Training in progress, step 348
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:f8f682a35358e2eb00d3c018feda3a8a6eb2e3c6bec92f3f97e6de5f0871a1ac
|
| 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 sha256:26bdaca7f0dd609a7ee8563f4878cbf6a223cea69b3a7770d28ae1d9105ba051
|
| 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:f1b842ebb3725f57b80bfa9a65e9763a664a98f8f3185301da7e4d3795e00b37
|
| 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 sha256:636cc85b337144183826bba8c1ce3cef15df22468af4f3299e0dc5c245c2a10b
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -304,3 +304,46 @@
|
|
| 304 |
{"current_steps": 304, "total_steps": 348, "loss": 0.3717, "lr": 4.797183254069176e-07, "epoch": 2.6131805157593124, "percentage": 87.36, "elapsed_time": "1:43:58", "remaining_time": "0:15:02"}
|
| 305 |
{"current_steps": 305, "total_steps": 348, "loss": 0.3808, "lr": 4.5849655814915683e-07, "epoch": 2.621776504297994, "percentage": 87.64, "elapsed_time": "1:44:17", "remaining_time": "0:14:42"}
|
| 306 |
{"current_steps": 306, "total_steps": 348, "loss": 0.3915, "lr": 4.3773230771879004e-07, "epoch": 2.6303724928366763, "percentage": 87.93, "elapsed_time": "1:44:38", "remaining_time": "0:14:21"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 304 |
{"current_steps": 304, "total_steps": 348, "loss": 0.3717, "lr": 4.797183254069176e-07, "epoch": 2.6131805157593124, "percentage": 87.36, "elapsed_time": "1:43:58", "remaining_time": "0:15:02"}
|
| 305 |
{"current_steps": 305, "total_steps": 348, "loss": 0.3808, "lr": 4.5849655814915683e-07, "epoch": 2.621776504297994, "percentage": 87.64, "elapsed_time": "1:44:17", "remaining_time": "0:14:42"}
|
| 306 |
{"current_steps": 306, "total_steps": 348, "loss": 0.3915, "lr": 4.3773230771879004e-07, "epoch": 2.6303724928366763, "percentage": 87.93, "elapsed_time": "1:44:38", "remaining_time": "0:14:21"}
|
| 307 |
+
{"current_steps": 307, "total_steps": 348, "loss": 0.4013, "lr": 4.1742766593278974e-07, "epoch": 2.6389684813753584, "percentage": 88.22, "elapsed_time": "1:44:58", "remaining_time": "0:14:01"}
|
| 308 |
+
{"current_steps": 308, "total_steps": 348, "loss": 0.4193, "lr": 3.9758467830656623e-07, "epoch": 2.64756446991404, "percentage": 88.51, "elapsed_time": "1:45:15", "remaining_time": "0:13:40"}
|
| 309 |
+
{"current_steps": 309, "total_steps": 348, "loss": 0.3669, "lr": 3.782053438479094e-07, "epoch": 2.656160458452722, "percentage": 88.79, "elapsed_time": "1:45:33", "remaining_time": "0:13:19"}
|
| 310 |
+
{"current_steps": 310, "total_steps": 348, "loss": 0.3754, "lr": 3.5929161485559694e-07, "epoch": 2.664756446991404, "percentage": 89.08, "elapsed_time": "1:45:54", "remaining_time": "0:12:58"}
|
| 311 |
+
{"current_steps": 311, "total_steps": 348, "loss": 0.3734, "lr": 3.4084539672271764e-07, "epoch": 2.673352435530086, "percentage": 89.37, "elapsed_time": "1:46:15", "remaining_time": "0:12:38"}
|
| 312 |
+
{"current_steps": 312, "total_steps": 348, "loss": 0.4144, "lr": 3.228685477447291e-07, "epoch": 2.681948424068768, "percentage": 89.66, "elapsed_time": "1:46:37", "remaining_time": "0:12:18"}
|
| 313 |
+
{"current_steps": 313, "total_steps": 348, "loss": 0.3474, "lr": 3.0536287893223603e-07, "epoch": 2.6905444126074496, "percentage": 89.94, "elapsed_time": "1:46:58", "remaining_time": "0:11:57"}
|
| 314 |
+
{"current_steps": 314, "total_steps": 348, "loss": 0.4335, "lr": 2.883301538285582e-07, "epoch": 2.6991404011461317, "percentage": 90.23, "elapsed_time": "1:47:18", "remaining_time": "0:11:37"}
|
| 315 |
+
