Training in progress, step 3561
Browse files
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:e53b09f08a6887a59a577f8afe6a2e0e027b1c32e0cafeadac549e218398e14d
|
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 sha256:3b3b9c3e9ec4611628804638a0fc7a4459bb36aa3fd3ff39d0b8a5e89425f450
|
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 sha256:92e1ee7dcd624e64d28663eb776996e9f5f46623ec1f5ae24a2e8fb410bf3702
|
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 sha256:8ce8f2753272f4f02abce119af78fb4ec91c006b8c317577d077538164e8a6fe
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -3504,3 +3504,59 @@
|
|
3504 |
{"current_steps": 3504, "total_steps": 3561, "loss": 0.3899, "lr": 7.807129773110822e-09, "epoch": 2.9511510387422795, "percentage": 98.4, "elapsed_time": "19:55:59", "remaining_time": "0:19:27"}
|
3505 |
{"current_steps": 3505, "total_steps": 3561, "loss": 0.3891, "lr": 7.535666554866483e-09, "epoch": 2.9519932622122402, "percentage": 98.43, "elapsed_time": "19:56:18", "remaining_time": "0:19:06"}
|
3506 |
{"current_steps": 3506, "total_steps": 3561, "loss": 0.3895, "lr": 7.269003208740244e-09, "epoch": 2.952835485682201, "percentage": 98.46, "elapsed_time": "19:56:39", "remaining_time": "0:18:46"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3504 |
{"current_steps": 3504, "total_steps": 3561, "loss": 0.3899, "lr": 7.807129773110822e-09, "epoch": 2.9511510387422795, "percentage": 98.4, "elapsed_time": "19:55:59", "remaining_time": "0:19:27"}
|
3505 |
{"current_steps": 3505, "total_steps": 3561, "loss": 0.3891, "lr": 7.535666554866483e-09, "epoch": 2.9519932622122402, "percentage": 98.43, "elapsed_time": "19:56:18", "remaining_time": "0:19:06"}
|
3506 |
{"current_steps": 3506, "total_steps": 3561, "loss": 0.3895, "lr": 7.269003208740244e-09, "epoch": 2.952835485682201, "percentage": 98.46, "elapsed_time": "19:56:39", "remaining_time": "0:18:46"}
|
3507 |
+
{"current_steps": 3507, "total_steps": 3561, "loss": 0.3721, "lr": 7.007139991108136e-09, "epoch": 2.9536777091521618, "percentage": 98.48, "elapsed_time": "19:56:59", "remaining_time": "0:18:25"}
|
3508 |
+
{"current_steps": 3508, "total_steps": 3561, "loss": 0.4012, "lr": 6.750077153731549e-09, "epoch": 2.9545199326221225, "percentage": 98.51, "elapsed_time": "19:57:21", "remaining_time": "0:18:05"}
|
3509 |
+
{"current_steps": 3509, "total_steps": 3561, "loss": 0.3837, "lr": 6.497814943756675e-09, "epoch": 2.9553621560920833, "percentage": 98.54, "elapsed_time": "19:57:41", "remaining_time": "0:17:44"}
|
3510 |
+
{"current_steps": 3510, "total_steps": 3561, "loss": 0.4119, "lr": 6.25035360371451e-09, "epoch": 2.9562043795620436, "percentage": 98.57, "elapsed_time": "19:58:00", "remaining_time": "0:17:24"}
|
3511 |
+
{"current_steps": 3511, "total_steps": 3561, "loss": 0.4078, "lr": 6.00769337151974e-09, "epoch": 2.9570466030320044, "percentage": 98.6, "elapsed_time": "19:58:20", "remaining_time": "0:17:03"}
|
3512 |
+
{"current_steps": 3512, "total_steps": 3561, "loss": 0.3523, "lr": 5.769834480472414e-09, "epoch": 2.957888826501965, "percentage": 98.62, "elapsed_time": "19:58:40", "remaining_time": "0:16:43"}
|
3513 |
+
{"current_steps": 3513, "total_steps": 3561, "loss": 0.3853, "lr": 5.536777159254603e-09, "epoch": 2.958731049971926, "percentage": 98.65, "elapsed_time": "19:59:01", "remaining_time": "0:16:22"}
|
3514 |
+
