Training in progress, step 260000
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 sha256:5be4494599af89e7ebbec9ba88aba84479819c14766889b10c4c6a154e4bc44a
|
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 sha256:5a4d08b06cc3a122e2f1fcb2b298adcf4031909277c0ded78eadb8c710c9a694
|
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:f8a497c610c02a4a009d872d66dced4d1393963fb757f284e9239de5518ca27c
|
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 sha256:9adb88500e7574d7a7ac9a59fb44162ff3db37217211a7dc3c10ee57873ded21
|
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:a7a3c4cc5aabe357053479b514531ffcf6d333c09651742c7a69bcb10728e34a
|
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 sha256:56e108e345685af06464f47031a3d8801b7bf55a13527cd0170b701839f73dd1
|
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 sha256:6369f21d759e2b79fe814584b0a422ef313050b150adf2eb06e997bb7cbe59a6
|
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 sha256:0048b2a6e4947157f4ece8c10d7fe8d4e74319c545c74873b383aa2c57e62380
|
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,
|
@@ -3066,6 +3066,66 @@
|
|
3066 |
"learning_rate": 7.784652673419626e-05,
|
3067 |
"loss": 0.33,
|
3068 |
"step": 255000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3069 |
}
|
3070 |
],
|
3071 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.425528293376226,
|
5 |
+
"global_step": 260000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3066 |
"learning_rate": 7.784652673419626e-05,
|
3067 |
"loss": 0.33,
|
3068 |
"step": 255000
|
3069 |
+
},
|
3070 |
+
{
|
3071 |
+
"epoch": 4.35,
|
3072 |
+
"learning_rate": 7.762673032567275e-05,
|
3073 |
+
"loss": 0.3298,
|
3074 |
+
"step": 255500
|
3075 |
+
},
|
3076 |
+
{
|
3077 |
+
"epoch": 4.36,
|
3078 |
+
"learning_rate": 7.74069573403628e-05,
|
3079 |
+
"loss": 0.33,
|
3080 |
+
"step": 256000
|
3081 |
+
},
|
3082 |
+
{
|
3083 |
+
"epoch": 4.37,
|
3084 |
+
"learning_rate": 7.718720994733705e-05,
|
3085 |
+
"loss": 0.3297,
|
3086 |
+
"step": 256500
|
3087 |
+
},
|
3088 |
+
{
|
3089 |
+
"epoch": 4.37,
|
3090 |
+
"learning_rate": 7.696749031541353e-05,
|
3091 |
+
"loss": 0.3298,
|
3092 |
+
"step": 257000
|
3093 |
+
},
|
3094 |
+
{
|
3095 |
+
"epoch": 4.38,
|
3096 |
+
"learning_rate": 7.674823996122986e-05,
|
3097 |
+
"loss": 0.3296,
|
3098 |
+
"step": 257500
|
3099 |
+
},
|
3100 |
+
{
|
3101 |
+
"epoch": 4.39,
|
3102 |
+
"learning_rate": 7.652858229048815e-05,
|
3103 |
+
"loss": 0.3297,
|
3104 |
+
"step": 258000
|
3105 |
+
},
|
3106 |
+
{
|
3107 |
+
"epoch": 4.4,
|
3108 |
+
"learning_rate": 7.630895888123776e-05,
|
3109 |
+
"loss": 0.3294,
|
3110 |
+
"step": 258500
|
3111 |
+
},
|
3112 |
+
{
|
3113 |
+
"epoch": 4.41,
|
3114 |
+
"learning_rate": 7.60893719010731e-05,
|
3115 |
+
"loss": 0.3295,
|
3116 |
+
"step": 259000
|
3117 |
+
},
|
3118 |
+
{
|
3119 |
+
"epoch": 4.42,
|
3120 |
+
"learning_rate": 7.587026257403724e-05,
|
3121 |
+
"loss": 0.3292,
|
3122 |
+
"step": 259500
|
3123 |
+
},
|
3124 |
+
{
|
3125 |
+
"epoch": 4.43,
|
3126 |
+
"learning_rate": 7.565119384297032e-05,
|
3127 |
+
"loss": 0.3292,
|
3128 |
+
"step": 260000
|
3129 |
}
|
3130 |
],
|
3131 |
"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 sha256:5a4d08b06cc3a122e2f1fcb2b298adcf4031909277c0ded78eadb8c710c9a694
|
3 |
size 201355195
|