Training in progress, step 400, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 323014168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78753ab537273541f6cd45d76e5c1871d220cbd5009e6b6482631c3c20a93b0b
|
| 3 |
size 323014168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 164465012
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5d1a9cd9ded4881a65505bdf5c118594bd0f7af5436648ab7f5f7c4a3fd4217
|
| 3 |
size 164465012
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37553bbc12e5a59786b13569ace17196557ba6326aba9cbcada11c4ecab2bcdf
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acaca55091cad13358c11632689bee2ba722202048435717d3d6f988abffbf55
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -2521,6 +2521,364 @@
|
|
| 2521 |
"eval_samples_per_second": 2.943,
|
| 2522 |
"eval_steps_per_second": 2.943,
|
| 2523 |
"step": 350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2524 |
}
|
| 2525 |
],
|
| 2526 |
"logging_steps": 1,
|
|
@@ -2535,7 +2893,7 @@
|
|
| 2535 |
"early_stopping_threshold": 0.0
|
| 2536 |
},
|
| 2537 |
"attributes": {
|
| 2538 |
-
"early_stopping_patience_counter":
|
| 2539 |
}
|
| 2540 |
},
|
| 2541 |
"TrainerControl": {
|
|
@@ -2549,7 +2907,7 @@
|
|
| 2549 |
"attributes": {}
|
| 2550 |
}
|
| 2551 |
},
|
| 2552 |
-
"total_flos": 2.
|
| 2553 |
"train_batch_size": 1,
|
| 2554 |
"trial_name": null,
|
| 2555 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.3837679922580719,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-400",
|
| 4 |
+
"epoch": 0.6789730532569489,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2521 |
"eval_samples_per_second": 2.943,
|
| 2522 |
"eval_steps_per_second": 2.943,
|
| 2523 |
"step": 350
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.5957988542329726,
|
| 2527 |
+
"grad_norm": 0.4255245625972748,
|
| 2528 |
+
"learning_rate": 0.00022042073441788358,
|
| 2529 |
+
"loss": 1.1602,
|
| 2530 |
+
"step": 351
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.597496286866115,
|
| 2534 |
+
"grad_norm": 1.3056901693344116,
|
| 2535 |
+
"learning_rate": 0.00022000009848385105,
|
| 2536 |
+
"loss": 0.9796,
|
| 2537 |
+
"step": 352
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.5991937194992574,
|
| 2541 |
+
"grad_norm": 0.21184608340263367,
|
| 2542 |
+
"learning_rate": 0.0002195787576496039,
|
| 2543 |
+
"loss": 0.6262,
|
| 2544 |
+
"step": 353
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.6008911521323997,
|
| 2548 |
+
"grad_norm": 0.24157075583934784,
|
| 2549 |
+
"learning_rate": 0.00021915671615803966,
|
| 2550 |
+
"loss": 0.8544,
|
| 2551 |
+
"step": 354
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.6025885847655421,
|
| 2555 |
+
"grad_norm": 0.20036348700523376,
|
| 2556 |
+
"learning_rate": 0.00021873397825911153,
|
| 2557 |
+
"loss": 0.6267,
|
| 2558 |
+
"step": 355
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.6042860173986845,
|
| 2562 |
+
"grad_norm": 0.20190277695655823,
|
| 2563 |
+
"learning_rate": 0.00021831054820978544,
|
| 2564 |
+
"loss": 0.6421,
|
| 2565 |
+
"step": 356
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.6059834500318269,
|
| 2569 |
+
"grad_norm": 0.2218364179134369,
|
| 2570 |
+
"learning_rate": 0.00021788643027399724,
|
| 2571 |
+
"loss": 0.7318,
|
| 2572 |
+
"step": 357
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.6076808826649692,
|
| 2576 |
+
"grad_norm": 0.2376060038805008,
|
| 2577 |
+
"learning_rate": 0.00021746162872260985,