{"current_steps": 315, "total_steps": 348, "loss": 0.4055, "lr": 2.717720883320685e-07, "epoch": 2.707736389684814, "percentage": 90.52, "elapsed_time": "1:47:40", "remaining_time": "0:11:16"}
|
| 316 |
+
{"current_steps": 316, "total_steps": 348, "loss": 0.3691, "lr": 2.556903505233216e-07, "epoch": 2.7163323782234956, "percentage": 90.8, "elapsed_time": "1:47:59", "remaining_time": "0:10:56"}
|
| 317 |
+
{"current_steps": 317, "total_steps": 348, "loss": 0.3979, "lr": 2.4008656049701875e-07, "epoch": 2.7249283667621778, "percentage": 91.09, "elapsed_time": "1:48:20", "remaining_time": "0:10:35"}
|
| 318 |
+
{"current_steps": 318, "total_steps": 348, "loss": 0.3735, "lr": 2.2496229019879635e-07, "epoch": 2.7335243553008595, "percentage": 91.38, "elapsed_time": "1:48:39", "remaining_time": "0:10:15"}
|
| 319 |
+
{"current_steps": 319, "total_steps": 348, "loss": 0.3772, "lr": 2.1031906326685946e-07, "epoch": 2.7421203438395416, "percentage": 91.67, "elapsed_time": "1:48:58", "remaining_time": "0:09:54"}
|
| 320 |
+
{"current_steps": 320, "total_steps": 348, "loss": 0.43, "lr": 1.9615835487849677e-07, "epoch": 2.7507163323782233, "percentage": 91.95, "elapsed_time": "1:49:17", "remaining_time": "0:09:33"}
|
| 321 |
+
{"current_steps": 321, "total_steps": 348, "loss": 0.363, "lr": 1.824815916014644e-07, "epoch": 2.7593123209169055, "percentage": 92.24, "elapsed_time": "1:49:39", "remaining_time": "0:09:13"}
|
| 322 |
+
{"current_steps": 322, "total_steps": 348, "loss": 0.427, "lr": 1.6929015125027314e-07, "epoch": 2.7679083094555876, "percentage": 92.53, "elapsed_time": "1:49:59", "remaining_time": "0:08:52"}
|
| 323 |
+
{"current_steps": 323, "total_steps": 348, "loss": 0.3538, "lr": 1.5658536274738623e-07, "epoch": 2.7765042979942693, "percentage": 92.82, "elapsed_time": "1:50:18", "remaining_time": "0:08:32"}
|
| 324 |
+
{"current_steps": 324, "total_steps": 348, "loss": 0.3903, "lr": 1.443685059893396e-07, "epoch": 2.785100286532951, "percentage": 93.1, "elapsed_time": "1:50:36", "remaining_time": "0:08:11"}
|
| 325 |
+
{"current_steps": 325, "total_steps": 348, "loss": 0.4137, "lr": 1.3264081171780797e-07, "epoch": 2.793696275071633, "percentage": 93.39, "elapsed_time": "1:50:55", "remaining_time": "0:07:50"}
|
| 326 |
+
{"current_steps": 326, "total_steps": 348, "loss": 0.4062, "lr": 1.2140346139561277e-07, "epoch": 2.8022922636103154, "percentage": 93.68, "elapsed_time": "1:51:16", "remaining_time": "0:07:30"}
|
| 327 |
+
{"current_steps": 327, "total_steps": 348, "loss": 0.3682, "lr": 1.1065758708770468e-07, "epoch": 2.810888252148997, "percentage": 93.97, "elapsed_time": "1:51:34", "remaining_time": "0:07:09"}
|
| 328 |
+
{"current_steps": 328, "total_steps": 348, "loss": 0.3626, "lr": 1.004042713471165e-07, "epoch": 2.819484240687679, "percentage": 94.25, "elapsed_time": "1:51:55", "remaining_time": "0:06:49"}
|
| 329 |
+
{"current_steps": 329, "total_steps": 348, "loss": 0.3953, "lr": 9.064454710590253e-08, "epoch": 2.828080229226361, "percentage": 94.54, "elapsed_time": "1:52:17", "remaining_time": "0:06:29"}
|
| 330 |
+
{"current_steps": 330, "total_steps": 348, "loss": 0.4007, "lr": 8.137939757108526e-08, "epoch": 2.836676217765043, "percentage": 94.83, "elapsed_time": "1:52:38", "remaining_time": "0:06:08"}
|
| 331 |
+
{"current_steps": 331, "total_steps": 348, "loss": 0.3827, "lr": 7.260975612560173e-08, "epoch": 2.845272206303725, "percentage": 95.11, "elapsed_time": "1:52:59", "remaining_time": "0:05:48"}
|
| 332 |
+
