Training in progress, step 8000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 613004648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63b8d2f54dcc233ad06ab39430ee3ef4e9969c8462dbe0a0663055814f28088c
|
| 3 |
size 613004648
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1226096954
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4236b0fedc806b4de7d27d910cef5ebb9c225250d3c23afcbea1ab330a679e73
|
| 3 |
size 1226096954
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff2a98b7b58dd272a86869334fd0edf641ab47ceb102b634b242c3ff92151a26
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7a23627952aa878a89c58e1effd3a883c81420a06e0fccd761ecb8b1539b91f
|
| 3 |
size 1000
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 3.
|
| 5 |
"eval_steps": 250,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -5355,6 +5355,770 @@
|
|
| 5355 |
"eval_spearman_manhattan": 0.7671464837523794,
|
| 5356 |
"eval_steps_per_second": 29.806,
|
| 5357 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5358 |
}
|
| 5359 |
],
|
| 5360 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.7488284910965324,
|
| 5 |
"eval_steps": 250,
|
| 6 |
+
"global_step": 8000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 5355 |
"eval_spearman_manhattan": 0.7671464837523794,
|
| 5356 |
"eval_steps_per_second": 29.806,
|
| 5357 |
"step": 7000
|
| 5358 |
+
},
|
| 5359 |
+
{
|
| 5360 |
+
"epoch": 3.2849109653233364,
|
| 5361 |
+
"grad_norm": 1.3316779136657715,
|
| 5362 |
+
"learning_rate": 1.7946930646672916e-05,
|
| 5363 |
+
"loss": 0.1139,
|
| 5364 |
+
"step": 7010
|
| 5365 |
+
},
|
| 5366 |
+
{
|
| 5367 |
+
"epoch": 3.2895970009372073,
|
| 5368 |
+
"grad_norm": 1.3782374858856201,
|
| 5369 |
+
"learning_rate": 1.794400187441425e-05,
|
| 5370 |
+
"loss": 0.1238,
|
| 5371 |
+
"step": 7020
|
| 5372 |
+
},
|
| 5373 |
+
{
|
| 5374 |
+
"epoch": 3.294283036551078,
|
| 5375 |
+
"grad_norm": 1.4582282304763794,
|
| 5376 |
+
"learning_rate": 1.7941073102155578e-05,
|
| 5377 |
+
"loss": 0.1279,
|
| 5378 |
+
"step": 7030
|
| 5379 |
+
},
|
| 5380 |
+
{
|
| 5381 |
+
"epoch": 3.2989690721649483,
|
| 5382 |
+
"grad_norm": 2.3581652641296387,
|
| 5383 |
+
"learning_rate": 1.793814432989691e-05,
|
| 5384 |
+
"loss": 0.118,
|
| 5385 |
+
"step": 7040
|
| 5386 |
+
},
|
| 5387 |
+
{
|
| 5388 |
+
"epoch": 3.303655107778819,
|
| 5389 |
+
"grad_norm": 2.1047656536102295,
|
| 5390 |
+
"learning_rate": 1.793521555763824e-05,
|
| 5391 |
+
"loss": 0.1086,
|
| 5392 |
+
"step": 7050
|
| 5393 |
+
},
|
| 5394 |
+
{
|
| 5395 |
+
"epoch": 3.3083411433926897,
|
| 5396 |
+
"grad_norm": 1.748353123664856,
|
| 5397 |
+
"learning_rate": 1.793228678537957e-05,
|
| 5398 |
+
"loss": 0.1357,
|
| 5399 |
+
"step": 7060
|
| 5400 |
+
},
|
| 5401 |
+
{
|
| 5402 |
+
"epoch": 3.3130271790065606,
|
| 5403 |
+
"grad_norm": 1.905609130859375,
|
| 5404 |
+
"learning_rate": 1.79293580131209e-05,
|
| 5405 |
+
"loss": 0.1239,
|
| 5406 |
+
"step": 7070
|
| 5407 |
+
},
|
| 5408 |
+
{
|
| 5409 |
+
"epoch": 3.317713214620431,
|
| 5410 |
+
"grad_norm": 1.5777533054351807,
|
| 5411 |
+
"learning_rate": 1.7926429240862232e-05,
|
| 5412 |
+
"loss": 0.1179,
|
| 5413 |
+
"step": 7080
|
| 5414 |
+
},
|
| 5415 |
+
{
|
| 5416 |
+
"epoch": 3.3223992502343016,
|
| 5417 |
+
"grad_norm": 1.8429454565048218,
|
| 5418 |
+
"learning_rate": 1.7923500468603562e-05,
|
| 5419 |
+
"loss": 0.1103,
|
| 5420 |
