AlekseyKorshuk commited on
Commit
41eda7c
•
1 Parent(s): 1303f6e

huggingartists

Browse files
README.md CHANGED
@@ -5,6 +5,8 @@ datasets:
5
  tags:
6
  - huggingartists
7
  - lyrics
 
 
8
  widget:
9
  - text: "I am"
10
  ---
@@ -12,7 +14,7 @@ widget:
12
  <div class="inline-flex flex-col" style="line-height: 1.5;">
13
  <div class="flex">
14
  <div
15
- style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/c6b5142a09ff5bd361d0f42a55692edc.1000x1000x1.jpg&#39;)">
16
  </div>
17
  </div>
18
  <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
@@ -43,25 +45,15 @@ from datasets import load_dataset
43
  dataset = load_dataset("huggingartists/drake")
44
  ```
45
 
46
- Or with Transformers library:
47
-
48
- ```python
49
- from transformers import AutoTokenizer, AutoModelWithLMHead
50
-
51
- tokenizer = AutoTokenizer.from_pretrained("huggingartists/drake")
52
-
53
- model = AutoModelWithLMHead.from_pretrained("huggingartists/drake")
54
- ```
55
-
56
- [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1ba7t9q0/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
57
 
58
  ## Training procedure
59
 
60
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Drake's lyrics.
61
 
62
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/18yhidb2) for full transparency and reproducibility.
63
 
64
- At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/18yhidb2/artifacts) is logged and versioned.
65
 
66
  ## How to use
67
 
@@ -74,6 +66,16 @@ generator = pipeline('text-generation',
74
  generator("I am", num_return_sequences=5)
75
  ```
76
 
 
 
 
 
 
 
 
 
 
 
77
  ## Limitations and bias
78
 
79
  The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
@@ -86,6 +88,10 @@ In addition, the data present in the user's tweets further affects the text gene
86
 
87
  [![Follow](https://img.shields.io/github/followers/AlekseyKorshuk?style=social)](https://github.com/AlekseyKorshuk)
88
 
 
 
 
 
89
  For more details, visit the project repository.
90
 
91
  [![GitHub stars](https://img.shields.io/github/stars/AlekseyKorshuk/huggingartists?style=social)](https://github.com/AlekseyKorshuk/huggingartists)
 
5
  tags:
6
  - huggingartists
7
  - lyrics
8
+ - lm-head
9
+ - causal-lm
10
  widget:
11
  - text: "I am"
12
  ---
 
14
  <div class="inline-flex flex-col" style="line-height: 1.5;">
15
  <div class="flex">
16
  <div
17
+ style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/d45e35e82e356571a1d4a78dde726e23.1000x1000x1.png&#39;)">
18
  </div>
19
  </div>
20
  <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
 
45
  dataset = load_dataset("huggingartists/drake")
46
  ```
47
 
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/zdmi3tvf/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 Drake's lyrics.
53
 
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/26dol7sm) for full transparency and reproducibility.
55
 
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/26dol7sm/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
 
66
  generator("I am", num_return_sequences=5)
67
  ```
68
 
69
+ Or with Transformers library:
70
+
71
+ ```python
72
+ from transformers import AutoTokenizer, AutoModelWithLMHead
73
+
74
+ tokenizer = AutoTokenizer.from_pretrained("huggingartists/drake")
75
+
76
+ model = AutoModelWithLMHead.from_pretrained("huggingartists/drake")
77
+ ```
78
+
79
  ## Limitations and bias
80
 
81
  The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
 
88
 
89
  [![Follow](https://img.shields.io/github/followers/AlekseyKorshuk?style=social)](https://github.com/AlekseyKorshuk)
90
 
91
+ [![Follow](https://img.shields.io/twitter/follow/alekseykorshuk?style=social)](https://twitter.com/intent/follow?screen_name=alekseykorshuk)
92
+
93
+ [![Follow](https://img.shields.io/badge/dynamic/json?color=blue&label=Telegram%20Channel&query=%24.result&url=https%3A%2F%2Fapi.telegram.org%2Fbot1929545866%3AAAFGhV-KKnegEcLiyYJxsc4zV6C-bdPEBtQ%2FgetChatMemberCount%3Fchat_id%3D-1001253621662&style=social&logo=telegram)](https://t.me/joinchat/_CQ04KjcJ-4yZTky)
94
+
95
  For more details, visit the project repository.
96
 
97
  [![GitHub stars](https://img.shields.io/github/stars/AlekseyKorshuk/huggingartists?style=social)](https://github.com/AlekseyKorshuk/huggingartists)
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
@@ -18,7 +18,9 @@
18
  "n_inner": null,
19
  "n_layer": 12,
20
  "n_positions": 1024,
 
