Training in progress, step 11250
Browse files- adapter_model.safetensors +1 -1
- last-checkpoint/adapter_config.json +6 -6
- last-checkpoint/adapter_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/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +6 -267
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 88891320
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30a9659336af14d60029333b18053f0d046106d149708bc639b1c2cdeacdc7af
|
| 3 |
size 88891320
|
last-checkpoint/adapter_config.json
CHANGED
|
@@ -30,15 +30,15 @@
|
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
| 33 |
-
"w3",
|
| 34 |
-
"o_proj",
|
| 35 |
"w2",
|
| 36 |
-
"v_proj",
|
| 37 |
"in_proj",
|
| 38 |
-
"k_proj",
|
| 39 |
-
"w1",
|
| 40 |
"q_proj",
|
| 41 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
],
|
| 43 |
"target_parameters": null,
|
| 44 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
|
|
|
|
|
|
| 33 |
"w2",
|
|
|
|
| 34 |
"in_proj",
|
|
|
|
|
|
|
| 35 |
"q_proj",
|
| 36 |
+
"w1",
|
| 37 |
+
"k_proj",
|
| 38 |
+
"v_proj",
|
| 39 |
+
"o_proj",
|
| 40 |
+
"out_proj",
|
| 41 |
+
"w3"
|
| 42 |
],
|
| 43 |
"target_parameters": null,
|
| 44 |
"task_type": "CAUSAL_LM",
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 88891320
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d59a26df247a9b3bd089944c699df5332df994dda9c303c5de94dc6e76616eb9
|
| 3 |
size 88891320
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 177891851
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca1ac60d2a733c3f6db08f04b7d8d4f6547bd586f287c155721433e984edc7db
|
| 3 |
size 177891851
|
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 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6b6744a57f42273e871a115e82b156c17e0c93e4839b3bac6dc6f53f8600e91
|
| 3 |
size 14917
|
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 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79bfae6c501e0b8cd471ca11801529a5af1b0faa0b363fbd03730ca881075ee9
|
| 3 |
size 14917
|
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:cb1f23b3450b5ea7f3c2c09c828367f5357644ec38f3b3af648f0d2bda902fef
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "./lfm25-kodcode-lora/checkpoint-
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 250,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -11231,267 +11231,6 @@
|
|
| 11231 |
"eval_samples_per_second": 5.851,
|
| 11232 |
"eval_steps_per_second": 1.464,
|
| 11233 |
"step": 10750
|
| 11234 |
-
},
|
| 11235 |
-
{
|
| 11236 |
-
"entropy": 0.2615930700674653,
|
| 11237 |
-
"epoch": 0.8151669539195818,
|
| 11238 |
-
"grad_norm": 0.4948700964450836,
|
| 11239 |
-
"learning_rate": 8.70287588830654e-06,
|
| 11240 |
-
"loss": 0.30023128986358644,
|
| 11241 |
-
