Training in progress, step 800
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 sha256:4dcb1290e2acd981e4ed8e66e94b8244915f75ec1ca514e783af06bc6e4247e7
|
| 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:e486cca27696b024110a9f71f3d9fda48ed9c7acd390389e72e6a3538cd5dd4c
|
| 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:a88add47dbef57350d20a94340f67f4ccb742bef385b37a8d3a56e436cc5296f
|
| 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:c6822818ea4e0c4fab26f4076507ac0b522e1df1071b2e53a3a3e86a91629e5e
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -119,3 +119,43 @@
|
|
| 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"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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"}
|
| 122 |
+
{"current_steps": 610, "total_steps": 9128, "loss": 0.2459, "lr": 2.6681270536692228e-05, "epoch": 0.46797084771768316, "percentage": 6.68, "elapsed_time": "4:04:59", "remaining_time": "2 days, 9:01:09"}
|
| 123 |
+
{"current_steps": 615, "total_steps": 9128, "loss": 0.2425, "lr": 2.690032858707558e-05, "epoch": 0.4718066743383199, "percentage": 6.74, "elapsed_time": "4:06:13", "remaining_time": "2 days, 8:48:17"}
|
| 124 |
+
{"current_steps": 620, "total_steps": 9128, "loss": 0.2553, "lr": 2.7119386637458932e-05, "epoch": 0.47564250095895666, "percentage": 6.79, "elapsed_time": "4:07:28", "remaining_time": "2 days, 8:36:01"}
|
| 125 |
+
{"current_steps": 625, "total_steps": 9128, "loss": 0.247, "lr": 2.733844468784228e-05, "epoch": 0.4794783275795934, "percentage": 6.85, "elapsed_time": "4:08:49", "remaining_time": "2 days, 8:25:09"}
|
| 126 |
+
{"current_steps": 630, "total_steps": 9128, "loss": 0.2496, "lr": 2.755750273822563e-05, "epoch": 0.48331415420023016, "percentage": 6.9, "elapsed_time": "4:10:04", "remaining_time": "2 days, 8:13:08"}
|
| 127 |
+
{"current_steps": 635, "total_steps": 9128, "loss": 0.2355, "lr": 2.7776560788608983e-05, "epoch": 0.4871499808208669, "percentage": 6.96, "elapsed_time": "4:11:17", "remaining_time": "2 days, 8:01:02"}
|
| 128 |
+
{"current_steps": 640, "total_steps": 9128, "loss": 0.2332, "lr": 2.7995618838992334e-05, "epoch": 0.49098580744150366, "percentage": 7.01, "elapsed_time": "4:12:32", "remaining_time": "2 days, 7:49:17"}
|
| 129 |
+
{"current_steps": 645, "total_steps": 9128, "loss": 0.239, "lr": 2.8214676889375688e-05, "epoch": 0.4948216340621404, "percentage": 7.07, "elapsed_time": "4:13:46", "remaining_time": "2 days, 7:37:40"}
|
| 130 |
+
{"current_steps": 650, "total_steps": 9128, "loss": 0.2414, "lr": 2.8433734939759038e-05, "epoch": 0.49865746068277716, "percentage": 7.12, "elapsed_time": "4:15:01", "remaining_time": "2 days, 7:26:18"}
|
| 131 |
+
{"current_steps": 655, "total_steps": 9128, "loss": 0.2368, "lr": 2.8652792990142392e-05, "epoch": 0.5024932873034139, "percentage": 7.18, "elapsed_time": "4:16:16", "remaining_time": "2 days, 7:15:13"}
|
| 132 |
+
{"current_steps": 660, "total_steps": 9128, "loss": 0.2297, "lr": 2.887185104052574e-05, "epoch": 0.5063291139240507, "percentage": 7.23, "elapsed_time": "4:17:31", "remaining_time": "2 days, 7:04:09"}
