Training in progress, step 11250, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
|
@@ -30,15 +30,15 @@
|
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
|
|
|
|
|
|
| 33 |
"w2",
|
|
|
|
| 34 |
"in_proj",
|
| 35 |
-
"q_proj",
|
| 36 |
-
"w1",
|
| 37 |
"k_proj",
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"out_proj"
|
| 41 |
-
"w3"
|
| 42 |
],
|
| 43 |
"target_parameters": null,
|
| 44 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 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 |
+
"out_proj"
|
|
|
|
| 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 sha256:30a9659336af14d60029333b18053f0d046106d149708bc639b1c2cdeacdc7af
|
| 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 sha256:22c9df3d0ab228782575e04322cfce96dfe16232adcd4a01c933aedcc9263046
|
| 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 sha256:5798918f25c946f05fb86c2b99ef635ca10209a90d5d35d0db43b5afb20b95a5
|
| 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 sha256:40e43d7058a98d7a61c3753db201831793bedd0b8abb30a9a89dc8a855304a43
|
| 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:d956e4d8841814e4beccde84734accda161421cf76ae832235ffac475edbcc61
|
| 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,
|
|
@@ -11231,6 +11231,528 @@
|
|
| 11231 |
"eval_samples_per_second": 5.851,
|
| 11232 |
"eval_steps_per_second": 1.464,
|
| 11233 |
"step": 10750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11234 |
}
|
| 11235 |
],
|
| 11236 |
"logging_steps": 10,
|
|
@@ -11250,7 +11772,7 @@
|
|
| 11250 |
"attributes": {}
|
| 11251 |
}
|
| 11252 |
},
|
| 11253 |
-
"total_flos": 9.
|
| 11254 |
"train_batch_size": 2,
|
| 11255 |
"trial_name": null,
|
| 11256 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 11250,
|
| 3 |
+
"best_metric": 0.28531700372695923,
|
| 4 |
+
"best_model_checkpoint": "./lfm25-kodcode-lora/checkpoint-11250",
|
| 5 |
+
"epoch": 0.8522888691073695,
|
| 6 |
"eval_steps": 250,
|
| 7 |
+
"global_step": 11250,
|
| 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 |
+
"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 |
+
"entropy": 0.32097633071243764,
|
| 11498 |
+
"epoch": 0.8341067065664123,
|
| 11499 |
+
"grad_norm": 0.4701482057571411,
|
| 11500 |
+
"learning_rate": 7.052591461235453e-06,
|
| 11501 |
+
"loss": 0.37491984367370607,
|
| 11502 |
+
"mean_token_accuracy": 0.8957624956965446,
|
| 11503 |
+
"num_tokens": 2599721.0,
|
| 11504 |
+
"step": 11010
|
| 11505 |
+
},
|
| 11506 |
+
{
|
| 11507 |
+
"entropy": 0.3161700405180454,
|
| 11508 |
+
"epoch": 0.8348642966722855,
|
| 11509 |
+
"grad_norm": 0.37062007188796997,
|
| 11510 |
+
"learning_rate": 6.989900903376534e-06,
|
| 11511 |
+
"loss": 0.37365403175354006,
|
| 11512 |
+
"mean_token_accuracy": 0.8983507692813874,
|
| 11513 |
+
"num_tokens": 2704511.0,
|
| 11514 |
+
"step": 11020
|
| 11515 |
+
},
|
| 11516 |
+
{
|
| 11517 |
+
"entropy": 0.3192948242649436,
|
| 11518 |
+
"epoch": 0.8356218867781586,
|
| 11519 |
+
"grad_norm": 0.4017787277698517,
|
| 11520 |
+
"learning_rate": 6.927469273292819e-06,
|
| 11521 |
+
"loss": 0.3574330806732178,
|
| 11522 |
+
