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 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1007143e4a28f0fa34b4a9ded490d5d0a8305337c43f20e9bf8c29c09ba72a5
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16cb61bc4a145468f3aa16cc44cfa810608f7dcc3197a1c154745aae243ebb0d
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb97b02ad0034a859fd26d309c0c3828dd13871f6be066eefefe0ad13a081eaf
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4c46547ba4036a6ce428800c10081c54bb54961c1b3b2b72f59cf0a784d684b
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -54,3 +54,59 @@
|
|
54 |
{"current_steps": 540, "total_steps": 4392, "loss": 0.7631, "lr": 5e-06, "epoch": 0.9831588529813382, "percentage": 12.3, "elapsed_time": "4:49:15", "remaining_time": "1 day, 10:23:25"}
|
55 |
{"current_steps": 549, "total_steps": 4392, "eval_loss": 0.7638739347457886, "epoch": 0.9995448338643604, "percentage": 12.5, "elapsed_time": "5:00:31", "remaining_time": "1 day, 11:03:42"}
|
56 |
{"current_steps": 550, "total_steps": 4392, "loss": 0.812, "lr": 5e-06, "epoch": 1.0013654984069185, "percentage": 12.52, "elapsed_time": "5:02:09", "remaining_time": "1 day, 11:10:43"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
{"current_steps": 540, "total_steps": 4392, "loss": 0.7631, "lr": 5e-06, "epoch": 0.9831588529813382, "percentage": 12.3, "elapsed_time": "4:49:15", "remaining_time": "1 day, 10:23:25"}
|
55 |
{"current_steps": 549, "total_steps": 4392, "eval_loss": 0.7638739347457886, "epoch": 0.9995448338643604, "percentage": 12.5, "elapsed_time": "5:00:31", "remaining_time": "1 day, 11:03:42"}
|
56 |
{"current_steps": 550, "total_steps": 4392, "loss": 0.812, "lr": 5e-06, "epoch": 1.0013654984069185, "percentage": 12.52, "elapsed_time": "5:02:09", "remaining_time": "1 day, 11:10:43"}
|
57 |
+
{"current_steps": 560, "total_steps": 4392, "loss": 0.7222, "lr": 5e-06, "epoch": 1.019572143832499, "percentage": 12.75, "elapsed_time": "5:07:31", "remaining_time": "1 day, 11:04:20"}
|
58 |
+
{"current_steps": 570, "total_steps": 4392, "loss": 0.7205, "lr": 5e-06, "epoch": 1.0377787892580792, "percentage": 12.98, "elapsed_time": "5:12:52", "remaining_time": "1 day, 10:57:54"}
|
59 |
+
{"current_steps": 580, "total_steps": 4392, "loss": 0.7205, "lr": 5e-06, "epoch": 1.0559854346836595, "percentage": 13.21, "elapsed_time": "5:18:13", "remaining_time": "1 day, 10:51:29"}
|
60 |
+
{"current_steps": 590, "total_steps": 4392, "loss": 0.7144, "lr": 5e-06, "epoch": 1.07419208010924, "percentage": 13.43, "elapsed_time": "5:23:34", "remaining_time": "1 day, 10:45:09"}
|
61 |
+
{"current_steps": 600, "total_steps": 4392, "loss": 0.7136, "lr": 5e-06, "epoch": 1.0923987255348202, "percentage": 13.66, "elapsed_time": "5:28:54", "remaining_time": "1 day, 10:38:40"}
|
62 |
+
{"current_steps": 610, "total_steps": 4392, "loss": 0.7189, "lr": 5e-06, "epoch": 1.1106053709604005, "percentage": 13.89, "elapsed_time": "5:34:16", "remaining_time": "1 day, 10:32:27"}
|
63 |
+
{"current_steps": 620, "total_steps": 4392, "loss": 0.7122, "lr": 5e-06, "epoch": 1.128812016385981, "percentage": 14.12, "elapsed_time": "5:39:38", "remaining_time": "1 day, 10:26:19"}
|
64 |
+