21
  "resid_pdrop": 0.1,
 
22
  "scale_attn_weights": true,
23
  "summary_activation": null,
24
  "summary_first_dropout": 0.1,
@@ -35,7 +37,7 @@
35
  }
36
  },
37
  "torch_dtype": "float32",
38
- "transformers_version": "4.9.1",
39
  "use_cache": true,
40
  "vocab_size": 50257
41
  }
 
1
  {
2
+ "_name_or_path": "drake",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
18
  "n_inner": null,
19
  "n_layer": 12,
20
  "n_positions": 1024,
21
+ "reorder_and_upcast_attn": false,
22
  "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
  "scale_attn_weights": true,
25
  "summary_activation": null,
26
  "summary_first_dropout": 0.1,
 
37
  }
38
  },
39
  "torch_dtype": "float32",
40
+ "transformers_version": "4.20.0",
41
  "use_cache": true,
42
  "vocab_size": 50257
43
  }
evaluation.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 3.1339056491851807, "eval_runtime": 9.8906, "eval_samples_per_second": 45.498, "eval_steps_per_second": 5.763, "epoch": 2.0}
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f955a88973413396f7ec4b9fc3d18ac455d9b19f440f5135cfa7291c70a600
3
+ size 497764120
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f54b613b898ec9cd602b10294cad4372affedb9070359bf8fb1e1efc0c38351b
3
  size 995604017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510cf9d28093435a6f14d9c62457eacbdaf147c9a782198e086f9ae40697394f
3
  size 995604017
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d646844d7a1967fa54609f85a5452b8eae50cafd2f88c1e934be317c5f71252
3
- size 510403817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:936dde6623deebfd8fa2cff18479909a6f6dd90daf7f48f9bf42d9a3df5c2744
3
+ size 510396521
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c479098b6ff1a7d6e1a01f9b8d8a54011a8cc009f5aa71d8d828ce9e600a222
3
  size 14567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe27f0f573405bd8961b9cdbc34715f4f83d3b82d9647c877952759bfcd31b44
3
  size 14567
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dab3de057a89d68db2661a52fbf111edc97698719020db0127718fdc9badb3d
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa8f8a4ea2104deacbe371cff162540194a1c1633aaca63b65c5835d3a06f383
3
  size 623
special_tokens_map.json CHANGED
@@ -1 +1,5 @@
1
- {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1,10 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "huggingartists/drake",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 1.0,
5
- "global_step": 386,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -468,11 +468,349 @@
468
  "learning_rate": 2.2720446338799106e-09,
469
  "loss": 3.2786,
470
  "step": 385
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
471
  }
472
  ],
473
- "max_steps": 386,
474
- "num_train_epochs": 1,
475
- "total_flos": 403042959360000.0,
476
  "trial_name": null,
477
  "trial_params": null
478
  }
 