{"current_steps": 3514, "total_steps": 3561, "loss": 0.4426, "lr": 5.308521631934294e-09, "epoch": 2.9595732734418867, "percentage": 98.68, "elapsed_time": "19:59:22", "remaining_time": "0:16:02"}
|
3515 |
+
{"current_steps": 3515, "total_steps": 3561, "loss": 0.3684, "lr": 5.08506811796039e-09, "epoch": 2.960415496911847, "percentage": 98.71, "elapsed_time": "19:59:42", "remaining_time": "0:15:42"}
|
3516 |
+
{"current_steps": 3516, "total_steps": 3561, "loss": 0.3978, "lr": 4.866416832167153e-09, "epoch": 2.9612577203818082, "percentage": 98.74, "elapsed_time": "20:00:00", "remaining_time": "0:15:21"}
|
3517 |
+
{"current_steps": 3517, "total_steps": 3561, "loss": 0.4047, "lr": 4.652567984770873e-09, "epoch": 2.9620999438517686, "percentage": 98.76, "elapsed_time": "20:00:18", "remaining_time": "0:15:00"}
|
3518 |
+
{"current_steps": 3518, "total_steps": 3561, "loss": 0.3751, "lr": 4.443521781370974e-09, "epoch": 2.9629421673217293, "percentage": 98.79, "elapsed_time": "20:00:36", "remaining_time": "0:14:40"}
|
3519 |
+
{"current_steps": 3519, "total_steps": 3561, "loss": 0.4199, "lr": 4.239278422948911e-09, "epoch": 2.96378439079169, "percentage": 98.82, "elapsed_time": "20:00:56", "remaining_time": "0:14:20"}
|
3520 |
+
{"current_steps": 3520, "total_steps": 3561, "loss": 0.3612, "lr": 4.0398381058692755e-09, "epoch": 2.964626614261651, "percentage": 98.85, "elapsed_time": "20:01:14", "remaining_time": "0:13:59"}
|
3521 |
+
{"current_steps": 3521, "total_steps": 3561, "loss": 0.376, "lr": 3.845201021879241e-09, "epoch": 2.9654688377316116, "percentage": 98.88, "elapsed_time": "20:01:34", "remaining_time": "0:13:39"}
|
3522 |
+
{"current_steps": 3522, "total_steps": 3561, "loss": 0.3834, "lr": 3.655367358106343e-09, "epoch": 2.966311061201572, "percentage": 98.9, "elapsed_time": "20:01:52", "remaining_time": "0:13:18"}
|
3523 |
+
{"current_steps": 3523, "total_steps": 3561, "loss": 0.4069, "lr": 3.470337297062365e-09, "epoch": 2.9671532846715327, "percentage": 98.93, "elapsed_time": "20:02:12", "remaining_time": "0:12:58"}
|
3524 |
+
{"current_steps": 3524, "total_steps": 3561, "loss": 0.3782, "lr": 3.290111016638342e-09, "epoch": 2.9679955081414935, "percentage": 98.96, "elapsed_time": "20:02:32", "remaining_time": "0:12:37"}
|
3525 |
+
{"current_steps": 3525, "total_steps": 3561, "loss": 0.3787, "lr": 3.1146886901090024e-09, "epoch": 2.9688377316114543, "percentage": 98.99, "elapsed_time": "20:02:50", "remaining_time": "0:12:17"}
|
3526 |
+
{"current_steps": 3526, "total_steps": 3561, "loss": 0.37, "lr": 2.9440704861288804e-09, "epoch": 2.969679955081415, "percentage": 99.02, "elapsed_time": "20:03:13", "remaining_time": "0:11:56"}
|
3527 |
+
{"current_steps": 3527, "total_steps": 3561, "loss": 0.3992, "lr": 2.7782565687339836e-09, "epoch": 2.970522178551376, "percentage": 99.05, "elapsed_time": "20:03:35", "remaining_time": "0:11:36"}
|
3528 |
+
{"current_steps": 3528, "total_steps": 3561, "loss": 0.3884, "lr": 2.617247097342901e-09, "epoch": 2.9713644020213366, "percentage": 99.07, "elapsed_time": "20:03:56", "remaining_time": "0:11:15"}
|
3529 |
+
{"current_steps": 3529, "total_steps": 3561, "loss": 0.365, "lr": 2.461042226752919e-09, "epoch": 2.972206625491297, "percentage": 99.1, "elapsed_time": "20:04:15", "remaining_time": "0:10:55"}
|
3530 |
+
