Training in progress, step 6000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2384234968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a51051b34edc25e0d64c30ca7f33b83a0761c13d9072778abfd10448c19f3f5e
|
| 3 |
size 2384234968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4768663315
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f3b41dca90dac11ca9ea5d9671e951dd4dabbed860e4fb7230df978f7f0f912
|
| 3 |
size 4768663315
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf6efc206c57420111096224e0f9dccda6dffe818f96d885666ae79f4ad31671
|
| 3 |
size 1465
|
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": 1.
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -4958,6 +4958,456 @@
|
|
| 4958 |
"mean_token_accuracy": 0.7709882587194443,
|
| 4959 |
"num_tokens": 45049856.0,
|
| 4960 |
"step": 5500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4961 |
}
|
| 4962 |
],
|
| 4963 |
"logging_steps": 10,
|
|
@@ -4977,7 +5427,7 @@
|
|
| 4977 |
"attributes": {}
|
| 4978 |
}
|
| 4979 |
},
|
| 4980 |
-
"total_flos": 1.
|
| 4981 |
"train_batch_size": 2,
|
| 4982 |
"trial_name": null,
|
| 4983 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.8068669527896994,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 6000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4958 |
"mean_token_accuracy": 0.7709882587194443,
|
| 4959 |
"num_tokens": 45049856.0,
|
| 4960 |
"step": 5500
|
| 4961 |
+
},
|
| 4962 |
+
{
|
| 4963 |
+
"epoch": 1.6592877042391385,
|
| 4964 |
+
"grad_norm": 0.7701192498207092,
|
| 4965 |
+
"learning_rate": 4.967655587776044e-06,
|
| 4966 |
+
"loss": 0.1216,
|
| 4967 |
+
"mean_token_accuracy": 0.7994618371129036,
|
| 4968 |
+
"num_tokens": 45131776.0,
|
| 4969 |
+
"step": 5510
|
| 4970 |
+
},
|
| 4971 |
+
{
|
| 4972 |
+
"epoch": 1.6622995256381297,
|
| 4973 |
+
"grad_norm": 1.0482795238494873,
|
| 4974 |
+
"learning_rate": 4.956502342181575e-06,
|
| 4975 |
+
"loss": 0.1661,
|
| 4976 |
+
"mean_token_accuracy": 0.7507583145052195,
|
| 4977 |
+
"num_tokens": 45213696.0,
|
| 4978 |
+
"step": 5520
|
| 4979 |
+
},
|
| 4980 |
+
{
|
| 4981 |
+
"epoch": 1.6653113470371208,
|
| 4982 |
+
"grad_norm": 1.0718356370925903,
|
| 4983 |
+
"learning_rate": 4.9453490965871075e-06,
|
| 4984 |
+
"loss": 0.1351,
|
| 4985 |
+
"mean_token_accuracy": 0.8001345373690129,
|
| 4986 |
+
"num_tokens": 45295616.0,
|
| 4987 |
+
"step": 5530
|
| 4988 |
+
},
|
| 4989 |
+
{
|
| 4990 |
+
"epoch": 1.6683231684361117,
|
| 4991 |
+
"grad_norm": 0.9752377271652222,
|
| 4992 |
+
"learning_rate": 4.934195850992639e-06,