+
"step": 7090
|
| 5421 |
+
},
|
| 5422 |
+
{
|
| 5423 |
+
"epoch": 3.3270852858481725,
|
| 5424 |
+
"grad_norm": 1.601769208908081,
|
| 5425 |
+
"learning_rate": 1.792057169634489e-05,
|
| 5426 |
+
"loss": 0.1282,
|
| 5427 |
+
"step": 7100
|
| 5428 |
+
},
|
| 5429 |
+
{
|
| 5430 |
+
"epoch": 3.331771321462043,
|
| 5431 |
+
"grad_norm": 1.948339581489563,
|
| 5432 |
+
"learning_rate": 1.7917642924086224e-05,
|
| 5433 |
+
"loss": 0.1314,
|
| 5434 |
+
"step": 7110
|
| 5435 |
+
},
|
| 5436 |
+
{
|
| 5437 |
+
"epoch": 3.336457357075914,
|
| 5438 |
+
"grad_norm": 2.035210609436035,
|
| 5439 |
+
"learning_rate": 1.7914714151827554e-05,
|
| 5440 |
+
"loss": 0.1232,
|
| 5441 |
+
"step": 7120
|
| 5442 |
+
},
|
| 5443 |
+
{
|
| 5444 |
+
"epoch": 3.3411433926897844,
|
| 5445 |
+
"grad_norm": 1.3871088027954102,
|
| 5446 |
+
"learning_rate": 1.7911785379568887e-05,
|
| 5447 |
+
"loss": 0.1225,
|
| 5448 |
+
"step": 7130
|
| 5449 |
+
},
|
| 5450 |
+
{
|
| 5451 |
+
"epoch": 3.345829428303655,
|
| 5452 |
+
"grad_norm": 1.9721599817276,
|
| 5453 |
+
"learning_rate": 1.7908856607310216e-05,
|
| 5454 |
+
"loss": 0.1364,
|
| 5455 |
+
"step": 7140
|
| 5456 |
+
},
|
| 5457 |
+
{
|
| 5458 |
+
"epoch": 3.350515463917526,
|
| 5459 |
+
"grad_norm": 2.2410221099853516,
|
| 5460 |
+
"learning_rate": 1.790592783505155e-05,
|
| 5461 |
+
"loss": 0.1277,
|
| 5462 |
+
"step": 7150
|
| 5463 |
+
},
|
| 5464 |
+
{
|
| 5465 |
+
"epoch": 3.3552014995313963,
|
| 5466 |
+
"grad_norm": 1.8568767309188843,
|
| 5467 |
+
"learning_rate": 1.790299906279288e-05,
|
| 5468 |
+
"loss": 0.1114,
|
| 5469 |
+
"step": 7160
|
| 5470 |
+
},
|
| 5471 |
+
{
|
| 5472 |
+
"epoch": 3.3598875351452673,
|
| 5473 |
+
"grad_norm": 2.367185115814209,
|
| 5474 |
+
"learning_rate": 1.790007029053421e-05,
|
| 5475 |
+
"loss": 0.1334,
|
| 5476 |
+
"step": 7170
|
| 5477 |
+
},
|
| 5478 |
+
{
|
| 5479 |
+
"epoch": 3.3645735707591378,
|
| 5480 |
+
"grad_norm": 1.6528865098953247,
|
| 5481 |
+
"learning_rate": 1.789714151827554e-05,
|
| 5482 |
+
"loss": 0.1223,
|
| 5483 |
+
"step": 7180
|
| 5484 |
+
},
|
| 5485 |
+
{
|
| 5486 |
+
"epoch": 3.3692596063730083,
|
| 5487 |
+
"grad_norm": 1.9136816263198853,
|
| 5488 |
+
"learning_rate": 1.789421274601687e-05,
|
| 5489 |
+
"loss": 0.1066,
|
| 5490 |
+
"step": 7190
|
| 5491 |
+
},
|
| 5492 |
+
{
|
| 5493 |
+
"epoch": 3.373945641986879,
|
| 5494 |
+
"grad_norm": 2.2870426177978516,
|
| 5495 |
+
"learning_rate": 1.7891283973758203e-05,
|
| 5496 |
+
"loss": 0.1058,
|
| 5497 |
+
"step": 7200
|
| 5498 |
+
},
|
| 5499 |
+
{
|
| 5500 |
+
"epoch": 3.3786316776007497,
|
| 5501 |
+
"grad_norm": 1.5177735090255737,
|
| 5502 |
+
"learning_rate": 1.7888355201499533e-05,
|
| 5503 |
+
"loss": 0.1179,
|
| 5504 |
+
"step": 7210
|
| 5505 |
+
},
|
| 5506 |
+
{
|
| 5507 |
+
"epoch": 3.3833177132146206,
|
| 5508 |
+
"grad_norm": 2.215899705886841,
|
| 5509 |
+
"learning_rate": 1.7885426429240866e-05,
|
| 5510 |
+
"loss": 0.1321,
|
| 5511 |
+
"step": 7220
|
| 5512 |
+
},
|
| 5513 |
+
{
|
| 5514 |
+
"epoch": 3.388003748828491,
|
| 5515 |
+
"grad_norm": 1.7164250612258911,
|
| 5516 |
+
"learning_rate": 1.7882497656982195e-05,
|
| 5517 |
+
"loss": 0.1111,
|
| 5518 |
+
"step": 7230
|
| 5519 |
+
},
|
| 5520 |
+
{
|
| 5521 |
+
"epoch": 3.3926897844423616,
|
| 5522 |
+
"grad_norm": 2.3435146808624268,
|
| 5523 |
+
"learning_rate": 1.7879568884723525e-05,
|
| 5524 |
+
