Training in progress, epoch 4
Browse files- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- trainer_log.jsonl +166 -0
- training_args.bin +2 -2
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d99584f80b5e05a01c898c66fe543f30c81dec2b018a8159684ace2520b9f283
|
3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3827997a2de82cb653bbfdac86c503612c97636f6c98edf99072fa38653daea6
|
3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b290dcebe07d36e106be4e830e45b5f5791b45fb72ac9d5dd9eef1e0f6dadef
|
3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9820e5524b2c68f74c9f62017a16dac27a2834dcea63ec01c37c59a41a9a8114
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -444,3 +444,169 @@
|
|
444 |
{"current_steps": 443, "total_steps": 555, "loss": 0.4754, "lr": 9.538830405358523e-06, "epoch": 3.986501687289089, "percentage": 79.82, "elapsed_time": "14:31:37", "remaining_time": "3:40:21"}
|
445 |
{"current_steps": 444, "total_steps": 555, "loss": 0.477, "lr": 9.376215759212423e-06, "epoch": 3.9955005624296964, "percentage": 80.0, "elapsed_time": "14:33:30", "remaining_time": "3:38:22"}
|
446 |
{"current_steps": 445, "total_steps": 555, "loss": 0.8853, "lr": 9.214814938060561e-06, "epoch": 4.004499437570304, "percentage": 80.18, "elapsed_time": "14:37:18", "remaining_time": "3:36:51"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
444 |
{"current_steps": 443, "total_steps": 555, "loss": 0.4754, "lr": 9.538830405358523e-06, "epoch": 3.986501687289089, "percentage": 79.82, "elapsed_time": "14:31:37", "remaining_time": "3:40:21"}
|
445 |
{"current_steps": 444, "total_steps": 555, "loss": 0.477, "lr": 9.376215759212423e-06, "epoch": 3.9955005624296964, "percentage": 80.0, "elapsed_time": "14:33:30", "remaining_time": "3:38:22"}
|
446 |
{"current_steps": 445, "total_steps": 555, "loss": 0.8853, "lr": 9.214814938060561e-06, "epoch": 4.004499437570304, "percentage": 80.18, "elapsed_time": "14:37:18", "remaining_time": "3:36:51"}
|
447 |
+
{"current_steps": 446, "total_steps": 555, "loss": 0.4499, "lr": 9.054634339294867e-06, "epoch": 4.013498312710911, "percentage": 80.36, "elapsed_time": "14:39:16", "remaining_time": "3:34:53"}
|
448 |
+
{"current_steps": 447, "total_steps": 555, "loss": 0.4457, "lr": 8.895680311941745e-06, "epoch": 4.022497187851519, "percentage": 80.54, "elapsed_time": "14:41:12", "remaining_time": "3:32:54"}
|
449 |
+
{"current_steps": 448, "total_steps": 555, "loss": 0.4537, "lr": 8.737959156410385e-06, "epoch": 4.031496062992126, "percentage": 80.72, "elapsed_time": "14:43:06", "remaining_time": "3:30:55"}
|
450 |
+
{"current_steps": 449, "total_steps": 555, "loss": 0.453, "lr": 8.581477124243002e-06, "epoch": 4.040494938132733, "percentage": 80.9, "elapsed_time": "14:45:01", "remaining_time": "3:28:56"}
|
451 |
+
{"current_steps": 450, "total_steps": 555, "loss": 0.4543, "lr": 8.426240417867121e-06, "epoch": 4.049493813273341, "percentage": 81.08, "elapsed_time": "14:46:56", "remaining_time": "3:26:57"}
|
452 |
+
{"current_steps": 451, "total_steps": 555, "loss": 0.4538, "lr": 8.272255190349678e-06, "epoch": 4.058492688413948, "percentage": 81.26, "elapsed_time": "14:48:52", "remaining_time": "3:24:58"}
|
453 |
+
{"current_steps": 452, "total_steps": 555, "loss": 0.4491, "lr": 8.119527545153137e-06, "epoch": 4.067491563554555, "percentage": 81.44, "elapsed_time": "14:50:46", "remaining_time": "3:22:59"}
|
454 |
+
{"current_steps": 453, "total_steps": 555, "loss": 0.4502, "lr": 7.968063535893588e-06, "epoch": 4.0764904386951635, "percentage": 81.62, "elapsed_time": "14:52:40", "remaining_time": "3:21:00"}
|
455 |
+
{"current_steps": 454, "total_steps": 555, "loss": 0.4509, "lr": 7.817869166100812e-06, "epoch": 4.085489313835771, "percentage": 81.8, "elapsed_time": "14:54:36", "remaining_time": "3:19:01"}
|
456 |
+
{"current_steps": 455, "total_steps": 555, "loss": 0.4474, "lr": 7.668950388980261e-06, "epoch": 4.094488188976378, "percentage": 81.98, "elapsed_time": "14:56:34", "remaining_time": "3:17:02"}
|
457 |
+
{"current_steps": 456, "total_steps": 555, "loss": 0.4529, "lr": 7.521313107177182e-06, "epoch": 4.103487064116985, "percentage": 82.16, "elapsed_time": "14:58:30", "remaining_time": "3:15:04"}
|
458 |
+
{"current_steps": 457, "total_steps": 555, "loss": 0.4551, "lr": 7.374963172542564e-06, "epoch": 4.112485939257593, "percentage": 82.34, "elapsed_time": "15:00:25", "remaining_time": "3:13:05"}
|
459 |
+
