Commit
•
c4cb4d3
1
Parent(s):
e2275aa
huggingartists
Browse files- README.md +3 -3
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +573 -7
- training_args.bin +1 -1
README.md
CHANGED
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
45 |
dataset = load_dataset("huggingartists/eminem")
|
46 |
```
|
47 |
|
48 |
-
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/
|
49 |
|
50 |
## Training procedure
|
51 |
|
52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Eminem's lyrics.
|
53 |
|
54 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/
|
55 |
|
56 |
-
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/
|
57 |
|
58 |
## How to use
|
59 |
|
|
|
45 |
dataset = load_dataset("huggingartists/eminem")
|
46 |
```
|
47 |
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/391kfg7f/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
49 |
|
50 |
## Training procedure
|
51 |
|
52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Eminem's lyrics.
|
53 |
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1361uz9o) for full transparency and reproducibility.
|
55 |
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1361uz9o/artifacts) is logged and versioned.
|
57 |
|
58 |
## How to use
|
59 |
|
evaluation.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eval_loss": 0.
|
|
|
1 |
+
{"eval_loss": 0.3943726122379303, "eval_runtime": 15.416, "eval_samples_per_second": 44.759, "eval_steps_per_second": 5.643, "epoch": 5.0}
|
flax_model.msgpack
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497764120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02edf25c965a60bf14d297e2e1b0c081720b9e8680d800634688a3fc4a2fb6e3
|
3 |
size 497764120
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995604017
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3549806e8df4af4ca7246f4b76fb32c1636959e4dcfdd8e7ae18219bcecf618d
|
3 |
size 995604017
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510396521
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74cc2a5b07365c0d471dcdc1b01d1d3b1079d6849be25c14f96e07d25c27d9e7
|
3 |
size 510396521
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4270d9bd9f11421914c6de82fdc91926e8d5b6956546e23f778f5df9e81d41a
|
3 |
size 14567
|
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 sha256:7478d4d8fd00284d9c6da95af37a13b23cb40ae04238067c0707b07c0d165090
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "output/eminem/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2360,11 +2360,577 @@
|
|
2360 |
"eval_samples_per_second": 44.716,
|
2361 |
"eval_steps_per_second": 5.64,
|
2362 |
"step": 1936
