Commit
•
81e6bf0
1
Parent(s):
8316459
Training in progress, step 97800, 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 1715561468
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ff2dae35f81010c72af01f07977963be57010375af5f3bff3c7967ef1499de0
|
| 3 |
size 1715561468
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3431474364
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f3263ed01043192613ac98e7715d788d77b459bd25223a60198e37a6edcc20c
|
| 3 |
size 3431474364
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be13e37a24a07e10fc68f5c2cd4ef1d31eaee86b299d03fbc1b4e1c4f98603ae
|
| 3 |
size 14244
|
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 sha256:0030adf7ec1a6b0e5ba568a360b75e530967917df22f6bc95fa46387ae323b64
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 4.
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -4006,6 +4006,206 @@
|
|
| 4006 |
"eval_samples_per_second": 9.146,
|
| 4007 |
"eval_steps_per_second": 0.143,
|
| 4008 |
"step": 93000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4009 |
}
|
| 4010 |
],
|
| 4011 |
"logging_steps": 200,
|
|
@@ -4025,7 +4225,7 @@
|
|
| 4025 |
"attributes": {}
|
| 4026 |
}
|
| 4027 |
},
|
| 4028 |
-
"total_flos": 1.
|
| 4029 |
"train_batch_size": 6,
|
| 4030 |
"trial_name": null,
|
| 4031 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.393925779495013,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 97800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 4006 |
"eval_samples_per_second": 9.146,
|
| 4007 |
"eval_steps_per_second": 0.143,
|
| 4008 |
"step": 93000
|
| 4009 |
+
},
|
| 4010 |
+
{
|
| 4011 |
+
"epoch": 4.187258513792794,
|
| 4012 |
+
"grad_norm": 18.494911193847656,
|
| 4013 |
+
"learning_rate": 4.913983787235996e-05,
|
| 4014 |
+
"loss": 0.5905,
|
| 4015 |
+
"step": 93200
|
| 4016 |
+
},
|
| 4017 |
+
{
|
| 4018 |
+
"epoch": 4.196244047084194,
|
| 4019 |
+
"grad_norm": 4.566243648529053,
|
| 4020 |
+
"learning_rate": 4.913616346215057e-05,
|
| 4021 |
+
"loss": 0.5712,
|
| 4022 |
+
"step": 93400
|
| 4023 |
+
},
|
| 4024 |
+
{
|
| 4025 |
+
"epoch": 4.205229580375596,
|
| 4026 |
+
"grad_norm": 5.748531818389893,
|
| 4027 |
+
"learning_rate": 4.9132481358518735e-05,
|
| 4028 |
+
"loss": 0.558,
|
| 4029 |
+
"step": 93600
|
| 4030 |
+
},
|
| 4031 |
+
{
|
| 4032 |
+
"epoch": 4.214215113666996,
|
| 4033 |
+
"grad_norm": 3.77885365486145,
|
| 4034 |
+
"learning_rate": 4.9128791562638096e-05,
|
| 4035 |
+
"loss": 0.5927,
|
| 4036 |
+
"step": 93800
|
| 4037 |
+
},
|
| 4038 |
+
{
|
| 4039 |
+
"epoch": 4.223200646958397,
|
| 4040 |
+
"grad_norm": 2.6284022331237793,
|
| 4041 |
+
"learning_rate": 4.9125094075684805e-05,
|
| 4042 |
+
"loss": 0.5953,
|
| 4043 |
+
"step": 94000
|
| 4044 |
+
},
|
| 4045 |
+
{
|
| 4046 |
+
"epoch": 4.223200646958397,
|
| 4047 |
+