|
| 4993 |
+
"loss": 0.1215,
|
| 4994 |
+
"mean_token_accuracy": 0.7919031277298927,
|
| 4995 |
+
"num_tokens": 45377536.0,
|
| 4996 |
+
"step": 5540
|
| 4997 |
+
},
|
| 4998 |
+
{
|
| 4999 |
+
"epoch": 1.6713349898351026,
|
| 5000 |
+
"grad_norm": 1.1375031471252441,
|
| 5001 |
+
"learning_rate": 4.923042605398171e-06,
|
| 5002 |
+
"loss": 0.1395,
|
| 5003 |
+
"mean_token_accuracy": 0.7713551849126816,
|
| 5004 |
+
"num_tokens": 45459456.0,
|
| 5005 |
+
"step": 5550
|
| 5006 |
+
},
|
| 5007 |
+
{
|
| 5008 |
+
"epoch": 1.6743468112340938,
|
| 5009 |
+
"grad_norm": 1.122489094734192,
|
| 5010 |
+
"learning_rate": 4.911889359803703e-06,
|
| 5011 |
+
"loss": 0.1349,
|
| 5012 |
+
"mean_token_accuracy": 0.7769814103841781,
|
| 5013 |
+
"num_tokens": 45541376.0,
|
| 5014 |
+
"step": 5560
|
| 5015 |
+
},
|
| 5016 |
+
{
|
| 5017 |
+
"epoch": 1.677358632633085,
|
| 5018 |
+
"grad_norm": 1.0552014112472534,
|
| 5019 |
+
"learning_rate": 4.900736114209236e-06,
|
| 5020 |
+
"loss": 0.1194,
|
| 5021 |
+
"mean_token_accuracy": 0.7823997054249048,
|
| 5022 |
+
"num_tokens": 45623296.0,
|
| 5023 |
+
"step": 5570
|
| 5024 |
+
},
|
| 5025 |
+
{
|
| 5026 |
+
"epoch": 1.6803704540320759,
|
| 5027 |
+
"grad_norm": 1.4772262573242188,
|
| 5028 |
+
"learning_rate": 4.889582868614767e-06,
|
| 5029 |
+
"loss": 0.1432,
|
| 5030 |
+
"mean_token_accuracy": 0.7968811176717281,
|
| 5031 |
+
"num_tokens": 45705216.0,
|
| 5032 |
+
"step": 5580
|
| 5033 |
+
},
|
| 5034 |
+
{
|
| 5035 |
+
"epoch": 1.6833822754310668,
|
| 5036 |
+
"grad_norm": 1.0504951477050781,
|
| 5037 |
+
"learning_rate": 4.878429623020299e-06,
|
| 5038 |
+
"loss": 0.1534,
|
| 5039 |
+
"mean_token_accuracy": 0.7667196691036224,
|
| 5040 |
+
"num_tokens": 45787136.0,
|
| 5041 |
+
"step": 5590
|
| 5042 |
+
},
|
| 5043 |
+
{
|
| 5044 |
+
"epoch": 1.6863940968300581,
|
| 5045 |
+
"grad_norm": 1.0767134428024292,
|
| 5046 |
+
"learning_rate": 4.8672763774258316e-06,
|
| 5047 |
+
"loss": 0.1384,
|
| 5048 |
+
"mean_token_accuracy": 0.7868884541094303,
|
| 5049 |
+
"num_tokens": 45869056.0,
|
| 5050 |
+
"step": 5600
|
| 5051 |
+
},
|
| 5052 |
+
{
|
| 5053 |
+
"epoch": 1.689405918229049,
|
| 5054 |
+
"grad_norm": 1.119947910308838,
|
| 5055 |
+
"learning_rate": 4.856123131831364e-06,
|
| 5056 |
+
"loss": 0.1249,
|
| 5057 |
+
"mean_token_accuracy": 0.7958781808614731,
|
| 5058 |
+
"num_tokens": 45950976.0,
|
| 5059 |
+
"step": 5610
|
| 5060 |
+
},
|
| 5061 |
+
{
|
| 5062 |
+
"epoch": 1.69241773962804,
|
| 5063 |
+
"grad_norm": 1.1654057502746582,
|
