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 sha256:32f640ecfb2b24c62f6f9ace94a941103b821be8c064fff1fc7654f94f36abc1
|
| 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:eccdc84a35e9f15ce6867a931f464ccc50c6285e4240d818930ac59141b59719
|
| 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 sha256:523e7fcb2734c5043b08224368f3515a9423cc3ca678a86e00f41dd07ba9d48f
|
| 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 sha256:586894097af51faf1f4e089324f26adb9d1716fe0bc2a411fe454a0a28e9ecb4
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -941,3 +941,43 @@
|
|
| 941 |
{"current_steps": 4590, "total_steps": 6713, "loss": 0.2089, "lr": 1.1009733141895823e-05, "epoch": 4.7876890975482524, "percentage": 68.37, "elapsed_time": "12:03:58", "remaining_time": "5:34:51"}
|
| 942 |
{"current_steps": 4595, "total_steps": 6713, "loss": 0.199, "lr": 1.0963309326839708e-05, "epoch": 4.792905581637976, "percentage": 68.45, "elapsed_time": "12:05:40", "remaining_time": "5:34:29"}
|
| 943 |
{"current_steps": 4600, "total_steps": 6713, "loss": 0.2058, "lr": 1.0916946610382966e-05, "epoch": 4.7981220657277, "percentage": 68.52, "elapsed_time": "12:07:19", "remaining_time": "5:34:05"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 941 |
{"current_steps": 4590, "total_steps": 6713, "loss": 0.2089, "lr": 1.1009733141895823e-05, "epoch": 4.7876890975482524, "percentage": 68.37, "elapsed_time": "12:03:58", "remaining_time": "5:34:51"}
|
| 942 |
{"current_steps": 4595, "total_steps": 6713, "loss": 0.199, "lr": 1.0963309326839708e-05, "epoch": 4.792905581637976, "percentage": 68.45, "elapsed_time": "12:05:40", "remaining_time": "5:34:29"}
|
| 943 |
{"current_steps": 4600, "total_steps": 6713, "loss": 0.2058, "lr": 1.0916946610382966e-05, "epoch": 4.7981220657277, "percentage": 68.52, "elapsed_time": "12:07:19", "remaining_time": "5:34:05"}
|
| 944 |
+
{"current_steps": 4605, "total_steps": 6713, "loss": 0.2151, "lr": 1.0870645305991772e-05, "epoch": 4.803338549817423, "percentage": 68.6, "elapsed_time": "12:10:31", "remaining_time": "5:34:24"}
|
| 945 |
+
{"current_steps": 4610, "total_steps": 6713, "loss": 0.2086, "lr": 1.0824405726717119e-05, "epoch": 4.808555033907147, "percentage": 68.67, "elapsed_time": "12:12:12", "remaining_time": "5:34:01"}
|
| 946 |
+
{"current_steps": 4615, "total_steps": 6713, "loss": 0.2224, "lr": 1.0778228185192639e-05, "epoch": 4.81377151799687, "percentage": 68.75, "elapsed_time": "12:13:50", "remaining_time": "5:33:36"}
|
| 947 |
+
{"current_steps": 4620, "total_steps": 6713, "loss": 0.2045, "lr": 1.0732112993632539e-05, "epoch": 4.818988002086593, "percentage": 68.82, "elapsed_time": "12:15:27", "remaining_time": "5:33:11"}
|
| 948 |
+
{"current_steps": 4625, "total_steps": 6713, "loss": 0.2193, "lr": 1.0686060463829451e-05, "epoch": 4.824204486176317, "percentage": 68.9, "elapsed_time": "12:17:12", "remaining_time": "5:32:49"}
|
| 949 |
+
{"current_steps": 4630, "total_steps": 6713, "loss": 0.2133, "lr": 1.0640070907152342e-05, "epoch": 4.829420970266041, "percentage": 68.97, "elapsed_time": "12:18:54", "remaining_time": "5:32:25"}
|
| 950 |
+
{"current_steps": 4635, "total_steps": 6713, "loss": 0.2127, "lr": 1.0594144634544405e-05, "epoch": 4.834637454355764, "percentage": 69.05, "elapsed_time": "12:20:32", "remaining_time": "5:32:00"}
|
| 951 |
+