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2363 |
}
|
2364 |
],
|
2365 |
-
"max_steps":
|
2366 |
-
"num_train_epochs":
|
2367 |
-
"total_flos":
|
2368 |
"trial_name": null,
|
2369 |
"trial_params": null
|
2370 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3943726122379303,
|
3 |
+
"best_model_checkpoint": "output/eminem/checkpoint-2400",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 2400,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2360 |
"eval_samples_per_second": 44.716,
|
2361 |
"eval_steps_per_second": 5.64,
|
2362 |
"step": 1936
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 4.04,
|
2366 |
+
"learning_rate": 0.00011450235959621898,
|
2367 |
+
"loss": 0.3751,
|
2368 |
+
"step": 1940
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 4.05,
|
2372 |
+
"learning_rate": 0.00011280977272542054,
|
2373 |
+
"loss": 0.7741,
|
2374 |
+
"step": 1945
|
2375 |
+
},
|
2376 |
+
{
|
2377 |
+
"epoch": 4.06,
|
2378 |
+
"learning_rate": 0.00011106984492265664,
|
2379 |
+
"loss": 0.6279,
|
2380 |
+
"step": 1950
|
2381 |
+
},
|
2382 |
+
{
|
2383 |
+
"epoch": 4.07,
|
2384 |
+
"learning_rate": 0.00010928443934619291,
|
2385 |
+
"loss": 0.4172,
|
2386 |
+
"step": 1955
|
2387 |
+
},
|
2388 |
+
{
|
2389 |
+
"epoch": 4.08,
|
2390 |
+
"learning_rate": 0.00010745546785304314,
|
2391 |
+
"loss": 0.8202,
|
2392 |
+
"step": 1960
|
2393 |
+
},
|
2394 |
+
{
|
2395 |
+
"epoch": 4.09,
|
2396 |
+
"learning_rate": 0.0001055848889516962,
|
2397 |
+
"loss": 0.7253,
|
2398 |
+
"step": 1965
|
2399 |
+
},
|
2400 |
+
{
|
2401 |
+
"epoch": 4.1,
|
2402 |
+
"learning_rate": 0.00010367470570488607,
|
2403 |
+
"loss": 0.6737,
|
2404 |
+
"step": 1970
|
2405 |
+
},
|
2406 |
+
{
|
2407 |
+
"epoch": 4.11,
|
2408 |
+
"learning_rate": 0.00010172696358468322,
|
2409 |
+
"loss": 0.602,
|
2410 |
+
"step": 1975
|
2411 |
+
},
|
2412 |
+
{
|
2413 |
+
"epoch": 4.12,
|
2414 |
+
"learning_rate": 9.974374828213395e-05,
|
2415 |
+
"loss": 0.7079,
|
2416 |
+
"step": 1980
|
2417 |
+
},
|
2418 |
+
{
|
2419 |
+
"epoch": 4.14,
|
2420 |
+
"learning_rate": 9.772718347385836e-05,
|
2421 |
+
"loss": 0.8964,
|
2422 |
+
"step": 1985
|
2423 |
+
},
|
2424 |
+
{
|
2425 |
+
"epoch": 4.15,
|
2426 |
+
"learning_rate": 9.567942854796078e-05,
|
2427 |
+
"loss": 0.4818,
|
2428 |
+
"step": 1990
|
2429 |
+
},
|
2430 |
+
{
|
2431 |
+
"epoch": 4.16,
|
2432 |
+
"learning_rate": 9.360267629171191e-05,
|
2433 |
+
"loss": 0.7278,
|
2434 |
+
"step": 1995
|
2435 |
+
},
|
2436 |
+
{
|
2437 |
+
"epoch": 4.17,
|
2438 |
+
"learning_rate": 9.149915054343752e-05,
|
2439 |
+
"loss": 0.6072,
|
2440 |
+
"step": 2000
|
2441 |
+
},