| 5064 |
+
"learning_rate": 4.844969886236895e-06,
|
| 5065 |
+
"loss": 0.1418,
|
| 5066 |
+
"mean_token_accuracy": 0.7592465754598379,
|
| 5067 |
+
"num_tokens": 46032896.0,
|
| 5068 |
+
"step": 5620
|
| 5069 |
+
},
|
| 5070 |
+
{
|
| 5071 |
+
"epoch": 1.6954295610270311,
|
| 5072 |
+
"grad_norm": 1.3118687868118286,
|
| 5073 |
+
"learning_rate": 4.8338166406424275e-06,
|
| 5074 |
+
"loss": 0.1268,
|
| 5075 |
+
"mean_token_accuracy": 0.7850048918277025,
|
| 5076 |
+
"num_tokens": 46114816.0,
|
| 5077 |
+
"step": 5630
|
| 5078 |
+
},
|
| 5079 |
+
{
|
| 5080 |
+
"epoch": 1.6984413824260223,
|
| 5081 |
+
"grad_norm": 0.907384991645813,
|
| 5082 |
+
"learning_rate": 4.82266339504796e-06,
|
| 5083 |
+
"loss": 0.1068,
|
| 5084 |
+
"mean_token_accuracy": 0.8026663415133953,
|
| 5085 |
+
"num_tokens": 46196736.0,
|
| 5086 |
+
"step": 5640
|
| 5087 |
+
},
|
| 5088 |
+
{
|
| 5089 |
+
"epoch": 1.7014532038250132,
|
| 5090 |
+
"grad_norm": 1.247758388519287,
|
| 5091 |
+
"learning_rate": 4.811510149453492e-06,
|
| 5092 |
+
"loss": 0.1181,
|
| 5093 |
+
"mean_token_accuracy": 0.784491191059351,
|
| 5094 |
+
"num_tokens": 46278656.0,
|
| 5095 |
+
"step": 5650
|
| 5096 |
+
},
|
| 5097 |
+
{
|
| 5098 |
+
"epoch": 1.7044650252240041,
|
| 5099 |
+
"grad_norm": 1.2206517457962036,
|
| 5100 |
+
"learning_rate": 4.800356903859023e-06,
|
| 5101 |
+
"loss": 0.1263,
|
| 5102 |
+
"mean_token_accuracy": 0.7789261259138585,
|
| 5103 |
+
"num_tokens": 46360576.0,
|
| 5104 |
+
"step": 5660
|
| 5105 |
+
},
|
| 5106 |
+
{
|
| 5107 |
+
"epoch": 1.7074768466229953,
|
| 5108 |
+
"grad_norm": 1.4693553447723389,
|
| 5109 |
+
"learning_rate": 4.789203658264555e-06,
|
| 5110 |
+
"loss": 0.1288,
|
| 5111 |
+
"mean_token_accuracy": 0.7743395268917084,
|
| 5112 |
+
"num_tokens": 46442496.0,
|
| 5113 |
+
"step": 5670
|
| 5114 |
+
},
|
| 5115 |
+
{
|
| 5116 |
+
"epoch": 1.7104886680219864,
|
| 5117 |
+
"grad_norm": 1.5424615144729614,
|
| 5118 |
+
"learning_rate": 4.778050412670087e-06,
|
| 5119 |
+
"loss": 0.1205,
|
| 5120 |
+
"mean_token_accuracy": 0.7858732886612415,
|
| 5121 |
+
"num_tokens": 46524416.0,
|
| 5122 |
+
"step": 5680
|
| 5123 |
+
},
|
| 5124 |
+
{
|
| 5125 |
+
"epoch": 1.7135004894209773,
|
| 5126 |
+
"grad_norm": 1.4653291702270508,
|
| 5127 |
+
"learning_rate": 4.766897167075619e-06,
|
| 5128 |
+
"loss": 0.1466,
|
| 5129 |
+
"mean_token_accuracy": 0.7676614470779896,
|
| 5130 |
+
"num_tokens": 46606336.0,
|
| 5131 |
+
"step": 5690
|
| 5132 |
+
},
|
| 5133 |
+
{
|
| 5134 |
+
"epoch": 1.7165123108199682,
|
| 5135 |
+
