Training in progress, step 430000
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/rng_state_4.pth +2 -2
- last-checkpoint/rng_state_5.pth +2 -2
- last-checkpoint/rng_state_6.pth +2 -2
- last-checkpoint/rng_state_7.pth +2 -2
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +203 -3
- 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 202194449
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2037a39653e9a86b52eb755df70a2048c15c66b97fc5c5b2e730133643a54847
|
3 |
size 202194449
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f68b8d9c04c07b07e7749f58776534bd53918c6e2c126a3b13ccf6e4c8fe0c11
|
3 |
size 102501541
|
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 sha256:9b2daf51037932e93e0733ea24caef617dc93e09ea15b9fd221dcc7444c15f0e
|
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:d3a3ebd3780a0e2b9539a7e9e3280f39aab22ea827f57421c4c22612d438cdfb
|
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 sha256:86247109bf049f289c15c3221972c6c603aeaaab8c73e9572f0b173c34fca77b
|
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 sha256:5cefc44f7d07864c913b59c01e54c2d25ff69e14a2f34a7e0e54f8b7ef0768fa
|
3 |
size 14503
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e44801ad618d45c1ec0026a0fb986a5b4b4808493b86436a804a9e6412bb1dd2
|
3 |
+
size 14439
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb1f285c2e8ce7b907118ccf23b5cb322a34d0e9eb54ad8436c82bf6abb8cfb2
|
3 |
+
size 14503
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b32a0be0231f2f19d42d8561635e493d94c812c82d1070981857c9fbb59cf960
|
3 |
+
size 14503
|
last-checkpoint/rng_state_7.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:847320643082b3f276294a5fa2113e3868a05e1a1e4d298c40cb20665e82af38
|
3 |
+
size 14439
|
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:f427c751ea4b109969727e0c5f2ef9ef6fd7587de8192ab50fc2201ab4ba3ed9
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -8406,11 +8406,211 @@
|
|
8406 |
"eval_samples_per_second": 1947.554,
|
8407 |
"eval_steps_per_second": 31.161,
|
8408 |
"step": 420000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8409 |
}
|
8410 |
],
|
8411 |
"max_steps": 500000,
|
8412 |
"num_train_epochs": 16,
|
8413 |
-
"total_flos": 1.
|
8414 |
"trial_name": null,
|
8415 |
"trial_params": null
|
8416 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 13.174423236006005,
|
5 |
+
"global_step": 430000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
8406 |
"eval_samples_per_second": 1947.554,
|
8407 |
"eval_steps_per_second": 31.161,
|
8408 |
"step": 420000
|
8409 |
+
},
|
8410 |
+
{
|
8411 |
+
"epoch": 12.88,
|
8412 |
+
"learning_rate": 2.9586456905128618e-05,
|
8413 |
+
"loss": 0.3162,
|
8414 |
+
"step": 420500
|
8415 |
+
},
|
8416 |
+
{
|
8417 |
+
"epoch": 12.9,
|
8418 |
+
"learning_rate": 2.9346475051519687e-05,
|
8419 |
+
"loss": 0.3163,
|
8420 |
+
"step": 421000