|
2442 |
+
{
|
2443 |
+
"epoch": 4.18,
|
2444 |
+
"learning_rate": 8.937110381119999e-05,
|
2445 |
+
"loss": 0.8248,
|
2446 |
+
"step": 2005
|
2447 |
+
},
|
2448 |
+
{
|
2449 |
+
"epoch": 4.19,
|
2450 |
+
"learning_rate": 8.722081486074574e-05,
|
2451 |
+
"loss": 0.8012,
|
2452 |
+
"step": 2010
|
2453 |
+
},
|
2454 |
+
{
|
2455 |
+
"epoch": 4.2,
|
2456 |
+
"learning_rate": 8.50505862753343e-05,
|
2457 |
+
"loss": 0.542,
|
2458 |
+
"step": 2015
|
2459 |
+
},
|
2460 |
+
{
|
2461 |
+
"epoch": 4.21,
|
2462 |
+
"learning_rate": 8.286274199009886e-05,
|
2463 |
+
"loss": 0.5911,
|
2464 |
+
"step": 2020
|
2465 |
+
},
|
2466 |
+
{
|
2467 |
+
"epoch": 4.22,
|
2468 |
+
"learning_rate": 8.06596248034977e-05,
|
2469 |
+
"loss": 0.6034,
|
2470 |
+
"step": 2025
|
2471 |
+
},
|
2472 |
+
{
|
2473 |
+
"epoch": 4.23,
|
2474 |
+
"learning_rate": 7.844359386859629e-05,
|
2475 |
+
"loss": 0.6177,
|
2476 |
+
"step": 2030
|
2477 |
+
},
|
2478 |
+
{
|
2479 |
+
"epoch": 4.24,
|
2480 |
+
"learning_rate": 7.621702216682333e-05,
|
2481 |
+
"loss": 0.7298,
|
2482 |
+
"step": 2035
|
2483 |
+
},
|
2484 |
+
{
|
2485 |
+
"epoch": 4.25,
|
2486 |
+
"learning_rate": 7.398229396693239e-05,
|
2487 |
+
"loss": 0.51,
|
2488 |
+
"step": 2040
|
2489 |
+
},
|
2490 |
+
{
|
2491 |
+
"epoch": 4.26,
|
2492 |
+
"learning_rate": 7.174180227184603e-05,
|
2493 |
+
"loss": 0.8855,
|
2494 |
+
"step": 2045
|
2495 |
+
},
|
2496 |
+
{
|
2497 |
+
"epoch": 4.27,
|
2498 |
+
"learning_rate": 6.94979462561934e-05,
|
2499 |
+
"loss": 0.6728,
|
2500 |
+
"step": 2050
|
2501 |
+
},
|
2502 |
+
{
|
2503 |
+
"epoch": 4.28,
|
2504 |
+
"learning_rate": 6.725312869720243e-05,
|
2505 |
+
"loss": 0.4899,
|
2506 |
+
"step": 2055
|
2507 |
+
},
|
2508 |
+
{
|
2509 |
+
"epoch": 4.29,
|
2510 |
+
"learning_rate": 6.500975340173405e-05,
|
2511 |
+
"loss": 0.4827,
|
2512 |
+
"step": 2060
|
2513 |
+
},
|
2514 |
+
{
|
2515 |
+
"epoch": 4.3,
|
2516 |
+
"learning_rate": 6.27702226322509e-05,
|
2517 |
+
"loss": 0.6521,
|
2518 |
+
"step": 2065
|
2519 |
+
},
|
2520 |
+
{
|
2521 |
+
"epoch": 4.31,
|
2522 |
+
"learning_rate": 6.05369345343951e-05,
|
2523 |
+
"loss": 0.5115,
|
2524 |
+
"step": 2070
|
2525 |
+
},
|
2526 |
+
{
|
2527 |
+
"epoch": 4.32,
|
2528 |
+
"learning_rate": 5.831228056899374e-05,
|
2529 |
+
"loss": 0.3792,
|
2530 |
+
"step": 2075
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 4.33,
|
2534 |
+
"learning_rate": 5.609864295123839e-05,
|
2535 |
+
"loss": 0.5564,
|
2536 |
+
"step": 2080
|
2537 |
+
},
|
2538 |
+
{
|
2539 |
+
"epoch": 4.34,
|
2540 |
+
"learning_rate": 5.389839209973954e-05,
|
2541 |
+
"loss": 0.8714,
|
2542 |
+
