Training in progress, step 600
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 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9c3021142a0b4802ba33941b9b1d471806bef720474693c44e217d19fe86531
|
| 3 |
size 4902257696
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a78d7453ada36403c4dd188943d73496bcd21bf7c3dfec42664f123580f5900
|
| 3 |
size 4915960368
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:215c18c75df403611542565ef8aa6f729c623522a41b3cb9575b862e37582edb
|
| 3 |
size 4983068496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d027589dd2eec8f3245f2d645e46337917f7f76b99acb8bfc7dec0cb4e5a4165
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -78,3 +78,44 @@
|
|
| 78 |
{"current_steps": 390, "total_steps": 9128, "loss": 0.2846, "lr": 1.7042716319824756e-05, "epoch": 0.2991944764096663, "percentage": 4.27, "elapsed_time": "3:07:35", "remaining_time": "2 days, 22:02:57"}
|
| 79 |
{"current_steps": 395, "total_steps": 9128, "loss": 0.2566, "lr": 1.7261774370208106e-05, "epoch": 0.30303030303030304, "percentage": 4.33, "elapsed_time": "3:08:49", "remaining_time": "2 days, 21:34:38"}
|
| 80 |
{"current_steps": 400, "total_steps": 9128, "loss": 0.2695, "lr": 1.7480832420591457e-05, "epoch": 0.3068661296509398, "percentage": 4.38, "elapsed_time": "3:10:04", "remaining_time": "2 days, 21:07:21"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
{"current_steps": 390, "total_steps": 9128, "loss": 0.2846, "lr": 1.7042716319824756e-05, "epoch": 0.2991944764096663, "percentage": 4.27, "elapsed_time": "3:07:35", "remaining_time": "2 days, 22:02:57"}
|
| 79 |
{"current_steps": 395, "total_steps": 9128, "loss": 0.2566, "lr": 1.7261774370208106e-05, "epoch": 0.30303030303030304, "percentage": 4.33, "elapsed_time": "3:08:49", "remaining_time": "2 days, 21:34:38"}
|
| 80 |
{"current_steps": 400, "total_steps": 9128, "loss": 0.2695, "lr": 1.7480832420591457e-05, "epoch": 0.3068661296509398, "percentage": 4.38, "elapsed_time": "3:10:04", "remaining_time": "2 days, 21:07:21"}
|
| 81 |
+
{"current_steps": 405, "total_steps": 9128, "loss": 0.2628, "lr": 1.769989047097481e-05, "epoch": 0.31070195627157654, "percentage": 4.44, "elapsed_time": "3:12:28", "remaining_time": "2 days, 21:05:28"}
|
| 82 |
+
{"current_steps": 410, "total_steps": 9128, "loss": 0.2574, "lr": 1.791894852135816e-05, "epoch": 0.3145377828922133, "percentage": 4.49, "elapsed_time": "3:13:42", "remaining_time": "2 days, 20:38:57"}
|
| 83 |
+
{"current_steps": 415, "total_steps": 9128, "loss": 0.275, "lr": 1.8138006571741515e-05, "epoch": 0.31837360951285004, "percentage": 4.55, "elapsed_time": "3:15:02", "remaining_time": "2 days, 20:14:47"}
|
| 84 |
+
{"current_steps": 420, "total_steps": 9128, "loss": 0.252, "lr": 1.8357064622124865e-05, "epoch": 0.3222094361334868, "percentage": 4.6, "elapsed_time": "3:16:16", "remaining_time": "2 days, 19:49:30"}
|
| 85 |
+
{"current_steps": 425, "total_steps": 9128, "loss": 0.2625, "lr": 1.8576122672508216e-05, "epoch": 0.3260452627541235, "percentage": 4.66, "elapsed_time": "3:17:31", "remaining_time": "2 days, 19:24:51"}
|
| 86 |
+
{"current_steps": 430, "total_steps": 9128, "loss": 0.2636, "lr": 1.879518072289157e-05, "epoch": 0.32988108937476024, "percentage": 4.71, "elapsed_time": "3:18:45", "remaining_time": "2 days, 19:00:33"}
|
| 87 |
+
{"current_steps": 435, "total_steps": 9128, "loss": 0.2609, "lr": 1.901423877327492e-05, "epoch": 0.333716915995397, "percentage": 4.77, "elapsed_time": "3:20:01", "remaining_time": "2 days, 18:37:18"}
|
| 88 |
+
