pszemraj commited on
Commit
c4283bf
1 Parent(s): 44ce8b3

Upload folder using huggingface_hub

Browse files
checkpoints/checkpoint-pt-80000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d997886f203862935d8f7b71bbc70610a616af83154cf80b9c1574aa2a4a71
3
+ size 1202681712
checkpoints/checkpoint-pt-80000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:634ae87ad9ec14553a807f970f4e595e3fef7b62fd4afaddf671a76426ff94ed
3
+ size 14344
checkpoints/checkpoint-pt-80001/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d997886f203862935d8f7b71bbc70610a616af83154cf80b9c1574aa2a4a71
3
+ size 1202681712
checkpoints/checkpoint-pt-80001/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8274e40f91e3bb36224874d76afb757bd0e2f557eb5c5924744f1157f737e27
3
+ size 14344
checkpoints/grad_l2_over_steps.png CHANGED
checkpoints/loss_over_steps.png CHANGED
checkpoints/lr_over_steps.png CHANGED
checkpoints/main.log CHANGED
@@ -1701,3 +1701,56 @@ Mixed precision type: bf16
1701
  [2024-08-12 21:19:24,074][Main][INFO] - [train] Step 78100 out of 80000 | Loss --> 1.707 | Grad_l2 --> 0.349 | Weights_l2 --> 9067.661 | Lr --> 0.000 | Seconds_per_step --> 3.398 |
1702
  [2024-08-12 21:22:14,845][Main][INFO] - [train] Step 78150 out of 80000 | Loss --> 1.701 | Grad_l2 --> 0.349 | Weights_l2 --> 9067.660 | Lr --> 0.000 | Seconds_per_step --> 3.415 |
1703
  [2024-08-12 21:25:04,253][Main][INFO] - [train] Step 78200 out of 80000 | Loss --> 1.707 | Grad_l2 --> 0.350 | Weights_l2 --> 9067.658 | Lr --> 0.000 | Seconds_per_step --> 3.388 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1701
  [2024-08-12 21:19:24,074][Main][INFO] - [train] Step 78100 out of 80000 | Loss --> 1.707 | Grad_l2 --> 0.349 | Weights_l2 --> 9067.661 | Lr --> 0.000 | Seconds_per_step --> 3.398 |
1702
  [2024-08-12 21:22:14,845][Main][INFO] - [train] Step 78150 out of 80000 | Loss --> 1.701 | Grad_l2 --> 0.349 | Weights_l2 --> 9067.660 | Lr --> 0.000 | Seconds_per_step --> 3.415 |
1703
  [2024-08-12 21:25:04,253][Main][INFO] - [train] Step 78200 out of 80000 | Loss --> 1.707 | Grad_l2 --> 0.350 | Weights_l2 --> 9067.658 | Lr --> 0.000 | Seconds_per_step --> 3.388 |
1704
+ [2024-08-12 21:27:53,707][Main][INFO] - [train] Step 78250 out of 80000 | Loss --> 1.707 | Grad_l2 --> 0.348 | Weights_l2 --> 9067.657 | Lr --> 0.000 | Seconds_per_step --> 3.389 |
1705
+ [2024-08-12 21:30:43,019][Main][INFO] - [train] Step 78300 out of 80000 | Loss --> 1.710 | Grad_l2 --> 0.350 | Weights_l2 --> 9067.656 | Lr --> 0.000 | Seconds_per_step --> 3.386 |
1706
+ [2024-08-12 21:33:33,014][Main][INFO] - [train] Step 78350 out of 80000 | Loss --> 1.710 | Grad_l2 --> 0.350 | Weights_l2 --> 9067.655 | Lr --> 0.000 | Seconds_per_step --> 3.400 |
1707
+ [2024-08-12 21:36:23,186][Main][INFO] - [train] Step 78400 out of 80000 | Loss --> 1.707 | Grad_l2 --> 0.349 | Weights_l2 --> 9067.653 | Lr --> 0.000 | Seconds_per_step --> 3.403 |
1708
+ [2024-08-12 21:39:12,309][Main][INFO] - [train] Step 78450 out of 80000 | Loss --> 1.720 | Grad_l2 --> 0.350 | Weights_l2 --> 9067.652 | Lr --> 0.000 | Seconds_per_step --> 3.382 |
1709
+ [2024-08-12 21:42:03,162][Main][INFO] - [train] Step 78500 out of 80000 | Loss --> 1.714 | Grad_l2 --> 0.350 | Weights_l2 --> 9067.651 | Lr --> 0.000 | Seconds_per_step --> 3.417 |
1710
+ [2024-08-12 21:44:53,192][Main][INFO] - [train] Step 78550 out of 80000 | Loss --> 1.724 | Grad_l2 --> 0.350 | Weights_l2 --> 9067.649 | Lr --> 0.000 | Seconds_per_step --> 3.401 |
1711
