Training in progress, step 4800
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 sha256:5ecfa780e318121e94ec76ea0981b440f727ae5c2d0d38ae8820f8dd749791b3
|
| 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:e50ad4876e22b3a60c27e5c3511e2058701e94009243e768c28fed220beda282
|
| 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 sha256:27ce2bc5b13353ed1c18fdaf6774771d913ae3950f212d4f21ba23cbcd531c02
|
| 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:e913e242a90949073cfa2f86ddcad3b0a37a063ba13dca49e691f524f3687dc9
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -918,3 +918,43 @@
|
|
| 918 |
{"current_steps": 4590, "total_steps": 6713, "loss": 0.205, "lr": 1.1009733141895823e-05, "epoch": 4.7876890975482524, "percentage": 68.37, "elapsed_time": "18:20:48", "remaining_time": "8:29:09"}
|
| 919 |
{"current_steps": 4595, "total_steps": 6713, "loss": 0.1921, "lr": 1.0963309326839708e-05, "epoch": 4.792905581637976, "percentage": 68.45, "elapsed_time": "18:23:39", "remaining_time": "8:28:42"}
|
| 920 |
{"current_steps": 4600, "total_steps": 6713, "loss": 0.1859, "lr": 1.0916946610382966e-05, "epoch": 4.7981220657277, "percentage": 68.52, "elapsed_time": "18:26:27", "remaining_time": "8:28:15"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 918 |
{"current_steps": 4590, "total_steps": 6713, "loss": 0.205, "lr": 1.1009733141895823e-05, "epoch": 4.7876890975482524, "percentage": 68.37, "elapsed_time": "18:20:48", "remaining_time": "8:29:09"}
|
| 919 |
{"current_steps": 4595, "total_steps": 6713, "loss": 0.1921, "lr": 1.0963309326839708e-05, "epoch": 4.792905581637976, "percentage": 68.45, "elapsed_time": "18:23:39", "remaining_time": "8:28:42"}
|
| 920 |
{"current_steps": 4600, "total_steps": 6713, "loss": 0.1859, "lr": 1.0916946610382966e-05, "epoch": 4.7981220657277, "percentage": 68.52, "elapsed_time": "18:26:27", "remaining_time": "8:28:15"}
|
| 921 |
+
{"current_steps": 4605, "total_steps": 6713, "loss": 0.1798, "lr": 1.0870645305991772e-05, "epoch": 4.803338549817423, "percentage": 68.6, "elapsed_time": "18:30:32", "remaining_time": "8:28:22"}
|
| 922 |
+
{"current_steps": 4610, "total_steps": 6713, "loss": 0.1937, "lr": 1.0824405726717119e-05, "epoch": 4.808555033907147, "percentage": 68.67, "elapsed_time": "18:33:16", "remaining_time": "8:27:51"}
|
| 923 |
+
{"current_steps": 4615, "total_steps": 6713, "loss": 0.1902, "lr": 1.0778228185192639e-05, "epoch": 4.81377151799687, "percentage": 68.75, "elapsed_time": "18:35:46", "remaining_time": "8:27:14"}
|
| 924 |
+
{"current_steps": 4620, "total_steps": 6713, "loss": 0.1881, "lr": 1.0732112993632539e-05, "epoch": 4.818988002086593, "percentage": 68.82, "elapsed_time": "18:38:42", "remaining_time": "8:26:48"}
|
| 925 |
+
{"current_steps": 4625, "total_steps": 6713, "loss": 0.1796, "lr": 1.0686060463829451e-05, "epoch": 4.824204486176317, "percentage": 68.9, "elapsed_time": "18:41:30", "remaining_time": "8:26:18"}
|
| 926 |
+
{"current_steps": 4630, "total_steps": 6713, "loss": 0.1957, "lr": 1.0640070907152342e-05, "epoch": 4.829420970266041, "percentage": 68.97, "elapsed_time": "18:44:08", "remaining_time": "8:25:44"}
|
| 927 |
+
{"current_steps": 4635, "total_steps": 6713, "loss": 0.1798, "lr": 1.0594144634544405e-05, "epoch": 4.834637454355764, "percentage": 69.05, "elapsed_time": "18:46:58", "remaining_time": "8:25:15"}
|
| 928 |
+
