Training in progress, epoch 1
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:e7482e16fe7d6eaa8e690be4afdde84f7f3fb7e2f417db60c5f78b4583242ab6
|
| 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:ee68a89a70b5332994d58452a226aeb57eb32b7249d0859115877b7c4eda14c8
|
| 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 sha256:65575003f64ba3a22718b7d4c3f5b2cffeca1bc5db52a5f67c5762c89268583e
|
| 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:ebc035188022ce69605c275e588ded1292257fa8b14fb3c2b00d5b4ef8a22ff5
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -73,3 +73,72 @@
|
|
| 73 |
{"current_steps": 73, "total_steps": 207, "loss": 0.6635, "lr": 8.192322712349917e-06, "epoch": 1.0478468899521531, "percentage": 35.27, "elapsed_time": "0:38:20", "remaining_time": "1:10:23"}
|
| 74 |
{"current_steps": 74, "total_steps": 207, "loss": 0.6695, "lr": 8.126872321608185e-06, "epoch": 1.062200956937799, "percentage": 35.75, "elapsed_time": "0:38:49", "remaining_time": "1:09:46"}
|
| 75 |
{"current_steps": 75, "total_steps": 207, "loss": 0.7012, "lr": 8.060529912738316e-06, "epoch": 1.076555023923445, "percentage": 36.23, "elapsed_time": "0:39:22", "remaining_time": "1:09:18"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
{"current_steps": 73, "total_steps": 207, "loss": 0.6635, "lr": 8.192322712349917e-06, "epoch": 1.0478468899521531, "percentage": 35.27, "elapsed_time": "0:38:20", "remaining_time": "1:10:23"}
|
| 74 |
{"current_steps": 74, "total_steps": 207, "loss": 0.6695, "lr": 8.126872321608185e-06, "epoch": 1.062200956937799, "percentage": 35.75, "elapsed_time": "0:38:49", "remaining_time": "1:09:46"}
|
| 75 |
{"current_steps": 75, "total_steps": 207, "loss": 0.7012, "lr": 8.060529912738316e-06, "epoch": 1.076555023923445, "percentage": 36.23, "elapsed_time": "0:39:22", "remaining_time": "1:09:18"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 207, "loss": 0.7472, "lr": 7.993314411563075e-06, "epoch": 1.0909090909090908, "percentage": 36.71, "elapsed_time": "0:39:57", "remaining_time": "1:08:52"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 207, "loss": 0.7198, "lr": 7.925244992976538e-06, "epoch": 1.1052631578947367, "percentage": 37.2, "elapsed_time": "0:40:26", "remaining_time": "1:08:16"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 207, "loss": 0.6603, "lr": 7.856341075473963e-06, "epoch": 1.1196172248803828, "percentage": 37.68, "elapsed_time": "0:40:54", "remaining_time": "1:07:39"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 207, "loss": 0.7573, "lr": 7.786622315612182e-06, "epoch": 1.1339712918660287, "percentage": 38.16, "elapsed_time": "0:41:26", "remaining_time": "1:07:08"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 207, "loss": 0.6886, "lr": 7.716108602402094e-06, "epoch": 1.1483253588516746, "percentage": 38.65, "elapsed_time": "0:41:49", "remaining_time": "1:06:23"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 207, "loss": 0.6959, "lr": 7.644820051634813e-06, "epoch": 1.1626794258373205, "percentage": 39.13, "elapsed_time": "0:42:13", "remaining_time": "1:05:41"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 207, "loss": 0.5509, "lr": 7.572777000143145e-06, "epoch": 1.1770334928229664, "percentage": 39.61, "elapsed_time": "0:42:41", "remaining_time": "1:05:04"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 207, "loss": 0.6593, "lr": 7.500000000000001e-06, "epoch": 1.1913875598086126, "percentage": 40.1, "elapsed_time": "0:43:05", "remaining_time": "1:04:22"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 207, "loss": 0.7186, "lr": 7.4265098126554065e-06, "epoch": 1.2057416267942584, "percentage": 40.58, "elapsed_time": "0:43:41", "remaining_time": "1:03:58"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 207, "loss": 0.6801, "lr": 7.352327403013779e-06, "epoch": 1.2200956937799043, "percentage": 41.06, "elapsed_time": "0:44:09", "remaining_time": "1:03:22"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 207, "loss": 0.7402, "lr": 7.27747393345317e-06, "epoch": 