Training in progress, step 210000
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:a46a253949850da32c9ade93641be8749099f65220005db6aa974521da1e8234
|
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 sha256:6cb41aa6426cd9827061ba03270427718db15f550044516b50c249dd3b89b81f
|
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 sha256:5bc28e59094bbc2fd8aa508743b188fe1339e678068fadeacab274fec292ab8a
|
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 sha256:10e1bbe122a3d57f8f42e0440225de6b31963f08a829688b44ef1141994d521e
|
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 sha256:157505080acfdc9d48a6fc658ea02b00489d9d9a50e5bbb8c8d41b6e85c0a7a6
|
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 sha256:6d1b526342a71678d08c040154fe3bcb505bc2cb399434890f420b26f5d165c4
|
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 sha256:3ddea67b8156ae82a63fca8e5c234d581040c8a5d2a86ec43a1c16f3fc37b187
|
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 sha256:3384b38b0df0b688e0fac4565e97f6e4a962c4650c722baa406786cb8ce462bf
|
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,
|
@@ -2466,6 +2466,66 @@
|
|
2466 |
"learning_rate": 9.956231909542228e-05,
|
2467 |
"loss": 0.3346,
|
2468 |
"step": 205000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2469 |
}
|
2470 |
],
|
2471 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.574468085106383,
|
5 |
+
"global_step": 210000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2466 |
"learning_rate": 9.956231909542228e-05,
|
2467 |
"loss": 0.3346,
|
2468 |
"step": 205000
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 3.5,
|
2472 |
+
"learning_rate": 9.935107338940626e-05,
|
2473 |
+
"loss": 0.3343,
|
2474 |
+
"step": 205500
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 3.51,
|
2478 |
+
"learning_rate": 9.913963669610826e-05,
|
2479 |
+
"loss": 0.334,
|
2480 |
+
"step": 206000
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 3.51,
|
2484 |
+
"learning_rate": 9.892801110232304e-05,
|
2485 |
+
"loss": 0.3337,
|
2486 |
+
"step": 206500
|
2487 |
+
},
|
2488 |
+
{
|
2489 |
+
"epoch": 3.52,
|
2490 |
+
"learning_rate": 9.871619869670978e-05,
|
2491 |
+
"loss": 0.3339,
|
2492 |
+
"step": 207000
|
2493 |
+
},
|
2494 |
+
{
|
2495 |
+
"epoch": 3.53,
|
2496 |
+
"learning_rate": 9.85042015697714e-05,
|
2497 |
+
"loss": 0.3337,
|
2498 |
+
"step": 207500
|
2499 |
+
},
|
2500 |
+
{
|
2501 |
+
"epoch": 3.54,
|
2502 |
+
"learning_rate": 9.8292021813834e-05,
|
2503 |
+
"loss": 0.3337,
|
2504 |
+
"step": 208000
|
2505 |
+
},
|
2506 |
+
{
|
2507 |
+
"epoch": 3.55,
|
2508 |
+
"learning_rate": 9.807966152302608e-05,
|
2509 |
+
"loss": 0.3336,
|
2510 |
+
"step": 208500
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 3.56,
|
2514 |
+
"learning_rate": 9.786712279325797e-05,
|
2515 |
+
"loss": 0.3332,
|
2516 |
+
"step": 209000
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 3.57,
|
2520 |
+
"learning_rate": 9.765440772220116e-05,
|
2521 |
+
"loss": 0.334,
|
2522 |
+
"step": 209500
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 3.57,
|
2526 |
+
"learning_rate": 9.744151840926749e-05,
|
2527 |
+
"loss": 0.3335,
|
2528 |
+
"step": 210000
|
2529 |
}
|
2530 |
],
|
2531 |
"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 sha256:6cb41aa6426cd9827061ba03270427718db15f550044516b50c249dd3b89b81f
|
3 |
size 201355195
|