"grad_norm": 1.5882482528686523,
|
| 5136 |
+
"learning_rate": 4.755743921481152e-06,
|
| 5137 |
+
"loss": 0.1065,
|
| 5138 |
+
"mean_token_accuracy": 0.7988013669848442,
|
| 5139 |
+
"num_tokens": 46688256.0,
|
| 5140 |
+
"step": 5700
|
| 5141 |
+
},
|
| 5142 |
+
{
|
| 5143 |
+
"epoch": 1.7195241322189594,
|
| 5144 |
+
"grad_norm": 1.2498167753219604,
|
| 5145 |
+
"learning_rate": 4.744590675886683e-06,
|
| 5146 |
+
"loss": 0.1202,
|
| 5147 |
+
"mean_token_accuracy": 0.7973214272409678,
|
| 5148 |
+
"num_tokens": 46770176.0,
|
| 5149 |
+
"step": 5710
|
| 5150 |
+
},
|
| 5151 |
+
{
|
| 5152 |
+
"epoch": 1.7225359536179505,
|
| 5153 |
+
"grad_norm": 1.5788949728012085,
|
| 5154 |
+
"learning_rate": 4.733437430292215e-06,
|
| 5155 |
+
"loss": 0.102,
|
| 5156 |
+
"mean_token_accuracy": 0.7933341491967439,
|
| 5157 |
+
"num_tokens": 46852096.0,
|
| 5158 |
+
"step": 5720
|
| 5159 |
+
},
|
| 5160 |
+
{
|
| 5161 |
+
"epoch": 1.7255477750169415,
|
| 5162 |
+
"grad_norm": 1.5957988500595093,
|
| 5163 |
+
"learning_rate": 4.7222841846977475e-06,
|
| 5164 |
+
"loss": 0.1407,
|
| 5165 |
+
"mean_token_accuracy": 0.7833292562514543,
|
| 5166 |
+
"num_tokens": 46934016.0,
|
| 5167 |
+
"step": 5730
|
| 5168 |
+
},
|
| 5169 |
+
{
|
| 5170 |
+
"epoch": 1.7285595964159324,
|
| 5171 |
+
"grad_norm": 1.243113398551941,
|
| 5172 |
+
"learning_rate": 4.71113093910328e-06,
|
| 5173 |
+
"loss": 0.1184,
|
| 5174 |
+
"mean_token_accuracy": 0.7828277878463268,
|
| 5175 |
+
"num_tokens": 47015936.0,
|
| 5176 |
+
"step": 5740
|
| 5177 |
+
},
|
| 5178 |
+
{
|
| 5179 |
+
"epoch": 1.7315714178149237,
|
| 5180 |
+
"grad_norm": 1.1513034105300903,
|
| 5181 |
+
"learning_rate": 4.699977693508811e-06,
|
| 5182 |
+
"loss": 0.1371,
|
| 5183 |
+
"mean_token_accuracy": 0.7631604719907046,
|
| 5184 |
+
"num_tokens": 47097856.0,
|
| 5185 |
+
"step": 5750
|
| 5186 |
+
},
|
| 5187 |
+
{
|
| 5188 |
+
"epoch": 1.7345832392139147,
|
| 5189 |
+
"grad_norm": 1.3796018362045288,
|
| 5190 |
+
"learning_rate": 4.6888244479143434e-06,
|
| 5191 |
+
"loss": 0.1624,
|
| 5192 |
+
"mean_token_accuracy": 0.7756115447729826,
|
| 5193 |
+
"num_tokens": 47179776.0,
|
| 5194 |
+
"step": 5760
|
| 5195 |
+
},
|
| 5196 |
+
{
|
| 5197 |
+
"epoch": 1.7375950606129056,
|
| 5198 |
+
"grad_norm": 1.6037061214447021,
|
| 5199 |
+
"learning_rate": 4.677671202319876e-06,
|
| 5200 |
+
"loss": 0.135,
|
| 5201 |
+
"mean_token_accuracy": 0.7826076343655586,
|
| 5202 |
+
"num_tokens": 47261696.0,
|
| 5203 |
+
"step": 5770
|
| 5204 |
+
},
|
| 5205 |
+
{
|
| 5206 |
+