"loss": 0.1513,
|
| 5525 |
+
"step": 7240
|
| 5526 |
+
},
|
| 5527 |
+
{
|
| 5528 |
+
"epoch": 3.3973758200562325,
|
| 5529 |
+
"grad_norm": 1.6385475397109985,
|
| 5530 |
+
"learning_rate": 1.7876640112464858e-05,
|
| 5531 |
+
"loss": 0.1252,
|
| 5532 |
+
"step": 7250
|
| 5533 |
+
},
|
| 5534 |
+
{
|
| 5535 |
+
"epoch": 3.3973758200562325,
|
| 5536 |
+
"eval_loss": 0.047000955790281296,
|
| 5537 |
+
"eval_pearson_cosine": 0.7888804465638501,
|
| 5538 |
+
"eval_pearson_dot": 0.6256929197655836,
|
| 5539 |
+
"eval_pearson_euclidean": 0.7570957556748965,
|
| 5540 |
+
"eval_pearson_manhattan": 0.7561323835241964,
|
| 5541 |
+
"eval_runtime": 3.4083,
|
| 5542 |
+
"eval_samples_per_second": 440.106,
|
| 5543 |
+
"eval_spearman_cosine": 0.7947042550328448,
|
| 5544 |
+
"eval_spearman_dot": 0.6282838912238756,
|
| 5545 |
+
"eval_spearman_euclidean": 0.7692784528325559,
|
| 5546 |
+
"eval_spearman_manhattan": 0.7683456146298958,
|
| 5547 |
+
"eval_steps_per_second": 27.58,
|
| 5548 |
+
"step": 7250
|
| 5549 |
+
},
|
| 5550 |
+
{
|
| 5551 |
+
"epoch": 3.402061855670103,
|
| 5552 |
+
"grad_norm": 1.5348442792892456,
|
| 5553 |
+
"learning_rate": 1.7873711340206187e-05,
|
| 5554 |
+
"loss": 0.1304,
|
| 5555 |
+
"step": 7260
|
| 5556 |
+
},
|
| 5557 |
+
{
|
| 5558 |
+
"epoch": 3.406747891283974,
|
| 5559 |
+
"grad_norm": 1.854861855506897,
|
| 5560 |
+
"learning_rate": 1.7870782567947517e-05,
|
| 5561 |
+
"loss": 0.1296,
|
| 5562 |
+
"step": 7270
|
| 5563 |
+
},
|
| 5564 |
+
{
|
| 5565 |
+
"epoch": 3.4114339268978444,
|
| 5566 |
+
"grad_norm": 1.5103728771209717,
|
| 5567 |
+
"learning_rate": 1.7867853795688846e-05,
|
| 5568 |
+
"loss": 0.1182,
|
| 5569 |
+
"step": 7280
|
| 5570 |
+
},
|
| 5571 |
+
{
|
| 5572 |
+
"epoch": 3.416119962511715,
|
| 5573 |
+
"grad_norm": 1.4604400396347046,
|
| 5574 |
+
"learning_rate": 1.786492502343018e-05,
|
| 5575 |
+
"loss": 0.1155,
|
| 5576 |
+
"step": 7290
|
| 5577 |
+
},
|
| 5578 |
+
{
|
| 5579 |
+
"epoch": 3.420805998125586,
|
| 5580 |
+
"grad_norm": 1.9087272882461548,
|
| 5581 |
+
"learning_rate": 1.786199625117151e-05,
|
| 5582 |
+
"loss": 0.1265,
|
| 5583 |
+
"step": 7300
|
| 5584 |
+
},
|
| 5585 |
+
{
|
| 5586 |
+
"epoch": 3.4254920337394563,
|
| 5587 |
+
"grad_norm": 2.3286941051483154,
|
| 5588 |
+
"learning_rate": 1.785906747891284e-05,
|
| 5589 |
+
"loss": 0.0926,
|
| 5590 |
+
"step": 7310
|
| 5591 |
+
},
|
| 5592 |
+
{
|
| 5593 |
+
"epoch": 3.4301780693533273,
|
| 5594 |
+
"grad_norm": 1.8551883697509766,
|
| 5595 |
+
"learning_rate": 1.785613870665417e-05,
|
| 5596 |
+
"loss": 0.122,
|
| 5597 |
+
"step": 7320
|
| 5598 |
+
},
|
| 5599 |
+
{
|
| 5600 |
+
"epoch": 3.4348641049671977,
|
| 5601 |
+
"grad_norm": 1.7142447233200073,
|
| 5602 |
+
"learning_rate": 1.7853209934395504e-05,
|
| 5603 |
+
"loss": 0.138,
|
| 5604 |
+
"step": 7330
|
| 5605 |
+
},
|
| 5606 |
+
{
|
| 5607 |
+
"epoch": 3.4395501405810682,
|
| 5608 |
+
"grad_norm": 1.5548756122589111,
|
| 5609 |
+
"learning_rate": 1.7850281162136833e-05,
|
| 5610 |
+
"loss": 0.1123,
|
| 5611 |
+
"step": 7340
|
| 5612 |
+
},
|
| 5613 |
+
{
|
| 5614 |
+
"epoch": 3.444236176194939,
|
| 5615 |
+
"grad_norm": 1.3273271322250366,
|
| 5616 |
+
"learning_rate": 1.7847352389878166e-05,
|
| 5617 |
+
"loss": 0.129,
|
| 5618 |
+
"step": 7350
|
| 5619 |
+
},
|
| 5620 |
+
{
|
| 5621 |
+
"epoch": 3.4489222118088096,
|
| 5622 |
+
"grad_norm": 2.410999298095703,
