Training in progress, step 4000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4523108832
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a10e10938ea6d53da3125e0f624b08ad1b09594c0419dfa07b7f2648579c958c
|
| 3 |
size 4523108832
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2912179275
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e1e5c56292a748b8b72632445cb4efc13d1068197c8852fc07c234fe4f81fb3
|
| 3 |
size 2912179275
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4801416a03beb0f63c300670679d3fb6cca48da8259362e9be9e6ffae0c5ffd0
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:603734df5c0a090a9f670fec916099f7dc5c53069330e2b824b964daab27b613
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2458,6 +2458,356 @@
|
|
| 2458 |
"learning_rate": 0.00013002,
|
| 2459 |
"loss": 0.06365590691566467,
|
| 2460 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2461 |
}
|
| 2462 |
],
|
| 2463 |
"logging_steps": 10,
|
|
@@ -2477,7 +2827,7 @@
|
|
| 2477 |
"attributes": {}
|
| 2478 |
}
|
| 2479 |
},
|
| 2480 |
-
"total_flos":
|
| 2481 |
"train_batch_size": 1,
|
| 2482 |
"trial_name": null,
|
| 2483 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.0128,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2458 |
"learning_rate": 0.00013002,
|
| 2459 |
"loss": 0.06365590691566467,
|
| 2460 |
"step": 3500
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 5.0262,
|
| 2464 |
+
"grad_norm": 0.2963351309299469,
|
| 2465 |
+
"learning_rate": 0.00012982,
|
| 2466 |
+
"loss": 0.06292765736579894,
|
| 2467 |
+
"step": 3510
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 5.0272,
|
| 2471 |
+
"grad_norm": 0.24942268431186676,
|
| 2472 |
+
"learning_rate": 0.00012962,
|
| 2473 |
+
"loss": 0.061947989463806155,
|
| 2474 |
+
"step": 3520
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 5.0282,
|
| 2478 |
+
"grad_norm": 0.31199055910110474,
|
| 2479 |
+
"learning_rate": 0.00012942000000000002,
|
| 2480 |
+
"loss": 0.06328007578849792,
|
| 2481 |
+
"step": 3530
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 5.0292,
|
| 2485 |
+
"grad_norm": 0.2745618522167206,
|
| 2486 |
+
"learning_rate": 0.00012922,
|
| 2487 |
+
"loss": 0.0613422691822052,
|
| 2488 |
+
"step": 3540
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 5.0302,
|
| 2492 |
+
"grad_norm": 0.3146347999572754,
|
| 2493 |
+
"learning_rate": 0.00012902,
|
| 2494 |
+
"loss": 0.05851168036460876,
|
| 2495 |
+
"step": 3550
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 5.0312,
|
| 2499 |
+
"grad_norm": 0.27351754903793335,
|
| 2500 |
+
"learning_rate": 0.00012882,
|
| 2501 |
+
"loss": 0.0684496819972992,
|
| 2502 |
+
"step": 3560
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 6.001,
|
| 2506 |
+
"grad_norm": 0.2317938506603241,
|
| 2507 |
+
"learning_rate": 0.00012862,
|
| 2508 |
+
"loss": 0.06254401206970214,
|
| 2509 |
+
"step": 3570
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 6.002,
|
| 2513 |
+
"grad_norm": 0.24452786147594452,
|
| 2514 |
+
"learning_rate": 0.00012842,
|
| 2515 |
+
"loss": 0.053379553556442264,
|
| 2516 |
+
"step": 3580
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 6.003,
|
| 2520 |
+
"grad_norm": 0.2590080201625824,
|
| 2521 |
+
"learning_rate": 0.00012822000000000002,
|
| 2522 |
+
"loss": 0.052920466661453246,
|
| 2523 |
+
"step": 3590
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 6.004,
|
| 2527 |
+
"grad_norm": 0.2468854933977127,
|
| 2528 |
+
"learning_rate": 0.00012802,
|
| 2529 |
+
"loss": 0.0584908664226532,
|
| 2530 |
+
"step": 3600
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 6.005,
|
| 2534 |
+
"grad_norm": 0.24238893389701843,
|
| 2535 |
+
"learning_rate": 0.00012782,
|
| 2536 |
+
"loss": 0.05077446103096008,
|
| 2537 |
+
"step": 3610
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 6.006,
|
| 2541 |
+
"grad_norm": 0.21615304052829742,
|
| 2542 |
+
"learning_rate": 0.00012762,
|
| 2543 |
+
"loss": 0.047195515036582945,
|
| 2544 |
+
"step": 3620
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 6.007,
|
| 2548 |
+
"grad_norm": 0.2538570761680603,
|
| 2549 |
+
"learning_rate": 0.00012742,
|
| 2550 |
+
"loss": 0.05251326560974121,
|
| 2551 |
+
"step": 3630