{"current_steps": 3530, "total_steps": 3561, "loss": 0.4103, "lr": 2.3096421071433508e-09, "epoch": 2.9730488489612577, "percentage": 99.13, "elapsed_time": "20:04:37", "remaining_time": "0:10:34"}
|
3531 |
+
{"current_steps": 3531, "total_steps": 3561, "loss": 0.3789, "lr": 2.1630468840738716e-09, "epoch": 2.9738910724312184, "percentage": 99.16, "elapsed_time": "20:04:59", "remaining_time": "0:10:14"}
|
3532 |
+
{"current_steps": 3532, "total_steps": 3561, "loss": 0.389, "lr": 2.0212566984845194e-09, "epoch": 2.974733295901179, "percentage": 99.19, "elapsed_time": "20:05:19", "remaining_time": "0:09:53"}
|
3533 |
+
{"current_steps": 3533, "total_steps": 3561, "loss": 0.3667, "lr": 1.8842716866956935e-09, "epoch": 2.97557551937114, "percentage": 99.21, "elapsed_time": "20:05:41", "remaining_time": "0:09:33"}
|
3534 |
+
{"current_steps": 3534, "total_steps": 3561, "loss": 0.4202, "lr": 1.7520919804075997e-09, "epoch": 2.9764177428411003, "percentage": 99.24, "elapsed_time": "20:06:02", "remaining_time": "0:09:12"}
|
3535 |
+
{"current_steps": 3535, "total_steps": 3561, "loss": 0.3371, "lr": 1.624717706701917e-09, "epoch": 2.977259966311061, "percentage": 99.27, "elapsed_time": "20:06:22", "remaining_time": "0:08:52"}
|
3536 |
+
{"current_steps": 3536, "total_steps": 3561, "loss": 0.4112, "lr": 1.5021489880384653e-09, "epoch": 2.978102189781022, "percentage": 99.3, "elapsed_time": "20:06:41", "remaining_time": "0:08:31"}
|
3537 |
+
{"current_steps": 3537, "total_steps": 3561, "loss": 0.3768, "lr": 1.3843859422574269e-09, "epoch": 2.9789444132509826, "percentage": 99.33, "elapsed_time": "20:07:01", "remaining_time": "0:08:11"}
|
3538 |
+
{"current_steps": 3538, "total_steps": 3561, "loss": 0.4226, "lr": 1.2714286825793453e-09, "epoch": 2.9797866367209433, "percentage": 99.35, "elapsed_time": "20:07:20", "remaining_time": "0:07:50"}
|
3539 |
+
{"current_steps": 3539, "total_steps": 3561, "loss": 0.3991, "lr": 1.163277317604572e-09, "epoch": 2.980628860190904, "percentage": 99.38, "elapsed_time": "20:07:43", "remaining_time": "0:07:30"}
|
3540 |
+
{"current_steps": 3540, "total_steps": 3561, "loss": 0.3532, "lr": 1.0599319513115992e-09, "epoch": 2.981471083660865, "percentage": 99.41, "elapsed_time": "20:08:04", "remaining_time": "0:07:09"}
|
3541 |
+
{"current_steps": 3541, "total_steps": 3561, "loss": 0.337, "lr": 9.613926830587262e-10, "epoch": 2.982313307130825, "percentage": 99.44, "elapsed_time": "20:08:22", "remaining_time": "0:06:49"}
|
3542 |
+
{"current_steps": 3542, "total_steps": 3561, "loss": 0.4365, "lr": 8.676596075851696e-10, "epoch": 2.983155530600786, "percentage": 99.47, "elapsed_time": "20:08:40", "remaining_time": "0:06:29"}
|
3543 |
+
{"current_steps": 3543, "total_steps": 3561, "loss": 0.3759, "lr": 7.787328150071771e-10, "epoch": 2.9839977540707467, "percentage": 99.49, "elapsed_time": "20:09:00", "remaining_time": "0:06:08"}
|
3544 |
+
{"current_steps": 3544, "total_steps": 3561, "loss": 0.4245, "lr": 6.946123908208036e-10, "epoch": 2.9848399775407075, "percentage": 99.52, "elapsed_time": "20:09:22", "remaining_time": "0:05:48"}
|
3545 |
+
{"current_steps": 3545, "total_steps": 3561, "loss": 0.3555, "lr": 6.152984159024655e-10, "epoch": 2.9856822010106683, "percentage": 99.55, "elapsed_time": "20:09:41", "remaining_time": "0:05:27"}
|
3546 |
+