1
  {
2
+ "best_metric": 3.1339056491851807,
3
+ "best_model_checkpoint": "output/drake/checkpoint-660",
4
+ "epoch": 2.0,
5
+ "global_step": 660,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
468
  "learning_rate": 2.2720446338799106e-09,
469
  "loss": 3.2786,
470
  "step": 385
471
+ },
472
+ {
473
+ "epoch": 1.18,
474
+ "learning_rate": 1.0890007647780969e-05,
475
+ "loss": 3.2655,
476
+ "step": 390
477
+ },
478
+ {
479
+ "epoch": 1.2,
480
+ "learning_rate": 1.2720089689346961e-05,
481
+ "loss": 3.1689,
482
+ "step": 395
483
+ },
484
+ {
485
+ "epoch": 1.21,
486
+ "learning_rate": 1.4676757700644785e-05,
487
+ "loss": 3.15,
488
+ "step": 400
489
+ },
490
+ {
491
+ "epoch": 1.23,
492
+ "learning_rate": 1.6755579199297876e-05,
493
+ "loss": 3.3109,
494
+ "step": 405
495
+ },
496
+ {
497
+ "epoch": 1.24,
498
+ "learning_rate": 1.8951844985992176e-05,
499
+ "loss": 3.3557,
500
+ "step": 410
501
+ },
502
+ {
503
+ "epoch": 1.26,
504
+ "learning_rate": 2.1260579812327114e-05,
505
+ "loss": 3.2466,
506
+ "step": 415
507
+ },
508
+ {
509
+ "epoch": 1.27,
510
+ "learning_rate": 2.3676553651353433e-05,
511
+ "loss": 3.4927,
512
+ "step": 420
513
+ },
514
+ {
515
+ "epoch": 1.29,
516
+ "learning_rate": 2.6194293545266464e-05,
517
+ "loss": 3.5059,
518
+ "step": 425
519
+ },
520
+ {
521
+ "epoch": 1.3,
522
+ "learning_rate": 2.8808096003415798e-05,
523
+ "loss": 3.3394,
524
+ "step": 430
525
+ },
526
+ {
527
+ "epoch": 1.32,
528
+ "learning_rate": 3.151203992254596e-05,
529
+ "loss": 2.9776,
530
+ "step": 435
531
+ },
532
+ {
533
+ "epoch": 1.33,
534
+ "learning_rate": 3.429999999999997e-05,
535
+ "loss": 3.1045,
536
+ "step": 440
537
+ },
538
+ {
539
+ "epoch": 1.35,
540
+ "learning_rate": 3.716566060949963e-05,
541
+ "loss": 3.3412,
542
+ "step": 445
543
+ },
544
+ {
545
+ "epoch": 1.36,
546
+ "learning_rate": 4.0102530108070535e-05,
547
+ "loss": 3.3821,
548
+ "step": 450
549
+ },
550
+ {
551
+ "epoch": 1.38,
552
+ "learning_rate": 4.3103955541701554e-05,
553
+ "loss": 3.2771,
554
+ "step": 455
555
+ },
556
+ {
557
+ "epoch": 1.39,
558
+ "learning_rate": 4.6163137716424864e-05,
559
+ "loss": 3.2889,
560
+ "step": 460
561
+ },
562
+ {
563
+ "epoch": 1.41,
564
+ "learning_rate": 4.927314660067792e-05,
565
+ "loss": 3.1803,
566
+ "step": 465
567
+ },
568
+ {
569
+ "epoch": 1.42,
570
+ "learning_rate": 5.242693702405331e-05,
571
+ "loss": 3.3752,
572
+ "step": 470
573
+ },
574
+ {
575
+ "epoch": 1.44,
576
+ "learning_rate": 5.561736463687583e-05,
577
+ "loss": 3.4172,
578
+ "step": 475
579
+ },
580
+ {
581
+ "epoch": 1.45,
582
+ "learning_rate": 5.883720209445263e-05,
583
+ "loss": 3.1247,
584
+ "step": 480
585
+ },
586
+ {
587
+ "epoch": 1.47,
588
+ "learning_rate": 6.207915542933309e-05,
589
+ "loss": 3.1979,
590
+ "step": 485
591
+ },
592
+ {
593
+ "epoch": 1.48,
594
+ "learning_rate": 6.533588057449125e-05,
595
+ "loss": 3.2403,
596
+ "step": 490
597
+ },
598
+ {
599
+ "epoch": 1.5,
600
+ "learning_rate": 6.859999999999999e-05,
601
+ "loss": 3.3824,
602
+ "step": 495
603
+ },
604
+ {
605
+ "epoch": 1.52,
606
+ "learning_rate": 7.186411942550872e-05,
607
+ "loss": 3.2565,
608
+ "step": 500
609
+ },
610
+ {
611
+ "epoch": 1.53,
612
+ "learning_rate": 7.512084457066689e-05,
613
+ "loss": 3.1016,
614
+ "step": 505
615
+ },
616
+ {
617
+ "epoch": 1.55,
618
+ "learning_rate": 7.836279790554734e-05,
619
+ "loss": 3.4194,
620
+ "step": 510
621
+ },
622
+ {
623
+ "epoch": 1.56,
624
+ "learning_rate": 8.158263536312414e-05,
625
+ "loss": 3.1877,
626
+ "step": 515
627
+ },
628
+ {
629
+ "epoch": 1.58,
630
+ "learning_rate": 8.477306297594667e-05,
631
+ "loss": 3.4791,
632
+ "step": 520
633
+ },
634
+ {
635
+ "epoch": 1.59,
636
+ "learning_rate": 8.792685339932205e-05,
637
+ "loss": 3.2052,
638
+ "step": 525
639
+ },
640
+ {
641
+ "epoch": 1.61,
642
+ "learning_rate": 9.103686228357512e-05,
643
+ "loss": 3.4702,