|
| 133 |
+
{"current_steps": 665, "total_steps": 9128, "loss": 0.2457, "lr": 2.9090909090909093e-05, "epoch": 0.5101649405446874, "percentage": 7.29, "elapsed_time": "4:18:47", "remaining_time": "2 days, 6:53:24"}
|
| 134 |
+
{"current_steps": 670, "total_steps": 9128, "loss": 0.231, "lr": 2.9309967141292443e-05, "epoch": 0.5140007671653242, "percentage": 7.34, "elapsed_time": "4:20:01", "remaining_time": "2 days, 6:42:30"}
|
| 135 |
+
{"current_steps": 675, "total_steps": 9128, "loss": 0.2285, "lr": 2.9529025191675797e-05, "epoch": 0.5178365937859609, "percentage": 7.39, "elapsed_time": "4:21:17", "remaining_time": "2 days, 6:32:07"}
|
| 136 |
+
{"current_steps": 680, "total_steps": 9128, "loss": 0.2266, "lr": 2.9748083242059147e-05, "epoch": 0.5216724204065977, "percentage": 7.45, "elapsed_time": "4:22:43", "remaining_time": "2 days, 6:23:57"}
|
| 137 |
+
{"current_steps": 685, "total_steps": 9128, "loss": 0.2133, "lr": 2.99671412924425e-05, "epoch": 0.5255082470272344, "percentage": 7.5, "elapsed_time": "4:23:59", "remaining_time": "2 days, 6:13:47"}
|
| 138 |
+
{"current_steps": 690, "total_steps": 9128, "loss": 0.2365, "lr": 3.018619934282585e-05, "epoch": 0.5293440736478712, "percentage": 7.56, "elapsed_time": "4:25:14", "remaining_time": "2 days, 6:03:36"}
|
| 139 |
+
{"current_steps": 695, "total_steps": 9128, "loss": 0.2311, "lr": 3.0405257393209205e-05, "epoch": 0.5331799002685078, "percentage": 7.61, "elapsed_time": "4:26:29", "remaining_time": "2 days, 5:53:37"}
|
| 140 |
+
{"current_steps": 700, "total_steps": 9128, "loss": 0.2347, "lr": 3.0624315443592556e-05, "epoch": 0.5370157268891446, "percentage": 7.67, "elapsed_time": "4:27:48", "remaining_time": "2 days, 5:44:23"}
|
| 141 |
+
{"current_steps": 705, "total_steps": 9128, "loss": 0.2385, "lr": 3.084337349397591e-05, "epoch": 0.5408515535097813, "percentage": 7.72, "elapsed_time": "4:29:04", "remaining_time": "2 days, 5:34:51"}
|
| 142 |
+
{"current_steps": 710, "total_steps": 9128, "loss": 0.2274, "lr": 3.1062431544359257e-05, "epoch": 0.5446873801304181, "percentage": 7.78, "elapsed_time": "4:30:19", "remaining_time": "2 days, 5:25:09"}
|
| 143 |
+
{"current_steps": 715, "total_steps": 9128, "loss": 0.2428, "lr": 3.128148959474261e-05, "epoch": 0.5485232067510548, "percentage": 7.83, "elapsed_time": "4:31:34", "remaining_time": "2 days, 5:15:27"}
|
| 144 |
+
{"current_steps": 720, "total_steps": 9128, "loss": 0.3383, "lr": 3.150054764512596e-05, "epoch": 0.5523590333716916, "percentage": 7.89, "elapsed_time": "4:33:19", "remaining_time": "2 days, 5:11:46"}
|
| 145 |
+
{"current_steps": 725, "total_steps": 9128, "loss": 0.4058, "lr": 3.171960569550932e-05, "epoch": 0.5561948599923283, "percentage": 7.94, "elapsed_time": "4:35:28", "remaining_time": "2 days, 5:12:45"}
|
| 146 |
+
{"current_steps": 730, "total_steps": 9128, "loss": 0.3978, "lr": 3.1938663745892665e-05, "epoch": 0.5600306866129651, "percentage": 8.0, "elapsed_time": "4:37:53", "remaining_time": "2 days, 5:16:56"}
|
| 147 |
+