{"current_steps": 458, "total_steps": 555, "loss": 0.4487, "lr": 7.229906385901264e-06, "epoch": 4.1214848143982, "percentage": 82.52, "elapsed_time": "15:02:20", "remaining_time": "3:11:06"}
|
460 |
+
{"current_steps": 459, "total_steps": 555, "loss": 0.4477, "lr": 7.086148496822054e-06, "epoch": 4.130483689538807, "percentage": 82.7, "elapsed_time": "15:04:15", "remaining_time": "3:09:07"}
|
461 |
+
{"current_steps": 460, "total_steps": 555, "loss": 0.459, "lr": 6.943695203389689e-06, "epoch": 4.139482564679415, "percentage": 82.88, "elapsed_time": "15:06:10", "remaining_time": "3:07:08"}
|
462 |
+
{"current_steps": 461, "total_steps": 555, "loss": 0.4524, "lr": 6.802552151979132e-06, "epoch": 4.1484814398200225, "percentage": 83.06, "elapsed_time": "15:08:05", "remaining_time": "3:05:09"}
|
463 |
+
{"current_steps": 462, "total_steps": 555, "loss": 0.4439, "lr": 6.662724937031697e-06, "epoch": 4.15748031496063, "percentage": 83.24, "elapsed_time": "15:10:00", "remaining_time": "3:03:10"}
|
464 |
+
{"current_steps": 463, "total_steps": 555, "loss": 0.452, "lr": 6.524219100833291e-06, "epoch": 4.166479190101238, "percentage": 83.42, "elapsed_time": "15:11:55", "remaining_time": "3:01:12"}
|
465 |
+
{"current_steps": 464, "total_steps": 555, "loss": 0.4548, "lr": 6.387040133294786e-06, "epoch": 4.175478065241845, "percentage": 83.6, "elapsed_time": "15:13:49", "remaining_time": "2:59:13"}
|
466 |
+
{"current_steps": 465, "total_steps": 555, "loss": 0.4621, "lr": 6.2511934717343955e-06, "epoch": 4.184476940382452, "percentage": 83.78, "elapsed_time": "15:15:45", "remaining_time": "2:57:14"}
|
467 |
+
{"current_steps": 466, "total_steps": 555, "loss": 0.4523, "lr": 6.116684500662127e-06, "epoch": 4.19347581552306, "percentage": 83.96, "elapsed_time": "15:17:41", "remaining_time": "2:55:15"}
|
468 |
+
{"current_steps": 467, "total_steps": 555, "loss": 0.4507, "lr": 5.983518551566403e-06, "epoch": 4.202474690663667, "percentage": 84.14, "elapsed_time": "15:19:37", "remaining_time": "2:53:17"}
|
469 |
+
{"current_steps": 468, "total_steps": 555, "loss": 0.4498, "lr": 5.8517009027027285e-06, "epoch": 4.211473565804274, "percentage": 84.32, "elapsed_time": "15:21:30", "remaining_time": "2:51:18"}
|
470 |
+
{"current_steps": 469, "total_steps": 555, "loss": 0.4539, "lr": 5.72123677888444e-06, "epoch": 4.2204724409448815, "percentage": 84.5, "elapsed_time": "15:23:26", "remaining_time": "2:49:19"}
|
471 |
+
{"current_steps": 470, "total_steps": 555, "loss": 0.4515, "lr": 5.592131351275671e-06, "epoch": 4.2294713160854895, "percentage": 84.68, "elapsed_time": "15:25:23", "remaining_time": "2:47:21"}
|
472 |
+
{"current_steps": 471, "total_steps": 555, "loss": 0.4469, "lr": 5.464389737186348e-06, "epoch": 4.238470191226097, "percentage": 84.86, "elapsed_time": "15:27:17", "remaining_time": "2:45:22"}
|
473 |
+
{"current_steps": 472, "total_steps": 555, "loss": 0.4534, "lr": 5.338016999869351e-06, "epoch": 4.247469066366704, "percentage": 85.05, "elapsed_time": "15:29:12", "remaining_time": "2:43:23"}
|
474 |
+
{"current_steps": 473, "total_steps": 555, "loss": 0.4486, "lr": 5.213018148319835e-06, "epoch": 4.256467941507312, "percentage": 85.23, "elapsed_time": "15:31:07", "remaining_time": "2:41:25"}
|
475 |
+
{"current_steps": 474, "total_steps": 555, "loss": 0.4471, "lr": 5.089398137076704e-06, "epoch": 4.265466816647919, "percentage": 85.41, "elapsed_time": "15:33:02", "remaining_time": "2:39:26"}
|
476 |
+
{"current_steps": 475, "total_steps": 555, "loss": 0.4536, "lr": 4.967161866026229e-06, "epoch": 4.274465691788526, "percentage": 85.59, "elapsed_time": "15:34:57", "remaining_time": "2:37:28"}
|
477 |
+
{"current_steps": 476, "total_steps": 555, "loss": 0.4508, "lr": 4.846314180207774e-06, "epoch": 4.283464566929134, "percentage": 85.77, "elapsed_time": "15:36:51", "remaining_time": "2:35:29"}
|
478 |
+
{"current_steps": 477, "total_steps": 555, "loss": 0.4495, "lr": 4.726859869621847e-06, "epoch": 4.292463442069741, "percentage": 85.95, "elapsed_time": "15:38:46", "remaining_time": "2:33:30"}
|
479 |
+
{"current_steps": 478, "total_steps": 555, "loss": 0.4493, "lr": 4.608803669040187e-06, "epoch": 4.3014623172103486, "percentage": 86.13, "elapsed_time": "15:40:40", "remaining_time": "2:31:31"}
|
480 |
+
{"current_steps": 479, "total_steps": 555, "loss": 0.4495, "lr": 4.492150257818066e-06, "epoch": 4.310461192350957, "percentage": 86.31, "elapsed_time": "15:42:36", "remaining_time": "2:29:33"}
|
481 |
+