+ [2024-08-12 21:47:43,149][Main][INFO] - [train] Step 78600 out of 80000 | Loss --> 1.714 | Grad_l2 --> 0.351 | Weights_l2 --> 9067.648 | Lr --> 0.000 | Seconds_per_step --> 3.399 |
1712
+ [2024-08-12 21:50:32,387][Main][INFO] - [train] Step 78650 out of 80000 | Loss --> 1.719 | Grad_l2 --> 0.350 | Weights_l2 --> 9067.647 | Lr --> 0.000 | Seconds_per_step --> 3.385 |
1713
+ [2024-08-12 21:53:22,026][Main][INFO] - [train] Step 78700 out of 80000 | Loss --> 1.714 | Grad_l2 --> 0.350 | Weights_l2 --> 9067.646 | Lr --> 0.000 | Seconds_per_step --> 3.393 |
1714
+ [2024-08-12 21:56:11,907][Main][INFO] - [train] Step 78750 out of 80000 | Loss --> 1.729 | Grad_l2 --> 0.351 | Weights_l2 --> 9067.645 | Lr --> 0.000 | Seconds_per_step --> 3.398 |
1715
+ [2024-08-12 21:59:00,947][Main][INFO] - [train] Step 78800 out of 80000 | Loss --> 1.719 | Grad_l2 --> 0.352 | Weights_l2 --> 9067.644 | Lr --> 0.000 | Seconds_per_step --> 3.381 |
1716
+ [2024-08-12 22:01:50,443][Main][INFO] - [train] Step 78850 out of 80000 | Loss --> 1.722 | Grad_l2 --> 0.352 | Weights_l2 --> 9067.643 | Lr --> 0.000 | Seconds_per_step --> 3.390 |
1717
+ [2024-08-12 22:04:39,064][Main][INFO] - [train] Step 78900 out of 80000 | Loss --> 1.739 | Grad_l2 --> 0.349 | Weights_l2 --> 9067.642 | Lr --> 0.000 | Seconds_per_step --> 3.372 |
1718
+ [2024-08-12 22:07:29,275][Main][INFO] - [train] Step 78950 out of 80000 | Loss --> 1.726 | Grad_l2 --> 0.349 | Weights_l2 --> 9067.641 | Lr --> 0.000 | Seconds_per_step --> 3.404 |
1719
+ [2024-08-12 22:10:18,964][Main][INFO] - [train] Step 79000 out of 80000 | Loss --> 1.729 | Grad_l2 --> 0.352 | Weights_l2 --> 9067.640 | Lr --> 0.000 | Seconds_per_step --> 3.394 |
1720
+ [2024-08-12 22:13:08,518][Main][INFO] - [train] Step 79050 out of 80000 | Loss --> 1.724 | Grad_l2 --> 0.351 | Weights_l2 --> 9067.639 | Lr --> 0.000 | Seconds_per_step --> 3.391 |
1721
+ [2024-08-12 22:15:58,096][Main][INFO] - [train] Step 79100 out of 80000 | Loss --> 1.731 | Grad_l2 --> 0.351 | Weights_l2 --> 9067.638 | Lr --> 0.000 | Seconds_per_step --> 3.392 |
1722
+ [2024-08-12 22:18:47,746][Main][INFO] - [train] Step 79150 out of 80000 | Loss --> 1.730 | Grad_l2 --> 0.352 | Weights_l2 --> 9067.637 | Lr --> 0.000 | Seconds_per_step --> 3.393 |
1723
+ [2024-08-12 22:21:37,645][Main][INFO] - [train] Step 79200 out of 80000 | Loss --> 1.733 | Grad_l2 --> 0.351 | Weights_l2 --> 9067.637 | Lr --> 0.000 | Seconds_per_step --> 3.398 |
1724
+ [2024-08-12 22:24:27,038][Main][INFO] - [train] Step 79250 out of 80000 | Loss --> 1.733 | Grad_l2 --> 0.350 | Weights_l2 --> 9067.636 | Lr --> 0.000 | Seconds_per_step --> 3.388 |
1725
+ [2024-08-12 22:27:16,116][Main][INFO] - [train] Step 79300 out of 80000 | Loss --> 1.735 | Grad_l2 --> 0.350 | Weights_l2 --> 9067.635 | Lr --> 0.000 | Seconds_per_step --> 3.382 |
1726
+ [2024-08-12 22:30:05,701][Main][INFO] - [train] Step 79350 out of 80000 | Loss --> 1.733 | Grad_l2 --> 0.351 | Weights_l2 --> 9067.635 | Lr --> 0.000 | Seconds_per_step --> 3.392 |
1727
+ [2024-08-12 22:32:54,419][Main][INFO] - [train] Step 79400 out of 80000 | Loss --> 1.730 | Grad_l2 --> 0.352 | Weights_l2 --> 9067.634 | Lr --> 0.000 | Seconds_per_step --> 3.374 |
1728
+ [2024-08-12 22:35:43,068][Main][INFO] - [train] Step 79450 out of 80000 | Loss --> 1.739 | Grad_l2 --> 0.351 | Weights_l2 --> 9067.633 | Lr --> 0.000 | Seconds_per_step --> 3.373 |
1729
+ [2024-08-12 22:38:32,666][Main][INFO] - [train] Step 79500 out of 80000 | Loss --> 1.745 | Grad_l2 --> 0.353 | Weights_l2 --> 9067.633 | Lr --> 0.000 | Seconds_per_step --> 3.392 |
1730
