Training in progress, step 90000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +303 -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 100172997
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0403e77fedd175fe2813435246e47b4db08141719006e4af642e66c252088876
|
| 3 |
size 100172997
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:459351fdd706b427a4771aa3d8515e577348d2de84329d8049ae17fe23916e8b
|
| 3 |
size 146774203
|
last-checkpoint/rng_state.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 sha256:70d5cceb52d0fa5a00f924e679cb68057477b161920a598903be579e5d6a58aa
|
| 3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 246899880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2086d296d1d3514176646dc6eef7a73ed351fdafb4d4a71a834e5c0056ed735
|
| 3 |
size 246899880
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -2406,11 +2406,311 @@
|
|
| 2406 |
"learning_rate": 0.0005701789946806666,
|
| 2407 |
"loss": 3.1995,
|
| 2408 |
"step": 80000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2409 |
}
|
| 2410 |
],
|
| 2411 |
"max_steps": 500000,
|
| 2412 |
"num_train_epochs": 3,
|
| 2413 |
-
"total_flos": 1.
|
| 2414 |
"trial_name": null,
|
| 2415 |
"trial_params": null
|
| 2416 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3867640739149119,
|
| 5 |
+
"global_step": 90000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 2406 |
"learning_rate": 0.0005701789946806666,
|
| 2407 |
"loss": 3.1995,
|
| 2408 |
"step": 80000
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 0.34,
|
| 2412 |
+
"learning_rate": 0.0005721781645068867,
|
| 2413 |
+
"loss": 3.2116,
|
| 2414 |
+
"step": 80200
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 0.35,
|
| 2418 |
+
"learning_rate": 0.000574176418806075,
|
| 2419 |
+
"loss": 3.2256,
|
| 2420 |
+
"step": 80400
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 0.35,
|
| 2424 |
+
"learning_rate": 0.0005761737225165182,
|
| 2425 |
+
"loss": 3.2221,
|
| 2426 |
+
"step": 80600
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 0.35,
|
| 2430 |
+
"learning_rate": 0.0005781700405931827,
|
| 2431 |
+
"loss": 3.1956,
|
| 2432 |
+
"step": 80800
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.35,
|
| 2436 |
+
"learning_rate": 0.0005801653380083288,
|
| 2437 |
+
"loss": 3.2031,
|
| 2438 |
+
"step": 81000
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.35,
|
| 2442 |
+
"learning_rate": 0.0005821595797521253,
|
| 2443 |
+
"loss": 3.2029,
|
| 2444 |
+
"step": 81200
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 0.35,
|
| 2448 |
+
"learning_rate": 0.0005841527308332645,
|
| 2449 |
+
"loss": 3.2065,
|
| 2450 |
+
"step": 81400
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 0.35,
|
| 2454 |
+
"learning_rate": 0.0005861447562795751,
|
| 2455 |
+
"loss": 3.1783,
|
| 2456 |
+
"step": 81600
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 0.35,
|
| 2460 |
+
"learning_rate": 0.0005881356211386371,
|
| 2461 |
+
"loss": 3.2181,
|
| 2462 |
+
"step": 81800
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 0.35,
|
| 2466 |
+
"learning_rate": 0.0005901252904783932,
|
| 2467 |
+
"loss": 3.1991,
|
| 2468 |
+
"step": 82000
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 0.35,
|
| 2472 |
+
"learning_rate": 0.0005921137293877644,
|
| 2473 |
+
"loss": 3.2011,
|
| 2474 |
+
"step": 82200
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.35,
|
| 2478 |
+
"learning_rate": 0.0005941009029772594,
|
| 2479 |
+
"loss": 3.1852,
|
| 2480 |
+
"step": 82400
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.35,
|
| 2484 |
+
"learning_rate": 0.00059608677637959,
|
| 2485 |
+
"loss": 3.1911,
|
| 2486 |
+
"step": 82600
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 0.36,
|
| 2490 |
+
"learning_rate": 0.00059807131475028,
|
| 2491 |
+
"loss": 3.1999,
|
| 2492 |
+
"step": 82800
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 0.36,
|
| 2496 |
+
"learning_rate": 0.000600054483268279,
|
| 2497 |
+
"loss": 3.1853,
|
| 2498 |
+
"step": 83000
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 0.36,
|
| 2502 |
+
"learning_rate": 0.0006020362471365711,
|
| 2503 |
+
"loss": 3.1928,
|
| 2504 |
+
"step": 83200
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 0.36,
|
| 2508 |
+
"learning_rate": 0.0006040165715827878,
|
| 2509 |
+
"loss": 3.1833,
|
| 2510 |
+
"step": 83400
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 0.36,
|
| 2514 |
+
"learning_rate": 0.0006059954218598161,
|
| 2515 |
+
"loss": 3.1972,
|
| 2516 |
+
"step": 83600
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.36,
|
| 2520 |
+
"learning_rate": 0.0006079727632464092,
|
| 2521 |
+
"loss": 3.2052,
|
| 2522 |
+
"step": 83800
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.36,
|
| 2526 |
+
"learning_rate": 0.000609948561047796,
|
| 2527 |
+
"loss": 3.1881,
|
| 2528 |
+
"step": 84000
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 0.36,
|
| 2532 |
+
"learning_rate": 0.0006119227805962891,
|
| 2533 |
+
"loss": 3.174,
|
| 2534 |
+
"step": 84200
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 0.36,
|
| 2538 |
+
"learning_rate": 0.0006138953872518932,
|