1.2344497607655502, "percentage": 41.55, "elapsed_time": "0:44:38", "remaining_time": "1:02:49"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 207, "loss": 0.685, "lr": 7.201970757788172e-06, "epoch": 1.2488038277511961, "percentage": 42.03, "elapsed_time": "0:45:13", "remaining_time": "1:02:22"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 207, "loss": 0.7496, "lr": 7.125839415178204e-06, "epoch": 1.263157894736842, "percentage": 42.51, "elapsed_time": "0:45:46", "remaining_time": "1:01:53"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 207, "loss": 0.7925, "lr": 7.049101623982938e-06, "epoch": 1.277511961722488, "percentage": 43.0, "elapsed_time": "0:46:18", "remaining_time": "1:01:24"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 207, "loss": 0.6172, "lr": 6.971779275566593e-06, "epoch": 1.291866028708134, "percentage": 43.48, "elapsed_time": "0:46:48", "remaining_time": "1:00:51"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 207, "loss": 0.7854, "lr": 6.893894428052881e-06, "epoch": 1.30622009569378, "percentage": 43.96, "elapsed_time": "0:47:22", "remaining_time": "1:00:23"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 207, "loss": 0.6519, "lr": 6.815469300032374e-06, "epoch": 1.3205741626794258, "percentage": 44.44, "elapsed_time": "0:47:52", "remaining_time": "0:59:50"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 207, "loss": 0.7472, "lr": 6.736526264224101e-06, "epoch": 1.3349282296650717, "percentage": 44.93, "elapsed_time": "0:48:30", "remaining_time": "0:59:27"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 207, "loss": 0.6688, "lr": 6.657087841093179e-06, "epoch": 1.3492822966507176, "percentage": 45.41, "elapsed_time": "0:49:00", "remaining_time": "0:58:54"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 207, "loss": 0.7773, "lr": 6.5771766924262795e-06, "epoch": 1.3636363636363638, "percentage": 45.89, "elapsed_time": "0:49:32", "remaining_time": "0:58:24"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 207, "loss": 0.6967, "lr": 6.496815614866792e-06, "epoch": 1.3779904306220097, "percentage": 46.38, "elapsed_time": "0:50:01", "remaining_time": "0:57:49"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 207, "loss": 0.7134, "lr": 6.41602753341152e-06, "epoch": 1.3923444976076556, "percentage": 46.86, "elapsed_time": "0:50:28", "remaining_time": "0:57:14"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 207, "loss": 0.6693, "lr": 6.334835494870759e-06, "epoch": 1.4066985645933014, "percentage": 47.34, "elapsed_time": "0:50:54", "remaining_time": "0:56:36"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 207, "loss": 0.7383, "lr": 6.2532626612936035e-06, "epoch": 1.4210526315789473, "percentage": 47.83, "elapsed_time": "0:51:24", "remaining_time": "0:56:05"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 207, "loss": 0.6147, "lr": 6.171332303360411e-06, "epoch": 1.4354066985645932, "percentage": 48.31, "elapsed_time": "0:51:51", "remaining_time": "0:55:29"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 207, "loss": 0.7924, "lr": 6.089067793744258e-06, "epoch": 1.4497607655502391, "percentage": 48.79, "elapsed_time": "0:52:18", "remaining_time": "0:54:54"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 207, "loss": 0.7318, "lr": 6.006492600443301e-06, "epoch": 1.464114832535885, "percentage": 49.28, "elapsed_time": "0:52:51", "remaining_time": "0:54:25"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 207, "loss": 0.6703, "lr": 5.923630280085948e-06, "epoch": 1.4784688995215312, "percentage": 49.76, "elapsed_time": "0:53:26", "remaining_time": "0:53:57"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 207, "loss": 0.741, "lr": 5.840504471210742e-06, "epoch": 1.492822966507177, "percentage": 50.24, "elapsed_time": "0:54:00", "remaining_time": "0:53:29"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 207, "loss": 0.7187, "lr": 5.757138887522884e-06, "epoch": 1.507177033492823, "percentage": 50.72, "elapsed_time": "0:54:32", "remaining_time": "0:52:58"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 