{"current_steps": 735, "total_steps": 9128, "loss": 0.3769, "lr": 3.215772179627602e-05, "epoch": 0.5638665132336018, "percentage": 8.05, "elapsed_time": "4:40:14", "remaining_time": "2 days, 5:20:01"}
|
| 148 |
+
{"current_steps": 740, "total_steps": 9128, "loss": 0.3726, "lr": 3.2376779846659366e-05, "epoch": 0.5677023398542386, "percentage": 8.11, "elapsed_time": "4:42:36", "remaining_time": "2 days, 5:23:27"}
|
| 149 |
+
{"current_steps": 745, "total_steps": 9128, "loss": 0.3895, "lr": 3.259583789704272e-05, "epoch": 0.5715381664748753, "percentage": 8.16, "elapsed_time": "4:44:57", "remaining_time": "2 days, 5:26:24"}
|
| 150 |
+
{"current_steps": 750, "total_steps": 9128, "loss": 0.357, "lr": 3.281489594742607e-05, "epoch": 0.5753739930955121, "percentage": 8.22, "elapsed_time": "4:47:10", "remaining_time": "2 days, 5:28:00"}
|
| 151 |
+
{"current_steps": 755, "total_steps": 9128, "loss": 0.3681, "lr": 3.303395399780942e-05, "epoch": 0.5792098197161488, "percentage": 8.27, "elapsed_time": "4:49:32", "remaining_time": "2 days, 5:31:03"}
|
| 152 |
+
{"current_steps": 760, "total_steps": 9128, "loss": 0.3632, "lr": 3.3253012048192774e-05, "epoch": 0.5830456463367856, "percentage": 8.33, "elapsed_time": "4:51:50", "remaining_time": "2 days, 5:33:22"}
|
| 153 |
+
{"current_steps": 765, "total_steps": 9128, "loss": 0.3807, "lr": 3.347207009857612e-05, "epoch": 0.5868814729574223, "percentage": 8.38, "elapsed_time": "4:54:12", "remaining_time": "2 days, 5:36:12"}
|
| 154 |
+
{"current_steps": 770, "total_steps": 9128, "loss": 0.3621, "lr": 3.3691128148959475e-05, "epoch": 0.5907172995780591, "percentage": 8.44, "elapsed_time": "4:56:24", "remaining_time": "2 days, 5:37:26"}
|
| 155 |
+
{"current_steps": 775, "total_steps": 9128, "loss": 0.3629, "lr": 3.391018619934283e-05, "epoch": 0.5945531261986958, "percentage": 8.49, "elapsed_time": "4:58:56", "remaining_time": "2 days, 5:42:04"}
|
| 156 |
+
{"current_steps": 780, "total_steps": 9128, "loss": 0.3591, "lr": 3.412924424972618e-05, "epoch": 0.5983889528193326, "percentage": 8.55, "elapsed_time": "5:01:10", "remaining_time": "2 days, 5:43:21"}
|
| 157 |
+
{"current_steps": 785, "total_steps": 9128, "loss": 0.3647, "lr": 3.434830230010953e-05, "epoch": 0.6022247794399693, "percentage": 8.6, "elapsed_time": "5:03:17", "remaining_time": "2 days, 5:43:22"}
|
| 158 |
+
{"current_steps": 790, "total_steps": 9128, "loss": 0.3719, "lr": 3.456736035049288e-05, "epoch": 0.6060606060606061, "percentage": 8.65, "elapsed_time": "5:04:58", "remaining_time": "2 days, 5:38:54"}
|
| 159 |
+
{"current_steps": 795, "total_steps": 9128, "loss": 0.3673, "lr": 3.478641840087624e-05, "epoch": 0.6098964326812428, "percentage": 8.71, "elapsed_time": "5:06:37", "remaining_time": "2 days, 5:33:54"}
|
| 160 |
+
{"current_steps": 800, "total_steps": 9128, "loss": 0.3637, "lr": 3.500547645125959e-05, "epoch": 0.6137322593018796, "percentage": 8.76, "elapsed_time": "5:08:19", "remaining_time": "2 days, 5:29:43"}
|
| 161 |
+
{"current_steps": 805, "total_steps": 9128, "loss": 0.3748, "lr": 3.522453450164294e-05, "epoch": 0.6175680859225163, "percentage": 8.82, "elapsed_time": "5:11:03", "remaining_time": "2 days, 5:36:05"}
|