{"current_steps": 630, "total_steps": 4392, "loss": 0.7138, "lr": 5e-06, "epoch": 1.1470186618115612, "percentage": 14.34, "elapsed_time": "5:45:00", "remaining_time": "1 day, 10:20:13"}
|
65 |
+
{"current_steps": 640, "total_steps": 4392, "loss": 0.7174, "lr": 5e-06, "epoch": 1.1652253072371415, "percentage": 14.57, "elapsed_time": "5:50:21", "remaining_time": "1 day, 10:14:00"}
|
66 |
+
{"current_steps": 650, "total_steps": 4392, "loss": 0.7183, "lr": 5e-06, "epoch": 1.183431952662722, "percentage": 14.8, "elapsed_time": "5:55:43", "remaining_time": "1 day, 10:07:54"}
|
67 |
+
{"current_steps": 660, "total_steps": 4392, "loss": 0.7169, "lr": 5e-06, "epoch": 1.2016385980883022, "percentage": 15.03, "elapsed_time": "6:01:06", "remaining_time": "1 day, 10:01:54"}
|
68 |
+
{"current_steps": 670, "total_steps": 4392, "loss": 0.7136, "lr": 5e-06, "epoch": 1.2198452435138827, "percentage": 15.26, "elapsed_time": "6:06:28", "remaining_time": "1 day, 9:55:52"}
|
69 |
+
{"current_steps": 680, "total_steps": 4392, "loss": 0.7114, "lr": 5e-06, "epoch": 1.238051888939463, "percentage": 15.48, "elapsed_time": "6:11:51", "remaining_time": "1 day, 9:49:52"}
|
70 |
+
{"current_steps": 690, "total_steps": 4392, "loss": 0.7185, "lr": 5e-06, "epoch": 1.2562585343650432, "percentage": 15.71, "elapsed_time": "6:17:12", "remaining_time": "1 day, 9:43:50"}
|
71 |
+
{"current_steps": 700, "total_steps": 4392, "loss": 0.7166, "lr": 5e-06, "epoch": 1.2744651797906235, "percentage": 15.94, "elapsed_time": "6:22:32", "remaining_time": "1 day, 9:37:38"}
|
72 |
+
{"current_steps": 710, "total_steps": 4392, "loss": 0.7158, "lr": 5e-06, "epoch": 1.292671825216204, "percentage": 16.17, "elapsed_time": "6:27:54", "remaining_time": "1 day, 9:31:39"}
|
73 |
+
{"current_steps": 720, "total_steps": 4392, "loss": 0.7144, "lr": 5e-06, "epoch": 1.3108784706417842, "percentage": 16.39, "elapsed_time": "6:33:15", "remaining_time": "1 day, 9:25:36"}
|
74 |
+
{"current_steps": 730, "total_steps": 4392, "loss": 0.718, "lr": 5e-06, "epoch": 1.3290851160673647, "percentage": 16.62, "elapsed_time": "6:38:37", "remaining_time": "1 day, 9:19:39"}
|
75 |
+
{"current_steps": 740, "total_steps": 4392, "loss": 0.7131, "lr": 5e-06, "epoch": 1.347291761492945, "percentage": 16.85, "elapsed_time": "6:43:58", "remaining_time": "1 day, 9:13:40"}
|
76 |
+
{"current_steps": 750, "total_steps": 4392, "loss": 0.7136, "lr": 5e-06, "epoch": 1.3654984069185252, "percentage": 17.08, "elapsed_time": "6:49:20", "remaining_time": "1 day, 9:07:45"}
|
77 |
+
{"current_steps": 760, "total_steps": 4392, "loss": 0.7154, "lr": 5e-06, "epoch": 1.3837050523441057, "percentage": 17.3, "elapsed_time": "6:54:39", "remaining_time": "1 day, 9:01:38"}
|
78 |
+
{"current_steps": 770, "total_steps": 4392, "loss": 0.7148, "lr": 5e-06, "epoch": 1.401911697769686, "percentage": 17.53, "elapsed_time": "7:00:00", "remaining_time": "1 day, 8:55:42"}
|
79 |
+
{"current_steps": 780, "total_steps": 4392, "loss": 0.7152, "lr": 5e-06, "epoch": 1.4201183431952662, "percentage": 17.76, "elapsed_time": "7:05:23", "remaining_time": "1 day, 8:49:51"}
|
80 |
+
