Training in progress, step 2808, 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 2384234968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:722a15a41fb1cf0c0aed8d758c5e1a337541cfa86629d2c46863528950276e2f
|
| 3 |
size 2384234968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4768663315
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d12628f51c7f4bc8cb3f237b3ca8b7dcf3d7dfee77e7169e602bea9973ebd683
|
| 3 |
size 4768663315
|
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:c29adc3f04b16f4ac7f5b1dc3d9fcb19c78040ad671c4b2bf4a3cc4d244df933
|
| 3 |
size 14645
|
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 sha256:284b167bb422ee615f8e9d8e8547811bfc46bf29da5b79cfc94d4da6720ac4b5
|
| 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": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2458,6 +2458,300 @@
|
|
| 2458 |
"eval_samples_per_second": 30.289,
|
| 2459 |
"eval_steps_per_second": 1.893,
|
| 2460 |
"step": 2500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2461 |
}
|
| 2462 |
],
|
| 2463 |
"logging_steps": 10,
|
|
@@ -2472,12 +2766,12 @@
|
|
| 2472 |
"should_evaluate": false,
|
| 2473 |
"should_log": false,
|
| 2474 |
"should_save": true,
|
| 2475 |
-
"should_training_stop":
|
| 2476 |
},
|
| 2477 |
"attributes": {}
|
| 2478 |
}
|
| 2479 |
},
|
| 2480 |
-
"total_flos":
|
| 2481 |
"train_batch_size": 2,
|
| 2482 |
"trial_name": null,
|
| 2483 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 2808,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2458 |
"eval_samples_per_second": 30.289,
|
| 2459 |
"eval_steps_per_second": 1.893,
|
| 2460 |
"step": 2500
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 2.6818060379374833,
|
| 2464 |
+
"grad_norm": 1.0547696352005005,
|
| 2465 |
+
"learning_rate": 1.183221210922042e-06,
|
| 2466 |
+
"loss": 0.158,
|
| 2467 |
+
"mean_token_accuracy": 0.826284246146679,
|
| 2468 |
+
"num_tokens": 20557824.0,
|
| 2469 |
+
"step": 2510
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 2.6924926529521773,
|
| 2473 |
+
"grad_norm": 1.7910685539245605,
|
| 2474 |
+
"learning_rate": 1.143648595172141e-06,
|
| 2475 |
+
"loss": 0.1559,
|
| 2476 |
+
"mean_token_accuracy": 0.8219667319208384,
|
| 2477 |
+
"num_tokens": 20639744.0,
|
| 2478 |
+
"step": 2520
|
| 2479 |
+
},
|
| 2480 |
+
{
|
| 2481 |
+
"epoch": 2.7031792679668714,
|
| 2482 |
+
"grad_norm": 1.1875276565551758,
|
| 2483 |
+
"learning_rate": 1.10407597942224e-06,
|
| 2484 |
+
"loss": 0.1595,
|
| 2485 |
+
"mean_token_accuracy": 0.8250611502677202,
|
| 2486 |
+
"num_tokens": 20721664.0,
|
| 2487 |
+
"step": 2530
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 2.7138658829815654,
|
| 2491 |
+
"grad_norm": 1.1379560232162476,
|
| 2492 |
+
"learning_rate": 1.064503363672339e-06,
|
| 2493 |
+
"loss": 0.1273,
|
| 2494 |
+
"mean_token_accuracy": 0.8377813111990691,
|
| 2495 |
+
"num_tokens": 20803584.0,
|
| 2496 |
+
"step": 2540
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 2.7245524979962594,
|
| 2500 |
+
"grad_norm": 1.1959253549575806,
|
| 2501 |
+
"learning_rate": 1.024930747922438e-06,
|
| 2502 |
+
"loss": 0.1348,
|
| 2503 |
+
