Training in progress, step 15000, checkpoint
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +353 -3
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 304481530
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1a26dcf49a9adec930252211cc2ebdb39eacfeed22076666661d9caed214679
|
| 3 |
size 304481530
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 402029570
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c979f073b59bd49cc8c35d18515eb7ddd7a81fbd717bb34c90967a1f381c67c5
|
| 3 |
size 402029570
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ba6101cd4bf8f7ce3d46d2382a668adc549af4a1a22b84d941c0306451bad54
|
| 3 |
size 14960
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c787066085cf3612c776a9db920df8b50e21936babcea06d25d76b00b6f6481
|
| 3 |
size 14960
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d923993877b77c02936b0de7d9cac94e6fa202dfaca7291842d5e19deb2cdb37
|
| 3 |
size 14960
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b72344aa5e79ea1dbe308108cb74bb1087ed0d7f8ad9e397ccfa76e1dcdde76c
|
| 3 |
size 14960
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51acafd4471f7843be9ffc9528db012939ee248bf40f7127aa783c5f97813694
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -4908,6 +4908,356 @@
|
|
| 4908 |
"learning_rate": 0.0004956114542377312,
|
| 4909 |
"loss": 20.9266,
|
| 4910 |
"step": 14000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4911 |
}
|
| 4912 |
],
|
| 4913 |
"logging_steps": 20,
|
|
@@ -4927,7 +5277,7 @@
|
|
| 4927 |
"attributes": {}
|
| 4928 |
}
|
| 4929 |
},
|
| 4930 |
-
"total_flos": 1.
|
| 4931 |
"train_batch_size": 48,
|
| 4932 |
"trial_name": null,
|
| 4933 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.029249601474179914,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 15000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4908 |
"learning_rate": 0.0004956114542377312,
|
| 4909 |
"loss": 20.9266,
|
| 4910 |
"step": 14000
|
| 4911 |
+
},
|
| 4912 |
+
{
|
| 4913 |
+
"epoch": 0.02733862751120016,
|
| 4914 |
+
"grad_norm": 12.875,
|
| 4915 |
+
"learning_rate": 0.0004956049522068218,
|
| 4916 |
+
"loss": 20.9607,
|
| 4917 |
+
"step": 14020
|
| 4918 |
+
},
|
| 4919 |
+
{
|
| 4920 |
+
"epoch": 0.0273776269798324,
|
| 4921 |
+
"grad_norm": 12.0625,
|
| 4922 |
+
"learning_rate": 0.0004955984501759125,
|
| 4923 |
+
"loss": 21.0236,
|
| 4924 |
+
"step": 14040
|
| 4925 |
+
},
|
| 4926 |
+
{
|
| 4927 |
+
"epoch": 0.02741662644846464,
|
| 4928 |
+
"grad_norm": 11.75,
|
| 4929 |
+
"learning_rate": 0.000495591948145003,
|
| 4930 |
+
"loss": 20.9549,
|
| 4931 |
+
"step": 14060
|
| 4932 |
+
},
|
| 4933 |
+
{
|