|
| 2578 |
+
"loss": 0.8077,
|
| 2579 |
+
"step": 358
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.6093783152981116,
|
| 2583 |
+
"grad_norm": 0.19997930526733398,
|
| 2584 |
+
"learning_rate": 0.0002170361478333702,
|
| 2585 |
+
"loss": 0.6109,
|
| 2586 |
+
"step": 359
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.611075747931254,
|
| 2590 |
+
"grad_norm": 0.25473812222480774,
|
| 2591 |
+
"learning_rate": 0.0002166099918908661,
|
| 2592 |
+
"loss": 0.7628,
|
| 2593 |
+
"step": 360
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.6127731805643963,
|
| 2597 |
+
"grad_norm": 0.16967284679412842,
|
| 2598 |
+
"learning_rate": 0.00021618316518648317,
|
| 2599 |
+
"loss": 0.3639,
|
| 2600 |
+
"step": 361
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.6144706131975387,
|
| 2604 |
+
"grad_norm": 0.2045927196741104,
|
| 2605 |
+
"learning_rate": 0.0002157556720183616,
|
| 2606 |
+
"loss": 0.5688,
|
| 2607 |
+
"step": 362
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.6161680458306811,
|
| 2611 |
+
"grad_norm": 0.30063769221305847,
|
| 2612 |
+
"learning_rate": 0.00021532751669135284,
|
| 2613 |
+
"loss": 0.8787,
|
| 2614 |
+
"step": 363
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.6178654784638234,
|
| 2618 |
+
"grad_norm": 0.22912342846393585,
|
| 2619 |
+
"learning_rate": 0.00021489870351697622,
|
| 2620 |
+
"loss": 0.5724,
|
| 2621 |
+
"step": 364
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.6195629110969658,
|
| 2625 |
+
"grad_norm": 0.1712283343076706,
|
| 2626 |
+
"learning_rate": 0.00021446923681337575,
|
| 2627 |
+
"loss": 0.3771,
|
| 2628 |
+
"step": 365
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.6212603437301082,
|
| 2632 |
+
"grad_norm": 0.22983159124851227,
|
| 2633 |
+
"learning_rate": 0.00021403912090527623,
|
| 2634 |
+
"loss": 0.6274,
|
| 2635 |
+
"step": 366
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.6229577763632506,
|
| 2639 |
+
"grad_norm": 0.2075144350528717,
|
| 2640 |
+
"learning_rate": 0.00021360836012394025,
|
| 2641 |
+
"loss": 0.5276,
|
| 2642 |
+
"step": 367
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.6246552089963929,
|
| 2646 |
+
"grad_norm": 0.1731417328119278,
|
| 2647 |
+
"learning_rate": 0.00021317695880712398,
|
| 2648 |
+
"loss": 0.314,
|
| 2649 |
+
"step": 368
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.6263526416295353,
|
| 2653 |
+
"grad_norm": 0.1949385702610016,
|
| 2654 |
+
"learning_rate": 0.0002127449212990339,
|
| 2655 |
+
"loss": 0.4633,
|
| 2656 |
+
"step": 369
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.6280500742626777,
|
| 2660 |
+
"grad_norm": 0.20679379999637604,
|
| 2661 |
+
"learning_rate": 0.00021231225195028297,
|
| 2662 |
+
"loss": 0.4547,
|
| 2663 |
+
"step": 370
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.62974750689582,
|
| 2667 |
+
"grad_norm": 0.1853644698858261,
|
| 2668 |
+
"learning_rate": 0.00021187895511784666,
|
| 2669 |
+
"loss": 0.3758,
|
| 2670 |
+
"step": 371
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.6314449395289624,
|
| 2674 |
+
"grad_norm": 0.2339005470275879,
|
| 2675 |
+
"learning_rate": 0.00021144503516501927,
|
| 2676 |
+
"loss": 0.4251,
|
| 2677 |
+
"step": 372
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.6331423721621048,
|
| 2681 |
+
"grad_norm": 0.12531976401805878,
|
| 2682 |
+
"learning_rate": 0.00021101049646137003,
|
| 2683 |
+
"loss": 0.1716,
|
| 2684 |