"mean_token_accuracy": 0.9172126367688179,
|
| 11242 |
-
"num_tokens": 95394.0,
|
| 11243 |
-
"step": 10760
|
| 11244 |
-
},
|
| 11245 |
-
{
|
| 11246 |
-
"entropy": 0.26154228337109087,
|
| 11247 |
-
"epoch": 0.815924544025455,
|
| 11248 |
-
"grad_norm": 0.3987369239330292,
|
| 11249 |
-
"learning_rate": 8.633838805669543e-06,
|
| 11250 |
-
"loss": 0.3083802223205566,
|
| 11251 |
-
"mean_token_accuracy": 0.916927844285965,
|
| 11252 |
-
"num_tokens": 198965.0,
|
| 11253 |
-
"step": 10770
|
| 11254 |
-
},
|
| 11255 |
-
{
|
| 11256 |
-
"entropy": 0.29399398546665906,
|
| 11257 |
-
"epoch": 0.8166821341313283,
|
| 11258 |
-
"grad_norm": 0.4157302677631378,
|
| 11259 |
-
"learning_rate": 8.565050754034847e-06,
|
| 11260 |
-
"loss": 0.330983567237854,
|
| 11261 |
-
"mean_token_accuracy": 0.907181803882122,
|
| 11262 |
-
"num_tokens": 300936.0,
|
| 11263 |
-
"step": 10780
|
| 11264 |
-
},
|
| 11265 |
-
{
|
| 11266 |
-
"entropy": 0.2811663061380386,
|
| 11267 |
-
"epoch": 0.8174397242372015,
|
| 11268 |
-
"grad_norm": 0.41286197304725647,
|
| 11269 |
-
"learning_rate": 8.496512147517688e-06,
|
| 11270 |
-
"loss": 0.3124821662902832,
|
| 11271 |
-
"mean_token_accuracy": 0.9098848760128021,
|
| 11272 |
-
"num_tokens": 407545.0,
|
| 11273 |
-
"step": 10790
|
| 11274 |
-
},
|
| 11275 |
-
{
|
| 11276 |
-
"entropy": 0.29347006008028986,
|
| 11277 |
-
"epoch": 0.8181973143430746,
|
| 11278 |
-
"grad_norm": 0.4638175666332245,
|
| 11279 |
-
"learning_rate": 8.428223398731588e-06,
|
| 11280 |
-
"loss": 0.32779746055603026,
|
| 11281 |
-
"mean_token_accuracy": 0.9062278017401695,
|
| 11282 |
-
"num_tokens": 511306.0,
|
| 11283 |
-
"step": 10800
|
| 11284 |
-
},
|
| 11285 |
-
{
|
| 11286 |
-
"entropy": 0.3169729994609952,
|
| 11287 |
-
"epoch": 0.8189549044489479,
|
| 11288 |
-
"grad_norm": 0.6172231435775757,
|
| 11289 |
-
"learning_rate": 8.360184918785902e-06,
|
| 11290 |
-
"loss": 0.3641566038131714,
|
| 11291 |
-
"mean_token_accuracy": 0.8966098591685295,
|
| 11292 |
-
"num_tokens": 615936.0,
|
| 11293 |
-
"step": 10810
|
| 11294 |
-
},
|
| 11295 |
-
{
|
| 11296 |
-
"entropy": 0.28694524206221106,
|
| 11297 |
-
"epoch": 0.8197124945548211,
|
| 11298 |
-
"grad_norm": 0.5250155925750732,
|
| 11299 |
-
"learning_rate": 8.292397117283318e-06,
|
| 11300 |
-
"loss": 0.3268028974533081,
|
| 11301 |
-
"mean_token_accuracy": 0.9117160573601722,
|
| 11302 |
-
"num_tokens": 707912.0,
|
| 11303 |
-
"step": 10820
|
| 11304 |
-
},
|
| 11305 |
-
{
|
| 11306 |
-
"entropy": 0.2993797710165381,
|
| 11307 |
-
"epoch": 0.8204700846606944,
|
| 11308 |
-
"grad_norm": 0.450602650642395,
|
| 11309 |
-
"learning_rate": 8.224860402317398e-06,
|
| 11310 |
-
"loss": 0.3751563549041748,
|
| 11311 |
-