{"current_steps": 4640, "total_steps": 6713, "loss": 0.1875, "lr": 1.0548281956520978e-05, "epoch": 4.839853938445488, "percentage": 69.12, "elapsed_time": "18:49:50", "remaining_time": "8:24:46"}
|
| 929 |
+
{"current_steps": 4645, "total_steps": 6713, "loss": 0.1863, "lr": 1.0502483183167395e-05, "epoch": 4.845070422535211, "percentage": 69.19, "elapsed_time": "18:52:42", "remaining_time": "8:24:17"}
|
| 930 |
+
{"current_steps": 4650, "total_steps": 6713, "loss": 0.1859, "lr": 1.0456748624136951e-05, "epoch": 4.850286906624935, "percentage": 69.27, "elapsed_time": "18:55:15", "remaining_time": "8:23:39"}
|
| 931 |
+
{"current_steps": 4655, "total_steps": 6713, "loss": 0.1919, "lr": 1.0411078588648756e-05, "epoch": 4.8555033907146585, "percentage": 69.34, "elapsed_time": "18:57:55", "remaining_time": "8:23:05"}
|
| 932 |
+
{"current_steps": 4660, "total_steps": 6713, "loss": 0.1953, "lr": 1.0365473385485662e-05, "epoch": 4.860719874804381, "percentage": 69.42, "elapsed_time": "19:00:36", "remaining_time": "8:22:30"}
|
| 933 |
+
{"current_steps": 4665, "total_steps": 6713, "loss": 0.1652, "lr": 1.0319933322992206e-05, "epoch": 4.865936358894105, "percentage": 69.49, "elapsed_time": "19:03:33", "remaining_time": "8:22:02"}
|
| 934 |
+
{"current_steps": 4670, "total_steps": 6713, "loss": 0.1868, "lr": 1.0274458709072459e-05, "epoch": 4.871152842983829, "percentage": 69.57, "elapsed_time": "19:06:30", "remaining_time": "8:21:33"}
|
| 935 |
+
{"current_steps": 4675, "total_steps": 6713, "loss": 0.1864, "lr": 1.022904985118803e-05, "epoch": 4.876369327073553, "percentage": 69.64, "elapsed_time": "19:09:13", "remaining_time": "8:20:59"}
|
| 936 |
+
{"current_steps": 4680, "total_steps": 6713, "loss": 0.1884, "lr": 1.0183707056355883e-05, "epoch": 4.881585811163276, "percentage": 69.72, "elapsed_time": "19:12:03", "remaining_time": "8:20:27"}
|
| 937 |
+
{"current_steps": 4685, "total_steps": 6713, "loss": 0.2014, "lr": 1.0138430631146372e-05, "epoch": 4.886802295252999, "percentage": 69.79, "elapsed_time": "19:14:52", "remaining_time": "8:19:54"}
|
| 938 |
+
{"current_steps": 4690, "total_steps": 6713, "loss": 0.1907, "lr": 1.009322088168108e-05, "epoch": 4.892018779342723, "percentage": 69.86, "elapsed_time": "19:17:33", "remaining_time": "8:19:18"}
|
| 939 |
+
{"current_steps": 4695, "total_steps": 6713, "loss": 0.1893, "lr": 1.0048078113630806e-05, "epoch": 4.897235263432447, "percentage": 69.94, "elapsed_time": "19:20:13", "remaining_time": "8:18:41"}
|
| 940 |
+
{"current_steps": 4700, "total_steps": 6713, "loss": 0.1723, "lr": 1.0003002632213455e-05, "epoch": 4.90245174752217, "percentage": 70.01, "elapsed_time": "19:23:09", "remaining_time": "8:18:10"}
|
| 941 |
+
{"current_steps": 4705, "total_steps": 6713, "loss": 0.1782, "lr": 9.95799474219202e-06, "epoch": 4.907668231611893, "percentage": 70.09, "elapsed_time": "19:25:58", "remaining_time": "8:17:37"}
|
| 942 |
+
{"current_steps": 4710, "total_steps": 6713, "loss": 0.1861, "lr": 9.913054747872473e-06, "epoch": 4.912884715701617, "percentage": 70.16, "elapsed_time": "19:28:41", "remaining_time": "8:17:00"}
|
| 943 |
+
{"current_steps": 4715, "total_steps": 6713, "loss": 0.1805, "lr": 9.868182953101754e-06, "epoch": 4.918101199791341, "percentage": 70.24, "elapsed_time": "19:31:32", "remaining_time": "8:16:26"}
|
| 944 |
+
{"current_steps": 4720, "total_steps": 6713, "loss": 0.1858, "lr": 9.823379661265677e-06, "epoch": 4.923317683881065, "percentage": 70.31, "elapsed_time": "19:34:10", "remaining_time": "8:15:47"}