{"current_steps": 440, "total_steps": 9128, "loss": 0.2587, "lr": 1.923329682365827e-05, "epoch": 0.33755274261603374, "percentage": 4.82, "elapsed_time": "3:21:17", "remaining_time": "2 days, 18:14:29"}
|
| 89 |
+
{"current_steps": 445, "total_steps": 9128, "loss": 0.2552, "lr": 1.9452354874041624e-05, "epoch": 0.3413885692366705, "percentage": 4.88, "elapsed_time": "3:22:30", "remaining_time": "2 days, 17:51:16"}
|
| 90 |
+
{"current_steps": 450, "total_steps": 9128, "loss": 0.2384, "lr": 1.9671412924424974e-05, "epoch": 0.34522439585730724, "percentage": 4.93, "elapsed_time": "3:23:44", "remaining_time": "2 days, 17:28:55"}
|
| 91 |
+
{"current_steps": 455, "total_steps": 9128, "loss": 0.2577, "lr": 1.9890470974808328e-05, "epoch": 0.349060222477944, "percentage": 4.98, "elapsed_time": "3:24:59", "remaining_time": "2 days, 17:07:33"}
|
| 92 |
+
{"current_steps": 460, "total_steps": 9128, "loss": 0.2594, "lr": 2.0109529025191675e-05, "epoch": 0.35289604909858074, "percentage": 5.04, "elapsed_time": "3:26:14", "remaining_time": "2 days, 16:46:10"}
|
| 93 |
+
{"current_steps": 465, "total_steps": 9128, "loss": 0.2533, "lr": 2.032858707557503e-05, "epoch": 0.3567318757192175, "percentage": 5.09, "elapsed_time": "3:27:28", "remaining_time": "2 days, 16:25:20"}
|
| 94 |
+
{"current_steps": 470, "total_steps": 9128, "loss": 0.2516, "lr": 2.054764512595838e-05, "epoch": 0.36056770233985425, "percentage": 5.15, "elapsed_time": "3:28:43", "remaining_time": "2 days, 16:05:00"}
|
| 95 |
+
{"current_steps": 475, "total_steps": 9128, "loss": 0.2608, "lr": 2.0766703176341733e-05, "epoch": 0.364403528960491, "percentage": 5.2, "elapsed_time": "3:29:58", "remaining_time": "2 days, 15:45:05"}
|
| 96 |
+
{"current_steps": 480, "total_steps": 9128, "loss": 0.2443, "lr": 2.0985761226725084e-05, "epoch": 0.36823935558112775, "percentage": 5.26, "elapsed_time": "3:31:12", "remaining_time": "2 days, 15:25:09"}
|
| 97 |
+
{"current_steps": 485, "total_steps": 9128, "loss": 0.2634, "lr": 2.1204819277108437e-05, "epoch": 0.3720751822017645, "percentage": 5.31, "elapsed_time": "3:32:30", "remaining_time": "2 days, 15:07:08"}
|
| 98 |
+
{"current_steps": 490, "total_steps": 9128, "loss": 0.2621, "lr": 2.1423877327491788e-05, "epoch": 0.37591100882240125, "percentage": 5.37, "elapsed_time": "3:33:49", "remaining_time": "2 days, 14:49:22"}
|
| 99 |
+
{"current_steps": 495, "total_steps": 9128, "loss": 0.2672, "lr": 2.164293537787514e-05, "epoch": 0.379746835443038, "percentage": 5.42, "elapsed_time": "3:35:05", "remaining_time": "2 days, 14:31:25"}
|
| 100 |
+
{"current_steps": 500, "total_steps": 9128, "loss": 0.2465, "lr": 2.186199342825849e-05, "epoch": 0.3835826620636747, "percentage": 5.48, "elapsed_time": "3:36:20", "remaining_time": "2 days, 14:13:05"}
|
| 101 |
+
{"current_steps": 505, "total_steps": 9128, "loss": 0.246, "lr": 2.2081051478641842e-05, "epoch": 0.38741848868431145, "percentage": 5.53, "elapsed_time": "3:37:35", "remaining_time": "2 days, 13:55:33"}
|
| 102 |
+
{"current_steps": 510, "total_steps": 9128, "loss": 0.2586, "lr": 2.2300109529025193e-05, "epoch": 0.3912543153049482, "percentage": 5.59, "elapsed_time": "3:38:50", "remaining_time": "2 days, 13:37:59"}
|
| 103 |
+
{"current_steps": 515, "total_steps": 9128, "loss": 0.2476, "lr": 2.2519167579408543e-05, "epoch": 0.39509014192558495, "percentage": 5.64, "elapsed_time": "3:40:04", "remaining_time": "2 days, 13:20:32"}
|
| 104 |
+
{"current_steps": 520, "total_steps": 9128, "loss": 0.2401, "lr": 2.2738225629791897e-05, "epoch": 0.3989259685462217, "percentage": 5.7, "elapsed_time": "3:41:17", "remaining_time": "2 days, 13:03:16"}
|
| 105 |
+