"mean_token_accuracy": 0.9021484076976776,
|
| 11312 |
-
"num_tokens": 797927.0,
|
| 11313 |
-
"step": 10830
|
| 11314 |
-
},
|
| 11315 |
-
{
|
| 11316 |
-
"entropy": 0.2887501694262028,
|
| 11317 |
-
"epoch": 0.8212276747665676,
|
| 11318 |
-
"grad_norm": 0.3982142210006714,
|
| 11319 |
-
"learning_rate": 8.157575180470139e-06,
|
| 11320 |
-
"loss": 0.3479593276977539,
|
| 11321 |
-
"mean_token_accuracy": 0.9077468276023865,
|
| 11322 |
-
"num_tokens": 904264.0,
|
| 11323 |
-
"step": 10840
|
| 11324 |
-
},
|
| 11325 |
-
{
|
| 11326 |
-
"entropy": 0.30117298644036056,
|
| 11327 |
-
"epoch": 0.8219852648724407,
|
| 11328 |
-
"grad_norm": 0.4184916913509369,
|
| 11329 |
-
"learning_rate": 8.090541856809465e-06,
|
| 11330 |
-
"loss": 0.33893485069274903,
|
| 11331 |
-
"mean_token_accuracy": 0.9050878256559372,
|
| 11332 |
-
"num_tokens": 1007433.0,
|
| 11333 |
-
"step": 10850
|
| 11334 |
-
},
|
| 11335 |
-
{
|
| 11336 |
-
"entropy": 0.30625202376395466,
|
| 11337 |
-
"epoch": 0.822742854978314,
|
| 11338 |
-
"grad_norm": 0.43937817215919495,
|
| 11339 |
-
"learning_rate": 8.02376083488688e-06,
|
| 11340 |
-
"loss": 0.34802818298339844,
|
| 11341 |
-
"mean_token_accuracy": 0.9029570311307907,
|
| 11342 |
-
"num_tokens": 1106432.0,
|
| 11343 |
-
"step": 10860
|
| 11344 |
-
},
|
| 11345 |
-
{
|
| 11346 |
-
"entropy": 0.29251224398612974,
|
| 11347 |
-
"epoch": 0.8235004450841872,
|
| 11348 |
-
"grad_norm": 0.4894697964191437,
|
| 11349 |
-
"learning_rate": 7.957232516734963e-06,
|
| 11350 |
-
"loss": 0.35279672145843505,
|
| 11351 |
-
"mean_token_accuracy": 0.9066073164343834,
|
| 11352 |
-
"num_tokens": 1204980.0,
|
| 11353 |
-
"step": 10870
|
| 11354 |
-
},
|
| 11355 |
-
{
|
| 11356 |
-
"entropy": 0.3121814550831914,
|
| 11357 |
-
"epoch": 0.8242580351900605,
|
| 11358 |
-
"grad_norm": 0.451427698135376,
|
| 11359 |
-
"learning_rate": 7.890957302865e-06,
|
| 11360 |
-
"loss": 0.37927200794219973,
|
| 11361 |
-
"mean_token_accuracy": 0.8981422513723374,
|
| 11362 |
-
"num_tokens": 1305202.0,
|
| 11363 |
-
"step": 10880
|
| 11364 |
-
},
|
| 11365 |
-
{
|
| 11366 |
-
"entropy": 0.29268699828535316,
|
| 11367 |
-
"epoch": 0.8250156252959336,
|
| 11368 |
-
"grad_norm": 0.3992355465888977,
|
| 11369 |
-
"learning_rate": 7.82493559226451e-06,
|
| 11370 |
-
"loss": 0.3250342607498169,
|
| 11371 |
-
"mean_token_accuracy": 0.9062216132879257,
|
| 11372 |
-
"num_tokens": 1407868.0,
|
| 11373 |
-
"step": 10890
|
| 11374 |
-
},
|
| 11375 |
-
{
|
| 11376 |
-
"entropy": 0.36002040691673753,
|
| 11377 |
-
"epoch": 0.8257732154018068,
|
| 11378 |
-
"grad_norm": 0.4525466561317444,
|
| 11379 |
-
"learning_rate": 7.759167782394916e-06,
|
| 11380 |
-
"loss": 0.4119568824768066,
|
| 11381 |
-
"mean_token_accuracy": 0.8839563131332397,