"mean_token_accuracy": 0.832387474551797,
|
| 2504 |
+
"num_tokens": 20885504.0,
|
| 2505 |
+
"step": 2550
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 2.735239113010954,
|
| 2509 |
+
"grad_norm": 1.2150254249572754,
|
| 2510 |
+
"learning_rate": 9.853581321725367e-07,
|
| 2511 |
+
"loss": 0.1551,
|
| 2512 |
+
"mean_token_accuracy": 0.821587573364377,
|
| 2513 |
+
"num_tokens": 20967424.0,
|
| 2514 |
+
"step": 2560
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 2.745925728025648,
|
| 2518 |
+
"grad_norm": 1.5686252117156982,
|
| 2519 |
+
"learning_rate": 9.457855164226357e-07,
|
| 2520 |
+
"loss": 0.1461,
|
| 2521 |
+
"mean_token_accuracy": 0.8346624251455068,
|
| 2522 |
+
"num_tokens": 21049344.0,
|
| 2523 |
+
"step": 2570
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 2.756612343040342,
|
| 2527 |
+
"grad_norm": 1.5219730138778687,
|
| 2528 |
+
"learning_rate": 9.062129006727345e-07,
|
| 2529 |
+
"loss": 0.1545,
|
| 2530 |
+
"mean_token_accuracy": 0.8117783740162849,
|
| 2531 |
+
"num_tokens": 21131264.0,
|
| 2532 |
+
"step": 2580
|
| 2533 |
+
},
|
| 2534 |
+
{
|
| 2535 |
+
"epoch": 2.767298958055036,
|
| 2536 |
+
"grad_norm": 1.216352939605713,
|
| 2537 |
+
"learning_rate": 8.666402849228335e-07,
|
| 2538 |
+
"loss": 0.1249,
|
| 2539 |
+
"mean_token_accuracy": 0.831531309708953,
|
| 2540 |
+
"num_tokens": 21213184.0,
|
| 2541 |
+
"step": 2590
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 2.77798557306973,
|
| 2545 |
+
"grad_norm": 0.99131840467453,
|
| 2546 |
+
"learning_rate": 8.270676691729324e-07,
|
| 2547 |
+
"loss": 0.1551,
|
| 2548 |
+
"step": 2600
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"epoch": 2.77798557306973,
|
| 2552 |
+
"eval_loss": 0.35856378078460693,
|
| 2553 |
+
"eval_mean_token_accuracy": 0.9245799160920657,
|
| 2554 |
+
"eval_num_tokens": 21295104.0,
|
| 2555 |
+
"eval_runtime": 54.645,
|
| 2556 |
+
"eval_samples_per_second": 30.451,
|
| 2557 |
+
"eval_steps_per_second": 1.903,
|
| 2558 |
+
"step": 2600
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 2.7886721880844245,
|
| 2562 |
+
"grad_norm": 1.2371041774749756,
|
| 2563 |
+
"learning_rate": 7.874950534230314e-07,
|
| 2564 |
+
"loss": 0.155,
|
| 2565 |
+
"mean_token_accuracy": 0.8295437873341143,
|
| 2566 |
+
"num_tokens": 21377024.0,
|
| 2567 |
+
"step": 2610
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 2.7993588030991186,
|
| 2571 |
+
"grad_norm": 1.222365140914917,
|
| 2572 |
+
"learning_rate": 7.479224376731302e-07,
|
| 2573 |
+
"loss": 0.1379,
|
| 2574 |
+
"mean_token_accuracy": 0.8334271032363176,
|
| 2575 |
+
"num_tokens": 21458944.0,
|
| 2576 |
+
"step": 2620
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 2.8100454181138126,
|
| 2580 |
+
"grad_norm": 1.0691900253295898,
|
| 2581 |
+
"learning_rate": 7.083498219232292e-07,
|
| 2582 |
+
"loss": 0.1298,
|
| 2583 |
+
"mean_token_accuracy": 0.8295743606984616,
|
| 2584 |
+
"num_tokens": 21540864.0,
|
| 2585 |
+
"step": 2630
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 2.8207320331285066,
|
| 2589 |
+
"grad_norm": 1.298315167427063,
|
| 2590 |
+
"learning_rate": 6.687772061733282e-07,
|
| 2591 |
+