{"current_steps": 525, "total_steps": 9128, "loss": 0.2491, "lr": 2.2957283680175247e-05, "epoch": 0.40276179516685845, "percentage": 5.75, "elapsed_time": "3:42:34", "remaining_time": "2 days, 12:47:17"}
|
| 106 |
+
{"current_steps": 530, "total_steps": 9128, "loss": 0.2518, "lr": 2.31763417305586e-05, "epoch": 0.4065976217874952, "percentage": 5.81, "elapsed_time": "3:43:48", "remaining_time": "2 days, 12:30:45"}
|
| 107 |
+
{"current_steps": 535, "total_steps": 9128, "loss": 0.249, "lr": 2.3395399780941948e-05, "epoch": 0.41043344840813195, "percentage": 5.86, "elapsed_time": "3:45:03", "remaining_time": "2 days, 12:14:44"}
|
| 108 |
+
{"current_steps": 540, "total_steps": 9128, "loss": 0.2422, "lr": 2.3614457831325302e-05, "epoch": 0.4142692750287687, "percentage": 5.92, "elapsed_time": "3:46:18", "remaining_time": "2 days, 11:59:02"}
|
| 109 |
+
{"current_steps": 545, "total_steps": 9128, "loss": 0.2472, "lr": 2.3833515881708652e-05, "epoch": 0.41810510164940545, "percentage": 5.97, "elapsed_time": "3:47:34", "remaining_time": "2 days, 11:43:54"}
|
| 110 |
+
{"current_steps": 550, "total_steps": 9128, "loss": 0.2429, "lr": 2.4052573932092006e-05, "epoch": 0.4219409282700422, "percentage": 6.03, "elapsed_time": "3:48:50", "remaining_time": "2 days, 11:29:10"}
|
| 111 |
+
{"current_steps": 555, "total_steps": 9128, "loss": 0.2436, "lr": 2.4271631982475357e-05, "epoch": 0.42577675489067895, "percentage": 6.08, "elapsed_time": "3:50:04", "remaining_time": "2 days, 11:14:00"}
|
| 112 |
+
{"current_steps": 560, "total_steps": 9128, "loss": 0.2412, "lr": 2.449069003285871e-05, "epoch": 0.4296125815113157, "percentage": 6.13, "elapsed_time": "3:51:19", "remaining_time": "2 days, 10:59:18"}
|
| 113 |
+
{"current_steps": 565, "total_steps": 9128, "loss": 0.2276, "lr": 2.470974808324206e-05, "epoch": 0.43344840813195246, "percentage": 6.19, "elapsed_time": "3:52:33", "remaining_time": "2 days, 10:44:33"}
|
| 114 |
+
{"current_steps": 570, "total_steps": 9128, "loss": 0.2339, "lr": 2.4928806133625415e-05, "epoch": 0.4372842347525892, "percentage": 6.24, "elapsed_time": "3:53:49", "remaining_time": "2 days, 10:30:43"}
|
| 115 |
+
{"current_steps": 575, "total_steps": 9128, "loss": 0.2449, "lr": 2.5147864184008765e-05, "epoch": 0.44112006137322596, "percentage": 6.3, "elapsed_time": "3:55:04", "remaining_time": "2 days, 10:16:45"}
|
| 116 |
+
{"current_steps": 580, "total_steps": 9128, "loss": 0.2319, "lr": 2.536692223439212e-05, "epoch": 0.44495588799386265, "percentage": 6.35, "elapsed_time": "3:56:20", "remaining_time": "2 days, 10:03:09"}
|
| 117 |
+
{"current_steps": 585, "total_steps": 9128, "loss": 0.2451, "lr": 2.5585980284775466e-05, "epoch": 0.4487917146144994, "percentage": 6.41, "elapsed_time": "3:57:33", "remaining_time": "2 days, 9:49:08"}
|
| 118 |
+
{"current_steps": 590, "total_steps": 9128, "loss": 0.2404, "lr": 2.580503833515882e-05, "epoch": 0.45262754123513615, "percentage": 6.46, "elapsed_time": "3:58:47", "remaining_time": "2 days, 9:35:37"}
|
| 119 |
+
{"current_steps": 595, "total_steps": 9128, "loss": 0.2412, "lr": 2.602409638554217e-05, "epoch": 0.4564633678557729, "percentage": 6.52, "elapsed_time": "4:00:02", "remaining_time": "2 days, 9:22:31"}
|
| 120 |
+
{"current_steps": 600, "total_steps": 9128, "loss": 0.2366, "lr": 2.6243154435925524e-05, "epoch": 0.46029919447640966, "percentage": 6.57, "elapsed_time": "4:01:18", "remaining_time": "2 days, 9:09:48"}
|
| 121 |
+
{"current_steps": 605, "total_steps": 9128, "loss": 0.2419, "lr": 2.6462212486308874e-05, "epoch": 0.4641350210970464, "percentage": 6.63, "elapsed_time": "4:03:45", "remaining_time": "2 days, 9:13:59"}
|