Training in progress, step 350000
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 sha256:332d7e19d8c2e706fff4837c739c772a3a277718a943e025ef96fbd93411ad9b
|
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:cf29e503432e13c62753fd18f87a3b65828c9ef6cd0d4bc5768ddb9f3fd99410
|
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:ba9912ba5c1ce39ac9cd517879f25eb93bc5e1e7300bbb5140413fe3820b08fe
|
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 sha256:34bff9087ce572776c985b3b5daa247f3dbbdd59ddc66d83df3defe5f7639d16
|
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 sha256:6e79bddc36d19aeefebc6f1cde3ff352ef85e79f7be40be0f5ffb24a1a345ab3
|
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 sha256:8f8c637186a7d311f7729599f3131a837626ad487a688411d3a0e3522339cbea
|
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:e9a6fb22c662a125baf3cb7fa7decdbb5d63df434be93e56401d1fb8a4a22f12
|
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 sha256:6a6b28f9aceb6447ed69f8c0f248ff85798b8992b91909f605b37a0278479ff9
|
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,
|
@@ -4146,6 +4146,66 @@
|
|
4146 |
"learning_rate": 4.0702922541024256e-05,
|
4147 |
"loss": 0.3223,
|
4148 |
"step": 345000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4149 |
}
|
4150 |
],
|
4151 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.95743866009651,
|
5 |
+
"global_step": 350000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
4146 |
"learning_rate": 4.0702922541024256e-05,
|
4147 |
"loss": 0.3223,
|
4148 |
"step": 345000
|
4149 |
+
},
|
4150 |
+
{
|
4151 |
+
"epoch": 5.88,
|
4152 |
+
"learning_rate": 4.052149143856278e-05,
|
4153 |
+
"loss": 0.3225,
|
4154 |
+
"step": 345500
|
4155 |
+
},
|
4156 |
+
{
|
4157 |
+
"epoch": 5.89,
|
4158 |
+
"learning_rate": 4.034008599521639e-05,
|
4159 |
+
"loss": 0.3224,
|
4160 |
+
"step": 346000
|
4161 |
+
},
|
4162 |
+
{
|
4163 |
+
"epoch": 5.9,
|
4164 |
+
"learning_rate": 4.015907197920985e-05,
|
4165 |
+
"loss": 0.3225,
|
4166 |
+
"step": 346500
|
4167 |
+
},
|
4168 |
+
{
|
4169 |
+
"epoch": 5.91,
|
4170 |
+
"learning_rate": 3.997881202506971e-05,
|
4171 |
+
"loss": 0.3221,
|
4172 |
+
"step": 347000
|
4173 |
+
},
|
4174 |
+
{
|
4175 |
+
"epoch": 5.91,
|
4176 |
+
"learning_rate": 3.979894548550711e-05,
|
4177 |
+
"loss": 0.3225,
|
4178 |
+
"step": 347500
|
4179 |
+
},
|
4180 |
+
{
|
4181 |
+
"epoch": 5.92,
|
4182 |
+
"learning_rate": 3.961911486455148e-05,
|
4183 |
+
"loss": 0.3226,
|
4184 |
+
"step": 348000
|
4185 |
+
},
|
4186 |
+
{
|
4187 |
+
"epoch": 5.93,
|
4188 |
+
"learning_rate": 3.9439682786629685e-05,
|
4189 |
+
"loss": 0.3224,
|
4190 |
+
"step": 348500
|
4191 |
+
},
|
4192 |
+
{
|
4193 |
+
"epoch": 5.94,
|
4194 |
+
"learning_rate": 3.9260651022663946e-05,
|
4195 |
+
"loss": 0.3223,
|
4196 |
+
"step": 349000
|
4197 |
+
},
|
4198 |
+
{
|
4199 |
+
"epoch": 5.95,
|
4200 |
+
"learning_rate": 3.908202133962548e-05,
|
4201 |
+
"loss": 0.3223,
|
4202 |
+
"step": 349500
|
4203 |
+
},
|
4204 |
+
{
|
4205 |
+
"epoch": 5.96,
|
4206 |
+
"learning_rate": 3.890379550051711e-05,
|
4207 |
+
"loss": 0.3224,
|
4208 |
+
"step": 350000
|
4209 |
}
|
4210 |
],
|
4211 |
"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:cf29e503432e13c62753fd18f87a3b65828c9ef6cd0d4bc5768ddb9f3fd99410
|
3 |
size 201355195
|