{"current_steps": 4640, "total_steps": 6713, "loss": 0.2101, "lr": 1.0548281956520978e-05, "epoch": 4.839853938445488, "percentage": 69.12, "elapsed_time": "12:22:17", "remaining_time": "5:31:37"}
|
| 952 |
+
{"current_steps": 4645, "total_steps": 6713, "loss": 0.2138, "lr": 1.0502483183167395e-05, "epoch": 4.845070422535211, "percentage": 69.19, "elapsed_time": "12:23:58", "remaining_time": "5:31:13"}
|
| 953 |
+
{"current_steps": 4650, "total_steps": 6713, "loss": 0.2074, "lr": 1.0456748624136951e-05, "epoch": 4.850286906624935, "percentage": 69.27, "elapsed_time": "12:25:34", "remaining_time": "5:30:46"}
|
| 954 |
+
{"current_steps": 4655, "total_steps": 6713, "loss": 0.2128, "lr": 1.0411078588648756e-05, "epoch": 4.8555033907146585, "percentage": 69.34, "elapsed_time": "12:27:14", "remaining_time": "5:30:21"}
|
| 955 |
+
{"current_steps": 4660, "total_steps": 6713, "loss": 0.2018, "lr": 1.0365473385485662e-05, "epoch": 4.860719874804381, "percentage": 69.42, "elapsed_time": "12:28:55", "remaining_time": "5:29:56"}
|
| 956 |
+
{"current_steps": 4665, "total_steps": 6713, "loss": 0.1991, "lr": 1.0319933322992206e-05, "epoch": 4.865936358894105, "percentage": 69.49, "elapsed_time": "12:30:39", "remaining_time": "5:29:32"}
|
| 957 |
+
{"current_steps": 4670, "total_steps": 6713, "loss": 0.2051, "lr": 1.0274458709072459e-05, "epoch": 4.871152842983829, "percentage": 69.57, "elapsed_time": "12:32:20", "remaining_time": "5:29:07"}
|
| 958 |
+
{"current_steps": 4675, "total_steps": 6713, "loss": 0.2026, "lr": 1.022904985118803e-05, "epoch": 4.876369327073553, "percentage": 69.64, "elapsed_time": "12:34:03", "remaining_time": "5:28:43"}
|
| 959 |
+
{"current_steps": 4680, "total_steps": 6713, "loss": 0.2161, "lr": 1.0183707056355883e-05, "epoch": 4.881585811163276, "percentage": 69.72, "elapsed_time": "12:35:41", "remaining_time": "5:28:16"}
|
| 960 |
+
{"current_steps": 4685, "total_steps": 6713, "loss": 0.2075, "lr": 1.0138430631146372e-05, "epoch": 4.886802295252999, "percentage": 69.79, "elapsed_time": "12:37:21", "remaining_time": "5:27:50"}
|
| 961 |
+
{"current_steps": 4690, "total_steps": 6713, "loss": 0.2119, "lr": 1.009322088168108e-05, "epoch": 4.892018779342723, "percentage": 69.86, "elapsed_time": "12:39:02", "remaining_time": "5:27:24"}
|
| 962 |
+
{"current_steps": 4695, "total_steps": 6713, "loss": 0.209, "lr": 1.0048078113630806e-05, "epoch": 4.897235263432447, "percentage": 69.94, "elapsed_time": "12:40:38", "remaining_time": "5:26:56"}
|
| 963 |
+
{"current_steps": 4700, "total_steps": 6713, "loss": 0.2117, "lr": 1.0003002632213455e-05, "epoch": 4.90245174752217, "percentage": 70.01, "elapsed_time": "12:42:24", "remaining_time": "5:26:32"}
|
| 964 |
+
{"current_steps": 4705, "total_steps": 6713, "loss": 0.2038, "lr": 9.95799474219202e-06, "epoch": 4.907668231611893, "percentage": 70.09, "elapsed_time": "12:44:13", "remaining_time": "5:26:09"}
|
| 965 |
+
{"current_steps": 4710, "total_steps": 6713, "loss": 0.198, "lr": 9.913054747872473e-06, "epoch": 4.912884715701617, "percentage": 70.16, "elapsed_time": "12:45:58", "remaining_time": "5:25:44"}
|
| 966 |
+
{"current_steps": 4715, "total_steps": 6713, "loss": 0.2042, "lr": 9.868182953101754e-06, "epoch": 4.918101199791341, "percentage": 70.24, "elapsed_time": "12:47:42", "remaining_time": "5:25:19"}
|
| 967 |
+
{"current_steps": 4720, "total_steps": 6713, "loss": 0.204, "lr": 9.823379661265677e-06, "epoch": 4.923317683881065, "percentage": 70.31, "elapsed_time": "12:49:23", "remaining_time": "5:24:52"}