"eval_loss": 2.712245225906372,
|
| 4048 |
+
"eval_runtime": 1088.8302,
|
| 4049 |
+
"eval_samples_per_second": 9.096,
|
| 4050 |
+
"eval_steps_per_second": 0.142,
|
| 4051 |
+
"step": 94000
|
| 4052 |
+
},
|
| 4053 |
+
{
|
| 4054 |
+
"epoch": 4.232186180249798,
|
| 4055 |
+
"grad_norm": 5.8867645263671875,
|
| 4056 |
+
"learning_rate": 4.9121388898837415e-05,
|
| 4057 |
+
"loss": 0.5895,
|
| 4058 |
+
"step": 94200
|
| 4059 |
+
},
|
| 4060 |
+
{
|
| 4061 |
+
"epoch": 4.241171713541199,
|
| 4062 |
+
"grad_norm": 6.118598937988281,
|
| 4063 |
+
"learning_rate": 4.911767603327698e-05,
|
| 4064 |
+
"loss": 0.6138,
|
| 4065 |
+
"step": 94400
|
| 4066 |
+
},
|
| 4067 |
+
{
|
| 4068 |
+
"epoch": 4.250157246832599,
|
| 4069 |
+
"grad_norm": 7.058086395263672,
|
| 4070 |
+
"learning_rate": 4.911395548018696e-05,
|
| 4071 |
+
"loss": 0.5921,
|
| 4072 |
+
"step": 94600
|
| 4073 |
+
},
|
| 4074 |
+
{
|
| 4075 |
+
"epoch": 4.259142780124001,
|
| 4076 |
+
"grad_norm": 6.587648391723633,
|
| 4077 |
+
"learning_rate": 4.911022724075329e-05,
|
| 4078 |
+
"loss": 0.5778,
|
| 4079 |
+
"step": 94800
|
| 4080 |
+
},
|
| 4081 |
+
{
|
| 4082 |
+
"epoch": 4.268128313415401,
|
| 4083 |
+
"grad_norm": 1.6069397926330566,
|
| 4084 |
+
"learning_rate": 4.910649131616435e-05,
|
| 4085 |
+
"loss": 0.6262,
|
| 4086 |
+
"step": 95000
|
| 4087 |
+
},
|
| 4088 |
+
{
|
| 4089 |
+
"epoch": 4.268128313415401,
|
| 4090 |
+
"eval_loss": 2.6547911167144775,
|
| 4091 |
+
"eval_runtime": 1085.8261,
|
| 4092 |
+
"eval_samples_per_second": 9.121,
|
| 4093 |
+
"eval_steps_per_second": 0.143,
|
| 4094 |
+
"step": 95000
|
| 4095 |
+
},
|
| 4096 |
+
{
|
| 4097 |
+
"epoch": 4.277113846706802,
|
| 4098 |
+
"grad_norm": 6.686661243438721,
|
| 4099 |
+
"learning_rate": 4.910274770761096e-05,
|
| 4100 |
+
"loss": 0.5864,
|
| 4101 |
+
"step": 95200
|
| 4102 |
+
},
|
| 4103 |
+
{
|
| 4104 |
+
"epoch": 4.286099379998203,
|
| 4105 |
+
"grad_norm": 7.897719860076904,
|
| 4106 |
+
"learning_rate": 4.909899641628641e-05,
|
| 4107 |
+
"loss": 0.5884,
|
| 4108 |
+
"step": 95400
|
| 4109 |
+
},
|
| 4110 |
+
{
|
| 4111 |
+
"epoch": 4.295084913289604,
|
| 4112 |
+
"grad_norm": 7.400073528289795,
|
| 4113 |
+
"learning_rate": 4.9095237443386435e-05,
|
| 4114 |
+
"loss": 0.6021,
|
| 4115 |
+
"step": 95600
|
| 4116 |
+
},
|
| 4117 |
+
{
|
| 4118 |
+
"epoch": 4.3040704465810045,
|
| 4119 |
+
"grad_norm": 4.220474720001221,
|
| 4120 |
+
"learning_rate": 4.9091470790109196e-05,
|
| 4121 |
+
"loss": 0.5518,
|
| 4122 |
+
"step": 95800
|
| 4123 |
+
},
|
| 4124 |
+
{
|
| 4125 |
+
"epoch": 4.313055979872406,
|
| 4126 |
+
"grad_norm": 1.6574774980545044,
|
| 4127 |
+
"learning_rate": 4.908769645765532e-05,
|
| 4128 |
+
"loss": 0.5867,
|
| 4129 |
+
"step": 96000
|
| 4130 |
+
},
|
| 4131 |
+
{
|
| 4132 |
+
"epoch": 4.313055979872406,