"step": 2085
|
2543 |
+
},
|
2544 |
+
{
|
2545 |
+
"epoch": 4.35,
|
2546 |
+
"learning_rate": 5.171388409821159e-05,
|
2547 |
+
"loss": 0.4843,
|
2548 |
+
"step": 2090
|
2549 |
+
},
|
2550 |
+
{
|
2551 |
+
"epoch": 4.36,
|
2552 |
+
"learning_rate": 4.9547458172542385e-05,
|
2553 |
+
"loss": 0.7155,
|
2554 |
+
"step": 2095
|
2555 |
+
},
|
2556 |
+
{
|
2557 |
+
"epoch": 4.38,
|
2558 |
+
"learning_rate": 4.74014341858799e-05,
|
2559 |
+
"loss": 0.4362,
|
2560 |
+
"step": 2100
|
2561 |
+
},
|
2562 |
+
{
|
2563 |
+
"epoch": 4.39,
|
2564 |
+
"learning_rate": 4.5278110154455465e-05,
|
2565 |
+
"loss": 0.4663,
|
2566 |
+
"step": 2105
|
2567 |
+
},
|
2568 |
+
{
|
2569 |
+
"epoch": 4.4,
|
2570 |
+
"learning_rate": 4.317975978682545e-05,
|
2571 |
+
"loss": 0.5994,
|
2572 |
+
"step": 2110
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 4.41,
|
2576 |
+
"learning_rate": 4.110863004912692e-05,
|
2577 |
+
"loss": 0.4463,
|
2578 |
+
"step": 2115
|
2579 |
+
},
|
2580 |
+
{
|
2581 |
+
"epoch": 4.42,
|
2582 |
+
"learning_rate": 3.9066938758951916e-05,
|
2583 |
+
"loss": 0.6226,
|
2584 |
+
"step": 2120
|
2585 |
+
},
|
2586 |
+
{
|
2587 |
+
"epoch": 4.43,
|
2588 |
+
"learning_rate": 3.7056872210476396e-05,
|
2589 |
+
"loss": 0.5947,
|
2590 |
+
"step": 2125
|
2591 |
+
},
|
2592 |
+
{
|
2593 |
+
"epoch": 4.44,
|
2594 |
+
"learning_rate": 3.508058283331054e-05,
|
2595 |
+
"loss": 0.5276,
|
2596 |
+
"step": 2130
|
2597 |
+
},
|
2598 |
+
{
|
2599 |
+
"epoch": 4.45,
|
2600 |
+
"learning_rate": 3.314018688761322e-05,
|
2601 |
+
"loss": 0.5118,
|
2602 |
+
"step": 2135
|
2603 |
+
},
|
2604 |
+
{
|
2605 |
+
"epoch": 4.46,
|
2606 |
+
"learning_rate": 3.123776219796979e-05,
|
2607 |
+
"loss": 0.6581,
|
2608 |
+
"step": 2140
|
2609 |
+
},
|
2610 |
+
{
|
2611 |
+
"epoch": 4.47,
|
2612 |
+
"learning_rate": 2.937534592838677e-05,
|
2613 |
+
"loss": 0.6129,
|
2614 |
+
"step": 2145
|
2615 |
+
},
|
2616 |
+
{
|
2617 |
+
"epoch": 4.48,
|
2618 |
+
"learning_rate": 2.7554932400854067e-05,
|
2619 |
+
"loss": 0.6305,
|
2620 |
+
"step": 2150
|
2621 |
+
},
|
2622 |
+
{
|
2623 |
+
"epoch": 4.49,
|
2624 |
+
"learning_rate": 2.577847095977183e-05,
|
2625 |
+
"loss": 0.6368,
|
2626 |
+
"step": 2155
|
2627 |
+
},
|
2628 |
+
{
|
2629 |
+
"epoch": 4.5,
|
2630 |
+
"learning_rate": 2.4047863884551244e-05,
|
2631 |
+
"loss": 0.6684,
|
2632 |
+
"step": 2160
|
2633 |
+
},
|
2634 |
+
{
|
2635 |
+
"epoch": 4.51,
|
2636 |
+
"learning_rate": 2.2364964352589423e-05,
|
2637 |
+
"loss": 0.7136,
|
2638 |
+
"step": 2165
|
2639 |
+
},
|
2640 |
+
{
|
2641 |
+
"epoch": 4.52,
|
2642 |
+
"learning_rate": 2.0731574454860283e-05,
|
2643 |