|
8421 |
+
},
|
8422 |
+
{
|
8423 |
+
"epoch": 12.9,
|
8424 |
+
"eval_loss": 0.7781884670257568,
|
8425 |
+
"eval_runtime": 0.5072,
|
8426 |
+
"eval_samples_per_second": 1971.754,
|
8427 |
+
"eval_steps_per_second": 31.548,
|
8428 |
+
"step": 421000
|
8429 |
+
},
|
8430 |
+
{
|
8431 |
+
"epoch": 12.91,
|
8432 |
+
"learning_rate": 2.910786732472815e-05,
|
8433 |
+
"loss": 0.3162,
|
8434 |
+
"step": 421500
|
8435 |
+
},
|
8436 |
+
{
|
8437 |
+
"epoch": 12.93,
|
8438 |
+
"learning_rate": 2.887063633412981e-05,
|
8439 |
+
"loss": 0.3161,
|
8440 |
+
"step": 422000
|
8441 |
+
},
|
8442 |
+
{
|
8443 |
+
"epoch": 12.93,
|
8444 |
+
"eval_loss": 0.7753953337669373,
|
8445 |
+
"eval_runtime": 0.5016,
|
8446 |
+
"eval_samples_per_second": 1993.582,
|
8447 |
+
"eval_steps_per_second": 31.897,
|
8448 |
+
"step": 422000
|
8449 |
+
},
|
8450 |
+
{
|
8451 |
+
"epoch": 12.94,
|
8452 |
+
"learning_rate": 2.863478467404478e-05,
|
8453 |
+
"loss": 0.3159,
|
8454 |
+
"step": 422500
|
8455 |
+
},
|
8456 |
+
{
|
8457 |
+
"epoch": 12.96,
|
8458 |
+
"learning_rate": 2.8400314923709112e-05,
|
8459 |
+
"loss": 0.3158,
|
8460 |
+
"step": 423000
|
8461 |
+
},
|
8462 |
+
{
|
8463 |
+
"epoch": 12.96,
|
8464 |
+
"eval_loss": 0.7729361653327942,
|
8465 |
+
"eval_runtime": 0.5075,
|
8466 |
+
"eval_samples_per_second": 1970.45,
|
8467 |
+
"eval_steps_per_second": 31.527,
|
8468 |
+
"step": 423000
|
8469 |
+
},
|
8470 |
+
{
|
8471 |
+
"epoch": 12.98,
|
8472 |
+
"learning_rate": 2.816722964724636e-05,
|
8473 |
+
"loss": 0.3159,
|
8474 |
+
"step": 423500
|
8475 |
+
},
|
8476 |
+
{
|
8477 |
+
"epoch": 12.99,
|
8478 |
+
"learning_rate": 2.793553139363981e-05,
|
8479 |
+
"loss": 0.3157,
|
8480 |
+
"step": 424000
|
8481 |
+
},
|
8482 |
+
{
|
8483 |
+
"epoch": 12.99,
|
8484 |
+
"eval_loss": 0.7751319408416748,
|
8485 |
+
"eval_runtime": 0.5075,
|
8486 |
+
"eval_samples_per_second": 1970.502,
|
8487 |
+
"eval_steps_per_second": 31.528,
|
8488 |
+
"step": 424000
|
8489 |
+
},
|
8490 |
+
{
|
8491 |
+
"epoch": 13.01,
|
8492 |
+
"learning_rate": 2.7705222696704366e-05,
|
8493 |
+
"loss": 0.3159,
|
8494 |
+
"step": 424500
|
8495 |
+
},
|
8496 |
+
{
|
8497 |
+
"epoch": 13.02,
|
8498 |
+
"learning_rate": 2.7476306075059096e-05,
|
8499 |
+
"loss": 0.3157,
|
8500 |
+
"step": 425000
|
8501 |
+
},
|
8502 |
+
{
|
8503 |
+
"epoch": 13.02,
|
8504 |
+
"eval_loss": 0.7777685523033142,
|
8505 |
+
"eval_runtime": 0.5223,
|
8506 |
+
"eval_samples_per_second": 1914.553,
|
8507 |
+
"eval_steps_per_second": 30.633,
|
8508 |
+
"step": 425000
|
8509 |
+
},
|
8510 |
+
{
|
8511 |
+
"epoch": 13.04,
|
8512 |
+
"learning_rate": 2.7248784032099478e-05,
|
8513 |
+
"loss": 0.3157,
|
8514 |
+
"step": 425500
|
8515 |
+
},
|
8516 |
+
{
|
8517 |
+
"epoch": 13.05,
|
8518 |
+
"learning_rate": 2.7022659055970144e-05,
|
8519 |
+
"loss": 0.3156,
|
8520 |
+
"step": 426000
|
8521 |
+