+ [2024-08-12 22:41:21,888][Main][INFO] - [train] Step 79550 out of 80000 | Loss --> 1.723 | Grad_l2 --> 0.350 | Weights_l2 --> 9067.632 | Lr --> 0.000 | Seconds_per_step --> 3.384 |
1731
+ [2024-08-12 22:44:11,844][Main][INFO] - [train] Step 79600 out of 80000 | Loss --> 1.742 | Grad_l2 --> 0.352 | Weights_l2 --> 9067.631 | Lr --> 0.000 | Seconds_per_step --> 3.399 |
1732
+ [2024-08-12 22:47:00,902][Main][INFO] - [train] Step 79650 out of 80000 | Loss --> 1.741 | Grad_l2 --> 0.352 | Weights_l2 --> 9067.630 | Lr --> 0.000 | Seconds_per_step --> 3.381 |
1733
+ [2024-08-12 22:49:50,032][Main][INFO] - [train] Step 79700 out of 80000 | Loss --> 1.739 | Grad_l2 --> 0.352 | Weights_l2 --> 9067.629 | Lr --> 0.000 | Seconds_per_step --> 3.383 |
1734
+ [2024-08-12 22:52:39,520][Main][INFO] - [train] Step 79750 out of 80000 | Loss --> 1.743 | Grad_l2 --> 0.351 | Weights_l2 --> 9067.629 | Lr --> 0.000 | Seconds_per_step --> 3.390 |
1735
+ [2024-08-12 22:55:29,331][Main][INFO] - [train] Step 79800 out of 80000 | Loss --> 1.745 | Grad_l2 --> 0.351 | Weights_l2 --> 9067.629 | Lr --> 0.000 | Seconds_per_step --> 3.396 |
1736
+ [2024-08-12 22:58:19,091][Main][INFO] - [train] Step 79850 out of 80000 | Loss --> 1.746 | Grad_l2 --> 0.352 | Weights_l2 --> 9067.628 | Lr --> 0.000 | Seconds_per_step --> 3.395 |
1737
+ [2024-08-12 23:01:08,868][Main][INFO] - [train] Step 79900 out of 80000 | Loss --> 1.737 | Grad_l2 --> 0.353 | Weights_l2 --> 9067.627 | Lr --> 0.000 | Seconds_per_step --> 3.396 |
1738
+ [2024-08-12 23:03:57,751][Main][INFO] - [train] Step 79950 out of 80000 | Loss --> 1.745 | Grad_l2 --> 0.352 | Weights_l2 --> 9067.627 | Lr --> 0.000 | Seconds_per_step --> 3.378 |
1739
+ [2024-08-12 23:06:47,601][Main][INFO] - [train] Step 80000 out of 80000 | Loss --> 1.740 | Grad_l2 --> 0.351 | Weights_l2 --> 9067.626 | Lr --> 0.000 | Seconds_per_step --> 3.397 |
1740
+ [2024-08-12 23:06:47,602][accelerate.accelerator][INFO] - Saving current state to checkpoint-pt-80000
1741
+ [2024-08-12 23:06:47,605][accelerate.utils.other][WARNING] - Removed shared tensor {'encoder.embed_tokens.weight', 'decoder.embed_tokens.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
1742
+ [2024-08-12 23:06:50,280][accelerate.checkpointing][INFO] - Model weights saved in checkpoint-pt-80000/model.safetensors
1743
+ [2024-08-12 23:06:53,299][accelerate.checkpointing][INFO] - Optimizer state saved in checkpoint-pt-80000/optimizer.bin
1744
+ [2024-08-12 23:06:53,299][accelerate.checkpointing][INFO] - Scheduler state saved in checkpoint-pt-80000/scheduler.bin
1745
+ [2024-08-12 23:06:53,299][accelerate.checkpointing][INFO] - Sampler state for dataloader 0 saved in checkpoint-pt-80000/sampler.bin
1746
+ [2024-08-12 23:06:53,299][accelerate.checkpointing][INFO] - Sampler state for dataloader 1 saved in checkpoint-pt-80000/sampler_1.bin
1747
+ [2024-08-12 23:06:53,300][accelerate.checkpointing][INFO] - Random states saved in checkpoint-pt-80000/random_states_0.pkl
1748
+ [2024-08-12 23:16:15,352][Main][INFO] - [eval] Step 80001 out of 80000 | Loss --> 2.053 | Accuracy --> 0.608 | Time --> 561.184 |
1749
+ [2024-08-12 23:16:15,356][accelerate.accelerator][INFO] - Saving current state to checkpoint-pt-80001
1750
+ [2024-08-12 23:16:15,361][accelerate.utils.other][WARNING] - Removed shared tensor {'encoder.embed_tokens.weight', 'decoder.embed_tokens.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
1751
+ [2024-08-12 23:16:17,400][accelerate.checkpointing][INFO] - Model weights saved in checkpoint-pt-80001/model.safetensors
1752