| 4934 |
+
"epoch": 0.02745562591709688,
|
| 4935 |
+
"grad_norm": 11.625,
|
| 4936 |
+
"learning_rate": 0.0004955854461140937,
|
| 4937 |
+
"loss": 20.9407,
|
| 4938 |
+
"step": 14080
|
| 4939 |
+
},
|
| 4940 |
+
{
|
| 4941 |
+
"epoch": 0.02749462538572912,
|
| 4942 |
+
"grad_norm": 11.6875,
|
| 4943 |
+
"learning_rate": 0.0004955789440831843,
|
| 4944 |
+
"loss": 20.9356,
|
| 4945 |
+
"step": 14100
|
| 4946 |
+
},
|
| 4947 |
+
{
|
| 4948 |
+
"epoch": 0.02753362485436136,
|
| 4949 |
+
"grad_norm": 12.1875,
|
| 4950 |
+
"learning_rate": 0.000495572442052275,
|
| 4951 |
+
"loss": 20.8993,
|
| 4952 |
+
"step": 14120
|
| 4953 |
+
},
|
| 4954 |
+
{
|
| 4955 |
+
"epoch": 0.027572624322993598,
|
| 4956 |
+
"grad_norm": 12.0,
|
| 4957 |
+
"learning_rate": 0.0004955659400213657,
|
| 4958 |
+
"loss": 20.789,
|
| 4959 |
+
"step": 14140
|
| 4960 |
+
},
|
| 4961 |
+
{
|
| 4962 |
+
"epoch": 0.02761162379162584,
|
| 4963 |
+
"grad_norm": 12.125,
|
| 4964 |
+
"learning_rate": 0.0004955594379904563,
|
| 4965 |
+
"loss": 20.8079,
|
| 4966 |
+
"step": 14160
|
| 4967 |
+
},
|
| 4968 |
+
{
|
| 4969 |
+
"epoch": 0.027650623260258078,
|
| 4970 |
+
"grad_norm": 12.0,
|
| 4971 |
+
"learning_rate": 0.000495552935959547,
|
| 4972 |
+
"loss": 20.9396,
|
| 4973 |
+
"step": 14180
|
| 4974 |
+
},
|
| 4975 |
+
{
|
| 4976 |
+
"epoch": 0.02768962272889032,
|
| 4977 |
+
"grad_norm": 11.8125,
|
| 4978 |
+
"learning_rate": 0.0004955464339286376,
|
| 4979 |
+
"loss": 20.8879,
|
| 4980 |
+
"step": 14200
|
| 4981 |
+
},
|
| 4982 |
+
{
|
| 4983 |
+
"epoch": 0.02772862219752256,
|
| 4984 |
+
"grad_norm": 11.8125,
|
| 4985 |
+
"learning_rate": 0.0004955399318977283,
|
| 4986 |
+
"loss": 20.8179,
|
| 4987 |
+
"step": 14220
|
| 4988 |
+
},
|
| 4989 |
+
{
|
| 4990 |
+
"epoch": 0.027767621666154797,
|
| 4991 |
+
"grad_norm": 13.1875,
|
| 4992 |
+
"learning_rate": 0.0004955334298668189,
|
| 4993 |
+
"loss": 20.9109,
|
| 4994 |
+
"step": 14240
|
| 4995 |
+
},
|
| 4996 |
+
{
|
| 4997 |
+
"epoch": 0.02780662113478704,
|
| 4998 |
+
"grad_norm": 11.75,
|
| 4999 |
+
"learning_rate": 0.0004955269278359096,
|
| 5000 |
+
"loss": 20.7993,
|
| 5001 |
+
"step": 14260
|
| 5002 |
+
},
|
| 5003 |
+
{
|
| 5004 |
+
"epoch": 0.027845620603419278,
|
| 5005 |
+
"grad_norm": 12.375,
|
| 5006 |
+
"learning_rate": 0.0004955204258050001,
|
| 5007 |
+
"loss": 20.9209,
|
| 5008 |
+
"step": 14280
|
| 5009 |
+
},
|
| 5010 |
+
{
|
| 5011 |
+
"epoch": 0.02788462007205152,
|
| 5012 |
+
"grad_norm": 11.25,
|
| 5013 |
+
"learning_rate": 0.0004955139237740908,
|
| 5014 |
+
"loss": 20.8294,
|
| 5015 |
+
"step": 14300
|
| 5016 |
+
},
|
| 5017 |
+
{
|
| 5018 |
+