},
|
8522 |
+
{
|
8523 |
+
"epoch": 13.05,
|
8524 |
+
"eval_loss": 0.7756606340408325,
|
8525 |
+
"eval_runtime": 0.511,
|
8526 |
+
"eval_samples_per_second": 1957.114,
|
8527 |
+
"eval_steps_per_second": 31.314,
|
8528 |
+
"step": 426000
|
8529 |
+
},
|
8530 |
+
{
|
8531 |
+
"epoch": 13.07,
|
8532 |
+
"learning_rate": 2.6797933619537604e-05,
|
8533 |
+
"loss": 0.3155,
|
8534 |
+
"step": 426500
|
8535 |
+
},
|
8536 |
+
{
|
8537 |
+
"epoch": 13.08,
|
8538 |
+
"learning_rate": 2.6574610180363166e-05,
|
8539 |
+
"loss": 0.3155,
|
8540 |
+
"step": 427000
|
8541 |
+
},
|
8542 |
+
{
|
8543 |
+
"epoch": 13.08,
|
8544 |
+
"eval_loss": 0.7737278938293457,
|
8545 |
+
"eval_runtime": 0.5036,
|
8546 |
+
"eval_samples_per_second": 1985.649,
|
8547 |
+
"eval_steps_per_second": 31.77,
|
8548 |
+
"step": 427000
|
8549 |
+
},
|
8550 |
+
{
|
8551 |
+
"epoch": 13.1,
|
8552 |
+
"learning_rate": 2.6352691180676286e-05,
|
8553 |
+
"loss": 0.3157,
|
8554 |
+
"step": 427500
|
8555 |
+
},
|
8556 |
+
{
|
8557 |
+
"epoch": 13.11,
|
8558 |
+
"learning_rate": 2.6132179047347505e-05,
|
8559 |
+
"loss": 0.3156,
|
8560 |
+
"step": 428000
|
8561 |
+
},
|
8562 |
+
{
|
8563 |
+
"epoch": 13.11,
|
8564 |
+
"eval_loss": 0.7748771905899048,
|
8565 |
+
"eval_runtime": 0.5178,
|
8566 |
+
"eval_samples_per_second": 1931.107,
|
8567 |
+
"eval_steps_per_second": 30.898,
|
8568 |
+
"step": 428000
|
8569 |
+
},
|
8570 |
+
{
|
8571 |
+
"epoch": 13.13,
|
8572 |
+
"learning_rate": 2.5913076191862238e-05,
|
8573 |
+
"loss": 0.3156,
|
8574 |
+
"step": 428500
|
8575 |
+
},
|
8576 |
+
{
|
8577 |
+
"epoch": 13.14,
|
8578 |
+
"learning_rate": 2.5695385010294165e-05,
|
8579 |
+
"loss": 0.3156,
|
8580 |
+
"step": 429000
|
8581 |
+
},
|
8582 |
+
{
|
8583 |
+
"epoch": 13.14,
|
8584 |
+
"eval_loss": 0.7763614058494568,
|
8585 |
+
"eval_runtime": 0.5128,
|
8586 |
+
"eval_samples_per_second": 1949.92,
|
8587 |
+
"eval_steps_per_second": 31.199,
|
8588 |
+
"step": 429000
|
8589 |
+
},
|
8590 |
+
{
|
8591 |
+
"epoch": 13.16,
|
8592 |
+
"learning_rate": 2.5479107883279144e-05,
|
8593 |
+
"loss": 0.3155,
|
8594 |
+
"step": 429500
|
8595 |
+
},
|
8596 |
+
{
|
8597 |
+
"epoch": 13.17,
|
8598 |
+
"learning_rate": 2.5264247175989292e-05,
|
8599 |
+
"loss": 0.3151,
|
8600 |
+
"step": 430000
|
8601 |
+
},
|
8602 |
+
{
|
8603 |
+
"epoch": 13.17,
|
8604 |
+
"eval_loss": 0.7742259502410889,
|
8605 |
+
"eval_runtime": 0.5135,
|
8606 |
+
"eval_samples_per_second": 1947.536,
|
8607 |
+
"eval_steps_per_second": 31.161,
|
8608 |
+
"step": 430000
|
8609 |
}
|
8610 |
],
|
8611 |
"max_steps": 500000,
|
8612 |
"num_train_epochs": 16,
|
8613 |
+
"total_flos": 1.3737843123927814e+22,
|
8614 |
"trial_name": null,
|
8615 |
"trial_params": null
|
8616 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f68b8d9c04c07b07e7749f58776534bd53918c6e2c126a3b13ccf6e4c8fe0c11
|
3 |
size 102501541
|