+ [2024-08-12 23:16:20,285][accelerate.checkpointing][INFO] - Optimizer state saved in checkpoint-pt-80001/optimizer.bin
1753
+ [2024-08-12 23:16:20,285][accelerate.checkpointing][INFO] - Scheduler state saved in checkpoint-pt-80001/scheduler.bin
1754
+ [2024-08-12 23:16:20,285][accelerate.checkpointing][INFO] - Sampler state for dataloader 0 saved in checkpoint-pt-80001/sampler.bin
1755
+ [2024-08-12 23:16:20,285][accelerate.checkpointing][INFO] - Sampler state for dataloader 1 saved in checkpoint-pt-80001/sampler_1.bin
1756
+ [2024-08-12 23:16:20,286][accelerate.checkpointing][INFO] - Random states saved in checkpoint-pt-80001/random_states_0.pkl
checkpoints/seconds_per_step_over_steps.png CHANGED
checkpoints/tokenizer/added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 48128,
3
+ "<extra_id_10>": 48138,
4
+ "<extra_id_11>": 48139,
5
+ "<extra_id_12>": 48140,
6
+ "<extra_id_13>": 48141,
7
+ "<extra_id_14>": 48142,
8
+ "<extra_id_15>": 48143,
9
+ "<extra_id_16>": 48144,
10
+ "<extra_id_17>": 48145,
11
+ "<extra_id_18>": 48146,
12
+ "<extra_id_19>": 48147,
13
+ "<extra_id_1>": 48129,
14
+ "<extra_id_20>": 48148,
15
+ "<extra_id_21>": 48149,
16
+ "<extra_id_22>": 48150,
17
+ "<extra_id_23>": 48151,
18
+ "<extra_id_24>": 48152,
19
+ "<extra_id_25>": 48153,
20
+ "<extra_id_26>": 48154,
21
+ "<extra_id_27>": 48155,
22
+ "<extra_id_28>": 48156,
23
+ "<extra_id_29>": 48157,
24
+ "<extra_id_2>": 48130,
25
+ "<extra_id_30>": 48158,
26
+ "<extra_id_31>": 48159,
27
+ "<extra_id_32>": 48160,
28
+ "<extra_id_33>": 48161,
29
+ "<extra_id_34>": 48162,
30
+ "<extra_id_35>": 48163,
31
+ "<extra_id_36>": 48164,
32
+ "<extra_id_37>": 48165,
33
+ "<extra_id_38>": 48166,
34
+ "<extra_id_39>": 48167,
35
+ "<extra_id_3>": 48131,
36
+ "<extra_id_40>": 48168,
37
+ "<extra_id_41>": 48169,
38
+ "<extra_id_42>": 48170,
39
+ "<extra_id_43>": 48171,
40
+ "<extra_id_44>": 48172,
41
+ "<extra_id_45>": 48173,
42
+ "<extra_id_46>": 48174,
43
+ "<extra_id_47>": 48175,
44
+ "<extra_id_48>": 48176,
45
+ "<extra_id_49>": 48177,
46
+ "<extra_id_4>": 48132,
47
+ "<extra_id_50>": 48178,
48
+ "<extra_id_51>": 48179,
49
+ "<extra_id_52>": 48180,
50
+ "<extra_id_53>": 48181,
51
+ "<extra_id_54>": 48182,
52
+ "<extra_id_55>": 48183,
53
+ "<extra_id_56>": 48184,
54
+ "<extra_id_57>": 48185,
55
+ "<extra_id_58>": 48186,
56
+ "<extra_id_59>": 48187,
57
+ "<extra_id_5>": 48133,
58
+ "<extra_id_60>": 48188,
59
+ "<extra_id_61>": 48189,
60
+ "<extra_id_62>": 48190,
61
+ "<extra_id_63>": 48191,
62
+ "<extra_id_64>": 48192,
63
+ "<extra_id_65>": 48193,
64
+ "<extra_id_66>": 48194,
65
+ "<extra_id_67>": 48195,
66
+ "<extra_id_68>": 48196,
67
+ "<extra_id_69>": 48197,
68
+ "<extra_id_6>": 48134,
69
+ "<extra_id_70>": 48198,
70
+ "<extra_id_71>": 48199,
71
+ "<extra_id_72>": 48200,
72
+ "<extra_id_73>": 48201,
73
+ "<extra_id_74>": 48202,
74
+ "<extra_id_75>": 48203,
75
+ "<extra_id_76>": 48204,
76
+ "<extra_id_77>": 48205,
77
+ "<extra_id_78>": 48206,
78
+ "<extra_id_79>": 48207,
79
+ "<extra_id_7>": 48135,
80
+ "<extra_id_80>": 48208,
81
+ "<extra_id_81>": 48209,
82
+ "<extra_id_82>": 48210,
83
+ "<extra_id_83>": 48211,
84
+ "<extra_id_84>": 48212,
85
+ "<extra_id_85>": 48213,
86
+ "<extra_id_86>": 48214,
87
+ "<extra_id_87>": 48215,
88
+ "<extra_id_88>": 48216,
89
+ "<extra_id_89>": 48217,
90
+ "<extra_id_8>": 48136,
91
+ "<extra_id_90>": 48218,
92
+ "<extra_id_91>": 48219,
93
+ "<extra_id_92>": 48220,
94
+ "<extra_id_93>": 48221,
95
+ "<extra_id_94>": 48222,
96
+ "<extra_id_95>": 48223,
97
+ "<extra_id_96>": 48224,
98
+ "<extra_id_97>": 48225,
99
+ "<extra_id_98>": 48226,