207, "loss": 0.7267, "lr": 5.673557311129306e-06, "epoch": 1.5215311004784688, "percentage": 51.21, "elapsed_time": "0:55:01", "remaining_time": "0:52:25"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 207, "loss": 0.7054, "lr": 5.5897835857542315e-06, "epoch": 1.535885167464115, "percentage": 51.69, "elapsed_time": "0:55:34", "remaining_time": "0:51:56"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 207, "loss": 0.6203, "lr": 5.505841609937162e-06, "epoch": 1.5502392344497609, "percentage": 52.17, "elapsed_time": "0:56:08", "remaining_time": "0:51:27"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 207, "loss": 0.7287, "lr": 5.421755330215223e-06, "epoch": 1.5645933014354068, "percentage": 52.66, "elapsed_time": "0:56:36", "remaining_time": "0:50:53"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 207, "loss": 0.6202, "lr": 5.337548734291827e-06, "epoch": 1.5789473684210527, "percentage": 53.14, "elapsed_time": "0:57:07", "remaining_time": "0:50:22"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 207, "loss": 0.7408, "lr": 5.253245844193564e-06, "epoch": 1.5933014354066986, "percentage": 53.62, "elapsed_time": "0:57:40", "remaining_time": "0:49:53"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 207, "loss": 0.6979, "lr": 5.168870709417342e-06, "epoch": 1.6076555023923444, "percentage": 54.11, "elapsed_time": "0:58:15", "remaining_time": "0:49:24"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 207, "loss": 0.7994, "lr": 5.084447400069656e-06, "epoch": 1.6220095693779903, "percentage": 54.59, "elapsed_time": "0:58:48", "remaining_time": "0:48:54"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 207, "loss": 0.7086, "lr": 5e-06, "epoch": 1.6363636363636362, "percentage": 55.07, "elapsed_time": "0:59:25", "remaining_time": "0:48:28"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 207, "loss": 0.6805, "lr": 4.915552599930345e-06, "epoch": 1.6507177033492821, "percentage": 55.56, "elapsed_time": "0:59:52", "remaining_time": "0:47:54"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 207, "loss": 0.7796, "lr": 4.83112929058266e-06, "epoch": 1.6650717703349283, "percentage": 56.04, "elapsed_time": "1:00:31", "remaining_time": "0:47:28"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 207, "loss": 0.6331, "lr": 4.746754155806437e-06, "epoch": 1.6794258373205742, "percentage": 56.52, "elapsed_time": "1:00:59", "remaining_time": "0:46:54"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 207, "loss": 0.6923, "lr": 4.662451265708174e-06, "epoch": 1.69377990430622, "percentage": 57.0, "elapsed_time": "1:01:29", "remaining_time": "0:46:22"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 207, "loss": 0.7035, "lr": 4.5782446697847775e-06, "epoch": 1.7081339712918662, "percentage": 57.49, "elapsed_time": "1:01:59", "remaining_time": "0:45:50"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 207, "loss": 0.7395, "lr": 4.49415839006284e-06, "epoch": 1.722488038277512, "percentage": 57.97, "elapsed_time": "1:02:29", "remaining_time": "0:45:18"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 207, "loss": 0.6636, "lr": 4.410216414245771e-06, "epoch": 1.736842105263158, "percentage": 58.45, "elapsed_time": "1:03:02", "remaining_time": "0:44:48"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 207, "loss": 0.797, "lr": 4.326442688870697e-06, "epoch": 1.7511961722488039, "percentage": 58.94, "elapsed_time": "1:03:43", "remaining_time": "0:44:23"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 207, "loss": 0.6631, "lr": 4.2428611124771184e-06, "epoch": 1.7655502392344498, "percentage": 59.42, "elapsed_time": "1:04:11", "remaining_time": "0:43:50"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 207, "loss": 0.6653, "lr": 4.15949552878926e-06, "epoch": 1.7799043062200957, "percentage": 59.9, "elapsed_time": "1:04:39", "remaining_time": "0:43:16"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 207, "loss": 0.6705, "lr": 4.076369719914055e-06, "epoch": 