"epoch": 0.02792361954068376,
|
| 5019 |
+
"grad_norm": 15.6875,
|
| 5020 |
+
"learning_rate": 0.0004955074217431815,
|
| 5021 |
+
"loss": 20.7905,
|
| 5022 |
+
"step": 14320
|
| 5023 |
+
},
|
| 5024 |
+
{
|
| 5025 |
+
"epoch": 0.027962619009315997,
|
| 5026 |
+
"grad_norm": 12.25,
|
| 5027 |
+
"learning_rate": 0.0004955009197122721,
|
| 5028 |
+
"loss": 20.7146,
|
| 5029 |
+
"step": 14340
|
| 5030 |
+
},
|
| 5031 |
+
{
|
| 5032 |
+
"epoch": 0.02800161847794824,
|
| 5033 |
+
"grad_norm": 12.0625,
|
| 5034 |
+
"learning_rate": 0.0004954944176813628,
|
| 5035 |
+
"loss": 20.7778,
|
| 5036 |
+
"step": 14360
|
| 5037 |
+
},
|
| 5038 |
+
{
|
| 5039 |
+
"epoch": 0.028040617946580478,
|
| 5040 |
+
"grad_norm": 12.6875,
|
| 5041 |
+
"learning_rate": 0.0004954879156504534,
|
| 5042 |
+
"loss": 20.8435,
|
| 5043 |
+
"step": 14380
|
| 5044 |
+
},
|
| 5045 |
+
{
|
| 5046 |
+
"epoch": 0.028079617415212716,
|
| 5047 |
+
"grad_norm": 10.8125,
|
| 5048 |
+
"learning_rate": 0.0004954814136195441,
|
| 5049 |
+
"loss": 20.8421,
|
| 5050 |
+
"step": 14400
|
| 5051 |
+
},
|
| 5052 |
+
{
|
| 5053 |
+
"epoch": 0.028118616883844958,
|
| 5054 |
+
"grad_norm": 11.4375,
|
| 5055 |
+
"learning_rate": 0.0004954749115886347,
|
| 5056 |
+
"loss": 20.8006,
|
| 5057 |
+
"step": 14420
|
| 5058 |
+
},
|
| 5059 |
+
{
|
| 5060 |
+
"epoch": 0.028157616352477197,
|
| 5061 |
+
"grad_norm": 11.3125,
|
| 5062 |
+
"learning_rate": 0.0004954684095577254,
|
| 5063 |
+
"loss": 20.8072,
|
| 5064 |
+
"step": 14440
|
| 5065 |
+
},
|
| 5066 |
+
{
|
| 5067 |
+
"epoch": 0.02819661582110944,
|
| 5068 |
+
"grad_norm": 11.5,
|
| 5069 |
+
"learning_rate": 0.0004954619075268161,
|
| 5070 |
+
"loss": 20.769,
|
| 5071 |
+
"step": 14460
|
| 5072 |
+
},
|
| 5073 |
+
{
|
| 5074 |
+
"epoch": 0.028235615289741677,
|
| 5075 |
+
"grad_norm": 11.4375,
|
| 5076 |
+
"learning_rate": 0.0004954554054959067,
|
| 5077 |
+
"loss": 20.8338,
|
| 5078 |
+
"step": 14480
|
| 5079 |
+
},
|
| 5080 |
+
{
|
| 5081 |
+
"epoch": 0.028274614758373916,
|
| 5082 |
+
"grad_norm": 10.375,
|
| 5083 |
+
"learning_rate": 0.0004954489034649974,
|
| 5084 |
+
"loss": 20.8088,
|
| 5085 |
+
"step": 14500
|
| 5086 |
+
},
|
| 5087 |
+
{
|
| 5088 |
+
"epoch": 0.028313614227006158,
|
| 5089 |
+
"grad_norm": 11.25,
|
| 5090 |
+
"learning_rate": 0.000495442401434088,
|
| 5091 |
+
"loss": 20.7043,
|
| 5092 |
+
"step": 14520
|
| 5093 |
+
},
|
| 5094 |
+
{
|
| 5095 |
+
"epoch": 0.028352613695638396,
|
| 5096 |
+
"grad_norm": 12.0625,
|
| 5097 |
+
"learning_rate": 0.0004954358994031786,
|
| 5098 |
+
"loss": 20.722,
|
| 5099 |
+
"step": 14540
|
| 5100 |
+
},
|
| 5101 |
+
{
|
| 5102 |
+