100
+ "<extra_id_99>": 48227,
101
+ "<extra_id_9>": 48137
102
+ }
checkpoints/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "bos_token": {
105
+ "content": "<s>",
106
+ "lstrip": false,
107
+ "normalized": true,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "eos_token": {
112
+ "content": "</s>",
113
+ "lstrip": false,
114
+ "normalized": true,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "pad_token": {
119
+ "content": "<pad>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "unk_token": {
126
+ "content": "<unk>",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false
131
+ }
132
+ }
checkpoints/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/tokenizer/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:165515d67d17852d3e7c30ec22d7a745330f2cba264f40c3ea9380eddf84396f
3
+ size 1042483
checkpoints/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,952 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": true,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "48128": {
39
+ "content": "<extra_id_0>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "48129": {
47
+ "content": "<extra_id_1>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "48130": {
55
+ "content": "<extra_id_2>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "48131": {
63
+ "content": "<extra_id_3>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "48132": {
71
+ "content": "<extra_id_4>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "48133": {
79
+ "content": "<extra_id_5>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "48134": {
87
+ "content": "<extra_id_6>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "48135": {
95
+ "content": "<extra_id_7>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "48136": {
103
+ "content": "<extra_id_8>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "48137": {
111
+ "content": "<extra_id_9>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "48138": {
119
+ "content": "<extra_id_10>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "48139": {
127
+ "content": "<extra_id_11>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "48140": {
135
+ "content": "<extra_id_12>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "48141": {
143
+ "content": "<extra_id_13>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "48142": {
151
+ "content": "<extra_id_14>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "48143": {
159
+ "content": "<extra_id_15>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "48144": {
167
+ "content": "<extra_id_16>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "48145": {
175
+ "content": "<extra_id_17>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "48146": {
183
+ "content": "<extra_id_18>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "48147": {
191
+ "content": "<extra_id_19>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "48148": {
199
+ "content": "<extra_id_20>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "48149": {
207
+ "content": "<extra_id_21>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "48150": {
215
+ "content": "<extra_id_22>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "48151": {
223
+ "content": "<extra_id_23>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "48152": {
231
+ "content": "<extra_id_24>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "48153": {
239
+ "content": "<extra_id_25>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "48154": {
247
+ "content": "<extra_id_26>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "48155": {