{"current_steps": 332, "total_steps": 348, "loss": 0.3848, "lr": 6.433650623427379e-08, "epoch": 2.853868194842407, "percentage": 95.4, "elapsed_time": "1:53:17", "remaining_time": "0:05:27"}
|
| 333 |
+
{"current_steps": 333, "total_steps": 348, "loss": 0.3442, "lr": 5.6560481354807625e-08, "epoch": 2.862464183381089, "percentage": 95.69, "elapsed_time": "1:53:36", "remaining_time": "0:05:07"}
|
| 334 |
+
{"current_steps": 334, "total_steps": 348, "loss": 0.4141, "lr": 4.928246485383148e-08, "epoch": 2.871060171919771, "percentage": 95.98, "elapsed_time": "1:53:58", "remaining_time": "0:04:46"}
|
| 335 |
+
{"current_steps": 335, "total_steps": 348, "loss": 0.428, "lr": 4.250318992797375e-08, "epoch": 2.8796561604584525, "percentage": 96.26, "elapsed_time": "1:54:19", "remaining_time": "0:04:26"}
|
| 336 |
+
{"current_steps": 336, "total_steps": 348, "loss": 0.3547, "lr": 3.622333953000601e-08, "epoch": 2.8882521489971347, "percentage": 96.55, "elapsed_time": "1:54:41", "remaining_time": "0:04:05"}
|
| 337 |
+
{"current_steps": 337, "total_steps": 348, "loss": 0.4037, "lr": 3.0443546300035764e-08, "epoch": 2.896848137535817, "percentage": 96.84, "elapsed_time": "1:55:00", "remaining_time": "0:03:45"}
|
| 338 |
+
{"current_steps": 338, "total_steps": 348, "loss": 0.3832, "lr": 2.516439250177749e-08, "epoch": 2.9054441260744985, "percentage": 97.13, "elapsed_time": "1:55:18", "remaining_time": "0:03:24"}
|
| 339 |
+
{"current_steps": 339, "total_steps": 348, "loss": 0.382, "lr": 2.038640996389285e-08, "epoch": 2.9140401146131802, "percentage": 97.41, "elapsed_time": "1:55:36", "remaining_time": "0:03:04"}
|
| 340 |
+
{"current_steps": 340, "total_steps": 348, "loss": 0.3902, "lr": 1.6110080026414123e-08, "epoch": 2.9226361031518624, "percentage": 97.7, "elapsed_time": "1:55:56", "remaining_time": "0:02:43"}
|
| 341 |
+
{"current_steps": 341, "total_steps": 348, "loss": 0.3983, "lr": 1.2335833492252425e-08, "epoch": 2.9312320916905446, "percentage": 97.99, "elapsed_time": "1:56:15", "remaining_time": "0:02:23"}
|
| 342 |
+
{"current_steps": 342, "total_steps": 348, "loss": 0.376, "lr": 9.06405058380022e-09, "epoch": 2.9398280802292263, "percentage": 98.28, "elapsed_time": "1:56:32", "remaining_time": "0:02:02"}
|
| 343 |
+
{"current_steps": 343, "total_steps": 348, "loss": 0.3898, "lr": 6.295060904623618e-09, "epoch": 2.9484240687679084, "percentage": 98.56, "elapsed_time": "1:56:50", "remaining_time": "0:01:42"}
|
| 344 |
+
{"current_steps": 344, "total_steps": 348, "loss": 0.4125, "lr": 4.02914340626226e-09, "epoch": 2.95702005730659, "percentage": 98.85, "elapsed_time": "1:57:10", "remaining_time": "0:01:21"}
|
| 345 |
+
{"current_steps": 345, "total_steps": 348, "loss": 0.3464, "lr": 2.2665263601240328e-09, "epoch": 2.9656160458452723, "percentage": 99.14, "elapsed_time": "1:57:31", "remaining_time": "0:01:01"}
|
| 346 |
+
{"current_steps": 346, "total_steps": 348, "loss": 0.4029, "lr": 1.0073873344895735e-09, "epoch": 2.974212034383954, "percentage": 99.43, "elapsed_time": "1:57:53", "remaining_time": "0:00:40"}
|
| 347 |
+
{"current_steps": 347, "total_steps": 348, "loss": 0.4093, "lr": 2.5185317662490547e-10, "epoch": 2.982808022922636, "percentage": 99.71, "elapsed_time": "1:58:13", "remaining_time": "0:00:20"}
|
| 348 |
+
{"current_steps": 348, "total_steps": 348, "loss": 0.3424, "lr": 0.0, "epoch": 2.9914040114613183, "percentage": 100.0, "elapsed_time": "1:58:33", "remaining_time": "0:00:00"}
|
| 349 |
+
{"current_steps": 348, "total_steps": 348, "epoch": 2.9914040114613183, "percentage": 100.0, "elapsed_time": "1:59:27", "remaining_time": "0:00:00"}
|