"mean_token_accuracy": 0.8968805193901062,
|
| 11523 |
+
"num_tokens": 2810832.0,
|
| 11524 |
+
"step": 11030
|
| 11525 |
+
},
|
| 11526 |
+
{
|
| 11527 |
+
"entropy": 0.3310425169765949,
|
| 11528 |
+
"epoch": 0.8363794768840319,
|
| 11529 |
+
"grad_norm": 0.466722309589386,
|
| 11530 |
+
"learning_rate": 6.865296946832866e-06,
|
| 11531 |
+
"loss": 0.3679776668548584,
|
| 11532 |
+
"mean_token_accuracy": 0.8972247004508972,
|
| 11533 |
+
"num_tokens": 2913394.0,
|
| 11534 |
+
"step": 11040
|
| 11535 |
+
},
|
| 11536 |
+
{
|
| 11537 |
+
"entropy": 0.3021887818351388,
|
| 11538 |
+
"epoch": 0.8371370669899051,
|
| 11539 |
+
"grad_norm": 0.33357468247413635,
|
| 11540 |
+
"learning_rate": 6.8033842982841545e-06,
|
| 11541 |
+
"loss": 0.3556036949157715,
|
| 11542 |
+
"mean_token_accuracy": 0.9023103356361389,
|
| 11543 |
+
"num_tokens": 3011528.0,
|
| 11544 |
+
"step": 11050
|
| 11545 |
+
},
|
| 11546 |
+
{
|
| 11547 |
+
"entropy": 0.3188148533925414,
|
| 11548 |
+
"epoch": 0.8378946570957784,
|
| 11549 |
+
"grad_norm": 0.5248581767082214,
|
| 11550 |
+
"learning_rate": 6.741731700370885e-06,
|
| 11551 |
+
"loss": 0.3591402530670166,
|
| 11552 |
+
"mean_token_accuracy": 0.8997363194823265,
|
| 11553 |
+
"num_tokens": 3114520.0,
|
| 11554 |
+
"step": 11060
|
| 11555 |
+
},
|
| 11556 |
+
{
|
| 11557 |
+
"entropy": 0.28566175922751424,
|
| 11558 |
+
"epoch": 0.8386522472016515,
|
| 11559 |
+
"grad_norm": 0.4290429651737213,
|
| 11560 |
+
"learning_rate": 6.680339524251694e-06,
|
| 11561 |
+
"loss": 0.33682057857513426,
|
| 11562 |
+
"mean_token_accuracy": 0.9096178874373436,
|
| 11563 |
+
"num_tokens": 3220100.0,
|
| 11564 |
+
"step": 11070
|
| 11565 |
+
},
|
| 11566 |
+
{
|
| 11567 |
+
"entropy": 0.2704159118235111,
|
| 11568 |
+
"epoch": 0.8394098373075247,
|
| 11569 |
+
"grad_norm": 0.5517525672912598,
|
| 11570 |
+
"learning_rate": 6.619208139517441e-06,
|
| 11571 |
+
"loss": 0.3258359909057617,
|
| 11572 |
+
"mean_token_accuracy": 0.9156906500458717,
|
| 11573 |
+
"num_tokens": 3311139.0,
|
| 11574 |
+
"step": 11080
|
| 11575 |
+
},
|
| 11576 |
+
{
|
| 11577 |
+
"entropy": 0.2802377393469214,
|
| 11578 |
+
"epoch": 0.840167427413398,
|
| 11579 |
+
"grad_norm": 0.43798232078552246,
|
| 11580 |
+
"learning_rate": 6.558337914188989e-06,
|
| 11581 |
+
"loss": 0.31688680648803713,
|
| 11582 |
+
"mean_token_accuracy": 0.9112754926085472,
|
| 11583 |
+
"num_tokens": 3408982.0,
|
| 11584 |
+
"step": 11090
|
| 11585 |
+
},
|
| 11586 |
+
{
|
| 11587 |
+
"entropy": 0.2785337887704372,
|
| 11588 |
+
"epoch": 0.8409250175192712,
|
| 11589 |
+
"grad_norm": 0.48913341760635376,
|
| 11590 |
+
"learning_rate": 6.497729214714959e-06,
|
| 11591 |
+
"loss": 0.33413968086242674,
|
| 11592 |
+
"mean_token_accuracy": 0.9114461779594422,
|
| 11593 |
+
"num_tokens": 3506297.0,
|
| 11594 |
+
"step": 11100
|
| 11595 |
+
},
|
| 11596 |
+
{
|
| 11597 |
+
"entropy": 0.25448127966374157,
|
| 11598 |
+
"epoch": 0.8416826076251445,
|
| 11599 |
+
"grad_norm": 0.6489408612251282,
|
| 11600 |
+
"learning_rate": 6.437382405969572e-06,
|
| 11601 |
+
"loss": 0.3060408115386963,
|
| 11602 |
+
"mean_token_accuracy": 0.9170120373368263,