{"current_steps": 480, "total_steps": 555, "loss": 0.4504, "lr": 4.376904259708892e-06, "epoch": 4.319460067491564, "percentage": 86.49, "elapsed_time": "15:44:33", "remaining_time": "2:27:35"}
|
482 |
+
{"current_steps": 481, "total_steps": 555, "loss": 0.4506, "lr": 4.263070242680866e-06, "epoch": 4.328458942632171, "percentage": 86.67, "elapsed_time": "15:46:27", "remaining_time": "2:25:36"}
|
483 |
+
{"current_steps": 482, "total_steps": 555, "loss": 0.452, "lr": 4.1506527187359765e-06, "epoch": 4.337457817772778, "percentage": 86.85, "elapsed_time": "15:48:23", "remaining_time": "2:23:38"}
|
484 |
+
{"current_steps": 483, "total_steps": 555, "loss": 0.4548, "lr": 4.039656143731128e-06, "epoch": 4.346456692913386, "percentage": 87.03, "elapsed_time": "15:50:17", "remaining_time": "2:21:39"}
|
485 |
+
{"current_steps": 484, "total_steps": 555, "loss": 0.4572, "lr": 3.930084917201508e-06, "epoch": 4.355455568053993, "percentage": 87.21, "elapsed_time": "15:52:13", "remaining_time": "2:19:41"}
|
486 |
+
{"current_steps": 485, "total_steps": 555, "loss": 0.4495, "lr": 3.821943382186275e-06, "epoch": 4.3644544431946, "percentage": 87.39, "elapsed_time": "15:54:09", "remaining_time": "2:17:42"}
|
487 |
+
{"current_steps": 486, "total_steps": 555, "loss": 0.4492, "lr": 3.715235825056338e-06, "epoch": 4.3734533183352085, "percentage": 87.57, "elapsed_time": "15:56:02", "remaining_time": "2:15:44"}
|
488 |
+
{"current_steps": 487, "total_steps": 555, "loss": 0.4533, "lr": 3.609966475344493e-06, "epoch": 4.382452193475816, "percentage": 87.75, "elapsed_time": "15:57:56", "remaining_time": "2:13:45"}
|
489 |
+
{"current_steps": 488, "total_steps": 555, "loss": 0.4505, "lr": 3.506139505577779e-06, "epoch": 4.391451068616423, "percentage": 87.93, "elapsed_time": "15:59:52", "remaining_time": "2:11:47"}
|
490 |
+
{"current_steps": 489, "total_steps": 555, "loss": 0.4641, "lr": 3.4037590311121015e-06, "epoch": 4.40044994375703, "percentage": 88.11, "elapsed_time": "16:01:48", "remaining_time": "2:09:48"}
|
491 |
+
{"current_steps": 490, "total_steps": 555, "loss": 0.4511, "lr": 3.302829109969072e-06, "epoch": 4.409448818897638, "percentage": 88.29, "elapsed_time": "16:03:43", "remaining_time": "2:07:50"}
|
492 |
+
{"current_steps": 491, "total_steps": 555, "loss": 0.454, "lr": 3.2033537426752236e-06, "epoch": 4.418447694038245, "percentage": 88.47, "elapsed_time": "16:05:39", "remaining_time": "2:05:52"}
|
493 |
+
{"current_steps": 492, "total_steps": 555, "loss": 0.4553, "lr": 3.1053368721033974e-06, "epoch": 4.427446569178852, "percentage": 88.65, "elapsed_time": "16:07:32", "remaining_time": "2:03:53"}
|
494 |
+
{"current_steps": 493, "total_steps": 555, "loss": 0.4553, "lr": 3.0087823833164596e-06, "epoch": 4.43644544431946, "percentage": 88.83, "elapsed_time": "16:09:29", "remaining_time": "2:01:55"}
|
495 |
+
{"current_steps": 494, "total_steps": 555, "loss": 0.4457, "lr": 2.9136941034133424e-06, "epoch": 4.4454443194600675, "percentage": 89.01, "elapsed_time": "16:11:26", "remaining_time": "1:59:57"}
|
496 |
+
{"current_steps": 495, "total_steps": 555, "loss": 0.4465, "lr": 2.8200758013773313e-06, "epoch": 4.454443194600675, "percentage": 89.19, "elapsed_time": "16:13:24", "remaining_time": "1:57:59"}
|
497 |
+
{"current_steps": 496, "total_steps": 555, "loss": 0.4532, "lr": 2.7279311879266645e-06, "epoch": 4.463442069741283, "percentage": 89.37, "elapsed_time": "16:15:18", "remaining_time": "1:56:00"}
|
498 |
+
{"current_steps": 497, "total_steps": 555, "loss": 0.4553, "lr": 2.637263915367476e-06, "epoch": 4.47244094488189, "percentage": 89.55, "elapsed_time": "16:17:13", "remaining_time": "1:54:02"}
|
499 |
+
{"current_steps": 498, "total_steps": 555, "loss": 0.4553, "lr": 2.5480775774490195e-06, "epoch": 4.481439820022497, "percentage": 89.73, "elapsed_time": "16:19:09", "remaining_time": "1:52:04"}
|
500 |
+
{"current_steps": 499, "total_steps": 555, "loss": 0.4459, "lr": 2.4603757092212057e-06, "epoch": 4.490438695163105, "percentage": 89.91, "elapsed_time": "16:21:06", "remaining_time": "1:50:06"}
|
501 |
+
{"current_steps": 445, "total_steps": 555, "loss": 0.4526, "lr": 9.214814938060561e-06, "epoch": 4.008998875140607, "percentage": 80.18, "elapsed_time": "0:01:53", "remaining_time": "0:00:28"}
|
502 |
+
{"current_steps": 446, "total_steps": 555, "loss": 0.4497, "lr": 9.054634339294867e-06, "epoch": 4.017997750281215, "percentage": 80.36, "elapsed_time": "0:03:35", "remaining_time": "0:00:52"}
|
503 |
+