"epoch": 0.02839161316427064,
|
| 5103 |
+
"grad_norm": 12.125,
|
| 5104 |
+
"learning_rate": 0.0004954293973722692,
|
| 5105 |
+
"loss": 20.8949,
|
| 5106 |
+
"step": 14560
|
| 5107 |
+
},
|
| 5108 |
+
{
|
| 5109 |
+
"epoch": 0.028430612632902877,
|
| 5110 |
+
"grad_norm": 13.1875,
|
| 5111 |
+
"learning_rate": 0.0004954228953413599,
|
| 5112 |
+
"loss": 20.771,
|
| 5113 |
+
"step": 14580
|
| 5114 |
+
},
|
| 5115 |
+
{
|
| 5116 |
+
"epoch": 0.028469612101535115,
|
| 5117 |
+
"grad_norm": 13.625,
|
| 5118 |
+
"learning_rate": 0.0004954163933104505,
|
| 5119 |
+
"loss": 20.7833,
|
| 5120 |
+
"step": 14600
|
| 5121 |
+
},
|
| 5122 |
+
{
|
| 5123 |
+
"epoch": 0.028508611570167357,
|
| 5124 |
+
"grad_norm": 11.125,
|
| 5125 |
+
"learning_rate": 0.0004954098912795412,
|
| 5126 |
+
"loss": 20.7086,
|
| 5127 |
+
"step": 14620
|
| 5128 |
+
},
|
| 5129 |
+
{
|
| 5130 |
+
"epoch": 0.028547611038799596,
|
| 5131 |
+
"grad_norm": 11.6875,
|
| 5132 |
+
"learning_rate": 0.0004954033892486319,
|
| 5133 |
+
"loss": 20.7229,
|
| 5134 |
+
"step": 14640
|
| 5135 |
+
},
|
| 5136 |
+
{
|
| 5137 |
+
"epoch": 0.028586610507431835,
|
| 5138 |
+
"grad_norm": 12.3125,
|
| 5139 |
+
"learning_rate": 0.0004953968872177225,
|
| 5140 |
+
"loss": 20.735,
|
| 5141 |
+
"step": 14660
|
| 5142 |
+
},
|
| 5143 |
+
{
|
| 5144 |
+
"epoch": 0.028625609976064077,
|
| 5145 |
+
"grad_norm": 12.4375,
|
| 5146 |
+
"learning_rate": 0.0004953903851868131,
|
| 5147 |
+
"loss": 20.6955,
|
| 5148 |
+
"step": 14680
|
| 5149 |
+
},
|
| 5150 |
+
{
|
| 5151 |
+
"epoch": 0.028664609444696315,
|
| 5152 |
+
"grad_norm": 10.375,
|
| 5153 |
+
"learning_rate": 0.0004953838831559037,
|
| 5154 |
+
"loss": 20.8495,
|
| 5155 |
+
"step": 14700
|
| 5156 |
+
},
|
| 5157 |
+
{
|
| 5158 |
+
"epoch": 0.028703608913328557,
|
| 5159 |
+
"grad_norm": 11.625,
|
| 5160 |
+
"learning_rate": 0.0004953773811249944,
|
| 5161 |
+
"loss": 20.7476,
|
| 5162 |
+
"step": 14720
|
| 5163 |
+
},
|
| 5164 |
+
{
|
| 5165 |
+
"epoch": 0.028742608381960796,
|
| 5166 |
+
"grad_norm": 12.125,
|
| 5167 |
+
"learning_rate": 0.000495370879094085,
|
| 5168 |
+
"loss": 20.7175,
|
| 5169 |
+
"step": 14740
|
| 5170 |
+
},
|
| 5171 |
+
{
|
| 5172 |
+
"epoch": 0.028781607850593034,
|
| 5173 |
+
"grad_norm": 11.125,
|
| 5174 |
+
"learning_rate": 0.0004953643770631757,
|
| 5175 |
+
"loss": 20.696,
|
| 5176 |
+
"step": 14760
|
| 5177 |
+
},
|
| 5178 |
+
{
|
| 5179 |
+
"epoch": 0.028820607319225276,
|
| 5180 |
+
"grad_norm": 10.875,
|
| 5181 |
+
"learning_rate": 0.0004953578750322664,
|
| 5182 |
+
"loss": 20.8024,
|
| 5183 |
+
"step": 14780
|
| 5184 |
+
},
|
| 5185 |
+
{
|
| 5186 |
+