255
+ "content": "<extra_id_27>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "48156": {
263
+ "content": "<extra_id_28>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "48157": {
271
+ "content": "<extra_id_29>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "48158": {
279
+ "content": "<extra_id_30>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "48159": {
287
+ "content": "<extra_id_31>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "48160": {
295
+ "content": "<extra_id_32>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "48161": {
303
+ "content": "<extra_id_33>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "48162": {
311
+ "content": "<extra_id_34>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "48163": {
319
+ "content": "<extra_id_35>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "48164": {
327
+ "content": "<extra_id_36>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": true
333
+ },
334
+ "48165": {
335
+ "content": "<extra_id_37>",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "48166": {
343
+ "content": "<extra_id_38>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "48167": {
351
+ "content": "<extra_id_39>",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "48168": {
359
+ "content": "<extra_id_40>",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": true
365
+ },
366
+ "48169": {
367
+ "content": "<extra_id_41>",
368
+ "lstrip": false,
369
+ "normalized": false,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": true
373
+ },
374
+ "48170": {
375
+ "content": "<extra_id_42>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": true
381
+ },
382
+ "48171": {
383
+ "content": "<extra_id_43>",
384
+ "lstrip": false,
385
+ "normalized": false,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": true
389
+ },
390
+ "48172": {
391
+ "content": "<extra_id_44>",
392
+ "lstrip": false,
393
+ "normalized": false,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": true
397
+ },
398
+ "48173": {
399
+ "content": "<extra_id_45>",
400
+ "lstrip": false,
401
+ "normalized": false,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": true
405
+ },
406
+ "48174": {
407
+ "content": "<extra_id_46>",
408
+ "lstrip": false,
409
+ "normalized": false,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": true
413
+ },
414
+ "48175": {
415
+ "content": "<extra_id_47>",
416
+ "lstrip": false,
417
+ "normalized": false,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": true
421
+ },
422
+ "48176": {
423
+ "content": "<extra_id_48>",
424
+ "lstrip": false,
425
+ "normalized": false,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": true
429
+ },
430
+ "48177": {
431
+ "content": "<extra_id_49>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": true
437
+ },
438
+ "48178": {
439
+ "content": "<extra_id_50>",
440
+ "lstrip": false,
441
+ "normalized": false,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": true
445
+ },
446
+ "48179": {
447
+ "content": "<extra_id_51>",
448
+ "lstrip": false,
449
+ "normalized": false,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": true
453
+ },
454
+ "48180": {
455
+ "content": "<extra_id_52>",
456
+ "lstrip": false,
457
+ "normalized": false,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": true
461
+ },
462
+ "48181": {
463
+ "content": "<extra_id_53>",
464
+ "lstrip": false,
465
+ "normalized": false,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": true
469
+ },
470
+ "48182": {
471
+ "content": "<extra_id_54>",