{"current_steps": 790, "total_steps": 4392, "loss": 0.7139, "lr": 5e-06, "epoch": 1.4383249886208467, "percentage": 17.99, "elapsed_time": "7:10:44", "remaining_time": "1 day, 8:43:58"}
|
81 |
+
{"current_steps": 800, "total_steps": 4392, "loss": 0.7169, "lr": 5e-06, "epoch": 1.456531634046427, "percentage": 18.21, "elapsed_time": "7:16:07", "remaining_time": "1 day, 8:38:12"}
|
82 |
+
{"current_steps": 810, "total_steps": 4392, "loss": 0.7157, "lr": 5e-06, "epoch": 1.4747382794720072, "percentage": 18.44, "elapsed_time": "7:21:27", "remaining_time": "1 day, 8:32:11"}
|
83 |
+
{"current_steps": 820, "total_steps": 4392, "loss": 0.7186, "lr": 5e-06, "epoch": 1.4929449248975877, "percentage": 18.67, "elapsed_time": "7:26:49", "remaining_time": "1 day, 8:26:23"}
|
84 |
+
{"current_steps": 830, "total_steps": 4392, "loss": 0.713, "lr": 5e-06, "epoch": 1.511151570323168, "percentage": 18.9, "elapsed_time": "7:32:11", "remaining_time": "1 day, 8:20:36"}
|
85 |
+
{"current_steps": 840, "total_steps": 4392, "loss": 0.7121, "lr": 5e-06, "epoch": 1.5293582157487484, "percentage": 19.13, "elapsed_time": "7:37:34", "remaining_time": "1 day, 8:14:52"}
|
86 |
+
{"current_steps": 850, "total_steps": 4392, "loss": 0.7161, "lr": 5e-06, "epoch": 1.5475648611743287, "percentage": 19.35, "elapsed_time": "7:42:56", "remaining_time": "1 day, 8:09:05"}
|
87 |
+
{"current_steps": 860, "total_steps": 4392, "loss": 0.7144, "lr": 5e-06, "epoch": 1.565771506599909, "percentage": 19.58, "elapsed_time": "7:48:16", "remaining_time": "1 day, 8:03:11"}
|
88 |
+
{"current_steps": 870, "total_steps": 4392, "loss": 0.7137, "lr": 5e-06, "epoch": 1.5839781520254892, "percentage": 19.81, "elapsed_time": "7:53:36", "remaining_time": "1 day, 7:57:16"}
|
89 |
+
{"current_steps": 880, "total_steps": 4392, "loss": 0.718, "lr": 5e-06, "epoch": 1.6021847974510697, "percentage": 20.04, "elapsed_time": "7:58:57", "remaining_time": "1 day, 7:51:27"}
|
90 |
+
{"current_steps": 890, "total_steps": 4392, "loss": 0.7107, "lr": 5e-06, "epoch": 1.62039144287665, "percentage": 20.26, "elapsed_time": "8:04:18", "remaining_time": "1 day, 7:45:40"}
|
91 |
+
{"current_steps": 900, "total_steps": 4392, "loss": 0.7101, "lr": 5e-06, "epoch": 1.6385980883022304, "percentage": 20.49, "elapsed_time": "8:09:40", "remaining_time": "1 day, 7:39:57"}
|
92 |
+
{"current_steps": 910, "total_steps": 4392, "loss": 0.7128, "lr": 5e-06, "epoch": 1.6568047337278107, "percentage": 20.72, "elapsed_time": "8:15:02", "remaining_time": "1 day, 7:34:13"}
|
93 |
+
{"current_steps": 920, "total_steps": 4392, "loss": 0.7104, "lr": 5e-06, "epoch": 1.675011379153391, "percentage": 20.95, "elapsed_time": "8:20:25", "remaining_time": "1 day, 7:28:34"}
|
94 |
+
{"current_steps": 930, "total_steps": 4392, "loss": 0.7115, "lr": 5e-06, "epoch": 1.6932180245789712, "percentage": 21.17, "elapsed_time": "8:25:46", "remaining_time": "1 day, 7:22:45"}
|
95 |
+
{"current_steps": 940, "total_steps": 4392, "loss": 0.7105, "lr": 5e-06, "epoch": 1.7114246700045517, "percentage": 21.4, "elapsed_time": "8:31:08", "remaining_time": "1 day, 7:17:03"}
|
96 |
+
{"current_steps": 950, "total_steps": 4392, "loss": 0.7116, "lr": 5e-06, "epoch": 1.7296313154301322, "percentage": 21.63, "elapsed_time": "8:36:30", "remaining_time": "1 day, 7:11:21"}