{"current_steps": 447, "total_steps": 555, "loss": 0.4455, "lr": 8.895680311941745e-06, "epoch": 4.026996625421822, "percentage": 80.54, "elapsed_time": "0:05:18", "remaining_time": "0:01:16"}
|
504 |
+
{"current_steps": 448, "total_steps": 555, "loss": 0.4527, "lr": 8.737959156410385e-06, "epoch": 4.0359955005624295, "percentage": 80.72, "elapsed_time": "0:06:59", "remaining_time": "0:01:40"}
|
505 |
+
{"current_steps": 449, "total_steps": 555, "loss": 0.451, "lr": 8.581477124243002e-06, "epoch": 4.0449943757030375, "percentage": 80.9, "elapsed_time": "0:08:40", "remaining_time": "0:02:02"}
|
506 |
+
{"current_steps": 450, "total_steps": 555, "loss": 0.4511, "lr": 8.426240417867121e-06, "epoch": 4.053993250843645, "percentage": 81.08, "elapsed_time": "0:10:22", "remaining_time": "0:02:25"}
|
507 |
+
{"current_steps": 451, "total_steps": 555, "loss": 0.4517, "lr": 8.272255190349678e-06, "epoch": 4.062992125984252, "percentage": 81.26, "elapsed_time": "0:12:04", "remaining_time": "0:02:47"}
|
508 |
+
{"current_steps": 452, "total_steps": 555, "loss": 0.4514, "lr": 8.119527545153137e-06, "epoch": 4.071991001124859, "percentage": 81.44, "elapsed_time": "0:13:46", "remaining_time": "0:03:08"}
|
509 |
+
{"current_steps": 453, "total_steps": 555, "loss": 0.4465, "lr": 7.968063535893588e-06, "epoch": 4.080989876265467, "percentage": 81.62, "elapsed_time": "0:15:27", "remaining_time": "0:03:28"}
|
510 |
+
{"current_steps": 454, "total_steps": 555, "loss": 0.4485, "lr": 7.817869166100812e-06, "epoch": 4.089988751406074, "percentage": 81.8, "elapsed_time": "0:17:09", "remaining_time": "0:03:49"}
|
511 |
+
{"current_steps": 455, "total_steps": 555, "loss": 0.4506, "lr": 7.668950388980261e-06, "epoch": 4.098987626546681, "percentage": 81.98, "elapsed_time": "0:18:51", "remaining_time": "0:04:08"}
|
512 |
+
{"current_steps": 456, "total_steps": 555, "loss": 0.4507, "lr": 7.521313107177182e-06, "epoch": 4.107986501687289, "percentage": 82.16, "elapsed_time": "0:20:33", "remaining_time": "0:04:27"}
|
513 |
+
{"current_steps": 457, "total_steps": 555, "loss": 0.4524, "lr": 7.374963172542564e-06, "epoch": 4.116985376827897, "percentage": 82.34, "elapsed_time": "0:22:16", "remaining_time": "0:04:46"}
|
514 |
+
{"current_steps": 458, "total_steps": 555, "loss": 0.4463, "lr": 7.229906385901264e-06, "epoch": 4.125984251968504, "percentage": 82.52, "elapsed_time": "0:23:58", "remaining_time": "0:05:04"}
|
515 |
+
{"current_steps": 459, "total_steps": 555, "loss": 0.4541, "lr": 7.086148496822054e-06, "epoch": 4.134983127109112, "percentage": 82.7, "elapsed_time": "0:25:39", "remaining_time": "0:05:22"}
|
516 |
+
{"current_steps": 460, "total_steps": 555, "loss": 0.4522, "lr": 6.943695203389689e-06, "epoch": 4.143982002249719, "percentage": 82.88, "elapsed_time": "0:27:20", "remaining_time": "0:05:38"}
|
517 |
+
{"current_steps": 461, "total_steps": 555, "loss": 0.4496, "lr": 6.802552151979132e-06, "epoch": 4.152980877390326, "percentage": 83.06, "elapsed_time": "0:29:02", "remaining_time": "0:05:55"}
|
518 |
+
{"current_steps": 462, "total_steps": 555, "loss": 0.4481, "lr": 6.662724937031697e-06, "epoch": 4.161979752530933, "percentage": 83.24, "elapsed_time": "0:30:43", "remaining_time": "0:06:11"}
|
519 |
+
{"current_steps": 463, "total_steps": 555, "loss": 0.45, "lr": 6.524219100833291e-06, "epoch": 4.170978627671541, "percentage": 83.42, "elapsed_time": "0:32:23", "remaining_time": "0:06:26"}
|
520 |
+
{"current_steps": 464, "total_steps": 555, "loss": 0.4556, "lr": 6.387040133294786e-06, "epoch": 4.179977502812148, "percentage": 83.6, "elapsed_time": "0:34:04", "remaining_time": "0:06:41"}
|
521 |
+
{"current_steps": 465, "total_steps": 555, "loss": 0.4585, "lr": 6.2511934717343955e-06, "epoch": 4.188976377952756, "percentage": 83.78, "elapsed_time": "0:35:46", "remaining_time": "0:06:55"}
|
522 |
+
{"current_steps": 466, "total_steps": 555, "loss": 0.4509, "lr": 6.116684500662127e-06, "epoch": 4.197975253093364, "percentage": 83.96, "elapsed_time": "0:37:27", "remaining_time": "0:07:09"}
|
523 |
+
{"current_steps": 467, "total_steps": 555, "loss": 0.4465, "lr": 5.983518551566403e-06, "epoch": 4.206974128233971, "percentage": 84.14, "elapsed_time": "0:39:07", "remaining_time": "0:07:22"}
|
524 |
+
{"current_steps": 468, "total_steps": 555, "loss": 0.4529, "lr": 5.8517009027027285e-06, "epoch": 4.215973003374578, "percentage": 84.32, "elapsed_time": "0:40:48", "remaining_time": "0:07:35"}
|
525 |
+