|
| 11382 |
-
"num_tokens": 1513950.0,
|
| 11383 |
-
"step": 10900
|
| 11384 |
-
},
|
| 11385 |
-
{
|
| 11386 |
-
"entropy": 0.30947884283959864,
|
| 11387 |
-
"epoch": 0.8265308055076801,
|
| 11388 |
-
"grad_norm": 0.4585402309894562,
|
| 11389 |
-
"learning_rate": 7.69365426918911e-06,
|
| 11390 |
-
"loss": 0.3610663414001465,
|
| 11391 |
-
"mean_token_accuracy": 0.9016437903046608,
|
| 11392 |
-
"num_tokens": 1613270.0,
|
| 11393 |
-
"step": 10910
|
| 11394 |
-
},
|
| 11395 |
-
{
|
| 11396 |
-
"entropy": 0.29806773774325845,
|
| 11397 |
-
"epoch": 0.8272883956135533,
|
| 11398 |
-
"grad_norm": 0.43951550126075745,
|
| 11399 |
-
"learning_rate": 7.628395447049058e-06,
|
| 11400 |
-
"loss": 0.34964966773986816,
|
| 11401 |
-
"mean_token_accuracy": 0.9043863728642464,
|
| 11402 |
-
"num_tokens": 1710564.0,
|
| 11403 |
-
"step": 10920
|
| 11404 |
-
},
|
| 11405 |
-
{
|
| 11406 |
-
"entropy": 0.27706831842660906,
|
| 11407 |
-
"epoch": 0.8280459857194266,
|
| 11408 |
-
"grad_norm": 0.43634042143821716,
|
| 11409 |
-
"learning_rate": 7.563391708843465e-06,
|
| 11410 |
-
"loss": 0.31148567199707033,
|
| 11411 |
-
"mean_token_accuracy": 0.9122755557298661,
|
| 11412 |
-
"num_tokens": 1804996.0,
|
| 11413 |
-
"step": 10930
|
| 11414 |
-
},
|
| 11415 |
-
{
|
| 11416 |
-
"entropy": 0.33176610227674247,
|
| 11417 |
-
"epoch": 0.8288035758252997,
|
| 11418 |
-
"grad_norm": 0.39294061064720154,
|
| 11419 |
-
"learning_rate": 7.498643445905385e-06,
|
| 11420 |
-
"loss": 0.37499704360961916,
|
| 11421 |
-
"mean_token_accuracy": 0.8953326553106308,
|
| 11422 |
-
"num_tokens": 1914019.0,
|
| 11423 |
-
"step": 10940
|
| 11424 |
-
},
|
| 11425 |
-
{
|
| 11426 |
-
"entropy": 0.2956154864281416,
|
| 11427 |
-
"epoch": 0.8295611659311729,
|
| 11428 |
-
"grad_norm": 0.4650717079639435,
|
| 11429 |
-
"learning_rate": 7.434151048029858e-06,
|
| 11430 |
-
"loss": 0.3409877777099609,
|
| 11431 |
-
"mean_token_accuracy": 0.9076192870736122,
|
| 11432 |
-
"num_tokens": 2009215.0,
|
| 11433 |
-
"step": 10950
|
| 11434 |
-
},
|
| 11435 |
-
{
|
| 11436 |
-
"entropy": 0.30589213948696853,
|
| 11437 |
-
"epoch": 0.8303187560370462,
|
| 11438 |
-
"grad_norm": 0.422702819108963,
|
| 11439 |
-
"learning_rate": 7.369914903471592e-06,
|
| 11440 |
-
"loss": 0.3454046487808228,
|
| 11441 |
-
"mean_token_accuracy": 0.9033974334597588,
|
| 11442 |
-
"num_tokens": 2113318.0,
|
| 11443 |
-
"step": 10960
|
| 11444 |
-
},
|
| 11445 |
-
{
|
| 11446 |
-
"entropy": 0.2733181806281209,
|
| 11447 |
-
"epoch": 0.8310763461429194,
|
| 11448 |
-
"grad_norm": 0.47341540455818176,
|
| 11449 |
-
"learning_rate": 7.305935398942598e-06,
|
| 11450 |
-
"loss": 0.3034660816192627,
|
| 11451 |
-
"mean_token_accuracy": 0.9125015497207641,