|
| 5623 |
+
"learning_rate": 1.7844423617619496e-05,
|
| 5624 |
+
"loss": 0.1329,
|
| 5625 |
+
"step": 7360
|
| 5626 |
+
},
|
| 5627 |
+
{
|
| 5628 |
+
"epoch": 3.4536082474226806,
|
| 5629 |
+
"grad_norm": 2.0272533893585205,
|
| 5630 |
+
"learning_rate": 1.784149484536083e-05,
|
| 5631 |
+
"loss": 0.1251,
|
| 5632 |
+
"step": 7370
|
| 5633 |
+
},
|
| 5634 |
+
{
|
| 5635 |
+
"epoch": 3.458294283036551,
|
| 5636 |
+
"grad_norm": 2.4070749282836914,
|
| 5637 |
+
"learning_rate": 1.7838566073102158e-05,
|
| 5638 |
+
"loss": 0.1384,
|
| 5639 |
+
"step": 7380
|
| 5640 |
+
},
|
| 5641 |
+
{
|
| 5642 |
+
"epoch": 3.4629803186504216,
|
| 5643 |
+
"grad_norm": 2.0983331203460693,
|
| 5644 |
+
"learning_rate": 1.7835637300843487e-05,
|
| 5645 |
+
"loss": 0.1268,
|
| 5646 |
+
"step": 7390
|
| 5647 |
+
},
|
| 5648 |
+
{
|
| 5649 |
+
"epoch": 3.4676663542642925,
|
| 5650 |
+
"grad_norm": 1.5650460720062256,
|
| 5651 |
+
"learning_rate": 1.783270852858482e-05,
|
| 5652 |
+
"loss": 0.1218,
|
| 5653 |
+
"step": 7400
|
| 5654 |
+
},
|
| 5655 |
+
{
|
| 5656 |
+
"epoch": 3.472352389878163,
|
| 5657 |
+
"grad_norm": 1.4505574703216553,
|
| 5658 |
+
"learning_rate": 1.782977975632615e-05,
|
| 5659 |
+
"loss": 0.1278,
|
| 5660 |
+
"step": 7410
|
| 5661 |
+
},
|
| 5662 |
+
{
|
| 5663 |
+
"epoch": 3.477038425492034,
|
| 5664 |
+
"grad_norm": 2.4104747772216797,
|
| 5665 |
+
"learning_rate": 1.782685098406748e-05,
|
| 5666 |
+
"loss": 0.1506,
|
| 5667 |
+
"step": 7420
|
| 5668 |
+
},
|
| 5669 |
+
{
|
| 5670 |
+
"epoch": 3.4817244611059044,
|
| 5671 |
+
"grad_norm": 2.2749085426330566,
|
| 5672 |
+
"learning_rate": 1.7823922211808812e-05,
|
| 5673 |
+
"loss": 0.1382,
|
| 5674 |
+
"step": 7430
|
| 5675 |
+
},
|
| 5676 |
+
{
|
| 5677 |
+
"epoch": 3.486410496719775,
|
| 5678 |
+
"grad_norm": 1.619983434677124,
|
| 5679 |
+
"learning_rate": 1.7820993439550142e-05,
|
| 5680 |
+
"loss": 0.1145,
|
| 5681 |
+
"step": 7440
|
| 5682 |
+
},
|
| 5683 |
+
{
|
| 5684 |
+
"epoch": 3.491096532333646,
|
| 5685 |
+
"grad_norm": 1.797600269317627,
|
| 5686 |
+
"learning_rate": 1.781806466729147e-05,
|
| 5687 |
+
"loss": 0.1381,
|
| 5688 |
+
"step": 7450
|
| 5689 |
+
},
|
| 5690 |
+
{
|
| 5691 |
+
"epoch": 3.4957825679475163,
|
| 5692 |
+
"grad_norm": 1.2865104675292969,
|
| 5693 |
+
"learning_rate": 1.7815135895032804e-05,
|
| 5694 |
+
"loss": 0.1088,
|
| 5695 |
+
"step": 7460
|
| 5696 |
+
},
|
| 5697 |
+
{
|
| 5698 |
+
"epoch": 3.5004686035613872,
|
| 5699 |
+
"grad_norm": 2.2955312728881836,
|
| 5700 |
+
"learning_rate": 1.7812207122774134e-05,
|
| 5701 |
+
"loss": 0.1389,
|
| 5702 |
+
"step": 7470
|
| 5703 |
+
},
|
| 5704 |
+
{
|
| 5705 |
+
"epoch": 3.5051546391752577,
|
| 5706 |
+
"grad_norm": 1.884758472442627,
|
| 5707 |
+
"learning_rate": 1.7809278350515463e-05,
|
| 5708 |
+
"loss": 0.1399,
|
| 5709 |
+
"step": 7480
|
| 5710 |
+
},
|
| 5711 |
+
{
|
| 5712 |
+
"epoch": 3.509840674789128,
|
| 5713 |
+
"grad_norm": 2.0076119899749756,
|
| 5714 |
+
"learning_rate": 1.7806349578256796e-05,
|
| 5715 |
+
"loss": 0.1028,
|
| 5716 |
+
"step": 7490
|
| 5717 |
+
},
|
| 5718 |
+
{
|
| 5719 |
+
"epoch": 3.514526710402999,
|
| 5720 |
+
"grad_norm": 1.5606528520584106,
|
| 5721 |
+
"learning_rate": 1.7803420805998125e-05,
|
| 5722 |
+
"loss": 0.1058,
|
| 5723 |
+
"step": 7500
|
| 5724 |
+
},
|
| 5725 |
+
{
|
| 5726 |
+
"epoch": 3.514526710402999,
|
| 5727 |
+
