Training in progress, step 275000
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 sha256:18cf5d89118f3fcc37338359d7a816d35e3eed32301fa09546f6d71e6300ea03
|
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 sha256:293343e481cd80d7de8f4c45dc3187298045e87b9a124d4f9a733901bd49b3fc
|
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 sha256:84f130ee6c6318231ece4d885782e25a7f07910bf8e88574476699c348777584
|
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:affe24bc2ab7509e5d146483cebb3893b2ccff7963453f6c199f15b761b9fe5a
|
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 sha256:4e130c30156d9bdb04ecf6b21d5fe7fdc59047a264a09c8684a03e61f0fe861b
|
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 sha256:6d6d06fd630644e8da44def3e57d9137d66969f8964345a5069a70cd48c1f16a
|
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 sha256:65be95d69caf661a66be280a9a4be2023f240619905ba86ace32391bc400e411
|
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:b713081b28bb34c45601a472d52359dd3c945b29f3fd5bf53e811dade70d8520
|
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,
|
@@ -3246,6 +3246,66 @@
|
|
3246 |
"learning_rate": 7.127511116710097e-05,
|
3247 |
"loss": 0.3286,
|
3248 |
"step": 270000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3249 |
}
|
3250 |
],
|
3251 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.680845269401963,
|
5 |
+
"global_step": 275000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3246 |
"learning_rate": 7.127511116710097e-05,
|
3247 |
"loss": 0.3286,
|
3248 |
"step": 270000
|
3249 |
+
},
|
3250 |
+
{
|
3251 |
+
"epoch": 4.6,
|
3252 |
+
"learning_rate": 7.10573942128076e-05,
|
3253 |
+
"loss": 0.3286,
|
3254 |
+
"step": 270500
|
3255 |
+
},
|
3256 |
+
{
|
3257 |
+
"epoch": 4.61,
|
3258 |
+
"learning_rate": 7.083932912507537e-05,
|
3259 |
+
"loss": 0.3284,
|
3260 |
+
"step": 271000
|
3261 |
+
},
|
3262 |
+
{
|
3263 |
+
"epoch": 4.62,
|
3264 |
+
"learning_rate": 7.062135444946636e-05,
|
3265 |
+
"loss": 0.3283,
|
3266 |
+
"step": 271500
|
3267 |
+
},
|
3268 |
+
{
|
3269 |
+
"epoch": 4.63,
|
3270 |
+
"learning_rate": 7.040347233730262e-05,
|
3271 |
+
"loss": 0.3281,
|
3272 |
+
"step": 272000
|
3273 |
+
},
|
3274 |
+
{
|
3275 |
+
"epoch": 4.64,
|
3276 |
+
"learning_rate": 7.018568493899267e-05,
|
3277 |
+
"loss": 0.3284,
|
3278 |
+
"step": 272500
|
3279 |
+
},
|
3280 |
+
{
|
3281 |
+
"epoch": 4.65,
|
3282 |
+
"learning_rate": 6.996799440401013e-05,
|
3283 |
+
"loss": 0.3281,
|
3284 |
+
"step": 273000
|
3285 |
+
},
|
3286 |
+
{
|
3287 |
+
"epoch": 4.66,
|
3288 |
+
"learning_rate": 6.975040288087275e-05,
|
3289 |
+
"loss": 0.3281,
|
3290 |
+
"step": 273500
|
3291 |
+
},
|
3292 |
+
{
|
3293 |
+
"epoch": 4.66,
|
3294 |
+
"learning_rate": 6.9532912517121e-05,
|
3295 |
+
"loss": 0.3281,
|
3296 |
+
"step": 274000
|
3297 |
+
},
|
3298 |
+
{
|
3299 |
+
"epoch": 4.67,
|
3300 |
+
"learning_rate": 6.931552545929699e-05,
|
3301 |
+
"loss": 0.3279,
|
3302 |
+
"step": 274500
|
3303 |
+
},
|
3304 |
+
{
|
3305 |
+
"epoch": 4.68,
|
3306 |
+
"learning_rate": 6.909824385292317e-05,
|
3307 |
+
"loss": 0.3281,
|
3308 |
+
"step": 275000
|
3309 |
}
|
3310 |
],
|
3311 |
"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 sha256:293343e481cd80d7de8f4c45dc3187298045e87b9a124d4f9a733901bd49b3fc
|
3 |
size 201355195
|