"epoch": 1.7406068820118967,
|
| 5207 |
+
"grad_norm": 1.030444860458374,
|
| 5208 |
+
"learning_rate": 4.666517956725408e-06,
|
| 5209 |
+
"loss": 0.1303,
|
| 5210 |
+
"mean_token_accuracy": 0.7866193737834692,
|
| 5211 |
+
"num_tokens": 47343616.0,
|
| 5212 |
+
"step": 5780
|
| 5213 |
+
},
|
| 5214 |
+
{
|
| 5215 |
+
"epoch": 1.7436187034108879,
|
| 5216 |
+
"grad_norm": 1.1653821468353271,
|
| 5217 |
+
"learning_rate": 4.655364711130939e-06,
|
| 5218 |
+
"loss": 0.1352,
|
| 5219 |
+
"mean_token_accuracy": 0.7857142832130194,
|
| 5220 |
+
"num_tokens": 47425536.0,
|
| 5221 |
+
"step": 5790
|
| 5222 |
+
},
|
| 5223 |
+
{
|
| 5224 |
+
"epoch": 1.7466305248098788,
|
| 5225 |
+
"grad_norm": 1.128597617149353,
|
| 5226 |
+
"learning_rate": 4.644211465536472e-06,
|
| 5227 |
+
"loss": 0.1329,
|
| 5228 |
+
"mean_token_accuracy": 0.7797822903841733,
|
| 5229 |
+
"num_tokens": 47507456.0,
|
| 5230 |
+
"step": 5800
|
| 5231 |
+
},
|
| 5232 |
+
{
|
| 5233 |
+
"epoch": 1.7496423462088697,
|
| 5234 |
+
"grad_norm": 1.2128268480300903,
|
| 5235 |
+
"learning_rate": 4.633058219942004e-06,
|
| 5236 |
+
"loss": 0.1336,
|
| 5237 |
+
"mean_token_accuracy": 0.7869496114552021,
|
| 5238 |
+
"num_tokens": 47589376.0,
|
| 5239 |
+
"step": 5810
|
| 5240 |
+
},
|
| 5241 |
+
{
|
| 5242 |
+
"epoch": 1.7526541676078609,
|
| 5243 |
+
"grad_norm": 1.5500558614730835,
|
| 5244 |
+
"learning_rate": 4.621904974347535e-06,
|
| 5245 |
+
"loss": 0.1571,
|
| 5246 |
+
"mean_token_accuracy": 0.7766511704772711,
|
| 5247 |
+
"num_tokens": 47671296.0,
|
| 5248 |
+
"step": 5820
|
| 5249 |
+
},
|
| 5250 |
+
{
|
| 5251 |
+
"epoch": 1.755665989006852,
|
| 5252 |
+
"grad_norm": 1.3147218227386475,
|
| 5253 |
+
"learning_rate": 4.6107517287530675e-06,
|
| 5254 |
+
"loss": 0.1131,
|
| 5255 |
+
"mean_token_accuracy": 0.7829745605587959,
|
| 5256 |
+
"num_tokens": 47753216.0,
|
| 5257 |
+
"step": 5830
|
| 5258 |
+
},
|
| 5259 |
+
{
|
| 5260 |
+
"epoch": 1.758677810405843,
|
| 5261 |
+
"grad_norm": 1.2580207586288452,
|
| 5262 |
+
"learning_rate": 4.599598483158599e-06,
|
| 5263 |
+
"loss": 0.1107,
|
| 5264 |
+
"mean_token_accuracy": 0.7984466716647148,
|
| 5265 |
+
"num_tokens": 47835136.0,
|
| 5266 |
+
"step": 5840
|
| 5267 |
+
},
|
| 5268 |
+
{
|
| 5269 |
+
"epoch": 1.7616896318048338,
|
| 5270 |
+
"grad_norm": 1.2919446229934692,
|
| 5271 |
+
"learning_rate": 4.588445237564131e-06,
|
| 5272 |
+
"loss": 0.1122,
|
| 5273 |
+
"mean_token_accuracy": 0.7956947181373835,
|
| 5274 |
+
"num_tokens": 47917056.0,
|
| 5275 |
+
"step": 5850
|
| 5276 |
+
},