+
"step": 373
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.6348398047952472,
|
| 2688 |
+
"grad_norm": 0.12999360263347626,
|
| 2689 |
+
"learning_rate": 0.00021057534338269872,
|
| 2690 |
+
"loss": 0.2032,
|
| 2691 |
+
"step": 374
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.6365372374283895,
|
| 2695 |
+
"grad_norm": 0.1318761557340622,
|
| 2696 |
+
"learning_rate": 0.00021013958031099205,
|
| 2697 |
+
"loss": 0.1968,
|
| 2698 |
+
"step": 375
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.6382346700615319,
|
| 2702 |
+
"grad_norm": 0.06346186250448227,
|
| 2703 |
+
"learning_rate": 0.00020970321163437934,
|
| 2704 |
+
"loss": 0.05,
|
| 2705 |
+
"step": 376
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.6399321026946743,
|
| 2709 |
+
"grad_norm": 0.12222940474748611,
|
| 2710 |
+
"learning_rate": 0.00020926624174708827,
|
| 2711 |
+
"loss": 0.1675,
|
| 2712 |
+
"step": 377
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.6416295353278166,
|
| 2716 |
+
"grad_norm": 0.12370602786540985,
|
| 2717 |
+
"learning_rate": 0.0002088286750494008,
|
| 2718 |
+
"loss": 0.0724,
|
| 2719 |
+
"step": 378
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.643326967960959,
|
| 2723 |
+
"grad_norm": 0.0037796611431986094,
|
| 2724 |
+
"learning_rate": 0.00020839051594760872,
|
| 2725 |
+
"loss": 0.0002,
|
| 2726 |
+
"step": 379
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.6450244005941014,
|
| 2730 |
+
"grad_norm": 0.08905645459890366,
|
| 2731 |
+
"learning_rate": 0.00020795176885396926,
|
| 2732 |
+
"loss": 0.0305,
|
| 2733 |
+
"step": 380
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.6467218332272437,
|
| 2737 |
+
"grad_norm": 0.11877533793449402,
|
| 2738 |
+
"learning_rate": 0.00020751243818666087,
|
| 2739 |
+
"loss": 0.1818,
|
| 2740 |
+
"step": 381
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.6484192658603861,
|
| 2744 |
+
"grad_norm": 0.0044077117927372456,
|
| 2745 |
+
"learning_rate": 0.00020707252836973844,
|
| 2746 |
+
"loss": 0.0001,
|
| 2747 |
+
"step": 382
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.6501166984935285,
|
| 2751 |
+
"grad_norm": 0.0014336027670651674,
|
| 2752 |
+
"learning_rate": 0.00020663204383308898,
|
| 2753 |
+
"loss": 0.0001,
|
| 2754 |
+
"step": 383
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.6518141311266709,
|
| 2758 |
+
"grad_norm": 0.025872627273201942,
|
| 2759 |
+
"learning_rate": 0.0002061909890123868,
|
| 2760 |
+
"loss": 0.0031,
|
| 2761 |
+
"step": 384
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.6535115637598132,
|
| 2765 |
+
"grad_norm": 0.007007645908743143,
|
| 2766 |
+
"learning_rate": 0.0002057493683490491,
|
| 2767 |
+
"loss": 0.0002,
|
| 2768 |
+
"step": 385
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.6552089963929556,
|
| 2772 |
+
"grad_norm": 0.01107161957770586,
|
| 2773 |
+
"learning_rate": 0.0002053071862901911,
|
| 2774 |
+
"loss": 0.0003,
|
| 2775 |
+
"step": 386
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.6569064290260981,
|
| 2779 |
+
"grad_norm": 0.014977892860770226,
|
| 2780 |
+
"learning_rate": 0.00020486444728858117,
|
| 2781 |
+
"loss": 0.0003,
|
| 2782 |
+
"step": 387
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.6586038616592405,
|
| 2786 |
+
"grad_norm": 0.011495725251734257,
|
| 2787 |
+
"learning_rate": 0.00020442115580259613,
|
| 2788 |
+
"loss": 0.0002,
|
| 2789 |
+
"step": 388