644
+ "step": 530
645
+ },
646
+ {
647
+ "epoch": 1.62,
648
+ "learning_rate": 9.409604445829843e-05,
649
+ "loss": 3.152,
650
+ "step": 535
651
+ },
652
+ {
653
+ "epoch": 1.64,
654
+ "learning_rate": 9.709746989192944e-05,
655
+ "loss": 3.2925,
656
+ "step": 540
657
+ },
658
+ {
659
+ "epoch": 1.65,
660
+ "learning_rate": 0.00010003433939050033,
661
+ "loss": 3.2007,
662
+ "step": 545
663
+ },
664
+ {
665
+ "epoch": 1.67,
666
+ "learning_rate": 0.00010290000000000001,
667
+ "loss": 3.444,
668
+ "step": 550
669
+ },
670
+ {
671
+ "epoch": 1.68,
672
+ "learning_rate": 0.00010568796007745401,
673
+ "loss": 3.227,
674
+ "step": 555
675
+ },
676
+ {
677
+ "epoch": 1.7,
678
+ "learning_rate": 0.00010839190399658417,
679
+ "loss": 3.133,
680
+ "step": 560
681
+ },
682
+ {
683
+ "epoch": 1.71,
684
+ "learning_rate": 0.00011100570645473351,
685
+ "loss": 3.1161,
686
+ "step": 565
687
+ },
688
+ {
689
+ "epoch": 1.73,
690
+ "learning_rate": 0.00011352344634864656,
691
+ "loss": 3.2043,
692
+ "step": 570
693
+ },
694
+ {
695
+ "epoch": 1.74,
696
+ "learning_rate": 0.00011593942018767285,
697
+ "loss": 3.265,
698
+ "step": 575
699
+ },
700
+ {
701
+ "epoch": 1.76,
702
+ "learning_rate": 0.00011824815501400781,
703
+ "loss": 3.3016,
704
+ "step": 580
705
+ },
706
+ {
707
+ "epoch": 1.77,
708
+ "learning_rate": 0.00012044442080070208,
709
+ "loss": 3.3944,
710
+ "step": 585
711
+ },
712
+ {
713
+ "epoch": 1.79,
714
+ "learning_rate": 0.0001225232422993552,
715
+ "loss": 3.4325,
716
+ "step": 590
717
+ },
718
+ {
719
+ "epoch": 1.8,
720
+ "learning_rate": 0.00012447991031065301,
721
+ "loss": 3.3161,
722
+ "step": 595
723
+ },
724
+ {
725
+ "epoch": 1.82,
726
+ "learning_rate": 0.000126309992352219,
727
+ "loss": 3.2818,
728
+ "step": 600
729
+ },
730
+ {
731
+ "epoch": 1.83,
732
+ "learning_rate": 0.00012800934269961248,
733
+ "loss": 3.2362,
734
+ "step": 605
735
+ },
736
+ {
737
+ "epoch": 1.85,
738
+ "learning_rate": 0.00012957411177772773,
739
+ "loss": 3.1107,
740
+ "step": 610
741
+ },
742
+ {
743
+ "epoch": 1.86,
744
+ "learning_rate": 0.00013100075488131993,
745
+ "loss": 3.2821,
746
+ "step": 615
747
+ },
748
+ {
749
+ "epoch": 1.88,
750
+ "learning_rate": 0.00013228604020490257,
751
+ "loss": 3.3709,
752
+ "step": 620
753
+ },
754
+ {
755
+ "epoch": 1.89,
756
+ "learning_rate": 0.00013342705616382626,
757
+ "loss": 3.3293,
758
+ "step": 625
759
+ },
760
+ {
761
+ "epoch": 1.91,
762
+ "learning_rate": 0.00013442121798995453,
763
+ "loss": 3.5064,
764
+ "step": 630
765
+ },
766
+ {
767
+ "epoch": 1.92,
768
+ "learning_rate": 0.00013526627358699495,
769
+ "loss": 3.2024,
770
+ "step": 635
771
+ },
772
+ {
773
+ "epoch": 1.94,
774
+ "learning_rate": 0.00013596030863222166,
775
+ "loss": 3.378,
776
+ "step": 640
777
+ },
778
+ {
779
+ "epoch": 1.95,
780
+ "learning_rate": 0.000136501750913032,
781
+ "loss": 3.215,
782
+ "step": 645
783
+ },
784
+ {
785
+ "epoch": 1.97,
786
+ "learning_rate": 0.0001368893738885136,
787
+ "loss": 3.2645,
788
+ "step": 650
789
+ },
790
+ {
791
+ "epoch": 1.98,
792
+ "learning_rate": 0.00013712229946795436,
793
+ "loss": 3.2699,
794
+ "step": 655
795
+ },
796
+ {
797
+ "epoch": 2.0,
798
+ "learning_rate": 0.0001372,
799
+ "loss": 2.9558,
800
+ "step": 660
801
+ },
802
+ {
803
+ "epoch": 2.0,
804
+ "eval_loss": 3.1339056491851807,
805
+ "eval_runtime": 9.8661,
806
+ "eval_samples_per_second": 45.611,
807
+ "eval_steps_per_second": 5.777,
808
+ "step": 660
809
  }
810
  ],
811
+ "max_steps": 660,
812
+ "num_train_epochs": 2,
813
+ "total_flos": 688765796352000.0,
814
  "trial_name": null,
815
  "trial_params": null
816
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:781ffb618640ff70dd3baac13df255d8dc426f031550cac003228fcbafce41fc
3
- size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30fd30de2e4d780d9dc1c08eade8a0e7ffd2b47e4ccbd978c8cce0f74354c17
3
+ size 3311