Training in progress, step 101000
Browse files- model.safetensors +1 -1
- trainer_log.jsonl +50 -0
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3554214752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69700b6b65f86fd92f33c3f57a5ffffef3ede26e6b13a95341d49372c9c4100a
|
3 |
size 3554214752
|
trainer_log.jsonl
CHANGED
@@ -10065,3 +10065,53 @@
|
|
10065 |
{"current_steps": 100640, "total_steps": 236854, "loss": 0.0071, "lr": 7.114649481195665e-06, "epoch": 0.8498026218572544, "percentage": 42.49, "elapsed_time": "19:37:48", "remaining_time": "1 day, 2:34:08"}
|
10066 |
{"current_steps": 100650, "total_steps": 236854, "loss": 0.0057, "lr": 7.113981723593828e-06, "epoch": 0.8498870617044183, "percentage": 42.49, "elapsed_time": "19:37:56", "remaining_time": "1 day, 2:34:02"}
|
10067 |
{"current_steps": 100660, "total_steps": 236854, "loss": 0.0127, "lr": 7.113313920076742e-06, "epoch": 0.8499715015515822, "percentage": 42.5, "elapsed_time": "19:38:03", "remaining_time": "1 day, 2:33:55"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10065 |
{"current_steps": 100640, "total_steps": 236854, "loss": 0.0071, "lr": 7.114649481195665e-06, "epoch": 0.8498026218572544, "percentage": 42.49, "elapsed_time": "19:37:48", "remaining_time": "1 day, 2:34:08"}
|
10066 |
{"current_steps": 100650, "total_steps": 236854, "loss": 0.0057, "lr": 7.113981723593828e-06, "epoch": 0.8498870617044183, "percentage": 42.49, "elapsed_time": "19:37:56", "remaining_time": "1 day, 2:34:02"}
|
10067 |
{"current_steps": 100660, "total_steps": 236854, "loss": 0.0127, "lr": 7.113313920076742e-06, "epoch": 0.8499715015515822, "percentage": 42.5, "elapsed_time": "19:38:03", "remaining_time": "1 day, 2:33:55"}
|
10068 |
+
{"current_steps": 100670, "total_steps": 236854, "loss": 0.0107, "lr": 7.11264607065891e-06, "epoch": 0.8500559413987461, "percentage": 42.5, "elapsed_time": "19:38:10", "remaining_time": "1 day, 2:33:48"}
|
10069 |
+
{"current_steps": 100680, "total_steps": 236854, "loss": 0.0056, "lr": 7.111978175354839e-06, "epoch": 0.85014038124591, "percentage": 42.51, "elapsed_time": "19:38:16", "remaining_time": "1 day, 2:33:39"}
|
10070 |
+
{"current_steps": 100690, "total_steps": 236854, "loss": 0.0115, "lr": 7.1113102341790345e-06, "epoch": 0.8502248210930738, "percentage": 42.51, "elapsed_time": "19:38:23", "remaining_time": "1 day, 2:33:32"}
|
10071 |
+
{"current_steps": 100700, "total_steps": 236854, "loss": 0.0095, "lr": 7.110642247146004e-06, "epoch": 0.8503092609402377, "percentage": 42.52, "elapsed_time": "19:38:29", "remaining_time": "1 day, 2:33:25"}
|
10072 |
+
{"current_steps": 100710, "total_steps": 236854, "loss": 0.0065, "lr": 7.1099742142702556e-06, "epoch": 0.8503937007874016, "percentage": 42.52, "elapsed_time": "19:38:36", "remaining_time": "1 day, 2:33:17"}
|
10073 |
+
{"current_steps": 100720, "total_steps": 236854, "loss": 0.0079, "lr": 7.109306135566301e-06, "epoch": 0.8504781406345655, "percentage": 42.52, "elapsed_time": "19:38:42", "remaining_time": "1 day, 2:33:09"}
|
10074 |
+
{"current_steps": 100730, "total_steps": 236854, "loss": 0.0084, "lr": 7.108638011048648e-06, "epoch": 0.8505625804817293, "percentage": 42.53, "elapsed_time": "19:38:50", "remaining_time": "1 day, 2:33:03"}