|
| 11603 |
+
"num_tokens": 3599883.0,
|
| 11604 |
+
"step": 11110
|
| 11605 |
+
},
|
| 11606 |
+
{
|
| 11607 |
+
"entropy": 0.2931193061172962,
|
| 11608 |
+
"epoch": 0.8424401977310176,
|
| 11609 |
+
"grad_norm": 0.39941656589508057,
|
| 11610 |
+
"learning_rate": 6.377297851250396e-06,
|
| 11611 |
+
"loss": 0.34188551902770997,
|
| 11612 |
+
"mean_token_accuracy": 0.9045077741146088,
|
| 11613 |
+
"num_tokens": 3695770.0,
|
| 11614 |
+
"step": 11120
|
| 11615 |
+
},
|
| 11616 |
+
{
|
| 11617 |
+
"entropy": 0.28530145399272444,
|
| 11618 |
+
"epoch": 0.8431977878368908,
|
| 11619 |
+
"grad_norm": 0.5832393169403076,
|
| 11620 |
+
"learning_rate": 6.317475912276205e-06,
|
| 11621 |
+
"loss": 0.3301248073577881,
|
| 11622 |
+
"mean_token_accuracy": 0.9066288366913795,
|
| 11623 |
+
"num_tokens": 3792849.0,
|
| 11624 |
+
"step": 11130
|
| 11625 |
+
},
|
| 11626 |
+
{
|
| 11627 |
+
"entropy": 0.28422479014843705,
|
| 11628 |
+
"epoch": 0.8439553779427641,
|
| 11629 |
+
"grad_norm": 0.5767186284065247,
|
| 11630 |
+
"learning_rate": 6.257916949184772e-06,
|
| 11631 |
+
"loss": 0.34296748638153074,
|
| 11632 |
+
"mean_token_accuracy": 0.9086409032344818,
|
| 11633 |
+
"num_tokens": 3886352.0,
|
| 11634 |
+
"step": 11140
|
| 11635 |
+
},
|
| 11636 |
+
{
|
| 11637 |
+
"entropy": 0.33191717118024827,
|
| 11638 |
+
"epoch": 0.8447129680486373,
|
| 11639 |
+
"grad_norm": 0.31320858001708984,
|
| 11640 |
+
"learning_rate": 6.1986213205307285e-06,
|
| 11641 |
+
"loss": 0.38002519607543944,
|
| 11642 |
+
"mean_token_accuracy": 0.8913838744163514,
|
| 11643 |
+
"num_tokens": 3990242.0,
|
| 11644 |
+
"step": 11150
|
| 11645 |
+
},
|
| 11646 |
+
{
|
| 11647 |
+
"entropy": 0.27569183316081763,
|
| 11648 |
+
"epoch": 0.8454705581545106,
|
| 11649 |
+
"grad_norm": 0.35137414932250977,
|
| 11650 |
+
"learning_rate": 6.139589383283367e-06,
|
| 11651 |
+
"loss": 0.3208441734313965,
|
| 11652 |
+
"mean_token_accuracy": 0.9123941317200661,
|
| 11653 |
+
"num_tokens": 4090031.0,
|
| 11654 |
+
"step": 11160
|
| 11655 |
+
},
|
| 11656 |
+
{
|
| 11657 |
+
"entropy": 0.26733697205781937,
|
| 11658 |
+
"epoch": 0.8462281482603837,
|
| 11659 |
+
"grad_norm": 0.4320410192012787,
|
| 11660 |
+
"learning_rate": 6.08082149282454e-06,
|
| 11661 |
+
"loss": 0.3125286102294922,
|
| 11662 |
+
"mean_token_accuracy": 0.914748401939869,
|
| 11663 |
+
"num_tokens": 4185773.0,
|
| 11664 |
+
"step": 11170
|
| 11665 |
+
},
|
| 11666 |
+
{
|
| 11667 |
+
"entropy": 0.23407292291522025,
|
| 11668 |
+
"epoch": 0.8469857383662569,
|
| 11669 |
+
"grad_norm": 0.48707106709480286,
|
| 11670 |
+
"learning_rate": 6.022318002946492e-06,
|
| 11671 |
+
"loss": 0.2711918830871582,
|
| 11672 |
+
"mean_token_accuracy": 0.9267101764678956,
|
| 11673 |
+
"num_tokens": 4278787.0,
|
| 11674 |
+
"step": 11180
|
| 11675 |
+
},
|
| 11676 |
+
{
|
| 11677 |
+
"entropy": 0.316350325755775,
|
| 11678 |
+
"epoch": 0.8477433284721302,
|
| 11679 |
+
"grad_norm": 0.3188752830028534,
|
| 11680 |
+
"learning_rate": 5.964079265849698e-06,
|
| 11681 |
+
"loss": 0.3772554397583008,
|
| 11682 |
+
"mean_token_accuracy": 0.8990112885832786,