"eval_loss": 0.044608332216739655,
|
| 5728 |
+
"eval_pearson_cosine": 0.7913143880230251,
|
| 5729 |
+
"eval_pearson_dot": 0.6221286850907433,
|
| 5730 |
+
"eval_pearson_euclidean": 0.7578325537672654,
|
| 5731 |
+
"eval_pearson_manhattan": 0.7571791901529252,
|
| 5732 |
+
"eval_runtime": 3.3012,
|
| 5733 |
+
"eval_samples_per_second": 454.374,
|
| 5734 |
+
"eval_spearman_cosine": 0.7958246101441605,
|
| 5735 |
+
"eval_spearman_dot": 0.6338421877202784,
|
| 5736 |
+
"eval_spearman_euclidean": 0.7715109007041803,
|
| 5737 |
+
"eval_spearman_manhattan": 0.7714185275105551,
|
| 5738 |
+
"eval_steps_per_second": 28.474,
|
| 5739 |
+
"step": 7500
|
| 5740 |
+
},
|
| 5741 |
+
{
|
| 5742 |
+
"epoch": 3.5192127460168696,
|
| 5743 |
+
"grad_norm": 1.9054310321807861,
|
| 5744 |
+
"learning_rate": 1.780049203373946e-05,
|
| 5745 |
+
"loss": 0.1149,
|
| 5746 |
+
"step": 7510
|
| 5747 |
+
},
|
| 5748 |
+
{
|
| 5749 |
+
"epoch": 3.5238987816307406,
|
| 5750 |
+
"grad_norm": 2.2473042011260986,
|
| 5751 |
+
"learning_rate": 1.7797563261480788e-05,
|
| 5752 |
+
"loss": 0.1241,
|
| 5753 |
+
"step": 7520
|
| 5754 |
+
},
|
| 5755 |
+
{
|
| 5756 |
+
"epoch": 3.528584817244611,
|
| 5757 |
+
"grad_norm": 2.9301676750183105,
|
| 5758 |
+
"learning_rate": 1.779463448922212e-05,
|
| 5759 |
+
"loss": 0.1155,
|
| 5760 |
+
"step": 7530
|
| 5761 |
+
},
|
| 5762 |
+
{
|
| 5763 |
+
"epoch": 3.5332708528584815,
|
| 5764 |
+
"grad_norm": 1.8250157833099365,
|
| 5765 |
+
"learning_rate": 1.779170571696345e-05,
|
| 5766 |
+
"loss": 0.118,
|
| 5767 |
+
"step": 7540
|
| 5768 |
+
},
|
| 5769 |
+
{
|
| 5770 |
+
"epoch": 3.5379568884723525,
|
| 5771 |
+
"grad_norm": 2.101794958114624,
|
| 5772 |
+
"learning_rate": 1.7788776944704783e-05,
|
| 5773 |
+
"loss": 0.1338,
|
| 5774 |
+
"step": 7550
|
| 5775 |
+
},
|
| 5776 |
+
{
|
| 5777 |
+
"epoch": 3.542642924086223,
|
| 5778 |
+
"grad_norm": 1.9058297872543335,
|
| 5779 |
+
"learning_rate": 1.7785848172446113e-05,
|
| 5780 |
+
"loss": 0.1172,
|
| 5781 |
+
"step": 7560
|
| 5782 |
+
},
|
| 5783 |
+
{
|
| 5784 |
+
"epoch": 3.547328959700094,
|
| 5785 |
+
"grad_norm": 2.1106228828430176,
|
| 5786 |
+
"learning_rate": 1.7782919400187446e-05,
|
| 5787 |
+
"loss": 0.119,
|
| 5788 |
+
"step": 7570
|
| 5789 |
+
},
|
| 5790 |
+
{
|
| 5791 |
+
"epoch": 3.5520149953139644,
|
| 5792 |
+
"grad_norm": 1.572771430015564,
|
| 5793 |
+
"learning_rate": 1.7779990627928775e-05,
|
| 5794 |
+
"loss": 0.1303,
|
| 5795 |
+
"step": 7580
|
| 5796 |
+
},
|
| 5797 |
+
{
|
| 5798 |
+
"epoch": 3.556701030927835,
|
| 5799 |
+
"grad_norm": 2.670691967010498,
|
| 5800 |
+
"learning_rate": 1.7777061855670105e-05,
|
| 5801 |
+
"loss": 0.1367,
|
| 5802 |
+
"step": 7590
|
| 5803 |
+
},
|
| 5804 |
+
{
|
| 5805 |
+
"epoch": 3.561387066541706,
|
| 5806 |
+
"grad_norm": 1.0899403095245361,
|
| 5807 |
+
"learning_rate": 1.7774133083411434e-05,
|
| 5808 |
+
"loss": 0.131,
|
| 5809 |
+
"step": 7600
|
| 5810 |
+
},
|
| 5811 |
+
{
|
| 5812 |
+
"epoch": 3.5660731021555763,
|
| 5813 |
+
"grad_norm": 1.66856050491333,
|
| 5814 |
+
"learning_rate": 1.7771204311152767e-05,
|
| 5815 |
+
"loss": 0.1282,
|
| 5816 |
+
"step": 7610
|
| 5817 |
+
},
|
| 5818 |
+
{
|
| 5819 |
+
"epoch": 3.570759137769447,
|
| 5820 |
+
"grad_norm": 1.9693597555160522,
|
| 5821 |
+
"learning_rate": 1.7768275538894096e-05,
|
| 5822 |
+
"loss": 0.1141,
|
| 5823 |
+
"step": 7620
|
| 5824 |