|
10075 |
+
{"current_steps": 100740, "total_steps": 236854, "loss": 0.0075, "lr": 7.10796984073181e-06, "epoch": 0.8506470203288932, "percentage": 42.53, "elapsed_time": "19:38:57", "remaining_time": "1 day, 2:32:56"}
|
10076 |
+
{"current_steps": 100750, "total_steps": 236854, "loss": 0.0063, "lr": 7.107301624630301e-06, "epoch": 0.850731460176057, "percentage": 42.54, "elapsed_time": "19:39:04", "remaining_time": "1 day, 2:32:49"}
|
10077 |
+
{"current_steps": 100760, "total_steps": 236854, "loss": 0.0092, "lr": 7.10663336275863e-06, "epoch": 0.8508159000232209, "percentage": 42.54, "elapsed_time": "19:39:11", "remaining_time": "1 day, 2:32:42"}
|
10078 |
+
{"current_steps": 100770, "total_steps": 236854, "loss": 0.0089, "lr": 7.105965055131314e-06, "epoch": 0.8509003398703848, "percentage": 42.55, "elapsed_time": "19:39:17", "remaining_time": "1 day, 2:32:33"}
|
10079 |
+
{"current_steps": 100780, "total_steps": 236854, "loss": 0.0086, "lr": 7.10529670176287e-06, "epoch": 0.8509847797175487, "percentage": 42.55, "elapsed_time": "19:39:23", "remaining_time": "1 day, 2:32:24"}
|
10080 |
+
{"current_steps": 100790, "total_steps": 236854, "loss": 0.0067, "lr": 7.104628302667813e-06, "epoch": 0.8510692195647126, "percentage": 42.55, "elapsed_time": "19:39:29", "remaining_time": "1 day, 2:32:17"}
|
10081 |
+
{"current_steps": 100800, "total_steps": 236854, "loss": 0.0074, "lr": 7.1039598578606605e-06, "epoch": 0.8511536594118765, "percentage": 42.56, "elapsed_time": "19:39:35", "remaining_time": "1 day, 2:32:08"}
|
10082 |
+
{"current_steps": 100810, "total_steps": 236854, "loss": 0.006, "lr": 7.103291367355931e-06, "epoch": 0.8512380992590404, "percentage": 42.56, "elapsed_time": "19:39:41", "remaining_time": "1 day, 2:31:59"}
|
10083 |
+
{"current_steps": 100820, "total_steps": 236854, "loss": 0.0095, "lr": 7.102622831168142e-06, "epoch": 0.8513225391062043, "percentage": 42.57, "elapsed_time": "19:39:48", "remaining_time": "1 day, 2:31:53"}
|
10084 |
+
{"current_steps": 100830, "total_steps": 236854, "loss": 0.006, "lr": 7.101954249311818e-06, "epoch": 0.8514069789533681, "percentage": 42.57, "elapsed_time": "19:39:54", "remaining_time": "1 day, 2:31:45"}
|
10085 |
+
{"current_steps": 100840, "total_steps": 236854, "loss": 0.0054, "lr": 7.101285621801479e-06, "epoch": 0.8514914188005319, "percentage": 42.57, "elapsed_time": "19:40:01", "remaining_time": "1 day, 2:31:37"}
|
10086 |
+
{"current_steps": 100850, "total_steps": 236854, "loss": 0.0101, "lr": 7.100616948651645e-06, "epoch": 0.8515758586476958, "percentage": 42.58, "elapsed_time": "19:40:07", "remaining_time": "1 day, 2:31:29"}
|
10087 |
+
{"current_steps": 100860, "total_steps": 236854, "loss": 0.0054, "lr": 7.099948229876843e-06, "epoch": 0.8516602984948597, "percentage": 42.58, "elapsed_time": "19:40:14", "remaining_time": "1 day, 2:31:22"}
|
10088 |
+
{"current_steps": 100870, "total_steps": 236854, "loss": 0.0108, "lr": 7.0992794654915945e-06, "epoch": 0.8517447383420236, "percentage": 42.59, "elapsed_time": "19:40:21", "remaining_time": "1 day, 2:31:14"}
|
10089 |
+
