Training in progress, step 255000
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 sha256:584ce1e297fb07dd53a8cb7091e14fc73741c312ea14cfd89bb2edf8282d3b78
|
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 sha256:73ce97d3e17c9c2e7a9d504f7f7b3cb2fed29aa48cdb44d8e8bdc67827d8e6d5
|
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:ecc364fcae64cc89948a302f947503b93e04375c7d19311b5b6d396a4b0bc7e3
|
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 sha256:6b8d3e79eedfc54272925941cd910b1b04ea28600b66b68a644abbf3c42dfbb1
|
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:e253a02e7b0f1a6343d5937525cb94f330e46b765484c4953d90b98d2d185c0f
|
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 sha256:3735ef55d5a06dd13c5aa4560e437e1275bbc7f3ea41ac5f24accb0c6837a65c
|
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 sha256:42644b050abaaed874d484487503139aee57db096407be9e56c0d8a15395a50a
|
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:ae9eef814f429ea0e53b0fcdc8f72e608df3bc1b80d5f78107ca6859ae2c5201
|
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": 4.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -3006,6 +3006,66 @@
|
|
3006 |
"learning_rate": 8.004442211714013e-05,
|
3007 |
"loss": 0.3298,
|
3008 |
"step": 250000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3009 |
}
|
3010 |
],
|
3011 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.340422634700981,
|
5 |
+
"global_step": 255000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3006 |
"learning_rate": 8.004442211714013e-05,
|
3007 |
"loss": 0.3298,
|
3008 |
"step": 250000
|
3009 |
+
},
|
3010 |
+
{
|
3011 |
+
"epoch": 4.26,
|
3012 |
+
"learning_rate": 7.982451081819563e-05,
|
3013 |
+
"loss": 0.33,
|
3014 |
+
"step": 250500
|
3015 |
+
},
|
3016 |
+
{
|
3017 |
+
"epoch": 4.27,
|
3018 |
+
"learning_rate": 7.960460125125849e-05,
|
3019 |
+
"loss": 0.33,
|
3020 |
+
"step": 251000
|
3021 |
+
},
|
3022 |
+
{
|
3023 |
+
"epoch": 4.28,
|
3024 |
+
"learning_rate": 7.938469558674736e-05,
|
3025 |
+
"loss": 0.3302,
|
3026 |
+
"step": 251500
|
3027 |
+
},
|
3028 |
+
{
|
3029 |
+
"epoch": 4.29,
|
3030 |
+
"learning_rate": 7.916479599504238e-05,
|
3031 |
+
"loss": 0.3301,
|
3032 |
+
"step": 252000
|
3033 |
+
},
|
3034 |
+
{
|
3035 |
+
"epoch": 4.3,
|
3036 |
+
"learning_rate": 7.894534441949177e-05,
|
3037 |
+
"loss": 0.3301,
|
3038 |
+
"step": 252500
|
3039 |
+
},
|
3040 |
+
{
|
3041 |
+
"epoch": 4.31,
|
3042 |
+
"learning_rate": 7.872546346128575e-05,
|
3043 |
+
"loss": 0.3303,
|
3044 |
+
"step": 253000
|
3045 |
+
},
|
3046 |
+
{
|
3047 |
+
"epoch": 4.31,
|
3048 |
+
"learning_rate": 7.850603480500256e-05,
|
3049 |
+
"loss": 0.33,
|
3050 |
+
"step": 253500
|
3051 |
+
},
|
3052 |
+
{
|
3053 |
+
"epoch": 4.32,
|
3054 |
+
"learning_rate": 7.828618114346693e-05,
|
3055 |
+
"loss": 0.3299,
|
3056 |
+
"step": 254000
|
3057 |
+
},
|
3058 |
+
{
|
3059 |
+
"epoch": 4.33,
|
3060 |
+
"learning_rate": 7.806634439663151e-05,
|
3061 |
+
"loss": 0.3301,
|
3062 |
+
"step": 254500
|
3063 |
+
},
|
3064 |
+
{
|
3065 |
+
"epoch": 4.34,
|
3066 |
+
"learning_rate": 7.784652673419626e-05,
|
3067 |
+
"loss": 0.33,
|
3068 |
+
"step": 255000
|
3069 |
}
|
3070 |
],
|
3071 |
"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 sha256:73ce97d3e17c9c2e7a9d504f7f7b3cb2fed29aa48cdb44d8e8bdc67827d8e6d5
|
3 |
size 201355195
|