+
},
|
| 5825 |
+
{
|
| 5826 |
+
"epoch": 3.5754451733833177,
|
| 5827 |
+
"grad_norm": 2.5107643604278564,
|
| 5828 |
+
"learning_rate": 1.7765346766635426e-05,
|
| 5829 |
+
"loss": 0.1302,
|
| 5830 |
+
"step": 7630
|
| 5831 |
+
},
|
| 5832 |
+
{
|
| 5833 |
+
"epoch": 3.580131208997188,
|
| 5834 |
+
"grad_norm": 1.843782663345337,
|
| 5835 |
+
"learning_rate": 1.776241799437676e-05,
|
| 5836 |
+
"loss": 0.1295,
|
| 5837 |
+
"step": 7640
|
| 5838 |
+
},
|
| 5839 |
+
{
|
| 5840 |
+
"epoch": 3.584817244611059,
|
| 5841 |
+
"grad_norm": 1.5396898984909058,
|
| 5842 |
+
"learning_rate": 1.7759489222118088e-05,
|
| 5843 |
+
"loss": 0.1146,
|
| 5844 |
+
"step": 7650
|
| 5845 |
+
},
|
| 5846 |
+
{
|
| 5847 |
+
"epoch": 3.5895032802249296,
|
| 5848 |
+
"grad_norm": 1.250181794166565,
|
| 5849 |
+
"learning_rate": 1.775656044985942e-05,
|
| 5850 |
+
"loss": 0.0997,
|
| 5851 |
+
"step": 7660
|
| 5852 |
+
},
|
| 5853 |
+
{
|
| 5854 |
+
"epoch": 3.5941893158388005,
|
| 5855 |
+
"grad_norm": 1.0038021802902222,
|
| 5856 |
+
"learning_rate": 1.775363167760075e-05,
|
| 5857 |
+
"loss": 0.131,
|
| 5858 |
+
"step": 7670
|
| 5859 |
+
},
|
| 5860 |
+
{
|
| 5861 |
+
"epoch": 3.598875351452671,
|
| 5862 |
+
"grad_norm": 1.7689967155456543,
|
| 5863 |
+
"learning_rate": 1.775070290534208e-05,
|
| 5864 |
+
"loss": 0.1323,
|
| 5865 |
+
"step": 7680
|
| 5866 |
+
},
|
| 5867 |
+
{
|
| 5868 |
+
"epoch": 3.6035613870665415,
|
| 5869 |
+
"grad_norm": 1.6515671014785767,
|
| 5870 |
+
"learning_rate": 1.7747774133083413e-05,
|
| 5871 |
+
"loss": 0.1228,
|
| 5872 |
+
"step": 7690
|
| 5873 |
+
},
|
| 5874 |
+
{
|
| 5875 |
+
"epoch": 3.6082474226804124,
|
| 5876 |
+
"grad_norm": 1.6234405040740967,
|
| 5877 |
+
"learning_rate": 1.7744845360824743e-05,
|
| 5878 |
+
"loss": 0.1177,
|
| 5879 |
+
"step": 7700
|
| 5880 |
+
},
|
| 5881 |
+
{
|
| 5882 |
+
"epoch": 3.612933458294283,
|
| 5883 |
+
"grad_norm": 1.1468828916549683,
|
| 5884 |
+
"learning_rate": 1.7741916588566075e-05,
|
| 5885 |
+
"loss": 0.121,
|
| 5886 |
+
"step": 7710
|
| 5887 |
+
},
|
| 5888 |
+
{
|
| 5889 |
+
"epoch": 3.617619493908154,
|
| 5890 |
+
"grad_norm": 2.2512290477752686,
|
| 5891 |
+
"learning_rate": 1.7738987816307405e-05,
|
| 5892 |
+
"loss": 0.1506,
|
| 5893 |
+
"step": 7720
|
| 5894 |
+
},
|
| 5895 |
+
{
|
| 5896 |
+
"epoch": 3.6223055295220243,
|
| 5897 |
+
"grad_norm": 1.967869758605957,
|
| 5898 |
+
"learning_rate": 1.7736059044048738e-05,
|
| 5899 |
+
"loss": 0.1278,
|
| 5900 |
+
"step": 7730
|
| 5901 |
+
},
|
| 5902 |
+
{
|
| 5903 |
+
"epoch": 3.626991565135895,
|
| 5904 |
+
"grad_norm": 1.6843619346618652,
|
| 5905 |
+
"learning_rate": 1.7733130271790067e-05,
|
| 5906 |
+
"loss": 0.1292,
|
| 5907 |
+
"step": 7740
|
| 5908 |
+
},
|
| 5909 |
+
{
|
| 5910 |
+
"epoch": 3.6316776007497658,
|
| 5911 |
+
"grad_norm": 1.7128106355667114,
|
| 5912 |
+
"learning_rate": 1.77302014995314e-05,
|
| 5913 |
+
"loss": 0.1144,
|
| 5914 |
+
"step": 7750
|
| 5915 |
+
},
|
| 5916 |
+
{
|
| 5917 |
+
"epoch": 3.6316776007497658,
|
| 5918 |
+
"eval_loss": 0.043338797986507416,
|
| 5919 |
+
"eval_pearson_cosine": 0.7938926107691149,
|
| 5920 |
+
"eval_pearson_dot": 0.6518687502689318,
|
| 5921 |
+
"eval_pearson_euclidean": 0.7541829192023144,
|
| 5922 |
+
"eval_pearson_manhattan": 0.7533667893162033,
|
| 5923 |
+
"eval_runtime": 3.5292,
|
| 5924 |
+
"eval_samples_per_second": 425.028,
|