+
"loss": 0.5243,
|
2644 |
+
"step": 2170
|
2645 |
+
},
|
2646 |
+
{
|
2647 |
+
"epoch": 4.53,
|
2648 |
+
"learning_rate": 1.914944326618096e-05,
|
2649 |
+
"loss": 0.665,
|
2650 |
+
"step": 2175
|
2651 |
+
},
|
2652 |
+
{
|
2653 |
+
"epoch": 4.54,
|
2654 |
+
"learning_rate": 1.7620264972250878e-05,
|
2655 |
+
"loss": 0.5977,
|
2656 |
+
"step": 2180
|
2657 |
+
},
|
2658 |
+
{
|
2659 |
+
"epoch": 4.55,
|
2660 |
+
"learning_rate": 1.6145677055492958e-05,
|
2661 |
+
"loss": 0.7612,
|
2662 |
+
"step": 2185
|
2663 |
+
},
|
2664 |
+
{
|
2665 |
+
"epoch": 4.56,
|
2666 |
+
"learning_rate": 1.4727258541581522e-05,
|
2667 |
+
"loss": 0.7172,
|
2668 |
+
"step": 2190
|
2669 |
+
},
|
2670 |
+
{
|
2671 |
+
"epoch": 4.57,
|
2672 |
+
"learning_rate": 1.3366528308588766e-05,
|
2673 |
+
"loss": 0.6571,
|
2674 |
+
"step": 2195
|
2675 |
+
},
|
2676 |
+
{
|
2677 |
+
"epoch": 4.58,
|
2678 |
+
"learning_rate": 1.2064943460529662e-05,
|
2679 |
+
"loss": 0.664,
|
2680 |
+
"step": 2200
|
2681 |
+
},
|
2682 |
+
{
|
2683 |
+
"epoch": 4.59,
|
2684 |
+
"learning_rate": 1.0823897767063955e-05,
|
2685 |
+
"loss": 1.1318,
|
2686 |
+
"step": 2205
|
2687 |
+
},
|
2688 |
+
{
|
2689 |
+
"epoch": 4.6,
|
2690 |
+
"learning_rate": 9.644720171000711e-06,
|
2691 |
+
"loss": 0.5895,
|
2692 |
+
"step": 2210
|
2693 |
+
},
|
2694 |
+
{
|
2695 |
+
"epoch": 4.61,
|
2696 |
+
"learning_rate": 8.52867336524718e-06,
|
2697 |
+
"loss": 0.5683,
|
2698 |
+
"step": 2215
|
2699 |
+
},
|
2700 |
+
{
|
2701 |
+
"epoch": 4.62,
|
2702 |
+
"learning_rate": 7.476952440678663e-06,
|
2703 |
+
"loss": 0.8862,
|
2704 |
+
"step": 2220
|
2705 |
+
},
|
2706 |
+
{
|
2707 |
+
"epoch": 4.64,
|
2708 |
+
"learning_rate": 6.490683606400273e-06,
|
2709 |
+
"loss": 0.5336,
|
2710 |
+
"step": 2225
|
2711 |
+
},
|
2712 |
+
{
|
2713 |
+
"epoch": 4.65,
|
2714 |
+
"learning_rate": 5.570922983785744e-06,
|
2715 |
+
"loss": 0.7185,
|
2716 |
+
"step": 2230
|
2717 |
+
},
|
2718 |
+
{
|
2719 |
+
"epoch": 4.66,
|
2720 |
+
"learning_rate": 4.718655475547088e-06,
|
2721 |
+
"loss": 0.6121,
|
2722 |
+
"step": 2235
|
2723 |
+
},
|
2724 |
+
{
|
2725 |
+
"epoch": 4.67,
|
2726 |
+
"learning_rate": 3.934793711076979e-06,
|
2727 |
+
"loss": 0.4995,
|
2728 |
+
"step": 2240
|
2729 |
+
},
|
2730 |
+
{
|
2731 |
+
"epoch": 4.68,
|
2732 |
+
"learning_rate": 3.2201770691879365e-06,
|
2733 |
+
"loss": 0.639,
|
2734 |
+
"step": 2245
|
2735 |
+
},
|
2736 |
+
{
|
2737 |
+
"epoch": 4.69,
|
2738 |
+
"learning_rate": 2.5755707792803602e-06,
|
2739 |
+
"loss": 0.6703,
|
2740 |
+
"step": 2250
|
2741 |
+
},
|
2742 |
+
{
|
2743 |
+
"epoch": 4.7,
|
2744 |
+