{"current_steps": 100880, "total_steps": 236854, "loss": 0.0073, "lr": 7.0986106555104275e-06, "epoch": 0.8518291781891875, "percentage": 42.59, "elapsed_time": "19:40:26", "remaining_time": "1 day, 2:31:06"}
|
10090 |
+
{"current_steps": 100890, "total_steps": 236854, "loss": 0.0133, "lr": 7.097941799947865e-06, "epoch": 0.8519136180363513, "percentage": 42.6, "elapsed_time": "19:40:34", "remaining_time": "1 day, 2:31:00"}
|
10091 |
+
{"current_steps": 100900, "total_steps": 236854, "loss": 0.007, "lr": 7.097272898818439e-06, "epoch": 0.8519980578835152, "percentage": 42.6, "elapsed_time": "19:40:40", "remaining_time": "1 day, 2:30:51"}
|
10092 |
+
{"current_steps": 100910, "total_steps": 236854, "loss": 0.0055, "lr": 7.096603952136674e-06, "epoch": 0.8520824977306791, "percentage": 42.6, "elapsed_time": "19:40:46", "remaining_time": "1 day, 2:30:43"}
|
10093 |
+
{"current_steps": 100920, "total_steps": 236854, "loss": 0.0056, "lr": 7.095934959917102e-06, "epoch": 0.852166937577843, "percentage": 42.61, "elapsed_time": "19:40:52", "remaining_time": "1 day, 2:30:35"}
|
10094 |
+
{"current_steps": 100930, "total_steps": 236854, "loss": 0.0055, "lr": 7.09526592217425e-06, "epoch": 0.8522513774250069, "percentage": 42.61, "elapsed_time": "19:40:59", "remaining_time": "1 day, 2:30:27"}
|
10095 |
+
{"current_steps": 100940, "total_steps": 236854, "loss": 0.0104, "lr": 7.094596838922654e-06, "epoch": 0.8523358172721708, "percentage": 42.62, "elapsed_time": "19:41:05", "remaining_time": "1 day, 2:30:19"}
|
10096 |
+
{"current_steps": 100950, "total_steps": 236854, "loss": 0.0176, "lr": 7.093927710176841e-06, "epoch": 0.8524202571193347, "percentage": 42.62, "elapsed_time": "19:41:11", "remaining_time": "1 day, 2:30:11"}
|
10097 |
+
{"current_steps": 100960, "total_steps": 236854, "loss": 0.0102, "lr": 7.0932585359513505e-06, "epoch": 0.8525046969664984, "percentage": 42.63, "elapsed_time": "19:41:19", "remaining_time": "1 day, 2:30:04"}
|
10098 |
+
{"current_steps": 100970, "total_steps": 236854, "loss": 0.0098, "lr": 7.092589316260712e-06, "epoch": 0.8525891368136623, "percentage": 42.63, "elapsed_time": "19:41:25", "remaining_time": "1 day, 2:29:57"}
|
10099 |
+
{"current_steps": 100980, "total_steps": 236854, "loss": 0.0071, "lr": 7.091920051119461e-06, "epoch": 0.8526735766608262, "percentage": 42.63, "elapsed_time": "19:41:32", "remaining_time": "1 day, 2:29:49"}
|
10100 |
+
{"current_steps": 100990, "total_steps": 236854, "loss": 0.0055, "lr": 7.091250740542136e-06, "epoch": 0.8527580165079901, "percentage": 42.64, "elapsed_time": "19:41:38", "remaining_time": "1 day, 2:29:41"}
|
10101 |
+
{"current_steps": 101000, "total_steps": 236854, "loss": 0.0068, "lr": 7.090581384543275e-06, "epoch": 0.852842456355154, "percentage": 42.64, "elapsed_time": "19:41:45", "remaining_time": "1 day, 2:29:34"}
|
10102 |
+
{"current_steps": 101010, "total_steps": 236854, "loss": 0.0066, "lr": 7.089911983137413e-06, "epoch": 0.8529268962023179, "percentage": 42.65, "elapsed_time": "19:42:14", "remaining_time": "1 day, 2:29:56"}
|
10103 |
+
{"current_steps": 101020, "total_steps": 236854, "loss": 0.0065, "lr": 7.089242536339093e-06, "epoch": 0.8530113360494818, "percentage": 42.65, "elapsed_time": "19:42:21", "remaining_time": "1 day, 2:29:49"}