| 5925 |
+
"eval_spearman_cosine": 0.7989181032598132,
|
| 5926 |
+
"eval_spearman_dot": 0.658312239789335,
|
| 5927 |
+
"eval_spearman_euclidean": 0.7677205029787961,
|
| 5928 |
+
"eval_spearman_manhattan": 0.7673451483642694,
|
| 5929 |
+
"eval_steps_per_second": 26.635,
|
| 5930 |
+
"step": 7750
|
| 5931 |
+
},
|
| 5932 |
+
{
|
| 5933 |
+
"epoch": 3.6363636363636362,
|
| 5934 |
+
"grad_norm": 2.2347500324249268,
|
| 5935 |
+
"learning_rate": 1.772727272727273e-05,
|
| 5936 |
+
"loss": 0.145,
|
| 5937 |
+
"step": 7760
|
| 5938 |
+
},
|
| 5939 |
+
{
|
| 5940 |
+
"epoch": 3.641049671977507,
|
| 5941 |
+
"grad_norm": 1.1075607538223267,
|
| 5942 |
+
"learning_rate": 1.772434395501406e-05,
|
| 5943 |
+
"loss": 0.122,
|
| 5944 |
+
"step": 7770
|
| 5945 |
+
},
|
| 5946 |
+
{
|
| 5947 |
+
"epoch": 3.6457357075913777,
|
| 5948 |
+
"grad_norm": 1.9819576740264893,
|
| 5949 |
+
"learning_rate": 1.772141518275539e-05,
|
| 5950 |
+
"loss": 0.1542,
|
| 5951 |
+
"step": 7780
|
| 5952 |
+
},
|
| 5953 |
+
{
|
| 5954 |
+
"epoch": 3.650421743205248,
|
| 5955 |
+
"grad_norm": 1.3385450839996338,
|
| 5956 |
+
"learning_rate": 1.771848641049672e-05,
|
| 5957 |
+
"loss": 0.1269,
|
| 5958 |
+
"step": 7790
|
| 5959 |
+
},
|
| 5960 |
+
{
|
| 5961 |
+
"epoch": 3.655107778819119,
|
| 5962 |
+
"grad_norm": 1.2146624326705933,
|
| 5963 |
+
"learning_rate": 1.771555763823805e-05,
|
| 5964 |
+
"loss": 0.1124,
|
| 5965 |
+
"step": 7800
|
| 5966 |
+
},
|
| 5967 |
+
{
|
| 5968 |
+
"epoch": 3.6597938144329896,
|
| 5969 |
+
"grad_norm": 1.8543137311935425,
|
| 5970 |
+
"learning_rate": 1.771262886597938e-05,
|
| 5971 |
+
"loss": 0.1513,
|
| 5972 |
+
"step": 7810
|
| 5973 |
+
},
|
| 5974 |
+
{
|
| 5975 |
+
"epoch": 3.6644798500468605,
|
| 5976 |
+
"grad_norm": 1.147740125656128,
|
| 5977 |
+
"learning_rate": 1.7709700093720713e-05,
|
| 5978 |
+
"loss": 0.1207,
|
| 5979 |
+
"step": 7820
|
| 5980 |
+
},
|
| 5981 |
+
{
|
| 5982 |
+
"epoch": 3.669165885660731,
|
| 5983 |
+
"grad_norm": 2.1737101078033447,
|
| 5984 |
+
"learning_rate": 1.7706771321462043e-05,
|
| 5985 |
+
"loss": 0.1345,
|
| 5986 |
+
"step": 7830
|
| 5987 |
+
},
|
| 5988 |
+
{
|
| 5989 |
+
"epoch": 3.6738519212746015,
|
| 5990 |
+
"grad_norm": 2.481095790863037,
|
| 5991 |
+
"learning_rate": 1.7703842549203376e-05,
|
| 5992 |
+
"loss": 0.1304,
|
| 5993 |
+
"step": 7840
|
| 5994 |
+
},
|
| 5995 |
+
{
|
| 5996 |
+
"epoch": 3.6785379568884724,
|
| 5997 |
+
"grad_norm": 1.9203423261642456,
|
| 5998 |
+
"learning_rate": 1.7700913776944705e-05,
|
| 5999 |
+
"loss": 0.1257,
|
| 6000 |
+
"step": 7850
|
| 6001 |
+
},
|
| 6002 |
+
{
|
| 6003 |
+
"epoch": 3.683223992502343,
|
| 6004 |
+
"grad_norm": 2.324158191680908,
|
| 6005 |
+
"learning_rate": 1.7697985004686038e-05,
|
| 6006 |
+
"loss": 0.126,
|
| 6007 |
+
"step": 7860
|
| 6008 |
+
},
|
| 6009 |
+
{
|
| 6010 |
+
"epoch": 3.687910028116214,
|
| 6011 |
+
"grad_norm": 1.6233323812484741,
|
| 6012 |
+
"learning_rate": 1.7695056232427368e-05,
|
| 6013 |
+
"loss": 0.1228,
|
| 6014 |
+
"step": 7870
|
| 6015 |
+
},
|
| 6016 |
+
{
|
| 6017 |
+
"epoch": 3.6925960637300843,
|
| 6018 |
+
"grad_norm": 1.0567041635513306,
|
| 6019 |
+
"learning_rate": 1.7692127460168697e-05,
|
| 6020 |
+
"loss": 0.1129,
|
| 6021 |
+
"step": 7880
|
| 6022 |
+
},
|
| 6023 |
+
{
|
| 6024 |
+
"epoch": 3.697282099343955,
|
| 6025 |
+
"grad_norm": 1.4684457778930664,
|
| 6026 |
+
