Training in progress, epoch 2
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 sha256:112e05e29b02b7e233387600a7919ca2d3eed917ed11b2c96c6ed853a02b41b8
|
| 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:ac9a08abbaf87ad3afc9857afd6f2a4a353de7fc75a4a58bf95709423b18c1e8
|
| 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 sha256:26c7991dc1527d6ba28f51d3014d8baa791ca14bd122dece44e22a3d71deb4b6
|
| 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 sha256:063e0569a1eee7fde57d56424d08b13df333ca7d25936b9d3b4503597ecd229f
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -62,3 +62,33 @@
|
|
| 62 |
{"current_steps": 62, "total_steps": 93, "loss": 0.3817, "lr": 1.2258994055955658e-05, "epoch": 1.984, "percentage": 66.67, "elapsed_time": "1:39:33", "remaining_time": "0:49:46"}
|
| 63 |
{"current_steps": 63, "total_steps": 93, "loss": 0.7898, "lr": 1.156669733099632e-05, "epoch": 2.016, "percentage": 67.74, "elapsed_time": "1:42:17", "remaining_time": "0:48:42"}
|
| 64 |
{"current_steps": 64, "total_steps": 93, "loss": 0.3525, "lr": 1.0886481230875172e-05, "epoch": 2.048, "percentage": 68.82, "elapsed_time": "1:43:52", "remaining_time": "0:47:03"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
{"current_steps": 62, "total_steps": 93, "loss": 0.3817, "lr": 1.2258994055955658e-05, "epoch": 1.984, "percentage": 66.67, "elapsed_time": "1:39:33", "remaining_time": "0:49:46"}
|
| 63 |
{"current_steps": 63, "total_steps": 93, "loss": 0.7898, "lr": 1.156669733099632e-05, "epoch": 2.016, "percentage": 67.74, "elapsed_time": "1:42:17", "remaining_time": "0:48:42"}
|
| 64 |
{"current_steps": 64, "total_steps": 93, "loss": 0.3525, "lr": 1.0886481230875172e-05, "epoch": 2.048, "percentage": 68.82, "elapsed_time": "1:43:52", "remaining_time": "0:47:03"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 93, "loss": 0.3394, "lr": 1.0219320158603337e-05, "epoch": 2.08, "percentage": 69.89, "elapsed_time": "1:45:15", "remaining_time": "0:45:20"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 93, "loss": 0.3834, "lr": 9.566169815990311e-06, "epoch": 2.112, "percentage": 70.97, "elapsed_time": "1:46:59", "remaining_time": "0:43:46"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 93, "loss": 0.3577, "lr": 8.92796583461031e-06, "epoch": 2.144, "percentage": 72.04, "elapsed_time": "1:48:34", "remaining_time": "0:42:08"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 93, "loss": 0.3831, "lr": 8.305622435519058e-06, "epoch": 2.176, "percentage": 73.12, "elapsed_time": "1:50:12", "remaining_time": "0:40:31"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 93, "loss": 0.376, "lr": 7.70003111964093e-06, "epoch": 2.208, "percentage": 74.19, "elapsed_time": "1:51:38", "remaining_time": "0:38:49"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 93, "loss": 0.3715, "lr": 7.112059390702459e-06, "epoch": 2.24, "percentage": 75.27, "elapsed_time": "1:53:13", "remaining_time": "0:37:12"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 93, "loss": 0.3713, "lr": 6.542549512541623e-06, "epoch": 2.2720000000000002, "percentage": 76.34, "elapsed_time": "1:54:41", "remaining_time": "0:35:32"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 93, "loss": 0.3303, "lr": 5.9923173025729895e-06, "epoch": 2.304, "percentage": 77.42, "elapsed_time": "1:56:08", "remaining_time": "0:33:52"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 93, "loss": 0.4568, "lr": 5.462150963137125e-06, "epoch": 2.336, "percentage": 78.49, "elapsed_time": "1:57:47", "remaining_time": "0:32:16"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 93, "loss": 0.3514, "lr": 4.952809952408375e-06, "epoch": 2.368, "percentage": 79.57, "elapsed_time": "1:59:09", "remaining_time": "0:30:35"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 