Training in progress, step 200000
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 sha256:24cafcbeca054b25eb45dbaa77e9f8e4d2734381f7efcddba664bdaf93deca83
|
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 sha256:9a3520f3f366946bb8d422fcaf739f21dd945b2e20f55d586a4a14b0481f2442
|
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:c73b265abbda8139d03edfbfcf191478d8c6105acae52cc06499f22208693c76
|
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:fde0b2674bffb99c9fee9b254d66d297ccebab478704221850071af4c7fcb0c8
|
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 sha256:46053bd5d3a47c8e18050207309bd7dc5d26fc2fddce7863f29da9dd2315e90e
|
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 sha256:04b29c8582a1bed5afdab5241883a8f2fb8264a9331b346b38cd7cabc6764f4c
|
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:d9178179c5f6e87d139e3c7e25a8cbd1dd75197a3ac0ebe74ab3cf58d5db03c9
|
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:a39e86546be16b5ca145673ff0b9725a2855fd59d28a37ec361ae0ce5dabec81
|
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": 3.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2346,6 +2346,66 @@
|
|
2346 |
"learning_rate": 0.00010374186085309757,
|
2347 |
"loss": 0.3337,
|
2348 |
"step": 195000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2349 |
}
|
2350 |
],
|
2351 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.404255319148936,
|
5 |
+
"global_step": 200000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2346 |
"learning_rate": 0.00010374186085309757,
|
2347 |
"loss": 0.3337,
|
2348 |
"step": 195000
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 3.33,
|
2352 |
+
"learning_rate": 0.00010353486773365143,
|
2353 |
+
"loss": 0.3338,
|
2354 |
+
"step": 195500
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 3.34,
|
2358 |
+
"learning_rate": 0.00010332764233456214,
|
2359 |
+
"loss": 0.3339,
|
2360 |
+
"step": 196000
|
2361 |
+
},
|
2362 |
+
{
|
2363 |
+
"epoch": 3.34,
|
2364 |
+
"learning_rate": 0.00010312060184074115,
|
2365 |
+
"loss": 0.3342,
|
2366 |
+
"step": 196500
|
2367 |
+
},
|
2368 |
+
{
|
2369 |
+
"epoch": 3.35,
|
2370 |
+
"learning_rate": 0.00010291291847465994,
|
2371 |
+
"loss": 0.3332,
|
2372 |
+
"step": 197000
|
2373 |
+
},
|
2374 |
+
{
|
2375 |
+
"epoch": 3.36,
|
2376 |
+
"learning_rate": 0.00010270500896732371,
|
2377 |
+
"loss": 0.3333,
|
2378 |
+
"step": 197500
|
2379 |
+
},
|
2380 |
+
{
|
2381 |
+
"epoch": 3.37,
|
2382 |
+
"learning_rate": 0.00010249687537071537,
|
2383 |
+
"loss": 0.3334,
|
2384 |
+
"step": 198000
|
2385 |
+
},
|
2386 |
+
{
|
2387 |
+
"epoch": 3.38,
|
2388 |
+
"learning_rate": 0.00010228851973902944,
|
2389 |
+
"loss": 0.3332,
|
2390 |
+
"step": 198500
|
2391 |
+
},
|
2392 |
+
{
|
2393 |
+
"epoch": 3.39,
|
2394 |
+
"learning_rate": 0.00010207994412865194,
|
2395 |
+
"loss": 0.3328,
|
2396 |
+
"step": 199000
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 3.4,
|
2400 |
+
"learning_rate": 0.00010187115059813993,
|
2401 |
+
"loss": 0.3329,
|
2402 |
+
"step": 199500
|
2403 |
+
},
|
2404 |
+
{
|
2405 |
+
"epoch": 3.4,
|
2406 |
+
"learning_rate": 0.00010166214120820125,
|
2407 |
+
"loss": 0.3323,
|
2408 |
+
"step": 200000
|
2409 |
}
|
2410 |
],
|
2411 |
"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 sha256:9a3520f3f366946bb8d422fcaf739f21dd945b2e20f55d586a4a14b0481f2442
|
3 |
size 201355195
|