"learning_rate": 1.768919868791003e-05,
|
| 6027 |
+
"loss": 0.1164,
|
| 6028 |
+
"step": 7890
|
| 6029 |
+
},
|
| 6030 |
+
{
|
| 6031 |
+
"epoch": 3.7019681349578257,
|
| 6032 |
+
"grad_norm": 2.070171594619751,
|
| 6033 |
+
"learning_rate": 1.768626991565136e-05,
|
| 6034 |
+
"loss": 0.1488,
|
| 6035 |
+
"step": 7900
|
| 6036 |
+
},
|
| 6037 |
+
{
|
| 6038 |
+
"epoch": 3.706654170571696,
|
| 6039 |
+
"grad_norm": 1.93710458278656,
|
| 6040 |
+
"learning_rate": 1.7683341143392693e-05,
|
| 6041 |
+
"loss": 0.1423,
|
| 6042 |
+
"step": 7910
|
| 6043 |
+
},
|
| 6044 |
+
{
|
| 6045 |
+
"epoch": 3.711340206185567,
|
| 6046 |
+
"grad_norm": 2.109379529953003,
|
| 6047 |
+
"learning_rate": 1.7680412371134022e-05,
|
| 6048 |
+
"loss": 0.1247,
|
| 6049 |
+
"step": 7920
|
| 6050 |
+
},
|
| 6051 |
+
{
|
| 6052 |
+
"epoch": 3.7160262417994376,
|
| 6053 |
+
"grad_norm": 1.9402395486831665,
|
| 6054 |
+
"learning_rate": 1.7677483598875355e-05,
|
| 6055 |
+
"loss": 0.1258,
|
| 6056 |
+
"step": 7930
|
| 6057 |
+
},
|
| 6058 |
+
{
|
| 6059 |
+
"epoch": 3.720712277413308,
|
| 6060 |
+
"grad_norm": 1.3770403861999512,
|
| 6061 |
+
"learning_rate": 1.7674554826616684e-05,
|
| 6062 |
+
"loss": 0.1152,
|
| 6063 |
+
"step": 7940
|
| 6064 |
+
},
|
| 6065 |
+
{
|
| 6066 |
+
"epoch": 3.725398313027179,
|
| 6067 |
+
"grad_norm": 1.8845633268356323,
|
| 6068 |
+
"learning_rate": 1.7671626054358014e-05,
|
| 6069 |
+
"loss": 0.1128,
|
| 6070 |
+
"step": 7950
|
| 6071 |
+
},
|
| 6072 |
+
{
|
| 6073 |
+
"epoch": 3.7300843486410495,
|
| 6074 |
+
"grad_norm": 1.80978524684906,
|
| 6075 |
+
"learning_rate": 1.7668697282099347e-05,
|
| 6076 |
+
"loss": 0.1506,
|
| 6077 |
+
"step": 7960
|
| 6078 |
+
},
|
| 6079 |
+
{
|
| 6080 |
+
"epoch": 3.7347703842549205,
|
| 6081 |
+
"grad_norm": 1.714689016342163,
|
| 6082 |
+
"learning_rate": 1.7665768509840676e-05,
|
| 6083 |
+
"loss": 0.1295,
|
| 6084 |
+
"step": 7970
|
| 6085 |
+
},
|
| 6086 |
+
{
|
| 6087 |
+
"epoch": 3.739456419868791,
|
| 6088 |
+
"grad_norm": 2.2683634757995605,
|
| 6089 |
+
"learning_rate": 1.7662839737582006e-05,
|
| 6090 |
+
"loss": 0.153,
|
| 6091 |
+
"step": 7980
|
| 6092 |
+
},
|
| 6093 |
+
{
|
| 6094 |
+
"epoch": 3.7441424554826614,
|
| 6095 |
+
"grad_norm": 1.1487226486206055,
|
| 6096 |
+
"learning_rate": 1.7659910965323335e-05,
|
| 6097 |
+
"loss": 0.1305,
|
| 6098 |
+
"step": 7990
|
| 6099 |
+
},
|
| 6100 |
+
{
|
| 6101 |
+
"epoch": 3.7488284910965324,
|
| 6102 |
+
"grad_norm": 1.4769738912582397,
|
| 6103 |
+
"learning_rate": 1.7656982193064668e-05,
|
| 6104 |
+
"loss": 0.0971,
|
| 6105 |
+
"step": 8000
|
| 6106 |
+
},
|
| 6107 |
+
{
|
| 6108 |
+
"epoch": 3.7488284910965324,
|
| 6109 |
+
"eval_loss": 0.04381699115037918,
|
| 6110 |
+
"eval_pearson_cosine": 0.7952038190054296,
|
| 6111 |
+
"eval_pearson_dot": 0.6344663529067152,
|
| 6112 |
+
"eval_pearson_euclidean": 0.7547335910463318,
|
| 6113 |
+
"eval_pearson_manhattan": 0.7536726944037966,
|
| 6114 |
+
"eval_runtime": 3.6935,
|
| 6115 |
+
"eval_samples_per_second": 406.123,
|
| 6116 |
+
"eval_spearman_cosine": 0.7993143516157027,
|
| 6117 |
+
"eval_spearman_dot": 0.6382938851288388,
|
| 6118 |
+
"eval_spearman_euclidean": 0.7679077610624258,
|
| 6119 |
+
"eval_spearman_manhattan": 0.767544325158077,
|
| 6120 |
+
"eval_steps_per_second": 25.45,
|
| 6121 |
+
"step": 8000
|
| 6122 |
}
|
| 6123 |
],
|
| 6124 |
"logging_steps": 10,
|