Training in progress, step 440000
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:fc0113f382a306d0a0270cc8535391c33e1b2af74c51de2e1c6e0d4578e71f9c
|
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 sha256:4b3d022a38f882829086501961b7aec842ba9d1cefbd1f74a31fb9e986a1e317
|
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:ed98cd2de93fa24e1ee3c183460e1effd6d0ba45b92a42bfec1f09fdd419d79d
|
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 sha256:363e1050ee631150a25cc4a6efefa58b6bb8d8306f6480ffc47a3c0e8283d574
|
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 sha256:70b712440aa43dfef04d3a47555cf899fa15b72d21aa9040c97153ccae5f1d3d
|
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:e73f119d26c8a8d8cbe371942faaf6d5f3c3d949f47febc7dbbe088658221663
|
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:a4e57b8b8ebc2b0b446feb6aa39819ad3fe38c47f0f6f4374fa7a07e55d973d2
|
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:eb2e2a4fb149e5bebf2830e61019116dbdc715ae62bbe8b853e44388c27574ef
|
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": 7.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -5226,6 +5226,66 @@
|
|
5226 |
"learning_rate": 1.578655734817838e-05,
|
5227 |
"loss": 0.3192,
|
5228 |
"step": 435000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5229 |
}
|
5230 |
],
|
5231 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.48935753738266,
|
5 |
+
"global_step": 440000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
5226 |
"learning_rate": 1.578655734817838e-05,
|
5227 |
"loss": 0.3192,
|
5228 |
"step": 435000
|
5229 |
+
},
|
5230 |
+
{
|
5231 |
+
"epoch": 7.41,
|
5232 |
+
"learning_rate": 1.5699323997352622e-05,
|
5233 |
+
"loss": 0.3192,
|
5234 |
+
"step": 435500
|
5235 |
+
},
|
5236 |
+
{
|
5237 |
+
"epoch": 7.42,
|
5238 |
+
"learning_rate": 1.5612725268239792e-05,
|
5239 |
+
"loss": 0.3193,
|
5240 |
+
"step": 436000
|
5241 |
+
},
|
5242 |
+
{
|
5243 |
+
"epoch": 7.43,
|
5244 |
+
"learning_rate": 1.5526762015534355e-05,
|
5245 |
+
"loss": 0.3192,
|
5246 |
+
"step": 436500
|
5247 |
+
},
|
5248 |
+
{
|
5249 |
+
"epoch": 7.44,
|
5250 |
+
"learning_rate": 1.5441435087658935e-05,
|
5251 |
+
"loss": 0.3192,
|
5252 |
+
"step": 437000
|
5253 |
+
},
|
5254 |
+
{
|
5255 |
+
"epoch": 7.45,
|
5256 |
+
"learning_rate": 1.53569140698284e-05,
|
5257 |
+
"loss": 0.3193,
|
5258 |
+
"step": 437500
|
5259 |
+
},
|
5260 |
+
{
|
5261 |
+
"epoch": 7.46,
|
5262 |
+
"learning_rate": 1.5273028503707987e-05,
|
5263 |
+
"loss": 0.3191,
|
5264 |
+
"step": 438000
|
5265 |
+
},
|
5266 |
+
{
|
5267 |
+
"epoch": 7.46,
|
5268 |
+
"learning_rate": 1.518961302104034e-05,
|
5269 |
+
"loss": 0.3191,
|
5270 |
+
"step": 438500
|
5271 |
+
},
|
5272 |
+
{
|
5273 |
+
"epoch": 7.47,
|
5274 |
+
"learning_rate": 1.5106837190727158e-05,
|
5275 |
+
"loss": 0.3192,
|
5276 |
+
"step": 439000
|
5277 |
+
},
|
5278 |
+
{
|
5279 |
+
"epoch": 7.48,
|
5280 |
+
"learning_rate": 1.5024701829732482e-05,
|
5281 |
+
"loss": 0.3196,
|
5282 |
+
"step": 439500
|
5283 |
+
},
|
5284 |
+
{
|
5285 |
+
"epoch": 7.49,
|
5286 |
+
"learning_rate": 1.4943207748699148e-05,
|
5287 |
+
"loss": 0.3192,
|
5288 |
+
"step": 440000
|
5289 |
}
|
5290 |
],
|
5291 |
"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 sha256:4b3d022a38f882829086501961b7aec842ba9d1cefbd1f74a31fb9e986a1e317
|
3 |
size 201355195
|