|
97 |
+
{"current_steps": 960, "total_steps": 4392, "loss": 0.7108, "lr": 5e-06, "epoch": 1.7478379608557124, "percentage": 21.86, "elapsed_time": "8:41:52", "remaining_time": "1 day, 7:05:41"}
|
98 |
+
{"current_steps": 970, "total_steps": 4392, "loss": 0.7107, "lr": 5e-06, "epoch": 1.7660446062812927, "percentage": 22.09, "elapsed_time": "8:47:10", "remaining_time": "1 day, 6:59:48"}
|
99 |
+
{"current_steps": 980, "total_steps": 4392, "loss": 0.7118, "lr": 5e-06, "epoch": 1.784251251706873, "percentage": 22.31, "elapsed_time": "8:52:30", "remaining_time": "1 day, 6:54:01"}
|
100 |
+
{"current_steps": 990, "total_steps": 4392, "loss": 0.7109, "lr": 5e-06, "epoch": 1.8024578971324532, "percentage": 22.54, "elapsed_time": "8:57:50", "remaining_time": "1 day, 6:48:13"}
|
101 |
+
{"current_steps": 1000, "total_steps": 4392, "loss": 0.7128, "lr": 5e-06, "epoch": 1.8206645425580337, "percentage": 22.77, "elapsed_time": "9:03:12", "remaining_time": "1 day, 6:42:32"}
|
102 |
+
{"current_steps": 1010, "total_steps": 4392, "loss": 0.7129, "lr": 5e-06, "epoch": 1.8388711879836142, "percentage": 23.0, "elapsed_time": "9:08:33", "remaining_time": "1 day, 6:36:52"}
|
103 |
+
{"current_steps": 1020, "total_steps": 4392, "loss": 0.7163, "lr": 5e-06, "epoch": 1.8570778334091944, "percentage": 23.22, "elapsed_time": "9:13:53", "remaining_time": "1 day, 6:31:06"}
|
104 |
+
{"current_steps": 1030, "total_steps": 4392, "loss": 0.712, "lr": 5e-06, "epoch": 1.8752844788347747, "percentage": 23.45, "elapsed_time": "9:19:15", "remaining_time": "1 day, 6:25:27"}
|
105 |
+
{"current_steps": 1040, "total_steps": 4392, "loss": 0.7106, "lr": 5e-06, "epoch": 1.893491124260355, "percentage": 23.68, "elapsed_time": "9:24:36", "remaining_time": "1 day, 6:19:47"}
|
106 |
+
{"current_steps": 1050, "total_steps": 4392, "loss": 0.7135, "lr": 5e-06, "epoch": 1.9116977696859354, "percentage": 23.91, "elapsed_time": "9:29:58", "remaining_time": "1 day, 6:14:10"}
|
107 |
+
{"current_steps": 1060, "total_steps": 4392, "loss": 0.7113, "lr": 5e-06, "epoch": 1.9299044151115157, "percentage": 24.13, "elapsed_time": "9:35:20", "remaining_time": "1 day, 6:08:32"}
|
108 |
+
{"current_steps": 1070, "total_steps": 4392, "loss": 0.7133, "lr": 5e-06, "epoch": 1.9481110605370962, "percentage": 24.36, "elapsed_time": "9:40:41", "remaining_time": "1 day, 6:02:52"}
|
109 |
+
{"current_steps": 1080, "total_steps": 4392, "loss": 0.7107, "lr": 5e-06, "epoch": 1.9663177059626764, "percentage": 24.59, "elapsed_time": "9:46:02", "remaining_time": "1 day, 5:57:10"}
|
110 |
+
{"current_steps": 1090, "total_steps": 4392, "loss": 0.7148, "lr": 5e-06, "epoch": 1.9845243513882567, "percentage": 24.82, "elapsed_time": "9:51:24", "remaining_time": "1 day, 5:51:36"}
|
111 |
+
{"current_steps": 1098, "total_steps": 4392, "eval_loss": 0.7494105696678162, "epoch": 1.9990896677287209, "percentage": 25.0, "elapsed_time": "10:02:05", "remaining_time": "1 day, 6:06:16"}
|
112 |
+
{"current_steps": 1100, "total_steps": 4392, "loss": 0.7534, "lr": 5e-06, "epoch": 2.002730996813837, "percentage": 25.05, "elapsed_time": "10:04:14", "remaining_time": "1 day, 6:08:19"}
|