Training in progress, step 6400
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:b629fd23b66ccec1e71e864a659cb106c0723d4c49f0781d197c7c13e82130e0
|
| 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 sha256:32d09621ca6be45dc954fa0c05f155b9969e9865fb0fc9ca5f18105f4be8c297
|
| 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 sha256:0465d7f7f2d1d15093eb6f5104d3199f6354e3f458a31247c6346740ae9d6a61
|
| 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:f988b6734183658e468d47014da28e1491f15cb5cdc24bc5e212e8afb727a7fd
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1960,3 +1960,43 @@
|
|
| 1960 |
{"current_steps": 6200, "total_steps": 7494, "loss": 0.3725, "lr": 3.5301514204230646e-06, "epoch": 0.8273423295691481, "percentage": 82.73, "elapsed_time": "1 day, 20:40:19", "remaining_time": "9:19:24"}
|
| 1961 |
{"current_steps": 6205, "total_steps": 7494, "loss": 0.3792, "lr": 3.503768017979412e-06, "epoch": 0.8280095411252523, "percentage": 82.8, "elapsed_time": "1 day, 20:43:27", "remaining_time": "9:17:27"}
|
| 1962 |
{"current_steps": 6210, "total_steps": 7494, "loss": 0.3777, "lr": 3.4774741085611007e-06, "epoch": 0.8286767526813564, "percentage": 82.87, "elapsed_time": "1 day, 20:45:34", "remaining_time": "9:15:16"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1960 |
{"current_steps": 6200, "total_steps": 7494, "loss": 0.3725, "lr": 3.5301514204230646e-06, "epoch": 0.8273423295691481, "percentage": 82.73, "elapsed_time": "1 day, 20:40:19", "remaining_time": "9:19:24"}
|
| 1961 |
{"current_steps": 6205, "total_steps": 7494, "loss": 0.3792, "lr": 3.503768017979412e-06, "epoch": 0.8280095411252523, "percentage": 82.8, "elapsed_time": "1 day, 20:43:27", "remaining_time": "9:17:27"}
|
| 1962 |
{"current_steps": 6210, "total_steps": 7494, "loss": 0.3777, "lr": 3.4774741085611007e-06, "epoch": 0.8286767526813564, "percentage": 82.87, "elapsed_time": "1 day, 20:45:34", "remaining_time": "9:15:16"}
|
| 1963 |
+
{"current_steps": 6215, "total_steps": 7494, "loss": 0.3762, "lr": 3.451269834814137e-06, "epoch": 0.8293439642374606, "percentage": 82.93, "elapsed_time": "1 day, 20:47:42", "remaining_time": "9:13:06"}
|
| 1964 |
+
{"current_steps": 6220, "total_steps": 7494, "loss": 0.3718, "lr": 3.4251553388982495e-06, "epoch": 0.8300111757935648, "percentage": 83.0, "elapsed_time": "1 day, 20:49:49", "remaining_time": "9:10:56"}
|
| 1965 |
+
{"current_steps": 6225, "total_steps": 7494, "loss": 0.3818, "lr": 3.399130762486096e-06, "epoch": 0.8306783873496689, "percentage": 83.07, "elapsed_time": "1 day, 20:51:56", "remaining_time": "9:08:46"}
|
| 1966 |
+
{"current_steps": 6230, "total_steps": 7494, "loss": 0.3746, "lr": 3.373196246762538e-06, "epoch": 0.8313455989057731, "percentage": 83.13, "elapsed_time": "1 day, 20:54:05", "remaining_time": "9:06:36"}
|
| 1967 |
+
{"current_steps": 6235, "total_steps": 7494, "loss": 0.3779, "lr": 3.3473519324238367e-06, "epoch": 0.8320128104618773, "percentage": 83.2, "elapsed_time": "1 day, 20:56:13", "remaining_time": "9:04:25"}
|
| 1968 |
+
{"current_steps": 6240, "total_steps": 7494, "loss": 0.3791, "lr": 3.3215979596769233e-06, "epoch": 0.8326800220179813, "percentage": 83.27, "elapsed_time": "1 day, 20:58:20", "remaining_time": "9:02:15"}
|
| 1969 |
+
{"current_steps": 6245, "total_steps": 7494, "loss": 0.3798, "lr": 3.2959344682385975e-06, "epoch": 0.8333472335740855, "percentage": 83.33, "elapsed_time": "1 day, 21:00:27", "remaining_time": "9:00:05"}
|
| 1970 |
+