472
+ "lstrip": false,
473
+ "normalized": false,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": true
477
+ },
478
+ "48183": {
479
+ "content": "<extra_id_55>",
480
+ "lstrip": false,
481
+ "normalized": false,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": true
485
+ },
486
+ "48184": {
487
+ "content": "<extra_id_56>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": true
493
+ },
494
+ "48185": {
495
+ "content": "<extra_id_57>",
496
+ "lstrip": false,
497
+ "normalized": false,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": true
501
+ },
502
+ "48186": {
503
+ "content": "<extra_id_58>",
504
+ "lstrip": false,
505
+ "normalized": false,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": true
509
+ },
510
+ "48187": {
511
+ "content": "<extra_id_59>",
512
+ "lstrip": false,
513
+ "normalized": false,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": true
517
+ },
518
+ "48188": {
519
+ "content": "<extra_id_60>",
520
+ "lstrip": false,
521
+ "normalized": false,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": true
525
+ },
526
+ "48189": {
527
+ "content": "<extra_id_61>",
528
+ "lstrip": false,
529
+ "normalized": false,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": true
533
+ },
534
+ "48190": {
535
+ "content": "<extra_id_62>",
536
+ "lstrip": false,
537
+ "normalized": false,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": true
541
+ },
542
+ "48191": {
543
+ "content": "<extra_id_63>",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": true
549
+ },
550
+ "48192": {
551
+ "content": "<extra_id_64>",
552
+ "lstrip": false,
553
+ "normalized": false,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": true
557
+ },
558
+ "48193": {
559
+ "content": "<extra_id_65>",
560
+ "lstrip": false,
561
+ "normalized": false,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": true
565
+ },
566
+ "48194": {
567
+ "content": "<extra_id_66>",
568
+ "lstrip": false,
569
+ "normalized": false,
570
+ "rstrip": false,
571
+ "single_word": false,
572
+ "special": true
573
+ },
574
+ "48195": {
575
+ "content": "<extra_id_67>",
576
+ "lstrip": false,
577
+ "normalized": false,
578
+ "rstrip": false,
579
+ "single_word": false,
580
+ "special": true
581
+ },
582
+ "48196": {
583
+ "content": "<extra_id_68>",
584
+ "lstrip": false,
585
+ "normalized": false,
586
+ "rstrip": false,
587
+ "single_word": false,
588
+ "special": true
589
+ },
590
+ "48197": {
591
+ "content": "<extra_id_69>",
592
+ "lstrip": false,
593
+ "normalized": false,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": true
597
+ },
598
+ "48198": {
599
+ "content": "<extra_id_70>",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false,
604
+ "special": true
605
+ },
606
+ "48199": {
607
+ "content": "<extra_id_71>",
608
+ "lstrip": false,
609
+ "normalized": false,
610
+ "rstrip": false,
611
+ "single_word": false,
612
+ "special": true
613
+ },
614
+ "48200": {
615
+ "content": "<extra_id_72>",
616
+ "lstrip": false,
617
+ "normalized": false,
618
+ "rstrip": false,
619
+ "single_word": false,
620
+ "special": true
621
+ },
622
+ "48201": {
623
+ "content": "<extra_id_73>",
624
+ "lstrip": false,
625
+ "normalized": false,
626
+ "rstrip": false,
627
+ "single_word": false,
628
+ "special": true
629
+ },
630
+ "48202": {
631
+ "content": "<extra_id_74>",
632
+ "lstrip": false,
633
+ "normalized": false,
634
+ "rstrip": false,
635
+ "single_word": false,
636
+ "special": true
637
+ },
638
+ "48203": {
639
+ "content": "<extra_id_75>",
640