{"current_steps": 3546, "total_steps": 3561, "loss": 0.4007, "lr": 5.40790966505611e-10, "epoch": 2.9865244244806286, "percentage": 99.58, "elapsed_time": "20:10:02", "remaining_time": "0:05:07"}
|
3547 |
+
{"current_steps": 3547, "total_steps": 3561, "loss": 0.3522, "lr": 4.710901142634949e-10, "epoch": 2.98736664795059, "percentage": 99.61, "elapsed_time": "20:10:20", "remaining_time": "0:04:46"}
|
3548 |
+
{"current_steps": 3548, "total_steps": 3561, "loss": 0.4172, "lr": 4.061959261886239e-10, "epoch": 2.98820887142055, "percentage": 99.63, "elapsed_time": "20:10:40", "remaining_time": "0:04:26"}
|
3549 |
+
{"current_steps": 3549, "total_steps": 3561, "loss": 0.4197, "lr": 3.4610846467109106e-10, "epoch": 2.989051094890511, "percentage": 99.66, "elapsed_time": "20:11:01", "remaining_time": "0:04:05"}
|
3550 |
+
{"current_steps": 3550, "total_steps": 3561, "loss": 0.3749, "lr": 2.9082778748135146e-10, "epoch": 2.9898933183604717, "percentage": 99.69, "elapsed_time": "20:11:20", "remaining_time": "0:03:45"}
|
3551 |
+
{"current_steps": 3551, "total_steps": 3561, "loss": 0.3636, "lr": 2.403539477668915e-10, "epoch": 2.9907355418304324, "percentage": 99.72, "elapsed_time": "20:11:41", "remaining_time": "0:03:24"}
|
3552 |
+
{"current_steps": 3552, "total_steps": 3561, "loss": 0.41, "lr": 1.9468699405444936e-10, "epoch": 2.991577765300393, "percentage": 99.75, "elapsed_time": "20:12:01", "remaining_time": "0:03:04"}
|
3553 |
+
{"current_steps": 3553, "total_steps": 3561, "loss": 0.4029, "lr": 1.538269702494599e-10, "epoch": 2.9924199887703535, "percentage": 99.78, "elapsed_time": "20:12:22", "remaining_time": "0:02:43"}
|
3554 |
+
{"current_steps": 3554, "total_steps": 3561, "loss": 0.3442, "lr": 1.1777391563549956e-10, "epoch": 2.9932622122403143, "percentage": 99.8, "elapsed_time": "20:12:42", "remaining_time": "0:02:23"}
|
3555 |
+
{"current_steps": 3555, "total_steps": 3561, "loss": 0.3797, "lr": 8.652786487484133e-11, "epoch": 2.994104435710275, "percentage": 99.83, "elapsed_time": "20:13:02", "remaining_time": "0:02:02"}
|
3556 |
+
{"current_steps": 3556, "total_steps": 3561, "loss": 0.434, "lr": 6.008884800845494e-11, "epoch": 2.994946659180236, "percentage": 99.86, "elapsed_time": "20:13:24", "remaining_time": "0:01:42"}
|
3557 |
+
{"current_steps": 3557, "total_steps": 3561, "loss": 0.3726, "lr": 3.8456890455451646e-11, "epoch": 2.9957888826501966, "percentage": 99.89, "elapsed_time": "20:13:44", "remaining_time": "0:01:21"}
|
3558 |
+
{"current_steps": 3558, "total_steps": 3561, "loss": 0.3561, "lr": 2.1632013013084265e-11, "epoch": 2.9966311061201574, "percentage": 99.92, "elapsed_time": "20:14:05", "remaining_time": "0:01:01"}
|
3559 |
+
{"current_steps": 3559, "total_steps": 3561, "loss": 0.4033, "lr": 9.614231857302258e-12, "epoch": 2.997473329590118, "percentage": 99.94, "elapsed_time": "20:14:24", "remaining_time": "0:00:40"}
|
3560 |
+
{"current_steps": 3560, "total_steps": 3561, "loss": 0.3676, "lr": 2.403558542196649e-12, "epoch": 2.9983155530600785, "percentage": 99.97, "elapsed_time": "20:14:45", "remaining_time": "0:00:20"}
|
3561 |
+
{"current_steps": 3561, "total_steps": 3561, "loss": 0.3956, "lr": 0.0, "epoch": 2.9991577765300392, "percentage": 100.0, "elapsed_time": "20:15:06", "remaining_time": "0:00:00"}
|
3562 |
+
{"current_steps": 3561, "total_steps": 3561, "epoch": 2.9991577765300392, "percentage": 100.0, "elapsed_time": "20:15:58", "remaining_time": "0:00:00"}
|