93, "loss": 0.3627, "lr": 4.465023896478293e-06, "epoch": 2.4, "percentage": 80.65, "elapsed_time": "2:00:49", "remaining_time": "0:28:59"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 93, "loss": 0.3054, "lr": 3.999491544173311e-06, "epoch": 2.432, "percentage": 81.72, "elapsed_time": "2:02:12", "remaining_time": "0:27:20"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 93, "loss": 0.375, "lr": 3.5568797661038004e-06, "epoch": 2.464, "percentage": 82.8, "elapsed_time": "2:03:56", "remaining_time": "0:25:45"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 93, "loss": 0.3537, "lr": 3.137822599378315e-06, "epoch": 2.496, "percentage": 83.87, "elapsed_time": "2:05:35", "remaining_time": "0:24:09"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 93, "loss": 0.378, "lr": 2.7429203393515426e-06, "epoch": 2.528, "percentage": 84.95, "elapsed_time": "2:07:18", "remaining_time": "0:22:33"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 93, "loss": 0.3232, "lr": 2.372738679707023e-06, "epoch": 2.56, "percentage": 86.02, "elapsed_time": "2:08:58", "remaining_time": "0:20:57"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 93, "loss": 0.3542, "lr": 2.02780790210636e-06, "epoch": 2.592, "percentage": 87.1, "elapsed_time": "2:10:25", "remaining_time": "0:19:19"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 93, "loss": 0.351, "lr": 1.7086221165658544e-06, "epoch": 2.624, "percentage": 88.17, "elapsed_time": "2:11:49", "remaining_time": "0:17:40"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 93, "loss": 0.3212, "lr": 1.4156385536486973e-06, "epoch": 2.656, "percentage": 89.25, "elapsed_time": "2:13:20", "remaining_time": "0:16:03"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 93, "loss": 0.3744, "lr": 1.1492769094865475e-06, "epoch": 2.6879999999999997, "percentage": 90.32, "elapsed_time": "2:14:51", "remaining_time": "0:14:26"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 93, "loss": 0.3071, "lr": 9.099187445688984e-07, "epoch": 2.7199999999999998, "percentage": 91.4, "elapsed_time": "2:16:13", "remaining_time": "0:12:49"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 93, "loss": 0.3755, "lr": 6.979069371613345e-07, "epoch": 2.752, "percentage": 92.47, "elapsed_time": "2:17:53", "remaining_time": "0:11:13"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 93, "loss": 0.2993, "lr": 5.135451921357337e-07, "epoch": 2.784, "percentage": 93.55, "elapsed_time": "2:19:11", "remaining_time": "0:09:35"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 93, "loss": 0.3725, "lr": 3.570976059159481e-07, "epoch": 2.816, "percentage": 94.62, "elapsed_time": "2:20:51", "remaining_time": "0:08:00"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 93, "loss": 0.3691, "lr": 2.2878828816222942e-07, "epoch": 2.848, "percentage": 95.7, "elapsed_time": "2:22:24", "remaining_time": "0:06:24"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 93, "loss": 0.3218, "lr": 1.2880104073630163e-07, "epoch": 2.88, "percentage": 96.77, "elapsed_time": "2:23:53", "remaining_time": "0:04:47"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 93, "loss": 0.3625, "lr": 5.7279094406959e-08, "epoch": 2.912, "percentage": 97.85, "elapsed_time": "2:25:27", "remaining_time": "0:03:11"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 93, "loss": 0.3543, "lr": 1.4324903673370583e-08, "epoch": 2.944, "percentage": 98.92, "elapsed_time": "2:27:13", "remaining_time": "0:01:36"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 93, "loss": 0.3917, "lr": 0.0, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "2:29:02", "remaining_time": "0:00:00"}
|
| 94 |
+
{"current_steps": 93, "total_steps": 93, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "2:31:19", "remaining_time": "0:00:00"}
|