{"current_steps": 469, "total_steps": 555, "loss": 0.4504, "lr": 5.72123677888444e-06, "epoch": 4.224971878515186, "percentage": 84.5, "elapsed_time": "0:42:28", "remaining_time": "0:07:47"}
|
526 |
+
{"current_steps": 470, "total_steps": 555, "loss": 0.4488, "lr": 5.592131351275671e-06, "epoch": 4.233970753655793, "percentage": 84.68, "elapsed_time": "0:44:10", "remaining_time": "0:07:59"}
|
527 |
+
{"current_steps": 471, "total_steps": 555, "loss": 0.4479, "lr": 5.464389737186348e-06, "epoch": 4.2429696287964, "percentage": 84.86, "elapsed_time": "0:45:50", "remaining_time": "0:08:10"}
|
528 |
+
{"current_steps": 472, "total_steps": 555, "loss": 0.4483, "lr": 5.338016999869351e-06, "epoch": 4.251968503937007, "percentage": 85.05, "elapsed_time": "0:47:31", "remaining_time": "0:08:21"}
|
529 |
+
{"current_steps": 473, "total_steps": 555, "loss": 0.4517, "lr": 5.213018148319835e-06, "epoch": 4.2609673790776155, "percentage": 85.23, "elapsed_time": "0:49:11", "remaining_time": "0:08:31"}
|
530 |
+
{"current_steps": 474, "total_steps": 555, "loss": 0.4506, "lr": 5.089398137076704e-06, "epoch": 4.269966254218223, "percentage": 85.41, "elapsed_time": "0:50:50", "remaining_time": "0:08:41"}
|
531 |
+
{"current_steps": 475, "total_steps": 555, "loss": 0.451, "lr": 4.967161866026229e-06, "epoch": 4.27896512935883, "percentage": 85.59, "elapsed_time": "0:52:30", "remaining_time": "0:08:50"}
|
532 |
+
{"current_steps": 476, "total_steps": 555, "loss": 0.4473, "lr": 4.846314180207774e-06, "epoch": 4.287964004499438, "percentage": 85.77, "elapsed_time": "0:54:11", "remaining_time": "0:08:59"}
|
533 |
+
{"current_steps": 477, "total_steps": 555, "loss": 0.4481, "lr": 4.726859869621847e-06, "epoch": 4.296962879640045, "percentage": 85.95, "elapsed_time": "0:55:51", "remaining_time": "0:09:07"}
|
534 |
+
{"current_steps": 478, "total_steps": 555, "loss": 0.4454, "lr": 4.608803669040187e-06, "epoch": 4.305961754780652, "percentage": 86.13, "elapsed_time": "0:57:31", "remaining_time": "0:09:16"}
|
535 |
+
{"current_steps": 479, "total_steps": 555, "loss": 0.4498, "lr": 4.492150257818066e-06, "epoch": 4.31496062992126, "percentage": 86.31, "elapsed_time": "0:59:11", "remaining_time": "0:09:23"}
|
536 |
+
{"current_steps": 480, "total_steps": 555, "loss": 0.4528, "lr": 4.376904259708892e-06, "epoch": 4.323959505061867, "percentage": 86.49, "elapsed_time": "1:00:51", "remaining_time": "0:09:30"}
|
537 |
+
{"current_steps": 481, "total_steps": 555, "loss": 0.447, "lr": 4.263070242680866e-06, "epoch": 4.3329583802024745, "percentage": 86.67, "elapsed_time": "1:02:32", "remaining_time": "0:09:37"}
|
538 |
+
{"current_steps": 482, "total_steps": 555, "loss": 0.4552, "lr": 4.1506527187359765e-06, "epoch": 4.3419572553430825, "percentage": 86.85, "elapsed_time": "1:04:12", "remaining_time": "0:09:43"}
|
539 |
+
{"current_steps": 483, "total_steps": 555, "loss": 0.449, "lr": 4.039656143731128e-06, "epoch": 4.35095613048369, "percentage": 87.03, "elapsed_time": "1:05:52", "remaining_time": "0:09:49"}
|
540 |
+
{"current_steps": 484, "total_steps": 555, "loss": 0.4541, "lr": 3.930084917201508e-06, "epoch": 4.359955005624297, "percentage": 87.21, "elapsed_time": "1:07:32", "remaining_time": "0:09:54"}
|
541 |
+
{"current_steps": 485, "total_steps": 555, "loss": 0.4472, "lr": 3.821943382186275e-06, "epoch": 4.368953880764904, "percentage": 87.39, "elapsed_time": "1:09:12", "remaining_time": "0:09:59"}
|
542 |
+
{"current_steps": 486, "total_steps": 555, "loss": 0.4541, "lr": 3.715235825056338e-06, "epoch": 4.377952755905512, "percentage": 87.57, "elapsed_time": "1:10:53", "remaining_time": "0:10:03"}
|
543 |
+
{"current_steps": 487, "total_steps": 555, "loss": 0.4507, "lr": 3.609966475344493e-06, "epoch": 4.386951631046119, "percentage": 87.75, "elapsed_time": "1:12:34", "remaining_time": "0:10:07"}
|
544 |
+
{"current_steps": 488, "total_steps": 555, "loss": 0.4538, "lr": 3.506139505577779e-06, "epoch": 4.395950506186726, "percentage": 87.93, "elapsed_time": "1:14:14", "remaining_time": "0:10:11"}
|
545 |
+
{"current_steps": 489, "total_steps": 555, "loss": 0.4547, "lr": 3.4037590311121015e-06, "epoch": 4.404949381327334, "percentage": 88.11, "elapsed_time": "1:15:54", "remaining_time": "0:10:14"}
|
546 |
+
{"current_steps": 490, "total_steps": 555, "loss": 0.4516, "lr": 3.302829109969072e-06, "epoch": 4.4139482564679415, "percentage": 88.29, "elapsed_time": "1:17:33", "remaining_time": "0:10:17"}
|
547 |
+