|
10104 |
+
{"current_steps": 101030, "total_steps": 236854, "loss": 0.0096, "lr": 7.088573044162851e-06, "epoch": 0.8530957758966456, "percentage": 42.65, "elapsed_time": "19:42:29", "remaining_time": "1 day, 2:29:44"}
|
10105 |
+
{"current_steps": 101040, "total_steps": 236854, "loss": 0.0112, "lr": 7.087903506623232e-06, "epoch": 0.8531802157438095, "percentage": 42.66, "elapsed_time": "19:42:36", "remaining_time": "1 day, 2:29:36"}
|
10106 |
+
{"current_steps": 101050, "total_steps": 236854, "loss": 0.0068, "lr": 7.087233923734776e-06, "epoch": 0.8532646555909734, "percentage": 42.66, "elapsed_time": "19:42:43", "remaining_time": "1 day, 2:29:29"}
|
10107 |
+
{"current_steps": 101060, "total_steps": 236854, "loss": 0.0098, "lr": 7.086564295512026e-06, "epoch": 0.8533490954381373, "percentage": 42.67, "elapsed_time": "19:42:50", "remaining_time": "1 day, 2:29:22"}
|
10108 |
+
{"current_steps": 101070, "total_steps": 236854, "loss": 0.0122, "lr": 7.0858946219695275e-06, "epoch": 0.8534335352853011, "percentage": 42.67, "elapsed_time": "19:42:56", "remaining_time": "1 day, 2:29:15"}
|
10109 |
+
{"current_steps": 101080, "total_steps": 236854, "loss": 0.0149, "lr": 7.085224903121827e-06, "epoch": 0.853517975132465, "percentage": 42.68, "elapsed_time": "19:43:04", "remaining_time": "1 day, 2:29:08"}
|
10110 |
+
{"current_steps": 101090, "total_steps": 236854, "loss": 0.0071, "lr": 7.084555138983467e-06, "epoch": 0.8536024149796289, "percentage": 42.68, "elapsed_time": "19:43:11", "remaining_time": "1 day, 2:29:01"}
|
10111 |
+
{"current_steps": 101100, "total_steps": 236854, "loss": 0.0096, "lr": 7.083885329568997e-06, "epoch": 0.8536868548267927, "percentage": 42.68, "elapsed_time": "19:43:19", "remaining_time": "1 day, 2:28:55"}
|
10112 |
+
{"current_steps": 101110, "total_steps": 236854, "loss": 0.0112, "lr": 7.0832154748929635e-06, "epoch": 0.8537712946739566, "percentage": 42.69, "elapsed_time": "19:43:25", "remaining_time": "1 day, 2:28:48"}
|
10113 |
+
{"current_steps": 101120, "total_steps": 236854, "loss": 0.009, "lr": 7.08254557496992e-06, "epoch": 0.8538557345211205, "percentage": 42.69, "elapsed_time": "19:43:33", "remaining_time": "1 day, 2:28:42"}
|
10114 |
+
{"current_steps": 101130, "total_steps": 236854, "loss": 0.0071, "lr": 7.081875629814412e-06, "epoch": 0.8539401743682844, "percentage": 42.7, "elapsed_time": "19:43:40", "remaining_time": "1 day, 2:28:35"}
|
10115 |
+
{"current_steps": 101140, "total_steps": 236854, "loss": 0.02, "lr": 7.0812056394409915e-06, "epoch": 0.8540246142154483, "percentage": 42.7, "elapsed_time": "19:43:47", "remaining_time": "1 day, 2:28:27"}
|
10116 |
+
{"current_steps": 101150, "total_steps": 236854, "loss": 0.0108, "lr": 7.080535603864211e-06, "epoch": 0.8541090540626122, "percentage": 42.71, "elapsed_time": "19:43:53", "remaining_time": "1 day, 2:28:19"}
|
10117 |
+
{"current_steps": 101160, "total_steps": 236854, "loss": 0.0137, "lr": 7.079865523098623e-06, "epoch": 0.8541934939097761, "percentage": 42.71, "elapsed_time": "19:44:00", "remaining_time": "1 day, 2:28:12"}
|