"loss": 0.1742,
|
| 2592 |
+
"mean_token_accuracy": 0.8030210331082344,
|
| 2593 |
+
"num_tokens": 21622784.0,
|
| 2594 |
+
"step": 2640
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 2.8314186481432007,
|
| 2598 |
+
"grad_norm": 1.385136604309082,
|
| 2599 |
+
"learning_rate": 6.29204590423427e-07,
|
| 2600 |
+
"loss": 0.1365,
|
| 2601 |
+
"mean_token_accuracy": 0.8225048929452896,
|
| 2602 |
+
"num_tokens": 21704704.0,
|
| 2603 |
+
"step": 2650
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 2.8421052631578947,
|
| 2607 |
+
"grad_norm": 1.5449044704437256,
|
| 2608 |
+
"learning_rate": 5.89631974673526e-07,
|
| 2609 |
+
"loss": 0.1761,
|
| 2610 |
+
"mean_token_accuracy": 0.8003669247031212,
|
| 2611 |
+
"num_tokens": 21786624.0,
|
| 2612 |
+
"step": 2660
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 2.8527918781725887,
|
| 2616 |
+
"grad_norm": 1.9411510229110718,
|
| 2617 |
+
"learning_rate": 5.500593589236249e-07,
|
| 2618 |
+
"loss": 0.1482,
|
| 2619 |
+
"mean_token_accuracy": 0.8060420740395784,
|
| 2620 |
+
"num_tokens": 21868544.0,
|
| 2621 |
+
"step": 2670
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 2.8634784931872828,
|
| 2625 |
+
"grad_norm": 1.0051461458206177,
|
| 2626 |
+
"learning_rate": 5.104867431737238e-07,
|
| 2627 |
+
"loss": 0.1443,
|
| 2628 |
+
"mean_token_accuracy": 0.8296232867985964,
|
| 2629 |
+
"num_tokens": 21950464.0,
|
| 2630 |
+
"step": 2680
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 2.874165108201977,
|
| 2634 |
+
"grad_norm": 1.6511443853378296,
|
| 2635 |
+
"learning_rate": 4.7091412742382274e-07,
|
| 2636 |
+
"loss": 0.1427,
|
| 2637 |
+
"mean_token_accuracy": 0.829244127869606,
|
| 2638 |
+
"num_tokens": 22032384.0,
|
| 2639 |
+
"step": 2690
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 2.8848517232166713,
|
| 2643 |
+
"grad_norm": 0.8944096565246582,
|
| 2644 |
+
"learning_rate": 4.3134151167392167e-07,
|
| 2645 |
+
"loss": 0.1335,
|
| 2646 |
+
"step": 2700
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 2.8848517232166713,
|
| 2650 |
+
"eval_loss": 0.35777753591537476,
|
| 2651 |
+
"eval_mean_token_accuracy": 0.9246739997313573,
|
| 2652 |
+
"eval_num_tokens": 22114304.0,
|
| 2653 |
+
"eval_runtime": 55.0863,
|
| 2654 |
+
"eval_samples_per_second": 30.207,
|
| 2655 |
+
"eval_steps_per_second": 1.888,
|
| 2656 |
+
"step": 2700
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 2.8955383382313653,
|
| 2660 |
+
"grad_norm": 1.2431285381317139,
|
| 2661 |
+
"learning_rate": 3.917688959240206e-07,
|
| 2662 |
+
"loss": 0.1319,
|
| 2663 |
+
"mean_token_accuracy": 0.8427042558789253,
|
| 2664 |
+
"num_tokens": 22196224.0,
|
| 2665 |
+
"step": 2710
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 2.9062249532460593,
|
| 2669 |
+
"grad_norm": 1.1439481973648071,
|
| 2670 |
+
"learning_rate": 3.5219628017411953e-07,
|
| 2671 |
+
"loss": 0.1556,
|
| 2672 |
+
"mean_token_accuracy": 0.82298189625144,
|
| 2673 |
+
"num_tokens": 22278144.0,
|
| 2674 |
+
"step": 2720
|
| 2675 |
+
},
|
| 2676 |
+
{
|
| 2677 |
+
"epoch": 2.9169115682607534,
|
| 2678 |
+
"grad_norm": 1.1549094915390015,
|
| 2679 |
+