|
| 5277 |
+
{
|
| 5278 |
+
"epoch": 1.764701453203825,
|
| 5279 |
+
"grad_norm": 1.4461500644683838,
|
| 5280 |
+
"learning_rate": 4.5772919919696635e-06,
|
| 5281 |
+
"loss": 0.1569,
|
| 5282 |
+
"mean_token_accuracy": 0.7789261236786842,
|
| 5283 |
+
"num_tokens": 47998976.0,
|
| 5284 |
+
"step": 5860
|
| 5285 |
+
},
|
| 5286 |
+
{
|
| 5287 |
+
"epoch": 1.7677132746028161,
|
| 5288 |
+
"grad_norm": 0.9612492918968201,
|
| 5289 |
+
"learning_rate": 4.566138746375196e-06,
|
| 5290 |
+
"loss": 0.1155,
|
| 5291 |
+
"mean_token_accuracy": 0.800122307986021,
|
| 5292 |
+
"num_tokens": 48080896.0,
|
| 5293 |
+
"step": 5870
|
| 5294 |
+
},
|
| 5295 |
+
{
|
| 5296 |
+
"epoch": 1.770725096001807,
|
| 5297 |
+
"grad_norm": 1.1701524257659912,
|
| 5298 |
+
"learning_rate": 4.554985500780727e-06,
|
| 5299 |
+
"loss": 0.1268,
|
| 5300 |
+
"mean_token_accuracy": 0.7784735832363368,
|
| 5301 |
+
"num_tokens": 48162816.0,
|
| 5302 |
+
"step": 5880
|
| 5303 |
+
},
|
| 5304 |
+
{
|
| 5305 |
+
"epoch": 1.773736917400798,
|
| 5306 |
+
"grad_norm": 0.8847672343254089,
|
| 5307 |
+
"learning_rate": 4.543832255186259e-06,
|
| 5308 |
+
"loss": 0.1395,
|
| 5309 |
+
"mean_token_accuracy": 0.771404106169939,
|
| 5310 |
+
"num_tokens": 48244736.0,
|
| 5311 |
+
"step": 5890
|
| 5312 |
+
},
|
| 5313 |
+
{
|
| 5314 |
+
"epoch": 1.7767487387997891,
|
| 5315 |
+
"grad_norm": 1.2543238401412964,
|
| 5316 |
+
"learning_rate": 4.532679009591792e-06,
|
| 5317 |
+
"loss": 0.1293,
|
| 5318 |
+
"mean_token_accuracy": 0.7882093921303749,
|
| 5319 |
+
"num_tokens": 48326656.0,
|
| 5320 |
+
"step": 5900
|
| 5321 |
+
},
|
| 5322 |
+
{
|
| 5323 |
+
"epoch": 1.7797605601987803,
|
| 5324 |
+
"grad_norm": 1.0476740598678589,
|
| 5325 |
+
"learning_rate": 4.521525763997324e-06,
|
| 5326 |
+
"loss": 0.1401,
|
| 5327 |
+
"mean_token_accuracy": 0.7806506846100092,
|
| 5328 |
+
"num_tokens": 48408576.0,
|
| 5329 |
+
"step": 5910
|
| 5330 |
+
},
|
| 5331 |
+
{
|
| 5332 |
+
"epoch": 1.7827723815977712,
|
| 5333 |
+
"grad_norm": 0.9780436754226685,
|
| 5334 |
+
"learning_rate": 4.510372518402855e-06,
|
| 5335 |
+
"loss": 0.128,
|
| 5336 |
+
"mean_token_accuracy": 0.7880748540163041,
|
| 5337 |
+
"num_tokens": 48490496.0,
|
| 5338 |
+
"step": 5920
|
| 5339 |
+
},
|
| 5340 |
+
{
|
| 5341 |
+
"epoch": 1.7857842029967623,
|
| 5342 |
+
"grad_norm": 1.645817756652832,
|
| 5343 |
+
"learning_rate": 4.4992192728083876e-06,
|
| 5344 |
+
"loss": 0.1207,
|
| 5345 |
+
"mean_token_accuracy": 0.7967710334807634,
|
| 5346 |
+
"num_tokens": 48572416.0,
|
| 5347 |