{"current_steps": 6250, "total_steps": 7494, "loss": 0.3775, "lr": 3.270361597334808e-06, "epoch": 0.8340144451301896, "percentage": 83.4, "elapsed_time": "1 day, 21:02:36", "remaining_time": "8:57:55"}
|
| 1971 |
+
{"current_steps": 6255, "total_steps": 7494, "loss": 0.3708, "lr": 3.244879485699879e-06, "epoch": 0.8346816566862938, "percentage": 83.47, "elapsed_time": "1 day, 21:04:44", "remaining_time": "8:55:45"}
|
| 1972 |
+
{"current_steps": 6260, "total_steps": 7494, "loss": 0.3809, "lr": 3.2194882715757636e-06, "epoch": 0.835348868242398, "percentage": 83.53, "elapsed_time": "1 day, 21:06:51", "remaining_time": "8:53:35"}
|
| 1973 |
+
{"current_steps": 6265, "total_steps": 7494, "loss": 0.3814, "lr": 3.1941880927112814e-06, "epoch": 0.8360160797985021, "percentage": 83.6, "elapsed_time": "1 day, 21:09:00", "remaining_time": "8:51:25"}
|
| 1974 |
+
{"current_steps": 6270, "total_steps": 7494, "loss": 0.3842, "lr": 3.1689790863613834e-06, "epoch": 0.8366832913546063, "percentage": 83.67, "elapsed_time": "1 day, 21:11:08", "remaining_time": "8:49:15"}
|
| 1975 |
+
{"current_steps": 6275, "total_steps": 7494, "loss": 0.3708, "lr": 3.143861389286418e-06, "epoch": 0.8373505029107104, "percentage": 83.73, "elapsed_time": "1 day, 21:13:15", "remaining_time": "8:47:05"}
|
| 1976 |
+
{"current_steps": 6280, "total_steps": 7494, "loss": 0.381, "lr": 3.1188351377513504e-06, "epoch": 0.8380177144668146, "percentage": 83.8, "elapsed_time": "1 day, 21:15:22", "remaining_time": "8:44:54"}
|
| 1977 |
+
{"current_steps": 6285, "total_steps": 7494, "loss": 0.3798, "lr": 3.0939004675250683e-06, "epoch": 0.8386849260229187, "percentage": 83.87, "elapsed_time": "1 day, 21:17:30", "remaining_time": "8:42:44"}
|
| 1978 |
+
{"current_steps": 6290, "total_steps": 7494, "loss": 0.3759, "lr": 3.069057513879623e-06, "epoch": 0.8393521375790228, "percentage": 83.93, "elapsed_time": "1 day, 21:19:38", "remaining_time": "8:40:34"}
|
| 1979 |
+
{"current_steps": 6295, "total_steps": 7494, "loss": 0.381, "lr": 3.044306411589484e-06, "epoch": 0.840019349135127, "percentage": 84.0, "elapsed_time": "1 day, 21:21:48", "remaining_time": "8:38:25"}
|
| 1980 |
+
{"current_steps": 6300, "total_steps": 7494, "loss": 0.3803, "lr": 3.019647294930843e-06, "epoch": 0.8406865606912312, "percentage": 84.07, "elapsed_time": "1 day, 21:23:56", "remaining_time": "8:36:15"}
|
| 1981 |
+
{"current_steps": 6305, "total_steps": 7494, "loss": 0.3813, "lr": 2.9950802976808437e-06, "epoch": 0.8413537722473353, "percentage": 84.13, "elapsed_time": "1 day, 21:26:03", "remaining_time": "8:34:04"}
|
| 1982 |
+
{"current_steps": 6310, "total_steps": 7494, "loss": 0.3767, "lr": 2.97060555311689e-06, "epoch": 0.8420209838034395, "percentage": 84.2, "elapsed_time": "1 day, 21:28:10", "remaining_time": "8:31:54"}
|
| 1983 |
+
{"current_steps": 6315, "total_steps": 7494, "loss": 0.3788, "lr": 2.9462231940159114e-06, "epoch": 0.8426881953595436, "percentage": 84.27, "elapsed_time": "1 day, 21:30:20", "remaining_time": "8:29:45"}
|
| 1984 |
+
{"current_steps": 6320, "total_steps": 7494, "loss": 0.3802, "lr": 2.921933352653623e-06, "epoch": 0.8433554069156478, "percentage": 84.33, "elapsed_time": "1 day, 21:32:28", "remaining_time": "8:27:34"}
|
| 1985 |
+
{"current_steps": 6325, "total_steps": 7494, "loss": 0.3773, "lr": 2.8977361608038433e-06, "epoch": 0.844022618471752, "percentage": 84.4, "elapsed_time": "1 day, 21:34:36", "remaining_time": "8:25:24"}
|
| 1986 |
+
{"current_steps": 6330, "total_steps": 7494, "loss": 0.3841, "lr": 2.873631749737764e-06, "epoch": 0.8446898300278561, "percentage": 84.47, "elapsed_time": "1 day, 21:36:43", "remaining_time": "8:23:14"}
