Training in progress, step 345000
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/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83dd4548116d466d7f885aa1b9d13ddf4c2114ba9456ee49e541f671ced0317f
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46280709d44b101f55196928bdadf92a3830c379d71f080dc686106279b434cb
|
3 |
size 201355195
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8fc97a7a5cc9b1e3956bbc3aca04392587007e110b6476a4890c44b5430aaf0
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caaccd9343d5c6a28ee2c948f61ec3a245a06908beeb0cf83e92e5bd8006cc24
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e74a987926af314083bfa4155b2bd811ab4c12de943a72163542b186ecabe194
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b77193a6645bf4845a62f17c19a70d379bf10a85c1dd5e911d82d77fd45b7920
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cc82eda5321344cebcb785e74dc4dfabbbe4188284e945fbed3ab3a89a6b518
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19b1746286e0e918c7d1f3e8d3df829475cd4bfa7b18e54415b34d1345657960
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 5.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -4086,6 +4086,66 @@
|
|
4086 |
"learning_rate": 4.254115608201689e-05,
|
4087 |
"loss": 0.3228,
|
4088 |
"step": 340000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4089 |
}
|
4090 |
],
|
4091 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.872333001421264,
|
5 |
+
"global_step": 345000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
4086 |
"learning_rate": 4.254115608201689e-05,
|
4087 |
"loss": 0.3228,
|
4088 |
"step": 340000
|
4089 |
+
},
|
4090 |
+
{
|
4091 |
+
"epoch": 5.8,
|
4092 |
+
"learning_rate": 4.2355566165147584e-05,
|
4093 |
+
"loss": 0.3225,
|
4094 |
+
"step": 340500
|
4095 |
+
},
|
4096 |
+
{
|
4097 |
+
"epoch": 5.8,
|
4098 |
+
"learning_rate": 4.217034778364253e-05,
|
4099 |
+
"loss": 0.3224,
|
4100 |
+
"step": 341000
|
4101 |
+
},
|
4102 |
+
{
|
4103 |
+
"epoch": 5.81,
|
4104 |
+
"learning_rate": 4.1985872081738785e-05,
|
4105 |
+
"loss": 0.3225,
|
4106 |
+
"step": 341500
|
4107 |
+
},
|
4108 |
+
{
|
4109 |
+
"epoch": 5.82,
|
4110 |
+
"learning_rate": 4.1801770064696236e-05,
|
4111 |
+
"loss": 0.3226,
|
4112 |
+
"step": 342000
|
4113 |
+
},
|
4114 |
+
{
|
4115 |
+
"epoch": 5.83,
|
4116 |
+
"learning_rate": 4.1617675731054795e-05,
|
4117 |
+
"loss": 0.3225,
|
4118 |
+
"step": 342500
|
4119 |
+
},
|
4120 |
+
{
|
4121 |
+
"epoch": 5.84,
|
4122 |
+
"learning_rate": 4.143396021545834e-05,
|
4123 |
+
"loss": 0.3226,
|
4124 |
+
"step": 343000
|
4125 |
+
},
|
4126 |
+
{
|
4127 |
+
"epoch": 5.85,
|
4128 |
+
"learning_rate": 4.12506253311048e-05,
|
4129 |
+
"loss": 0.3224,
|
4130 |
+
"step": 343500
|
4131 |
+
},
|
4132 |
+
{
|
4133 |
+
"epoch": 5.86,
|
4134 |
+
"learning_rate": 4.1067672887435514e-05,
|
4135 |
+
"loss": 0.3228,
|
4136 |
+
"step": 344000
|
4137 |
+
},
|
4138 |
+
{
|
4139 |
+
"epoch": 5.86,
|
4140 |
+
"learning_rate": 4.0885104690117184e-05,
|
4141 |
+
"loss": 0.3225,
|
4142 |
+
"step": 344500
|
4143 |
+
},
|
4144 |
+
{
|
4145 |
+
"epoch": 5.87,
|
4146 |
+
"learning_rate": 4.0702922541024256e-05,
|
4147 |
+
"loss": 0.3223,
|
4148 |
+
"step": 345000
|
4149 |
}
|
4150 |
],
|
4151 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46280709d44b101f55196928bdadf92a3830c379d71f080dc686106279b434cb
|
3 |
size 201355195
|