|
| 11452 |
-
"num_tokens": 2212212.0,
|
| 11453 |
-
"step": 10970
|
| 11454 |
-
},
|
| 11455 |
-
{
|
| 11456 |
-
"entropy": 0.32005896270275114,
|
| 11457 |
-
"epoch": 0.8318339362487925,
|
| 11458 |
-
"grad_norm": 0.4640633761882782,
|
| 11459 |
-
"learning_rate": 7.2422129196098695e-06,
|
| 11460 |
-
"loss": 0.3682070255279541,
|
| 11461 |
-
"mean_token_accuracy": 0.8993272170424461,
|
| 11462 |
-
"num_tokens": 2309913.0,
|
| 11463 |
-
"step": 10980
|
| 11464 |
-
},
|
| 11465 |
-
{
|
| 11466 |
-
"entropy": 0.29598398655653,
|
| 11467 |
-
"epoch": 0.8325915263546658,
|
| 11468 |
-
"grad_norm": 0.43602728843688965,
|
| 11469 |
-
"learning_rate": 7.178747849093093e-06,
|
| 11470 |
-
"loss": 0.34798197746276854,
|
| 11471 |
-
"mean_token_accuracy": 0.9048758611083031,
|
| 11472 |
-
"num_tokens": 2406011.0,
|
| 11473 |
-
"step": 10990
|
| 11474 |
-
},
|
| 11475 |
-
{
|
| 11476 |
-
"entropy": 0.2882571941241622,
|
| 11477 |
-
"epoch": 0.833349116460539,
|
| 11478 |
-
"grad_norm": 0.3429960608482361,
|
| 11479 |
-
"learning_rate": 7.115540569462254e-06,
|
| 11480 |
-
"loss": 0.31615209579467773,
|
| 11481 |
-
"mean_token_accuracy": 0.9083688676357269,
|
| 11482 |
-
"num_tokens": 2498979.0,
|
| 11483 |
-
"step": 11000
|
| 11484 |
-
},
|
| 11485 |
-
{
|
| 11486 |
-
"epoch": 0.833349116460539,
|
| 11487 |
-
"eval_entropy": 0.2886375365185827,
|
| 11488 |
-
"eval_loss": 0.28569018840789795,
|
| 11489 |
-
"eval_mean_token_accuracy": 0.9073382049017631,
|
| 11490 |
-
"eval_num_tokens": 2498979.0,
|
| 11491 |
-
"eval_runtime": 363.4037,
|
| 11492 |
-
"eval_samples_per_second": 5.872,
|
| 11493 |
-
"eval_steps_per_second": 1.469,
|
| 11494 |
-
"step": 11000
|
| 11495 |
}
|
| 11496 |
],
|
| 11497 |
"logging_steps": 10,
|
|
@@ -11511,7 +11250,7 @@
|
|
| 11511 |
"attributes": {}
|
| 11512 |
}
|
| 11513 |
},
|
| 11514 |
-
"total_flos": 9.
|
| 11515 |
"train_batch_size": 2,
|
| 11516 |
"trial_name": null,
|
| 11517 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 10750,
|
| 3 |
+
"best_metric": 0.28601643443107605,
|
| 4 |
+
"best_model_checkpoint": "./lfm25-kodcode-lora/checkpoint-10750",
|
| 5 |
+
"epoch": 0.8144093638137085,
|
| 6 |
"eval_steps": 250,
|
| 7 |
+
"global_step": 10750,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11231 |
"eval_samples_per_second": 5.851,
|
| 11232 |
"eval_steps_per_second": 1.464,
|
| 11233 |
"step": 10750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11234 |
}
|
| 11235 |
],
|
| 11236 |
"logging_steps": 10,
|
|
|
|
| 11250 |
"attributes": {}
|
| 11251 |
}
|
| 11252 |
},
|
| 11253 |
+
"total_flos": 9.324210024475525e+17,
|
| 11254 |
"train_batch_size": 2,
|
| 11255 |
"trial_name": null,
|
| 11256 |
"trial_params": null
|