1.7942583732057416, "percentage": 60.39, "elapsed_time": "1:05:05", "remaining_time": "0:42:41"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 207, "loss": 0.7049, "lr": 3.993507399556699e-06, "epoch": 1.8086124401913874, "percentage": 60.87, "elapsed_time": "1:05:36", "remaining_time": "0:42:10"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 207, "loss": 0.5775, "lr": 3.910932206255742e-06, "epoch": 1.8229665071770333, "percentage": 61.35, "elapsed_time": "1:06:08", "remaining_time": "0:41:40"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 207, "loss": 0.7015, "lr": 3.8286676966395895e-06, "epoch": 1.8373205741626795, "percentage": 61.84, "elapsed_time": "1:06:42", "remaining_time": "0:41:10"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 207, "loss": 0.7644, "lr": 3.7467373387063973e-06, "epoch": 1.8516746411483254, "percentage": 62.32, "elapsed_time": "1:07:18", "remaining_time": "0:40:41"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 207, "loss": 0.6665, "lr": 3.6651645051292415e-06, "epoch": 1.8660287081339713, "percentage": 62.8, "elapsed_time": "1:07:52", "remaining_time": "0:40:12"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 207, "loss": 0.7223, "lr": 3.58397246658848e-06, "epoch": 1.8803827751196174, "percentage": 63.29, "elapsed_time": "1:08:32", "remaining_time": "0:39:46"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 207, "loss": 0.62, "lr": 3.5031843851332105e-06, "epoch": 1.8947368421052633, "percentage": 63.77, "elapsed_time": "1:09:05", "remaining_time": "0:39:15"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 207, "loss": 0.743, "lr": 3.4228233075737225e-06, "epoch": 1.9090909090909092, "percentage": 64.25, "elapsed_time": "1:09:40", "remaining_time": "0:38:46"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 207, "loss": 0.6161, "lr": 3.3429121589068213e-06, "epoch": 1.923444976076555, "percentage": 64.73, "elapsed_time": "1:10:09", "remaining_time": "0:38:13"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 207, "loss": 0.7556, "lr": 3.2634737357758994e-06, "epoch": 1.937799043062201, "percentage": 65.22, "elapsed_time": "1:10:40", "remaining_time": "0:37:41"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 207, "loss": 0.6835, "lr": 3.1845306999676274e-06, "epoch": 1.9521531100478469, "percentage": 65.7, "elapsed_time": "1:11:09", "remaining_time": "0:37:09"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 207, "loss": 0.6996, "lr": 3.10610557194712e-06, "epoch": 1.9665071770334928, "percentage": 66.18, "elapsed_time": "1:11:43", "remaining_time": "0:36:38"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 207, "loss": 0.6532, "lr": 3.0282207244334084e-06, "epoch": 1.9808612440191387, "percentage": 66.67, "elapsed_time": "1:12:08", "remaining_time": "0:36:04"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 207, "loss": 0.822, "lr": 2.950898376017064e-06, "epoch": 1.9952153110047846, "percentage": 67.15, "elapsed_time": "1:12:42", "remaining_time": "0:35:34"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 207, "loss": 0.7384, "lr": 2.874160584821798e-06, "epoch": 2.0095693779904304, "percentage": 67.63, "elapsed_time": "1:13:59", "remaining_time": "0:35:24"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 207, "loss": 0.6775, "lr": 2.7980292422118282e-06, "epoch": 2.0239234449760763, "percentage": 68.12, "elapsed_time": "1:14:31", "remaining_time": "0:34:52"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 207, "loss": 0.7364, "lr": 2.72252606654683e-06, "epoch": 2.0382775119617227, "percentage": 68.6, "elapsed_time": "1:15:08", "remaining_time": "0:34:23"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 207, "loss": 0.6684, "lr": 2.6476725969862227e-06, "epoch": 2.0526315789473686, "percentage": 69.08, "elapsed_time": "1:15:43", "remaining_time": "0:33:53"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 207, "loss": 0.5368, "lr": 2.573490187344596e-06, "epoch": 2.0669856459330145, "percentage": 69.57, "elapsed_time": "1:16:17", "remaining_time": "0:33:22"}
|