{"current_steps": 491, "total_steps": 555, "loss": 0.4556, "lr": 3.2033537426752236e-06, "epoch": 4.422947131608549, "percentage": 88.47, "elapsed_time": "1:19:14", "remaining_time": "0:10:19"}
|
548 |
+
{"current_steps": 492, "total_steps": 555, "loss": 0.4566, "lr": 3.1053368721033974e-06, "epoch": 4.431946006749157, "percentage": 88.65, "elapsed_time": "1:20:54", "remaining_time": "0:10:21"}
|
549 |
+
{"current_steps": 493, "total_steps": 555, "loss": 0.4455, "lr": 3.0087823833164596e-06, "epoch": 4.440944881889764, "percentage": 88.83, "elapsed_time": "1:22:34", "remaining_time": "0:10:23"}
|
550 |
+
{"current_steps": 494, "total_steps": 555, "loss": 0.4469, "lr": 2.9136941034133424e-06, "epoch": 4.449943757030371, "percentage": 89.01, "elapsed_time": "1:24:13", "remaining_time": "0:10:24"}
|
551 |
+
{"current_steps": 495, "total_steps": 555, "loss": 0.4501, "lr": 2.8200758013773313e-06, "epoch": 4.458942632170979, "percentage": 89.19, "elapsed_time": "1:25:53", "remaining_time": "0:10:24"}
|
552 |
+
{"current_steps": 496, "total_steps": 555, "loss": 0.4522, "lr": 2.7279311879266645e-06, "epoch": 4.467941507311586, "percentage": 89.37, "elapsed_time": "1:27:33", "remaining_time": "0:10:24"}
|
553 |
+
{"current_steps": 497, "total_steps": 555, "loss": 0.4539, "lr": 2.637263915367476e-06, "epoch": 4.476940382452193, "percentage": 89.55, "elapsed_time": "1:29:13", "remaining_time": "0:10:24"}
|
554 |
+
{"current_steps": 498, "total_steps": 555, "loss": 0.4505, "lr": 2.5480775774490195e-06, "epoch": 4.4859392575928005, "percentage": 89.73, "elapsed_time": "1:30:53", "remaining_time": "0:10:24"}
|
555 |
+
{"current_steps": 499, "total_steps": 555, "loss": 0.4506, "lr": 2.4603757092212057e-06, "epoch": 4.494938132733409, "percentage": 89.91, "elapsed_time": "1:32:34", "remaining_time": "0:10:23"}
|
556 |
+
{"current_steps": 500, "total_steps": 555, "loss": 0.4535, "lr": 2.374161786894513e-06, "epoch": 4.503937007874016, "percentage": 90.09, "elapsed_time": "1:34:14", "remaining_time": "0:10:21"}
|
557 |
+
{"current_steps": 501, "total_steps": 555, "loss": 0.4511, "lr": 2.2894392277022125e-06, "epoch": 4.512935883014623, "percentage": 90.27, "elapsed_time": "1:35:54", "remaining_time": "0:10:20"}
|
558 |
+
{"current_steps": 502, "total_steps": 555, "loss": 0.4531, "lr": 2.206211389764854e-06, "epoch": 4.521934758155231, "percentage": 90.45, "elapsed_time": "1:37:33", "remaining_time": "0:10:18"}
|
559 |
+
{"current_steps": 503, "total_steps": 555, "loss": 0.4537, "lr": 2.124481571957242e-06, "epoch": 4.530933633295838, "percentage": 90.63, "elapsed_time": "1:39:13", "remaining_time": "0:10:15"}
|
560 |
+
{"current_steps": 504, "total_steps": 555, "loss": 0.4431, "lr": 2.0442530137776374e-06, "epoch": 4.539932508436445, "percentage": 90.81, "elapsed_time": "1:40:53", "remaining_time": "0:10:12"}
|
561 |
+
{"current_steps": 505, "total_steps": 555, "loss": 0.4567, "lr": 1.9655288952193442e-06, "epoch": 4.548931383577052, "percentage": 90.99, "elapsed_time": "1:42:33", "remaining_time": "0:10:09"}
|
562 |
+
{"current_steps": 506, "total_steps": 555, "loss": 0.4507, "lr": 1.8883123366446955e-06, "epoch": 4.55793025871766, "percentage": 91.17, "elapsed_time": "1:44:13", "remaining_time": "0:10:05"}
|
563 |
+
{"current_steps": 507, "total_steps": 555, "loss": 0.45, "lr": 1.8126063986613652e-06, "epoch": 4.566929133858268, "percentage": 91.35, "elapsed_time": "1:45:53", "remaining_time": "0:10:01"}
|
564 |
+
{"current_steps": 508, "total_steps": 555, "loss": 0.4489, "lr": 1.7384140820010253e-06, "epoch": 4.575928008998876, "percentage": 91.53, "elapsed_time": "1:47:33", "remaining_time": "0:09:57"}
|
565 |
+
{"current_steps": 509, "total_steps": 555, "loss": 0.4534, "lr": 1.6657383274004545e-06, "epoch": 4.584926884139483, "percentage": 91.71, "elapsed_time": "1:49:13", "remaining_time": "0:09:52"}
|
566 |
+
{"current_steps": 510, "total_steps": 555, "loss": 0.4469, "lr": 1.5945820154849512e-06, "epoch": 4.59392575928009, "percentage": 91.89, "elapsed_time": "1:50:53", "remaining_time": "0:09:47"}
|
567 |
+
{"current_steps": 511, "total_steps": 555, "loss": 0.4535, "lr": 1.524947966654131e-06, "epoch": 4.602924634420697, "percentage": 92.07, "elapsed_time": "1:52:33", "remaining_time": "0:09:41"}
|
568 |
+
{"current_steps": 512, "total_steps": 555, "loss": 0.4535, "lr": 1.4568389409702e-06, "epoch": 4.611923509561305, "percentage": 92.25, "elapsed_time": "1:54:13", "remaining_time": "0:09:35"}
|
569 |
+