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 6.008,
|
| 2555 |
+
"grad_norm": 0.21952210366725922,
|
| 2556 |
+
"learning_rate": 0.00012722000000000002,
|
| 2557 |
+
"loss": 0.04804377257823944,
|
| 2558 |
+
"step": 3640
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 6.009,
|
| 2562 |
+
"grad_norm": 0.2638396620750427,
|
| 2563 |
+
"learning_rate": 0.00012702000000000001,
|
| 2564 |
+
"loss": 0.05005112886428833,
|
| 2565 |
+
"step": 3650
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 6.01,
|
| 2569 |
+
"grad_norm": 0.2512870728969574,
|
| 2570 |
+
"learning_rate": 0.00012682,
|
| 2571 |
+
"loss": 0.05190543532371521,
|
| 2572 |
+
"step": 3660
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 6.011,
|
| 2576 |
+
"grad_norm": 0.26794344186782837,
|
| 2577 |
+
"learning_rate": 0.00012662,
|
| 2578 |
+
"loss": 0.05652360320091247,
|
| 2579 |
+
"step": 3670
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 6.012,
|
| 2583 |
+
"grad_norm": 0.24694757163524628,
|
| 2584 |
+
"learning_rate": 0.00012642,
|
| 2585 |
+
"loss": 0.05183016061782837,
|
| 2586 |
+
"step": 3680
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 6.013,
|
| 2590 |
+
"grad_norm": 0.27098706364631653,
|
| 2591 |
+
"learning_rate": 0.00012622,
|
| 2592 |
+
"loss": 0.05123690366744995,
|
| 2593 |
+
"step": 3690
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 6.014,
|
| 2597 |
+
"grad_norm": 0.23455461859703064,
|
| 2598 |
+
"learning_rate": 0.00012602000000000002,
|
| 2599 |
+
"loss": 0.05616133213043213,
|
| 2600 |
+
"step": 3700
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 6.015,
|
| 2604 |
+
"grad_norm": 0.23430338501930237,
|
| 2605 |
+
"learning_rate": 0.00012582,
|
| 2606 |
+
"loss": 0.05355681180953979,
|
| 2607 |
+
"step": 3710
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 6.016,
|
| 2611 |
+
"grad_norm": 0.23048514127731323,
|
| 2612 |
+
"learning_rate": 0.00012562,
|
| 2613 |
+
"loss": 0.11050782203674317,
|
| 2614 |
+
"step": 3720
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 6.017,
|
| 2618 |
+
"grad_norm": 0.2567964494228363,
|
| 2619 |
+
"learning_rate": 0.00012542,
|
| 2620 |
+
"loss": 0.05631558299064636,
|
| 2621 |
+
"step": 3730
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 6.018,
|
| 2625 |
+
"grad_norm": 0.3105704188346863,
|
| 2626 |
+
"learning_rate": 0.00012522,
|
| 2627 |
+
"loss": 0.05600916147232056,
|
| 2628 |
+
"step": 3740
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 6.019,
|
| 2632 |
+
"grad_norm": 0.25742048025131226,
|
| 2633 |
+
"learning_rate": 0.00012502,
|
| 2634 |
+
"loss": 0.0482271134853363,
|
| 2635 |
+
"step": 3750
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 6.02,
|
| 2639 |
+
"grad_norm": 0.2826644480228424,
|
| 2640 |
+
"learning_rate": 0.00012482000000000001,
|
| 2641 |
+
"loss": 0.050260508060455324,
|
| 2642 |
+
"step": 3760
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 6.021,
|
| 2646 |
+
"grad_norm": 0.2458411604166031,
|
| 2647 |
+
"learning_rate": 0.00012462,
|
| 2648 |
+
"loss": 0.05451898574829102,
|
| 2649 |
+
"step": 3770
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 6.022,
|
| 2653 |
+
"grad_norm": 0.26720693707466125,
|
| 2654 |
+
"learning_rate": 0.00012442,
|
| 2655 |
+
"loss": 0.05155031681060791,
|
| 2656 |
+
"step": 3780
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 6.023,
|
| 2660 |
+
"grad_norm": 0.24704712629318237,
|
| 2661 |
+
"learning_rate": 0.00012422,
|
| 2662 |
+
"loss": 0.06429644227027893,
|
| 2663 |
+
"step": 3790
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 6.024,
|
| 2667 |
+
"grad_norm": 0.23193997144699097,
|
| 2668 |
+
"learning_rate": 0.00012402,
|
| 2669 |
+
"loss": 0.051171398162841795,
|
| 2670 |
+
"step": 3800
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 6.025,
|
| 2674 |
+
"grad_norm": 0.2553248405456543,
|
| 2675 |
+
"learning_rate": 0.00012382,
|
| 2676 |
+
"loss": 0.04670791625976563,
|
| 2677 |
+
"step": 3810
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 6.026,
|
| 2681 |
+
"grad_norm": 0.22213296592235565,
|
| 2682 |
+
"learning_rate": 0.00012362,
|
| 2683 |
+
"loss": 0.04988162517547608,
|
| 2684 |
+
"step": 3820