"learning_rate": 2.001665101912862e-06,
|
2745 |
+
"loss": 0.5835,
|
2746 |
+
"step": 2255
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 4.71,
|
2750 |
+
"learning_rate": 1.499074589660724e-06,
|
2751 |
+
"loss": 0.8827,
|
2752 |
+
"step": 2260
|
2753 |
+
},
|
2754 |
+
{
|
2755 |
+
"epoch": 4.72,
|
2756 |
+
"learning_rate": 1.0683374290336727e-06,
|
2757 |
+
"loss": 0.521,
|
2758 |
+
"step": 2265
|
2759 |
+
},
|
2760 |
+
{
|
2761 |
+
"epoch": 4.73,
|
2762 |
+
"learning_rate": 7.099148641708803e-07,
|
2763 |
+
"loss": 0.5759,
|
2764 |
+
"step": 2270
|
2765 |
+
},
|
2766 |
+
{
|
2767 |
+
"epoch": 4.74,
|
2768 |
+
"learning_rate": 4.2419070293249417e-07,
|
2769 |
+
"loss": 0.4576,
|
2770 |
+
"step": 2275
|
2771 |
+
},
|
2772 |
+
{
|
2773 |
+
"epoch": 4.75,
|
2774 |
+
"learning_rate": 2.1147090590762733e-07,
|
2775 |
+
"loss": 0.9183,
|
2776 |
+
"step": 2280
|
2777 |
+
},
|
2778 |
+
{
|
2779 |
+
"epoch": 4.76,
|
2780 |
+
"learning_rate": 7.19832587822494e-08,
|
2781 |
+
"loss": 0.6811,
|
2782 |
+
"step": 2285
|
2783 |
+
},
|
2784 |
+
{
|
2785 |
+
"epoch": 4.77,
|
2786 |
+
"learning_rate": 5.877128423112166e-09,
|
2787 |
+
"loss": 0.6599,
|
2788 |
+
"step": 2290
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 4.78,
|
2792 |
+
"learning_rate": 1.3223302930315373e-08,
|
2793 |
+
"loss": 0.8066,
|
2794 |
+
"step": 2295
|
2795 |
+
},
|
2796 |
+
{
|
2797 |
+
"epoch": 4.79,
|
2798 |
+
"learning_rate": 9.401391583621219e-08,
|
2799 |
+
"loss": 0.93,
|
2800 |
+
"step": 2300
|
2801 |
+
},
|
2802 |
+
{
|
2803 |
+
"epoch": 4.8,
|
2804 |
+
"learning_rate": 2.4816245452881085e-07,
|
2805 |
+
"loss": 0.7526,
|
2806 |
+
"step": 2305
|
2807 |
+
},
|
2808 |
+
{
|
2809 |
+
"epoch": 4.81,
|
2810 |
+
"learning_rate": 4.755038528919192e-07,
|
2811 |
+
"loss": 0.6209,
|
2812 |
+
"step": 2310
|
2813 |
+
},
|
2814 |
+
{
|
2815 |
+
"epoch": 4.82,
|
2816 |
+
"learning_rate": 7.757946680618806e-07,
|
2817 |
+
"loss": 0.5472,
|
2818 |
+
"step": 2315
|
2819 |
+
},
|
2820 |
+
{
|
2821 |
+
"epoch": 4.83,
|
2822 |
+
"learning_rate": 1.1487133411127057e-06,
|
2823 |
+
"loss": 0.5128,
|
2824 |
+
"step": 2320
|
2825 |
+
},
|
2826 |
+
{
|
2827 |
+
"epoch": 4.84,
|
2828 |
+
"learning_rate": 1.5938605413876288e-06,
|
2829 |
+
"loss": 0.5971,
|
2830 |
+
"step": 2325
|
2831 |
+
},
|
2832 |
+
{
|
2833 |
+
"epoch": 4.85,
|
2834 |
+
"learning_rate": 2.1107595941164267e-06,
|
2835 |
+
"loss": 0.9001,
|
2836 |
+
"step": 2330
|
2837 |
+
},
|
2838 |
+
{
|
2839 |
+
"epoch": 4.86,
|
2840 |
+
"learning_rate": 2.698856990845814e-06,
|
2841 |
+
"loss": 0.624,
|
2842 |
+
"step": 2335
|
2843 |
+
},
|
2844 |
+
{
|
2845 |
+