{"current_steps": 513, "total_steps": 555, "loss": 0.4552, "lr": 1.390257638048489e-06, "epoch": 4.620922384701912, "percentage": 92.43, "elapsed_time": "1:55:53", "remaining_time": "0:09:29"}
|
570 |
+
{"current_steps": 514, "total_steps": 555, "loss": 0.4502, "lr": 1.3252066969504874e-06, "epoch": 4.6299212598425195, "percentage": 92.61, "elapsed_time": "1:57:33", "remaining_time": "0:09:22"}
|
571 |
+
{"current_steps": 515, "total_steps": 555, "loss": 0.451, "lr": 1.261688696079233e-06, "epoch": 4.6389201349831275, "percentage": 92.79, "elapsed_time": "1:59:14", "remaining_time": "0:09:15"}
|
572 |
+
{"current_steps": 516, "total_steps": 555, "loss": 0.4513, "lr": 1.1997061530771004e-06, "epoch": 4.647919010123735, "percentage": 92.97, "elapsed_time": "2:00:54", "remaining_time": "0:09:08"}
|
573 |
+
{"current_steps": 517, "total_steps": 555, "loss": 0.4509, "lr": 1.1392615247260275e-06, "epoch": 4.656917885264342, "percentage": 93.15, "elapsed_time": "2:02:34", "remaining_time": "0:09:00"}
|
574 |
+
{"current_steps": 518, "total_steps": 555, "loss": 0.4497, "lr": 1.080357206850131e-06, "epoch": 4.665916760404949, "percentage": 93.33, "elapsed_time": "2:04:15", "remaining_time": "0:08:52"}
|
575 |
+
{"current_steps": 519, "total_steps": 555, "loss": 0.4556, "lr": 1.0229955342207254e-06, "epoch": 4.674915635545557, "percentage": 93.51, "elapsed_time": "2:05:54", "remaining_time": "0:08:44"}
|
576 |
+
{"current_steps": 520, "total_steps": 555, "loss": 0.4537, "lr": 9.67178780463809e-07, "epoch": 4.683914510686164, "percentage": 93.69, "elapsed_time": "2:07:35", "remaining_time": "0:08:35"}
|
577 |
+
{"current_steps": 521, "total_steps": 555, "loss": 0.4534, "lr": 9.129091579699412e-07, "epoch": 4.692913385826771, "percentage": 93.87, "elapsed_time": "2:09:15", "remaining_time": "0:08:26"}
|
578 |
+
{"current_steps": 522, "total_steps": 555, "loss": 0.4501, "lr": 8.601888178065177e-07, "epoch": 4.701912260967379, "percentage": 94.05, "elapsed_time": "2:10:54", "remaining_time": "0:08:16"}
|
579 |
+
{"current_steps": 523, "total_steps": 555, "loss": 0.4506, "lr": 8.090198496325485e-07, "epoch": 4.7109111361079865, "percentage": 94.23, "elapsed_time": "2:12:35", "remaining_time": "0:08:06"}
|
580 |
+
{"current_steps": 524, "total_steps": 555, "loss": 0.4529, "lr": 7.594042816158187e-07, "epoch": 4.719910011248594, "percentage": 94.41, "elapsed_time": "2:14:15", "remaining_time": "0:07:56"}
|
581 |
+
{"current_steps": 525, "total_steps": 555, "loss": 0.4531, "lr": 7.113440803524896e-07, "epoch": 4.728908886389202, "percentage": 94.59, "elapsed_time": "2:15:54", "remaining_time": "0:07:45"}
|
582 |
+
{"current_steps": 526, "total_steps": 555, "loss": 0.4522, "lr": 6.648411507891528e-07, "epoch": 4.737907761529809, "percentage": 94.77, "elapsed_time": "2:17:35", "remaining_time": "0:07:35"}
|
583 |
+
{"current_steps": 527, "total_steps": 555, "loss": 0.4495, "lr": 6.198973361473349e-07, "epoch": 4.746906636670416, "percentage": 94.95, "elapsed_time": "2:19:15", "remaining_time": "0:07:23"}
|
584 |
+
{"current_steps": 528, "total_steps": 555, "loss": 0.4526, "lr": 5.765144178504222e-07, "epoch": 4.755905511811024, "percentage": 95.14, "elapsed_time": "2:20:55", "remaining_time": "0:07:12"}
|
585 |
+
{"current_steps": 529, "total_steps": 555, "loss": 0.4532, "lr": 5.34694115453065e-07, "epoch": 4.764904386951631, "percentage": 95.32, "elapsed_time": "2:22:34", "remaining_time": "0:07:00"}
|
586 |
+
{"current_steps": 530, "total_steps": 555, "loss": 0.4529, "lr": 4.944380865730125e-07, "epoch": 4.773903262092238, "percentage": 95.5, "elapsed_time": "2:24:14", "remaining_time": "0:06:48"}
|
587 |
+
{"current_steps": 531, "total_steps": 555, "loss": 0.4502, "lr": 4.5574792682541167e-07, "epoch": 4.7829021372328455, "percentage": 95.68, "elapsed_time": "2:25:54", "remaining_time": "0:06:35"}
|
588 |
+
{"current_steps": 532, "total_steps": 555, "loss": 0.4471, "lr": 4.186251697595678e-07, "epoch": 4.791901012373454, "percentage": 95.86, "elapsed_time": "2:27:34", "remaining_time": "0:06:22"}
|
589 |
+
{"current_steps": 533, "total_steps": 555, "loss": 0.4434, "lr": 3.83071286798149e-07, "epoch": 4.800899887514061, "percentage": 96.04, "elapsed_time": "2:29:14", "remaining_time": "0:06:09"}
|
590 |
+
{"current_steps": 534, "total_steps": 555, "loss": 0.45, "lr": 3.4908768717887286e-07, "epoch": 4.809898762654668, "percentage": 96.22, "elapsed_time": "2:30:54", "remaining_time": "0:05:56"}
|
591 |
+