"epoch": 0.028859606787857515,
|
| 5187 |
+
"grad_norm": 10.0625,
|
| 5188 |
+
"learning_rate": 0.000495351373001357,
|
| 5189 |
+
"loss": 20.6606,
|
| 5190 |
+
"step": 14800
|
| 5191 |
+
},
|
| 5192 |
+
{
|
| 5193 |
+
"epoch": 0.028898606256489757,
|
| 5194 |
+
"grad_norm": 11.0625,
|
| 5195 |
+
"learning_rate": 0.0004953448709704477,
|
| 5196 |
+
"loss": 20.681,
|
| 5197 |
+
"step": 14820
|
| 5198 |
+
},
|
| 5199 |
+
{
|
| 5200 |
+
"epoch": 0.028937605725121995,
|
| 5201 |
+
"grad_norm": 11.5,
|
| 5202 |
+
"learning_rate": 0.0004953383689395382,
|
| 5203 |
+
"loss": 20.7311,
|
| 5204 |
+
"step": 14840
|
| 5205 |
+
},
|
| 5206 |
+
{
|
| 5207 |
+
"epoch": 0.028976605193754234,
|
| 5208 |
+
"grad_norm": 11.6875,
|
| 5209 |
+
"learning_rate": 0.0004953318669086289,
|
| 5210 |
+
"loss": 20.6885,
|
| 5211 |
+
"step": 14860
|
| 5212 |
+
},
|
| 5213 |
+
{
|
| 5214 |
+
"epoch": 0.029015604662386476,
|
| 5215 |
+
"grad_norm": 12.0,
|
| 5216 |
+
"learning_rate": 0.0004953253648777195,
|
| 5217 |
+
"loss": 20.6885,
|
| 5218 |
+
"step": 14880
|
| 5219 |
+
},
|
| 5220 |
+
{
|
| 5221 |
+
"epoch": 0.029054604131018714,
|
| 5222 |
+
"grad_norm": 12.125,
|
| 5223 |
+
"learning_rate": 0.0004953188628468102,
|
| 5224 |
+
"loss": 20.7221,
|
| 5225 |
+
"step": 14900
|
| 5226 |
+
},
|
| 5227 |
+
{
|
| 5228 |
+
"epoch": 0.029093603599650953,
|
| 5229 |
+
"grad_norm": 12.6875,
|
| 5230 |
+
"learning_rate": 0.0004953123608159008,
|
| 5231 |
+
"loss": 20.7323,
|
| 5232 |
+
"step": 14920
|
| 5233 |
+
},
|
| 5234 |
+
{
|
| 5235 |
+
"epoch": 0.029132603068283195,
|
| 5236 |
+
"grad_norm": 10.625,
|
| 5237 |
+
"learning_rate": 0.0004953058587849915,
|
| 5238 |
+
"loss": 20.6526,
|
| 5239 |
+
"step": 14940
|
| 5240 |
+
},
|
| 5241 |
+
{
|
| 5242 |
+
"epoch": 0.029171602536915434,
|
| 5243 |
+
"grad_norm": 11.0625,
|
| 5244 |
+
"learning_rate": 0.0004952993567540822,
|
| 5245 |
+
"loss": 20.754,
|
| 5246 |
+
"step": 14960
|
| 5247 |
+
},
|
| 5248 |
+
{
|
| 5249 |
+
"epoch": 0.029210602005547676,
|
| 5250 |
+
"grad_norm": 16.875,
|
| 5251 |
+
"learning_rate": 0.0004952928547231728,
|
| 5252 |
+
"loss": 20.5829,
|
| 5253 |
+
"step": 14980
|
| 5254 |
+
},
|
| 5255 |
+
{
|
| 5256 |
+
"epoch": 0.029249601474179914,
|
| 5257 |
+
"grad_norm": 13.1875,
|
| 5258 |
+
"learning_rate": 0.0004952863526922635,
|
| 5259 |
+
"loss": 20.6348,
|
| 5260 |
+
"step": 15000
|
| 5261 |
}
|
| 5262 |
],
|
| 5263 |
"logging_steps": 20,
|
|
|
|
| 5277 |
"attributes": {}
|
| 5278 |
}
|
| 5279 |
},
|
| 5280 |
+
"total_flos": 1.102761022435256e+19,
|
| 5281 |
"train_batch_size": 48,
|
| 5282 |
"trial_name": null,
|
| 5283 |
"trial_params": null
|