|
| 945 |
+
{"current_steps": 4725, "total_steps": 6713, "loss": 0.1886, "lr": 9.778645175286904e-06, "epoch": 4.9285341679707875, "percentage": 70.39, "elapsed_time": "19:36:57", "remaining_time": "8:15:11"}
|
| 946 |
+
{"current_steps": 4730, "total_steps": 6713, "loss": 0.1863, "lr": 9.733979797622874e-06, "epoch": 4.933750652060511, "percentage": 70.46, "elapsed_time": "19:39:45", "remaining_time": "8:14:36"}
|
| 947 |
+
{"current_steps": 4735, "total_steps": 6713, "loss": 0.178, "lr": 9.689383830263808e-06, "epoch": 4.938967136150235, "percentage": 70.53, "elapsed_time": "19:42:37", "remaining_time": "8:14:01"}
|
| 948 |
+
{"current_steps": 4740, "total_steps": 6713, "loss": 0.1873, "lr": 9.6448575747306e-06, "epoch": 4.944183620239958, "percentage": 70.61, "elapsed_time": "19:45:30", "remaining_time": "8:13:27"}
|
| 949 |
+
{"current_steps": 4745, "total_steps": 6713, "loss": 0.1805, "lr": 9.60040133207281e-06, "epoch": 4.949400104329682, "percentage": 70.68, "elapsed_time": "19:48:28", "remaining_time": "8:12:55"}
|
| 950 |
+
{"current_steps": 4750, "total_steps": 6713, "loss": 0.1907, "lr": 9.556015402866661e-06, "epoch": 4.954616588419405, "percentage": 70.76, "elapsed_time": "19:51:06", "remaining_time": "8:12:14"}
|
| 951 |
+
{"current_steps": 4755, "total_steps": 6713, "loss": 0.188, "lr": 9.511700087212934e-06, "epoch": 4.959833072509129, "percentage": 70.83, "elapsed_time": "19:53:45", "remaining_time": "8:11:33"}
|
| 952 |
+
{"current_steps": 4760, "total_steps": 6713, "loss": 0.178, "lr": 9.467455684735015e-06, "epoch": 4.965049556598853, "percentage": 70.91, "elapsed_time": "19:56:41", "remaining_time": "8:10:59"}
|
| 953 |
+
{"current_steps": 4765, "total_steps": 6713, "loss": 0.1985, "lr": 9.423282494576804e-06, "epoch": 4.970266040688576, "percentage": 70.98, "elapsed_time": "19:59:10", "remaining_time": "8:10:14"}
|
| 954 |
+
{"current_steps": 4770, "total_steps": 6713, "loss": 0.1835, "lr": 9.379180815400753e-06, "epoch": 4.975482524778299, "percentage": 71.06, "elapsed_time": "20:02:02", "remaining_time": "8:09:38"}
|
| 955 |
+
{"current_steps": 4775, "total_steps": 6713, "loss": 0.1839, "lr": 9.33515094538579e-06, "epoch": 4.980699008868023, "percentage": 71.13, "elapsed_time": "20:04:54", "remaining_time": "8:09:01"}
|
| 956 |
+
{"current_steps": 4780, "total_steps": 6713, "loss": 0.1878, "lr": 9.291193182225341e-06, "epoch": 4.985915492957746, "percentage": 71.21, "elapsed_time": "20:07:35", "remaining_time": "8:08:20"}
|
| 957 |
+
{"current_steps": 4785, "total_steps": 6713, "loss": 0.1827, "lr": 9.247307823125296e-06, "epoch": 4.99113197704747, "percentage": 71.28, "elapsed_time": "20:10:09", "remaining_time": "8:07:36"}
|
| 958 |
+
{"current_steps": 4790, "total_steps": 6713, "loss": 0.175, "lr": 9.203495164802027e-06, "epoch": 4.9963484611371936, "percentage": 71.35, "elapsed_time": "20:13:02", "remaining_time": "8:06:59"}
|
| 959 |
+
{"current_steps": 4795, "total_steps": 6713, "loss": 0.183, "lr": 9.159755503480345e-06, "epoch": 5.001043296817945, "percentage": 71.43, "elapsed_time": "20:15:08", "remaining_time": "8:06:03"}
|
| 960 |
+
{"current_steps": 4800, "total_steps": 6713, "loss": 0.1824, "lr": 9.116089134891532e-06, "epoch": 5.006259780907668, "percentage": 71.5, "elapsed_time": "20:17:42", "remaining_time": "8:05:18"}
|