{"current_steps": 535, "total_steps": 555, "loss": 0.4539, "lr": 3.1667571789864015e-07, "epoch": 4.818897637795276, "percentage": 96.4, "elapsed_time": "2:32:34", "remaining_time": "0:05:42"}
|
592 |
+
{"current_steps": 536, "total_steps": 555, "loss": 0.451, "lr": 2.858366636601639e-07, "epoch": 4.827896512935883, "percentage": 96.58, "elapsed_time": "2:34:14", "remaining_time": "0:05:28"}
|
593 |
+
{"current_steps": 537, "total_steps": 555, "loss": 0.4501, "lr": 2.5657174682101936e-07, "epoch": 4.83689538807649, "percentage": 96.76, "elapsed_time": "2:35:54", "remaining_time": "0:05:13"}
|
594 |
+
{"current_steps": 538, "total_steps": 555, "loss": 0.4495, "lr": 2.288821273452113e-07, "epoch": 4.845894263217097, "percentage": 96.94, "elapsed_time": "2:37:34", "remaining_time": "0:04:58"}
|
595 |
+
{"current_steps": 539, "total_steps": 555, "loss": 0.4527, "lr": 2.027689027572066e-07, "epoch": 4.854893138357705, "percentage": 97.12, "elapsed_time": "2:39:15", "remaining_time": "0:04:43"}
|
596 |
+
{"current_steps": 540, "total_steps": 555, "loss": 0.4464, "lr": 1.7823310809840456e-07, "epoch": 4.863892013498313, "percentage": 97.3, "elapsed_time": "2:40:55", "remaining_time": "0:04:28"}
|
597 |
+
{"current_steps": 541, "total_steps": 555, "loss": 0.4519, "lr": 1.55275715886134e-07, "epoch": 4.872890888638921, "percentage": 97.48, "elapsed_time": "2:42:34", "remaining_time": "0:04:12"}
|
598 |
+
{"current_steps": 542, "total_steps": 555, "loss": 0.455, "lr": 1.3389763607509765e-07, "epoch": 4.881889763779528, "percentage": 97.66, "elapsed_time": "2:44:15", "remaining_time": "0:03:56"}
|
599 |
+
{"current_steps": 543, "total_steps": 555, "loss": 0.4502, "lr": 1.1409971602130754e-07, "epoch": 4.890888638920135, "percentage": 97.84, "elapsed_time": "2:45:55", "remaining_time": "0:03:40"}
|
600 |
+
{"current_steps": 544, "total_steps": 555, "loss": 0.4541, "lr": 9.588274044848523e-08, "epoch": 4.899887514060742, "percentage": 98.02, "elapsed_time": "2:47:35", "remaining_time": "0:03:23"}
|
601 |
+
{"current_steps": 545, "total_steps": 555, "loss": 0.4534, "lr": 7.924743141698888e-08, "epoch": 4.90888638920135, "percentage": 98.2, "elapsed_time": "2:49:15", "remaining_time": "0:03:06"}
|
602 |
+
{"current_steps": 546, "total_steps": 555, "loss": 0.4514, "lr": 6.419444829515175e-08, "epoch": 4.917885264341957, "percentage": 98.38, "elapsed_time": "2:50:55", "remaining_time": "0:02:49"}
|
603 |
+
{"current_steps": 547, "total_steps": 555, "loss": 0.4483, "lr": 5.072438773318755e-08, "epoch": 4.926884139482564, "percentage": 98.56, "elapsed_time": "2:52:35", "remaining_time": "0:02:31"}
|
604 |
+
{"current_steps": 548, "total_steps": 555, "loss": 0.453, "lr": 3.8837783639507076e-08, "epoch": 4.9358830146231725, "percentage": 98.74, "elapsed_time": "2:54:15", "remaining_time": "0:02:13"}
|
605 |
+
{"current_steps": 549, "total_steps": 555, "loss": 0.4519, "lr": 2.8535107159584076e-08, "epoch": 4.94488188976378, "percentage": 98.92, "elapsed_time": "2:55:55", "remaining_time": "0:01:55"}
|
606 |
+
{"current_steps": 550, "total_steps": 555, "loss": 0.4498, "lr": 1.9816766657254626e-08, "epoch": 4.953880764904387, "percentage": 99.1, "elapsed_time": "2:57:36", "remaining_time": "0:01:36"}
|
607 |
+
{"current_steps": 551, "total_steps": 555, "loss": 0.4495, "lr": 1.268310769855674e-08, "epoch": 4.962879640044994, "percentage": 99.28, "elapsed_time": "2:59:16", "remaining_time": "0:01:18"}
|
608 |
+
{"current_steps": 552, "total_steps": 555, "loss": 0.4487, "lr": 7.134413038012433e-09, "epoch": 4.971878515185602, "percentage": 99.46, "elapsed_time": "3:00:56", "remaining_time": "0:00:59"}
|
609 |
+
{"current_steps": 553, "total_steps": 555, "loss": 0.4502, "lr": 3.170902607432247e-09, "epoch": 4.980877390326209, "percentage": 99.64, "elapsed_time": "3:02:36", "remaining_time": "0:00:39"}
|
610 |
+
{"current_steps": 554, "total_steps": 555, "loss": 0.4553, "lr": 7.92733507188892e-10, "epoch": 4.989876265466816, "percentage": 99.82, "elapsed_time": "3:04:16", "remaining_time": "0:00:19"}
|
611 |
+
{"current_steps": 555, "total_steps": 555, "loss": 0.4591, "lr": 0.0, "epoch": 4.998875140607424, "percentage": 100.0, "elapsed_time": "3:05:56", "remaining_time": "0:00:00"}
|
612 |
+
{"current_steps": 555, "total_steps": 555, "epoch": 4.998875140607424, "percentage": 100.0, "elapsed_time": "3:08:49", "remaining_time": "0:00:00"}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc95d8d0203bed7e55a359199e3eb547b4c92b98d973ab3a276edc27082afed8
|
3 |
+
size 7416
|