|
| 1987 |
+
{"current_steps": 6335, "total_steps": 7494, "loss": 0.3761, "lr": 2.849620250223215e-06, "epoch": 0.8453570415839602, "percentage": 84.53, "elapsed_time": "1 day, 21:38:50", "remaining_time": "8:21:04"}
|
| 1988 |
+
{"current_steps": 6340, "total_steps": 7494, "loss": 0.3786, "lr": 2.825701792523996e-06, "epoch": 0.8460242531400644, "percentage": 84.6, "elapsed_time": "1 day, 21:40:58", "remaining_time": "8:18:54"}
|
| 1989 |
+
{"current_steps": 6345, "total_steps": 7494, "loss": 0.3822, "lr": 2.801876506399144e-06, "epoch": 0.8466914646961685, "percentage": 84.67, "elapsed_time": "1 day, 21:43:05", "remaining_time": "8:16:44"}
|
| 1990 |
+
{"current_steps": 6350, "total_steps": 7494, "loss": 0.381, "lr": 2.778144521102226e-06, "epoch": 0.8473586762522727, "percentage": 84.73, "elapsed_time": "1 day, 21:45:14", "remaining_time": "8:14:34"}
|
| 1991 |
+
{"current_steps": 6355, "total_steps": 7494, "loss": 0.3759, "lr": 2.754505965380654e-06, "epoch": 0.8480258878083768, "percentage": 84.8, "elapsed_time": "1 day, 21:47:24", "remaining_time": "8:12:24"}
|
| 1992 |
+
{"current_steps": 6360, "total_steps": 7494, "loss": 0.3775, "lr": 2.730960967474987e-06, "epoch": 0.848693099364481, "percentage": 84.87, "elapsed_time": "1 day, 21:49:31", "remaining_time": "8:10:14"}
|
| 1993 |
+
{"current_steps": 6365, "total_steps": 7494, "loss": 0.377, "lr": 2.7075096551182055e-06, "epoch": 0.8493603109205852, "percentage": 84.93, "elapsed_time": "1 day, 21:51:38", "remaining_time": "8:08:04"}
|
| 1994 |
+
{"current_steps": 6370, "total_steps": 7494, "loss": 0.3802, "lr": 2.6841521555350625e-06, "epoch": 0.8500275224766893, "percentage": 85.0, "elapsed_time": "1 day, 21:53:46", "remaining_time": "8:05:54"}
|
| 1995 |
+
{"current_steps": 6375, "total_steps": 7494, "loss": 0.384, "lr": 2.6608885954413643e-06, "epoch": 0.8506947340327935, "percentage": 85.07, "elapsed_time": "1 day, 21:55:53", "remaining_time": "8:03:44"}
|
| 1996 |
+
{"current_steps": 6380, "total_steps": 7494, "loss": 0.3848, "lr": 2.637719101043277e-06, "epoch": 0.8513619455888976, "percentage": 85.13, "elapsed_time": "1 day, 21:58:02", "remaining_time": "8:01:34"}
|
| 1997 |
+
{"current_steps": 6385, "total_steps": 7494, "loss": 0.3808, "lr": 2.614643798036678e-06, "epoch": 0.8520291571450017, "percentage": 85.2, "elapsed_time": "1 day, 22:00:08", "remaining_time": "7:59:24"}
|
| 1998 |
+
{"current_steps": 6390, "total_steps": 7494, "loss": 0.3813, "lr": 2.591662811606428e-06, "epoch": 0.8526963687011059, "percentage": 85.27, "elapsed_time": "1 day, 22:02:16", "remaining_time": "7:57:14"}
|
| 1999 |
+
{"current_steps": 6395, "total_steps": 7494, "loss": 0.3838, "lr": 2.5687762664257297e-06, "epoch": 0.85336358025721, "percentage": 85.33, "elapsed_time": "1 day, 22:04:23", "remaining_time": "7:55:04"}
|
| 2000 |
+
{"current_steps": 6400, "total_steps": 7494, "loss": 0.3782, "lr": 2.5459842866554364e-06, "epoch": 0.8540307918133142, "percentage": 85.4, "elapsed_time": "1 day, 22:06:30", "remaining_time": "7:52:53"}
|
| 2001 |
+
{"current_steps": 6405, "total_steps": 7494, "loss": 0.379, "lr": 2.523286995943366e-06, "epoch": 0.8546980033694184, "percentage": 85.47, "elapsed_time": "1 day, 22:09:37", "remaining_time": "7:50:54"}
|
| 2002 |
+
{"current_steps": 6410, "total_steps": 7494, "loss": 0.3781, "lr": 2.500684517423657e-06, "epoch": 0.8553652149255225, "percentage": 85.54, "elapsed_time": "1 day, 22:11:45", "remaining_time": "7:48:43"}
|