| 2539 |
+
"loss": 3.1831,
|
| 2540 |
+
"step": 84400
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 0.36,
|
| 2544 |
+
"learning_rate": 0.0006158663464029133,
|
| 2545 |
+
"loss": 3.1961,
|
| 2546 |
+
"step": 84600
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 0.36,
|
| 2550 |
+
"learning_rate": 0.0006178356234665618,
|
| 2551 |
+
"loss": 3.1759,
|
| 2552 |
+
"step": 84800
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 0.37,
|
| 2556 |
+
"learning_rate": 0.0006198031838895652,
|
| 2557 |
+
"loss": 3.1728,
|
| 2558 |
+
"step": 85000
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.37,
|
| 2562 |
+
"learning_rate": 0.0006217689931487707,
|
| 2563 |
+
"loss": 3.194,
|
| 2564 |
+
"step": 85200
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.37,
|
| 2568 |
+
"learning_rate": 0.0006237330167517514,
|
| 2569 |
+
"loss": 3.1747,
|
| 2570 |
+
"step": 85400
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 0.37,
|
| 2574 |
+
"learning_rate": 0.0006256952202374121,
|
| 2575 |
+
"loss": 3.1805,
|
| 2576 |
+
"step": 85600
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 0.37,
|
| 2580 |
+
"learning_rate": 0.0006276555691765935,
|
| 2581 |
+
"loss": 3.1781,
|
| 2582 |
+
"step": 85800
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 0.37,
|
| 2586 |
+
"learning_rate": 0.0006296140291726768,
|
| 2587 |
+
"loss": 3.1829,
|
| 2588 |
+
"step": 86000
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 0.37,
|
| 2592 |
+
"learning_rate": 0.0006315705658621865,
|
| 2593 |
+
"loss": 3.1832,
|
| 2594 |
+
"step": 86200
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 0.37,
|
| 2598 |
+
"learning_rate": 0.0006335251449153937,
|
| 2599 |
+
"loss": 3.1634,
|
| 2600 |
+
"step": 86400
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.37,
|
| 2604 |
+
"learning_rate": 0.0006354777320369192,
|
| 2605 |
+
"loss": 3.1664,
|
| 2606 |
+
"step": 86600
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.37,
|
| 2610 |
+
"learning_rate": 0.0006374282929663341,
|
| 2611 |
+
"loss": 3.1576,
|
| 2612 |
+
"step": 86800
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 0.37,
|
| 2616 |
+
"learning_rate": 0.0006393767934787615,
|
| 2617 |
+
"loss": 3.1667,
|
| 2618 |
+
"step": 87000
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 0.37,
|
| 2622 |
+
"learning_rate": 0.0006413231993854767,
|
| 2623 |
+
"loss": 3.1718,
|
| 2624 |
+
"step": 87200
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 0.38,
|
| 2628 |
+
"learning_rate": 0.0006432674765345077,
|
| 2629 |
+
"loss": 3.1645,
|
| 2630 |
+
"step": 87400
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 0.38,
|
| 2634 |
+
"learning_rate": 0.0006452095908112336,
|
| 2635 |
+
"loss": 3.2063,
|
| 2636 |
+
"step": 87600
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 0.38,
|
| 2640 |
+
"learning_rate": 0.0006471495081389843,
|
| 2641 |
+
"loss": 3.2638,
|
| 2642 |
+
"step": 87800
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.38,
|
| 2646 |
+
"learning_rate": 0.0006490871944796369,
|
| 2647 |
+
"loss": 3.2685,
|
| 2648 |
+
"step": 88000
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.38,
|
| 2652 |
+
"learning_rate": 0.0006510226158342146,
|
| 2653 |
+
"loss": 3.2519,
|
| 2654 |
+
"step": 88200
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 0.38,
|
| 2658 |
+
"learning_rate": 0.0006529557382434818,
|
| 2659 |
+
"loss": 3.2101,
|
| 2660 |
+
"step": 88400
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 0.38,
|
| 2664 |
+
"learning_rate": 0.0006548865277885411,
|
| 2665 |
+
"loss": 3.2109,
|
| 2666 |
+
"step": 88600
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 0.38,
|
| 2670 |
+
"learning_rate": 0.0006568149505914273,
|
| 2671 |
+
"loss": 3.2291,
|
| 2672 |
+
"step": 88800
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 0.38,
|
| 2676 |
+
"learning_rate": 0.0006587409728157031,
|
| 2677 |
+
"loss": 3.2282,
|
| 2678 |
+
"step": 89000
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 0.38,
|
| 2682 |
+
"learning_rate": 0.000660664560667052,
|
| 2683 |
+
"loss": 3.2404,
|
| 2684 |
+
"step": 89200
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.38,
|
| 2688 |
+
"learning_rate": 0.0006625856803938711,
|
| 2689 |
+
"loss": 3.2334,
|
| 2690 |
+
"step": 89400
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.39,
|
| 2694 |
+
"learning_rate": 0.000664504298287864,
|
| 2695 |
+
"loss": 3.243,
|
| 2696 |
+
"step": 89600
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 0.39,
|
| 2700 |
+
"learning_rate": 0.0006664203806846319,
|
| 2701 |
+
"loss": 3.2475,
|
| 2702 |
+
"step": 89800
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 0.39,
|
| 2706 |
+
"learning_rate": 0.0006683338939642638,
|
| 2707 |
+
"loss": 3.3556,
|
| 2708 |
+
"step": 90000
|
| 2709 |
}
|
| 2710 |
],
|
| 2711 |
"max_steps": 500000,
|
| 2712 |
"num_train_epochs": 3,
|
| 2713 |
+
"total_flos": 1.4344469839872e+17,
|
| 2714 |
"trial_name": null,
|
| 2715 |
"trial_params": null
|
| 2716 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:459351fdd706b427a4771aa3d8515e577348d2de84329d8049ae17fe23916e8b
|
| 3 |
size 146774203
|