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.6603012942923828,
|
| 2793 |
+
"grad_norm": 0.0011856303317472339,
|
| 2794 |
+
"learning_rate": 0.00020397731629617636,
|
| 2795 |
+
"loss": 0.0001,
|
| 2796 |
+
"step": 389
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.6619987269255252,
|
| 2800 |
+
"grad_norm": 0.000914178614038974,
|
| 2801 |
+
"learning_rate": 0.00020353293323878074,
|
| 2802 |
+
"loss": 0.0,
|
| 2803 |
+
"step": 390
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.6636961595586676,
|
| 2807 |
+
"grad_norm": 0.01322512049227953,
|
| 2808 |
+
"learning_rate": 0.00020308801110534178,
|
| 2809 |
+
"loss": 0.0003,
|
| 2810 |
+
"step": 391
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.6653935921918099,
|
| 2814 |
+
"grad_norm": 0.07302884012460709,
|
| 2815 |
+
"learning_rate": 0.00020264255437622036,
|
| 2816 |
+
"loss": 0.0008,
|
| 2817 |
+
"step": 392
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.6670910248249523,
|
| 2821 |
+
"grad_norm": 0.002658440498635173,
|
| 2822 |
+
"learning_rate": 0.00020219656753716074,
|
| 2823 |
+
"loss": 0.0001,
|
| 2824 |
+
"step": 393
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.6687884574580947,
|
| 2828 |
+
"grad_norm": 0.0038816186133772135,
|
| 2829 |
+
"learning_rate": 0.00020175005507924558,
|
| 2830 |
+
"loss": 0.0001,
|
| 2831 |
+
"step": 394
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.670485890091237,
|
| 2835 |
+
"grad_norm": 0.0019201135728508234,
|
| 2836 |
+
"learning_rate": 0.00020130302149885031,
|
| 2837 |
+
"loss": 0.0,
|
| 2838 |
+
"step": 395
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.6721833227243794,
|
| 2842 |
+
"grad_norm": 0.005636914633214474,
|
| 2843 |
+
"learning_rate": 0.00020085547129759806,
|
| 2844 |
+
"loss": 0.0002,
|
| 2845 |
+
"step": 396
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.6738807553575218,
|
| 2849 |
+
"grad_norm": 0.003746110713109374,
|
| 2850 |
+
"learning_rate": 0.00020040740898231448,
|
| 2851 |
+
"loss": 0.0001,
|
| 2852 |
+
"step": 397
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.6755781879906642,
|
| 2856 |
+
"grad_norm": 0.004497275687754154,
|
| 2857 |
+
"learning_rate": 0.0001999588390649821,
|
| 2858 |
+
"loss": 0.0001,
|
| 2859 |
+
"step": 398
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.6772756206238065,
|
| 2863 |
+
"grad_norm": 0.004322202410548925,
|
| 2864 |
+
"learning_rate": 0.00019950976606269497,
|
| 2865 |
+
"loss": 0.0001,
|
| 2866 |
+
"step": 399
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.6789730532569489,
|
| 2870 |
+
"grad_norm": 0.025630857795476913,
|
| 2871 |
+
"learning_rate": 0.00019906019449761325,
|
| 2872 |
+
"loss": 0.0003,
|
| 2873 |
+
"step": 400
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.6789730532569489,
|
| 2877 |
+
"eval_loss": 0.3837679922580719,
|
| 2878 |
+
"eval_runtime": 65.6798,
|
| 2879 |
+
"eval_samples_per_second": 2.938,
|
| 2880 |
+
"eval_steps_per_second": 2.938,
|
| 2881 |
+
"step": 400
|
| 2882 |
}
|
| 2883 |
],
|
| 2884 |
"logging_steps": 1,
|
|
|
|
| 2893 |
"early_stopping_threshold": 0.0
|
| 2894 |
},
|
| 2895 |
"attributes": {
|
| 2896 |
+
"early_stopping_patience_counter": 0
|
| 2897 |
}
|
| 2898 |
},
|
| 2899 |
"TrainerControl": {
|
|
|
|
| 2907 |
"attributes": {}
|
| 2908 |
}
|
| 2909 |
},
|
| 2910 |
+
"total_flos": 2.5934376577794048e+17,
|
| 2911 |
"train_batch_size": 1,
|
| 2912 |
"trial_name": null,
|
| 2913 |
"trial_params": null
|