|
| 4133 |
+
"eval_loss": 2.691925525665283,
|
| 4134 |
+
"eval_runtime": 1089.0317,
|
| 4135 |
+
"eval_samples_per_second": 9.094,
|
| 4136 |
+
"eval_steps_per_second": 0.142,
|
| 4137 |
+
"step": 96000
|
| 4138 |
+
},
|
| 4139 |
+
{
|
| 4140 |
+
"epoch": 4.322041513163806,
|
| 4141 |
+
"grad_norm": 3.5609164237976074,
|
| 4142 |
+
"learning_rate": 4.908391444722787e-05,
|
| 4143 |
+
"loss": 0.5803,
|
| 4144 |
+
"step": 96200
|
| 4145 |
+
},
|
| 4146 |
+
{
|
| 4147 |
+
"epoch": 4.331027046455207,
|
| 4148 |
+
"grad_norm": 3.427290201187134,
|
| 4149 |
+
"learning_rate": 4.908012476003239e-05,
|
| 4150 |
+
"loss": 0.554,
|
| 4151 |
+
"step": 96400
|
| 4152 |
+
},
|
| 4153 |
+
{
|
| 4154 |
+
"epoch": 4.340012579746608,
|
| 4155 |
+
"grad_norm": 52.728878021240234,
|
| 4156 |
+
"learning_rate": 4.907632739727682e-05,
|
| 4157 |
+
"loss": 0.5962,
|
| 4158 |
+
"step": 96600
|
| 4159 |
+
},
|
| 4160 |
+
{
|
| 4161 |
+
"epoch": 4.348998113038009,
|
| 4162 |
+
"grad_norm": 12.754006385803223,
|
| 4163 |
+
"learning_rate": 4.907252236017159e-05,
|
| 4164 |
+
"loss": 0.5742,
|
| 4165 |
+
"step": 96800
|
| 4166 |
+
},
|
| 4167 |
+
{
|
| 4168 |
+
"epoch": 4.3579836463294095,
|
| 4169 |
+
"grad_norm": 8.12136173248291,
|
| 4170 |
+
"learning_rate": 4.9068709649929544e-05,
|
| 4171 |
+
"loss": 0.6085,
|
| 4172 |
+
"step": 97000
|
| 4173 |
+
},
|
| 4174 |
+
{
|
| 4175 |
+
"epoch": 4.3579836463294095,
|
| 4176 |
+
"eval_loss": 2.6768929958343506,
|
| 4177 |
+
"eval_runtime": 1090.8411,
|
| 4178 |
+
"eval_samples_per_second": 9.079,
|
| 4179 |
+
"eval_steps_per_second": 0.142,
|
| 4180 |
+
"step": 97000
|
| 4181 |
+
},
|
| 4182 |
+
{
|
| 4183 |
+
"epoch": 4.366969179620811,
|
| 4184 |
+
"grad_norm": 5.45872688293457,
|
| 4185 |
+
"learning_rate": 4.9064889267766e-05,
|
| 4186 |
+
"loss": 0.5137,
|
| 4187 |
+
"step": 97200
|
| 4188 |
+
},
|
| 4189 |
+
{
|
| 4190 |
+
"epoch": 4.375954712912211,
|
| 4191 |
+
"grad_norm": 3.9804370403289795,
|
| 4192 |
+
"learning_rate": 4.9061061214898707e-05,
|
| 4193 |
+
"loss": 0.5567,
|
| 4194 |
+
"step": 97400
|
| 4195 |
+
},
|
| 4196 |
+
{
|
| 4197 |
+
"epoch": 4.3849402462036124,
|
| 4198 |
+
"grad_norm": 29.226791381835938,
|
| 4199 |
+
"learning_rate": 4.9057225492547846e-05,
|
| 4200 |
+
"loss": 0.5694,
|
| 4201 |
+
"step": 97600
|
| 4202 |
+
},
|
| 4203 |
+
{
|
| 4204 |
+
"epoch": 4.393925779495013,
|
| 4205 |
+
"grad_norm": 6.9307169914245605,
|
| 4206 |
+
"learning_rate": 4.9053382101936076e-05,
|
| 4207 |
+
"loss": 0.5909,
|
| 4208 |
+
"step": 97800
|
| 4209 |
}
|
| 4210 |
],
|
| 4211 |
"logging_steps": 200,
|
|
|
|
| 4225 |
"attributes": {}
|
| 4226 |
}
|
| 4227 |
},
|
| 4228 |
+
"total_flos": 1.4020652132868096e+18,
|
| 4229 |
"train_batch_size": 6,
|
| 4230 |
"trial_name": null,
|
| 4231 |
"trial_params": null
|