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:db0082585963d0779a3f6f845b8a80f0898e8eedf6b822ae1abfa3c565e33123
|
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 sha256:54fb806d94f7814d043292764ccbf83208093216238755776971fd13549a8417
|
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 sha256:02ff42f6c9444191a36be04b13f7af185230adc9bf275d0694e2347ba302132d
|
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:effaa00a349e084c8da5b94ad9b11caf6487ba546f1186937a88a0177e674c2a
|
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:a8cbaa6dd387c55ef769edc414fe52b33f735df38dad67cd88e3197b2fccab40
|
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 sha256:0660ca2210537ad62887c89aee0a6b18f7d33e103b3c25af90e948e70a018db8
|
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:c04d92b6e9668a995aa67c0fd2cccd57c4af61acd1f14d12f1653f5c4a66c8e5
|
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:f1aa56a28bbfa690d13bc1188d2e157d2070090a00f8611ce9f5fd886a2b26ea
|
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": 0.00010374392960436561,
|
2347 |
"loss": 0.3369,
|
2348 |
"step": 195000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2349 |
}
|
2350 |
],
|
2351 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.404251878707415,
|
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": 0.00010374392960436561,
|
2347 |
"loss": 0.3369,
|
2348 |
"step": 195000
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 3.33,
|
2352 |
+
"learning_rate": 0.00010353693881803657,
|
2353 |
+
"loss": 0.3364,
|
2354 |
+
"step": 195500
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 3.34,
|
2358 |
+
"learning_rate": 0.00010332971573162363,
|
2359 |
+
"loss": 0.3363,
|
2360 |
+
"step": 196000
|
2361 |
+
},
|
2362 |
+
{
|
2363 |
+
"epoch": 3.34,
|
2364 |
+
"learning_rate": 0.00010312226239033498,
|
2365 |
+
"loss": 0.336,
|
2366 |
+
"step": 196500
|
2367 |
+
},
|
2368 |
+
{
|
2369 |
+
"epoch": 3.35,
|
2370 |
+
"learning_rate": 0.0001029145808416514,
|
2371 |
+
"loss": 0.336,
|
2372 |
+
"step": 197000
|
2373 |
+
},
|
2374 |
+
{
|
2375 |
+
"epoch": 3.36,
|
2376 |
+
"learning_rate": 0.00010270667313530591,
|
2377 |
+
"loss": 0.3357,
|
2378 |
+
"step": 197500
|
2379 |
+
},
|
2380 |
+
{
|
2381 |
+
"epoch": 3.37,
|
2382 |
+
"learning_rate": 0.0001024985413232636,
|
2383 |
+
"loss": 0.3357,
|
2384 |
+
"step": 198000
|
2385 |
+
},
|
2386 |
+
{
|
2387 |
+
"epoch": 3.38,
|
2388 |
+
"learning_rate": 0.0001022901874597015,
|
2389 |
+
"loss": 0.3354,
|
2390 |
+
"step": 198500
|
2391 |
+
},
|
2392 |
+
{
|
2393 |
+
"epoch": 3.39,
|
2394 |
+
"learning_rate": 0.00010208161360098805,
|
2395 |
+
"loss": 0.3355,
|
2396 |
+
"step": 199000
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 3.4,
|
2400 |
+
"learning_rate": 0.00010187282180566307,
|
2401 |
+
"loss": 0.3354,
|
2402 |
+
"step": 199500
|
2403 |
+
},
|
2404 |
+
{
|
2405 |
+
"epoch": 3.4,
|
2406 |
+
"learning_rate": 0.00010166506882009926,
|
2407 |
+
"loss": 0.3356,
|
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 sha256:54fb806d94f7814d043292764ccbf83208093216238755776971fd13549a8417
|
3 |
size 201355195
|