|
| 11683 |
+
"num_tokens": 4385286.0,
|
| 11684 |
+
"step": 11190
|
| 11685 |
+
},
|
| 11686 |
+
{
|
| 11687 |
+
"entropy": 0.28382357601076363,
|
| 11688 |
+
"epoch": 0.8485009185780034,
|
| 11689 |
+
"grad_norm": 0.5237545371055603,
|
| 11690 |
+
"learning_rate": 5.906105632140818e-06,
|
| 11691 |
+
"loss": 0.33560957908630373,
|
| 11692 |
+
"mean_token_accuracy": 0.9108323022723198,
|
| 11693 |
+
"num_tokens": 4478235.0,
|
| 11694 |
+
"step": 11200
|
| 11695 |
+
},
|
| 11696 |
+
{
|
| 11697 |
+
"entropy": 0.29501939918845893,
|
| 11698 |
+
"epoch": 0.8492585086838765,
|
| 11699 |
+
"grad_norm": 0.4553075134754181,
|
| 11700 |
+
"learning_rate": 5.848397450830539e-06,
|
| 11701 |
+
"loss": 0.3474492073059082,
|
| 11702 |
+
"mean_token_accuracy": 0.9073790535330772,
|
| 11703 |
+
"num_tokens": 4574842.0,
|
| 11704 |
+
"step": 11210
|
| 11705 |
+
},
|
| 11706 |
+
{
|
| 11707 |
+
"entropy": 0.2461070492863655,
|
| 11708 |
+
"epoch": 0.8500160987897498,
|
| 11709 |
+
"grad_norm": 0.3291778564453125,
|
| 11710 |
+
"learning_rate": 5.7909550693314665e-06,
|
| 11711 |
+
"loss": 0.2918540477752686,
|
| 11712 |
+
"mean_token_accuracy": 0.9265199154615402,
|
| 11713 |
+
"num_tokens": 4661233.0,
|
| 11714 |
+
"step": 11220
|
| 11715 |
+
},
|
| 11716 |
+
{
|
| 11717 |
+
"entropy": 0.2952361168339849,
|
| 11718 |
+
"epoch": 0.850773688895623,
|
| 11719 |
+
"grad_norm": 0.5359086990356445,
|
| 11720 |
+
"learning_rate": 5.73377883345606e-06,
|
| 11721 |
+
"loss": 0.3461754560470581,
|
| 11722 |
+
"mean_token_accuracy": 0.9084222391247749,
|
| 11723 |
+
"num_tokens": 4753367.0,
|
| 11724 |
+
"step": 11230
|
| 11725 |
+
},
|
| 11726 |
+
{
|
| 11727 |
+
"entropy": 0.28638926018029454,
|
| 11728 |
+
"epoch": 0.8515312790014963,
|
| 11729 |
+
"grad_norm": 0.4929027855396271,
|
| 11730 |
+
"learning_rate": 5.676869087414544e-06,
|
| 11731 |
+
"loss": 0.3351025104522705,
|
| 11732 |
+
"mean_token_accuracy": 0.9095506638288497,
|
| 11733 |
+
"num_tokens": 4846891.0,
|
| 11734 |
+
"step": 11240
|
| 11735 |
+
},
|
| 11736 |
+
{
|
| 11737 |
+
"entropy": 0.2919112669304013,
|
| 11738 |
+
"epoch": 0.8522888691073695,
|
| 11739 |
+
"grad_norm": 0.43144306540489197,
|
| 11740 |
+
"learning_rate": 5.6202261738128145e-06,
|
| 11741 |
+
"loss": 0.3436851739883423,
|
| 11742 |
+
"mean_token_accuracy": 0.908247809112072,
|
| 11743 |
+
"num_tokens": 4945534.0,
|
| 11744 |
+
"step": 11250
|
| 11745 |
+
},
|
| 11746 |
+
{
|
| 11747 |
+
"epoch": 0.8522888691073695,
|
| 11748 |
+
"eval_entropy": 0.28951325608689465,
|
| 11749 |
+
"eval_loss": 0.28531700372695923,
|
| 11750 |
+
"eval_mean_token_accuracy": 0.907498625333836,
|
| 11751 |
+
"eval_num_tokens": 4945534.0,
|
| 11752 |
+
"eval_runtime": 363.816,
|
| 11753 |
+
"eval_samples_per_second": 5.866,
|
| 11754 |
+
"eval_steps_per_second": 1.468,
|
| 11755 |
+
"step": 11250
|
| 11756 |
}
|
| 11757 |
],
|
| 11758 |
"logging_steps": 10,
|
|
|
|
| 11772 |
"attributes": {}
|
| 11773 |
}
|
| 11774 |
},
|
| 11775 |
+
"total_flos": 9.758203209695887e+17,
|
| 11776 |
"train_batch_size": 2,
|
| 11777 |
"trial_name": null,
|
| 11778 |
"trial_params": null
|