_per_second": 1841.612,
|
| 484 |
-
"eval_steps_per_second": 28.775,
|
| 485 |
-
"step": 1900
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"epoch": 0.9979529170931423,
|
| 489 |
-
"grad_norm": 0.2840637266635895,
|
| 490 |
-
"learning_rate": 1.9466864085158615e-05,
|
| 491 |
-
"loss": 0.1001,
|
| 492 |
-
"step": 1950
|
| 493 |
-
},
|
| 494 |
-
{
|
| 495 |
-
"epoch": 1.0235414534288638,
|
| 496 |
-
"grad_norm": 0.2238200604915619,
|
| 497 |
-
"learning_rate": 1.9177529701060805e-05,
|
| 498 |
-
"loss": 0.0942,
|
| 499 |
-
"step": 2000
|
| 500 |
-
},
|
| 501 |
-
{
|
| 502 |
-
"epoch": 1.0235414534288638,
|
| 503 |
-
"eval_entity_f1": 0.7392205751307963,
|
| 504 |
-
"eval_entity_precision": 0.6629398923410562,
|
| 505 |
-
"eval_entity_recall": 0.8785199791408643,
|
| 506 |
-
"eval_loss": 0.0928674191236496,
|
| 507 |
-
"eval_runtime": 216.5147,
|
| 508 |
-
"eval_samples_per_second": 1847.45,
|
| 509 |
-
"eval_steps_per_second": 28.866,
|
| 510 |
-
"step": 2000
|
| 511 |
-
},
|
| 512 |
-
{
|
| 513 |
-
"epoch": 1.0491299897645854,
|
| 514 |
-
"grad_norm": 0.2200816422700882,
|
| 515 |
-
"learning_rate": 1.888309949494192e-05,
|
| 516 |
-
"loss": 0.0971,
|
| 517 |
-
"step": 2050
|
| 518 |
-
},
|
| 519 |
-
{
|
| 520 |
-
"epoch": 1.0747185261003072,
|
| 521 |
-
"grad_norm": 0.2416696548461914,
|
| 522 |
-
"learning_rate": 1.8583798155271386e-05,
|
| 523 |
-
"loss": 0.0943,
|
| 524 |
-
"step": 2100
|
| 525 |
-
},
|
| 526 |
-
{
|
| 527 |
-
"epoch": 1.0747185261003072,
|
| 528 |
-
"eval_entity_f1": 0.7417569335572907,
|
| 529 |
-
"eval_entity_precision": 0.6657956342235335,
|
| 530 |
-
"eval_entity_recall": 0.8759614757838472,
|
| 531 |
-
"eval_loss": 0.09199530631303787,
|
| 532 |
-
"eval_runtime": 216.9146,
|
| 533 |
-
"eval_samples_per_second": 1844.044,
|
| 534 |
-
"eval_steps_per_second": 28.813,
|
| 535 |
-
"step": 2100
|
| 536 |
-
},
|
| 537 |
-
{
|
| 538 |
-
"epoch": 1.1003070624360287,
|
| 539 |
-
"grad_norm": 0.22305117547512054,
|
| 540 |
-
"learning_rate": 1.827985408782587e-05,
|
| 541 |
-
"loss": 0.0929,
|
| 542 |
-
"step": 2150
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 1.1258955987717503,
|
| 546 |
-
"grad_norm": 0.238594189286232,
|
| 547 |
-
"learning_rate": 1.7971499241386046e-05,
|
| 548 |
-
"loss": 0.0923,
|
| 549 |
-
"step": 2200
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 1.1258955987717503,
|
| 553 |
-
"eval_entity_f1": 0.7342133375205078,
|
| 554 |
-
"eval_entity_precision": 0.6547647133099047,
|
| 555 |
-
"eval_entity_recall": 0.8795242324489929,
|
| 556 |
-
"eval_loss": 0.09313961118459702,
|
| 557 |
-
"eval_runtime": 216.7658,
|
| 558 |
-
"eval_samples_per_second": 1845.309,
|
| 559 |
-
"eval_steps_per_second": 28.833,
|
| 560 |
-
"step": 2200
|
| 561 |
}
|
| 562 |
],
|
| 563 |
"logging_steps": 50,
|
| 564 |
-
"max_steps":
|
| 565 |
"num_input_tokens_seen": 0,
|
| 566 |
"num_train_epochs": 3,
|
| 567 |
"save_steps": 100,
|
|
@@ -572,12 +47,12 @@
|
|
| 572 |
"should_evaluate": false,
|
| 573 |
"should_log": false,
|
| 574 |
"should_save": true,
|
| 575 |
-
"should_training_stop":
|
| 576 |
},
|
| 577 |
"attributes": {}
|
| 578 |
}
|
| 579 |
},
|
| 580 |
-
"total_flos":
|
| 581 |
"train_batch_size": 256,
|
| 582 |
"trial_name": null,
|
| 583 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 100,
|
| 3 |
+
"best_metric": 0.6188621659702391,
|
| 4 |
+
"best_model_checkpoint": "model/checkpoint-100",
|
| 5 |
+
"epoch": 0.025595085743537242,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.012797542871768621,
|
| 14 |
+
"grad_norm": 9.050909996032715,
|
| 15 |
+
"learning_rate": 3.480113636363636e-06,
|
| 16 |
+
"loss": 2.0533,
|
| 17 |
"step": 50
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.025595085743537242,
|
| 21 |
+
"grad_norm": 0.4976651966571808,
|
| 22 |
+
"learning_rate": 7.031250000000001e-06,
|
| 23 |
+
"loss": 0.4441,
|
| 24 |
"step": 100
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.025595085743537242,
|
| 28 |
+
"eval_entity_f1": 0.6188621659702391,
|
| 29 |
+
"eval_entity_precision": 0.5423644511336975,
|
| 30 |
+
"eval_entity_recall": 0.7347582104885526,
|
| 31 |
+
"eval_loss": 0.2756767272949219,
|
| 32 |
+
"eval_runtime": 476.506,
|
| 33 |
+
"eval_samples_per_second": 1678.888,
|
| 34 |
+
"eval_steps_per_second": 26.233,
|
| 35 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
}
|
| 37 |
],
|
| 38 |
"logging_steps": 50,
|
| 39 |
+
"max_steps": 11721,
|
| 40 |
"num_input_tokens_seen": 0,
|
| 41 |
"num_train_epochs": 3,
|
| 42 |
"save_steps": 100,
|
|
|
|
| 47 |
"should_evaluate": false,
|
| 48 |
"should_log": false,
|
| 49 |
"should_save": true,
|
| 50 |
+
"should_training_stop": false
|
| 51 |
},
|
| 52 |
"attributes": {}
|
| 53 |
}
|
| 54 |
},
|
| 55 |
+
"total_flos": 1.2695778908700672e+16,
|
| 56 |
"train_batch_size": 256,
|
| 57 |
"trial_name": null,
|
| 58 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5905
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:251e5d533273f92c9e82d56f2e883d5984e73d18e9b16c4f83a9e06c9de248fb
|
| 3 |
size 5905
|