+
"step": 5930
|
| 5348 |
+
},
|
| 5349 |
+
{
|
| 5350 |
+
"epoch": 1.7887960243957535,
|
| 5351 |
+
"grad_norm": 1.1234519481658936,
|
| 5352 |
+
"learning_rate": 4.48806602721392e-06,
|
| 5353 |
+
"loss": 0.1117,
|
| 5354 |
+
"mean_token_accuracy": 0.7863380637019872,
|
| 5355 |
+
"num_tokens": 48654336.0,
|
| 5356 |
+
"step": 5940
|
| 5357 |
+
},
|
| 5358 |
+
{
|
| 5359 |
+
"epoch": 1.7918078457947444,
|
| 5360 |
+
"grad_norm": 1.2160331010818481,
|
| 5361 |
+
"learning_rate": 4.476912781619452e-06,
|
| 5362 |
+
"loss": 0.1089,
|
| 5363 |
+
"mean_token_accuracy": 0.7874755386263133,
|
| 5364 |
+
"num_tokens": 48736256.0,
|
| 5365 |
+
"step": 5950
|
| 5366 |
+
},
|
| 5367 |
+
{
|
| 5368 |
+
"epoch": 1.7948196671937353,
|
| 5369 |
+
"grad_norm": 1.0973700284957886,
|
| 5370 |
+
"learning_rate": 4.4657595360249835e-06,
|
| 5371 |
+
"loss": 0.1106,
|
| 5372 |
+
"mean_token_accuracy": 0.7923556726425887,
|
| 5373 |
+
"num_tokens": 48818176.0,
|
| 5374 |
+
"step": 5960
|
| 5375 |
+
},
|
| 5376 |
+
{
|
| 5377 |
+
"epoch": 1.7978314885927265,
|
| 5378 |
+
"grad_norm": 1.1763473749160767,
|
| 5379 |
+
"learning_rate": 4.454606290430516e-06,
|
| 5380 |
+
"loss": 0.1464,
|
| 5381 |
+
"mean_token_accuracy": 0.7801859095692635,
|
| 5382 |
+
"num_tokens": 48900096.0,
|
| 5383 |
+
"step": 5970
|
| 5384 |
+
},
|
| 5385 |
+
{
|
| 5386 |
+
"epoch": 1.8008433099917176,
|
| 5387 |
+
"grad_norm": 1.0403779745101929,
|
| 5388 |
+
"learning_rate": 4.443453044836047e-06,
|
| 5389 |
+
"loss": 0.1553,
|
| 5390 |
+
"mean_token_accuracy": 0.7728351287543773,
|
| 5391 |
+
"num_tokens": 48982016.0,
|
| 5392 |
+
"step": 5980
|
| 5393 |
+
},
|
| 5394 |
+
{
|
| 5395 |
+
"epoch": 1.8038551313907085,
|
| 5396 |
+
"grad_norm": 1.446248173713684,
|
| 5397 |
+
"learning_rate": 4.4322997992415794e-06,
|
| 5398 |
+
"loss": 0.1393,
|
| 5399 |
+
"mean_token_accuracy": 0.783953033387661,
|
| 5400 |
+
"num_tokens": 49063936.0,
|
| 5401 |
+
"step": 5990
|
| 5402 |
+
},
|
| 5403 |
+
{
|
| 5404 |
+
"epoch": 1.8068669527896994,
|
| 5405 |
+
"grad_norm": 1.383080005645752,
|
| 5406 |
+
"learning_rate": 4.421146553647112e-06,
|
| 5407 |
+
"loss": 0.134,
|
| 5408 |
+
"mean_token_accuracy": 0.7743395321071148,
|
| 5409 |
+
"num_tokens": 49145856.0,
|
| 5410 |
+
"step": 6000
|
| 5411 |
}
|
| 5412 |
],
|
| 5413 |
"logging_steps": 10,
|
|
|
|
| 5427 |
"attributes": {}
|
| 5428 |
}
|
| 5429 |
},
|
| 5430 |
+
"total_flos": 1.2988290099157402e+17,
|
| 5431 |
"train_batch_size": 2,
|
| 5432 |
"trial_name": null,
|
| 5433 |
"trial_params": null
|