"epoch": 4.88,
|
2846 |
+
"learning_rate": 3.3575229821519346e-06,
|
2847 |
+
"loss": 0.469,
|
2848 |
+
"step": 2340
|
2849 |
+
},
|
2850 |
+
{
|
2851 |
+
"epoch": 4.89,
|
2852 |
+
"learning_rate": 4.086052251995796e-06,
|
2853 |
+
"loss": 0.7627,
|
2854 |
+
"step": 2345
|
2855 |
+
},
|
2856 |
+
{
|
2857 |
+
"epoch": 4.9,
|
2858 |
+
"learning_rate": 4.883664672985776e-06,
|
2859 |
+
"loss": 0.5373,
|
2860 |
+
"step": 2350
|
2861 |
+
},
|
2862 |
+
{
|
2863 |
+
"epoch": 4.91,
|
2864 |
+
"learning_rate": 5.749506141764069e-06,
|
2865 |
+
"loss": 0.684,
|
2866 |
+
"step": 2355
|
2867 |
+
},
|
2868 |
+
{
|
2869 |
+
"epoch": 4.92,
|
2870 |
+
"learning_rate": 6.682649493598944e-06,
|
2871 |
+
"loss": 0.6701,
|
2872 |
+
"step": 2360
|
2873 |
+
},
|
2874 |
+
{
|
2875 |
+
"epoch": 4.93,
|
2876 |
+
"learning_rate": 7.682095495217462e-06,
|
2877 |
+
"loss": 0.5721,
|
2878 |
+
"step": 2365
|
2879 |
+
},
|
2880 |
+
{
|
2881 |
+
"epoch": 4.94,
|
2882 |
+
"learning_rate": 8.746773914805009e-06,
|
2883 |
+
"loss": 0.5432,
|
2884 |
+
"step": 2370
|
2885 |
+
},
|
2886 |
+
{
|
2887 |
+
"epoch": 4.95,
|
2888 |
+
"learning_rate": 9.875544668046303e-06,
|
2889 |
+
"loss": 0.6582,
|
2890 |
+
"step": 2375
|
2891 |
+
},
|
2892 |
+
{
|
2893 |
+
"epoch": 4.96,
|
2894 |
+
"learning_rate": 1.1067199038944353e-05,
|
2895 |
+
"loss": 0.5341,
|
2896 |
+
"step": 2380
|
2897 |
+
},
|
2898 |
+
{
|
2899 |
+
"epoch": 4.97,
|
2900 |
+
"learning_rate": 1.2320460974148876e-05,
|
2901 |
+
"loss": 0.677,
|
2902 |
+
"step": 2385
|
2903 |
+
},
|
2904 |
+
{
|
2905 |
+
"epoch": 4.98,
|
2906 |
+
"learning_rate": 1.3633988449393231e-05,
|
2907 |
+
"loss": 0.5661,
|
2908 |
+
"step": 2390
|
2909 |
+
},
|
2910 |
+
{
|
2911 |
+
"epoch": 4.99,
|
2912 |
+
"learning_rate": 1.5006374906553291e-05,
|
2913 |
+
"loss": 0.4745,
|
2914 |
+
"step": 2395
|
2915 |
+
},
|
2916 |
+
{
|
2917 |
+
"epoch": 5.0,
|
2918 |
+
"learning_rate": 1.6436150759836066e-05,
|
2919 |
+
"loss": 0.746,
|
2920 |
+
"step": 2400
|
2921 |
+
},
|
2922 |
+
{
|
2923 |
+
"epoch": 5.0,
|
2924 |
+
"eval_loss": 0.3943726122379303,
|
2925 |
+
"eval_runtime": 15.4496,
|
2926 |
+
"eval_samples_per_second": 44.661,
|
2927 |
+
"eval_steps_per_second": 5.631,
|
2928 |
+
"step": 2400
|
2929 |
}
|
2930 |
],
|
2931 |
+
"max_steps": 2400,
|
2932 |
+
"num_train_epochs": 5,
|
2933 |
+
"total_flos": 2505790586880000.0,
|
2934 |
"trial_name": null,
|
2935 |
"trial_params": null
|
2936 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3375
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16468c38c400c76b00da680c27696240fef059a3ea4837c5eeffa1b293611cac
|
3 |
size 3375
|