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 6.027,
|
| 2688 |
+
"grad_norm": 0.288107305765152,
|
| 2689 |
+
"learning_rate": 0.00012342,
|
| 2690 |
+
"loss": 0.04665826857089996,
|
| 2691 |
+
"step": 3830
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 6.028,
|
| 2695 |
+
"grad_norm": 0.21731558442115784,
|
| 2696 |
+
"learning_rate": 0.00012322,
|
| 2697 |
+
"loss": 0.04808914065361023,
|
| 2698 |
+
"step": 3840
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 6.029,
|
| 2702 |
+
"grad_norm": 0.22236528992652893,
|
| 2703 |
+
"learning_rate": 0.00012302,
|
| 2704 |
+
"loss": 0.04851194024085999,
|
| 2705 |
+
"step": 3850
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 6.03,
|
| 2709 |
+
"grad_norm": 0.23472720384597778,
|
| 2710 |
+
"learning_rate": 0.00012282,
|
| 2711 |
+
"loss": 0.04830377697944641,
|
| 2712 |
+
"step": 3860
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 6.031,
|
| 2716 |
+
"grad_norm": 0.2267661690711975,
|
| 2717 |
+
"learning_rate": 0.00012262,
|
| 2718 |
+
"loss": 0.050290358066558835,
|
| 2719 |
+
"step": 3870
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 7.0008,
|
| 2723 |
+
"grad_norm": 0.24839870631694794,
|
| 2724 |
+
"learning_rate": 0.00012242,
|
| 2725 |
+
"loss": 0.051380503177642825,
|
| 2726 |
+
"step": 3880
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 7.0018,
|
| 2730 |
+
"grad_norm": 0.21834354102611542,
|
| 2731 |
+
"learning_rate": 0.00012222,
|
| 2732 |
+
"loss": 0.04199742078781128,
|
| 2733 |
+
"step": 3890
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 7.0028,
|
| 2737 |
+
"grad_norm": 0.22921745479106903,
|
| 2738 |
+
"learning_rate": 0.00012202,
|
| 2739 |
+
"loss": 0.04476028978824616,
|
| 2740 |
+
"step": 3900
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 7.0038,
|
| 2744 |
+
"grad_norm": 0.2517320215702057,
|
| 2745 |
+
"learning_rate": 0.00012182,
|
| 2746 |
+
"loss": 0.04470941722393036,
|
| 2747 |
+
"step": 3910
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 7.0048,
|
| 2751 |
+
"grad_norm": 0.23211771249771118,
|
| 2752 |
+
"learning_rate": 0.00012162,
|
| 2753 |
+
"loss": 0.04450752139091492,
|
| 2754 |
+
"step": 3920
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 7.0058,
|
| 2758 |
+
"grad_norm": 0.21550092101097107,
|
| 2759 |
+
"learning_rate": 0.00012142,
|
| 2760 |
+
"loss": 0.03875753879547119,
|
| 2761 |
+
"step": 3930
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 7.0068,
|
| 2765 |
+
"grad_norm": 0.25320014357566833,
|
| 2766 |
+
"learning_rate": 0.00012122,
|
| 2767 |
+
"loss": 0.04415590167045593,
|
| 2768 |
+
"step": 3940
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 7.0078,
|
| 2772 |
+
"grad_norm": 0.19818426668643951,
|
| 2773 |
+
"learning_rate": 0.00012102,
|
| 2774 |
+
"loss": 0.04161977171897888,
|
| 2775 |
+
"step": 3950
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 7.0088,
|
| 2779 |
+
"grad_norm": 0.20641763508319855,
|
| 2780 |
+
"learning_rate": 0.00012082,
|
| 2781 |
+
"loss": 0.04034121632575989,
|
| 2782 |
+
"step": 3960
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 7.0098,
|
| 2786 |
+
"grad_norm": 0.19377565383911133,
|
| 2787 |
+
"learning_rate": 0.00012062,
|
| 2788 |
+
"loss": 0.04172587096691131,
|
| 2789 |
+
"step": 3970
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 7.0108,
|
| 2793 |
+
"grad_norm": 0.18526528775691986,
|
| 2794 |
+
"learning_rate": 0.00012042,
|
| 2795 |
+
"loss": 0.04182737171649933,
|
| 2796 |
+
"step": 3980
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 7.0118,
|
| 2800 |
+
"grad_norm": 0.2163708209991455,
|
| 2801 |
+
"learning_rate": 0.00012022,
|
| 2802 |
+
"loss": 0.042621687054634094,
|
| 2803 |
+
"step": 3990
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 7.0128,
|
| 2807 |
+
"grad_norm": 0.19984810054302216,
|
| 2808 |
+
"learning_rate": 0.00012001999999999999,
|
| 2809 |
+
"loss": 0.04216248393058777,
|
| 2810 |
+
"step": 4000
|
| 2811 |
}
|
| 2812 |
],
|
| 2813 |
"logging_steps": 10,
|
|
|
|
| 2827 |
"attributes": {}
|
| 2828 |
}
|
| 2829 |
},
|
| 2830 |
+
"total_flos": 3.385768491215585e+17,
|
| 2831 |
"train_batch_size": 1,
|
| 2832 |
"trial_name": null,
|
| 2833 |
"trial_params": null
|