"learning_rate": 3.1262366442421846e-07,
|
| 2680 |
+
"loss": 0.1336,
|
| 2681 |
+
"mean_token_accuracy": 0.8487646751105785,
|
| 2682 |
+
"num_tokens": 22360064.0,
|
| 2683 |
+
"step": 2730
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 2.9275981832754474,
|
| 2687 |
+
"grad_norm": 1.5530976057052612,
|
| 2688 |
+
"learning_rate": 2.730510486743174e-07,
|
| 2689 |
+
"loss": 0.1643,
|
| 2690 |
+
"mean_token_accuracy": 0.8154109574854373,
|
| 2691 |
+
"num_tokens": 22441984.0,
|
| 2692 |
+
"step": 2740
|
| 2693 |
+
},
|
| 2694 |
+
{
|
| 2695 |
+
"epoch": 2.9382847982901414,
|
| 2696 |
+
"grad_norm": 1.057889699935913,
|
| 2697 |
+
"learning_rate": 2.3347843292441632e-07,
|
| 2698 |
+
"loss": 0.1249,
|
| 2699 |
+
"mean_token_accuracy": 0.8479207433760166,
|
| 2700 |
+
"num_tokens": 22523904.0,
|
| 2701 |
+
"step": 2750
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 2.948971413304836,
|
| 2705 |
+
"grad_norm": 1.149165153503418,
|
| 2706 |
+
"learning_rate": 1.9390581717451524e-07,
|
| 2707 |
+
"loss": 0.1343,
|
| 2708 |
+
"mean_token_accuracy": 0.8305650681257248,
|
| 2709 |
+
"num_tokens": 22605824.0,
|
| 2710 |
+
"step": 2760
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 2.95965802831953,
|
| 2714 |
+
"grad_norm": 1.325223684310913,
|
| 2715 |
+
"learning_rate": 1.5433320142461417e-07,
|
| 2716 |
+
"loss": 0.1251,
|
| 2717 |
+
"mean_token_accuracy": 0.8496453046798706,
|
| 2718 |
+
"num_tokens": 22687744.0,
|
| 2719 |
+
"step": 2770
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 2.970344643334224,
|
| 2723 |
+
"grad_norm": 1.2108739614486694,
|
| 2724 |
+
"learning_rate": 1.1476058567471311e-07,
|
| 2725 |
+
"loss": 0.14,
|
| 2726 |
+
"mean_token_accuracy": 0.8448997050523758,
|
| 2727 |
+
"num_tokens": 22769664.0,
|
| 2728 |
+
"step": 2780
|
| 2729 |
+
},
|
| 2730 |
+
{
|
| 2731 |
+
"epoch": 2.981031258348918,
|
| 2732 |
+
"grad_norm": 1.3373411893844604,
|
| 2733 |
+
"learning_rate": 7.518796992481203e-08,
|
| 2734 |
+
"loss": 0.1486,
|
| 2735 |
+
"mean_token_accuracy": 0.8307362981140614,
|
| 2736 |
+
"num_tokens": 22851584.0,
|
| 2737 |
+
"step": 2790
|
| 2738 |
+
},
|
| 2739 |
+
{
|
| 2740 |
+
"epoch": 2.991717873363612,
|
| 2741 |
+
"grad_norm": 1.7406622171401978,
|
| 2742 |
+
"learning_rate": 3.5615354174910966e-08,
|
| 2743 |
+
"loss": 0.1905,
|
| 2744 |
+
"step": 2800
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"epoch": 2.991717873363612,
|
| 2748 |
+
"eval_loss": 0.3580096960067749,
|
| 2749 |
+
"eval_mean_token_accuracy": 0.924671647640375,
|
| 2750 |
+
"eval_num_tokens": 22933504.0,
|
| 2751 |
+
"eval_runtime": 54.8159,
|
| 2752 |
+
"eval_samples_per_second": 30.356,
|
| 2753 |
+
"eval_steps_per_second": 1.897,
|
| 2754 |
+
"step": 2800
|
| 2755 |
}
|
| 2756 |
],
|
| 2757 |
"logging_steps": 10,
|
|
|
|
| 2766 |
"should_evaluate": false,
|
| 2767 |
"should_log": false,
|
| 2768 |
"should_save": true,
|
| 2769 |
+
"should_training_stop": true
|
| 2770 |
},
|
| 2771 |
"attributes": {}
|
| 2772 |
}
|
| 2773 |
},
|
| 2774 |
+
"total_flos": 6.077655937135411e+16,
|
| 2775 |
"train_batch_size": 2,
|
| 2776 |
"trial_name": null,
|
| 2777 |
"trial_params": null
|