|
| 968 |
+
{"current_steps": 4725, "total_steps": 6713, "loss": 0.197, "lr": 9.778645175286904e-06, "epoch": 4.9285341679707875, "percentage": 70.39, "elapsed_time": "12:51:03", "remaining_time": "5:24:25"}
|
| 969 |
+
{"current_steps": 4730, "total_steps": 6713, "loss": 0.1966, "lr": 9.733979797622874e-06, "epoch": 4.933750652060511, "percentage": 70.46, "elapsed_time": "12:52:45", "remaining_time": "5:23:58"}
|
| 970 |
+
{"current_steps": 4735, "total_steps": 6713, "loss": 0.2001, "lr": 9.689383830263808e-06, "epoch": 4.938967136150235, "percentage": 70.53, "elapsed_time": "12:54:22", "remaining_time": "5:23:29"}
|
| 971 |
+
{"current_steps": 4740, "total_steps": 6713, "loss": 0.1967, "lr": 9.6448575747306e-06, "epoch": 4.944183620239958, "percentage": 70.61, "elapsed_time": "12:56:04", "remaining_time": "5:23:02"}
|
| 972 |
+
{"current_steps": 4745, "total_steps": 6713, "loss": 0.2189, "lr": 9.60040133207281e-06, "epoch": 4.949400104329682, "percentage": 70.68, "elapsed_time": "12:57:43", "remaining_time": "5:22:33"}
|
| 973 |
+
{"current_steps": 4750, "total_steps": 6713, "loss": 0.2066, "lr": 9.556015402866661e-06, "epoch": 4.954616588419405, "percentage": 70.76, "elapsed_time": "12:59:17", "remaining_time": "5:22:03"}
|
| 974 |
+
{"current_steps": 4755, "total_steps": 6713, "loss": 0.203, "lr": 9.511700087212934e-06, "epoch": 4.959833072509129, "percentage": 70.83, "elapsed_time": "13:01:02", "remaining_time": "5:21:37"}
|
| 975 |
+
{"current_steps": 4760, "total_steps": 6713, "loss": 0.1924, "lr": 9.467455684735015e-06, "epoch": 4.965049556598853, "percentage": 70.91, "elapsed_time": "13:02:39", "remaining_time": "5:21:07"}
|
| 976 |
+
{"current_steps": 4765, "total_steps": 6713, "loss": 0.2087, "lr": 9.423282494576804e-06, "epoch": 4.970266040688576, "percentage": 70.98, "elapsed_time": "13:04:18", "remaining_time": "5:20:38"}
|
| 977 |
+
{"current_steps": 4770, "total_steps": 6713, "loss": 0.206, "lr": 9.379180815400753e-06, "epoch": 4.975482524778299, "percentage": 71.06, "elapsed_time": "13:05:58", "remaining_time": "5:20:09"}
|
| 978 |
+
{"current_steps": 4775, "total_steps": 6713, "loss": 0.2077, "lr": 9.33515094538579e-06, "epoch": 4.980699008868023, "percentage": 71.13, "elapsed_time": "13:07:40", "remaining_time": "5:19:41"}
|
| 979 |
+
{"current_steps": 4780, "total_steps": 6713, "loss": 0.2053, "lr": 9.291193182225341e-06, "epoch": 4.985915492957746, "percentage": 71.21, "elapsed_time": "13:09:21", "remaining_time": "5:19:12"}
|
| 980 |
+
{"current_steps": 4785, "total_steps": 6713, "loss": 0.2073, "lr": 9.247307823125296e-06, "epoch": 4.99113197704747, "percentage": 71.28, "elapsed_time": "13:11:01", "remaining_time": "5:18:43"}
|
| 981 |
+
{"current_steps": 4790, "total_steps": 6713, "loss": 0.2103, "lr": 9.203495164802027e-06, "epoch": 4.9963484611371936, "percentage": 71.35, "elapsed_time": "13:12:42", "remaining_time": "5:18:14"}
|
| 982 |
+
{"current_steps": 4795, "total_steps": 6713, "loss": 0.1863, "lr": 9.159755503480345e-06, "epoch": 5.001043296817945, "percentage": 71.43, "elapsed_time": "13:14:40", "remaining_time": "5:17:52"}
|
| 983 |
+
{"current_steps": 4800, "total_steps": 6713, "loss": 0.1582, "lr": 9.116089134891532e-06, "epoch": 5.006259780907668, "percentage": 71.5, "elapsed_time": "13:17:37", "remaining_time": "5:17:53"}
|