+ "lstrip": false,
641
+ "normalized": false,
642
+ "rstrip": false,
643
+ "single_word": false,
644
+ "special": true
645
+ },
646
+ "48204": {
647
+ "content": "<extra_id_76>",
648
+ "lstrip": false,
649
+ "normalized": false,
650
+ "rstrip": false,
651
+ "single_word": false,
652
+ "special": true
653
+ },
654
+ "48205": {
655
+ "content": "<extra_id_77>",
656
+ "lstrip": false,
657
+ "normalized": false,
658
+ "rstrip": false,
659
+ "single_word": false,
660
+ "special": true
661
+ },
662
+ "48206": {
663
+ "content": "<extra_id_78>",
664
+ "lstrip": false,
665
+ "normalized": false,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": true
669
+ },
670
+ "48207": {
671
+ "content": "<extra_id_79>",
672
+ "lstrip": false,
673
+ "normalized": false,
674
+ "rstrip": false,
675
+ "single_word": false,
676
+ "special": true
677
+ },
678
+ "48208": {
679
+ "content": "<extra_id_80>",
680
+ "lstrip": false,
681
+ "normalized": false,
682
+ "rstrip": false,
683
+ "single_word": false,
684
+ "special": true
685
+ },
686
+ "48209": {
687
+ "content": "<extra_id_81>",
688
+ "lstrip": false,
689
+ "normalized": false,
690
+ "rstrip": false,
691
+ "single_word": false,
692
+ "special": true
693
+ },
694
+ "48210": {
695
+ "content": "<extra_id_82>",
696
+ "lstrip": false,
697
+ "normalized": false,
698
+ "rstrip": false,
699
+ "single_word": false,
700
+ "special": true
701
+ },
702
+ "48211": {
703
+ "content": "<extra_id_83>",
704
+ "lstrip": false,
705
+ "normalized": false,
706
+ "rstrip": false,
707
+ "single_word": false,
708
+ "special": true
709
+ },
710
+ "48212": {
711
+ "content": "<extra_id_84>",
712
+ "lstrip": false,
713
+ "normalized": false,
714
+ "rstrip": false,
715
+ "single_word": false,
716
+ "special": true
717
+ },
718
+ "48213": {
719
+ "content": "<extra_id_85>",
720
+ "lstrip": false,
721
+ "normalized": false,
722
+ "rstrip": false,
723
+ "single_word": false,
724
+ "special": true
725
+ },
726
+ "48214": {
727
+ "content": "<extra_id_86>",
728
+ "lstrip": false,
729
+ "normalized": false,
730
+ "rstrip": false,
731
+ "single_word": false,
732
+ "special": true
733
+ },
734
+ "48215": {
735
+ "content": "<extra_id_87>",
736
+ "lstrip": false,
737
+ "normalized": false,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": true
741
+ },
742
+ "48216": {
743
+ "content": "<extra_id_88>",
744
+ "lstrip": false,
745
+ "normalized": false,
746
+ "rstrip": false,
747
+ "single_word": false,
748
+ "special": true
749
+ },
750
+ "48217": {
751
+ "content": "<extra_id_89>",
752
+ "lstrip": false,
753
+ "normalized": false,
754
+ "rstrip": false,
755
+ "single_word": false,
756
+ "special": true
757
+ },
758
+ "48218": {
759
+ "content": "<extra_id_90>",
760
+ "lstrip": false,
761
+ "normalized": false,
762
+ "rstrip": false,
763
+ "single_word": false,
764
+ "special": true
765
+ },
766
+ "48219": {
767
+ "content": "<extra_id_91>",
768
+ "lstrip": false,
769
+ "normalized": false,
770
+ "rstrip": false,
771
+ "single_word": false,
772
+ "special": true
773
+ },
774
+ "48220": {
775
+ "content": "<extra_id_92>",
776
+ "lstrip": false,
777
+ "normalized": false,
778
+ "rstrip": false,
779
+ "single_word": false,
780
+ "special": true
781
+ },
782
+ "48221": {
783
+ "content": "<extra_id_93>",
784
+ "lstrip": false,
785
+ "normalized": false,
786
+ "rstrip": false,
787
+ "single_word": false,
788
+ "special": true
789
+ },
790
+ "48222": {
791
+ "content": "<extra_id_94>",
792
+ "lstrip": false,
793
+ "normalized": false,
794
+ "rstrip": false,
795
+ "single_word": false,
796
+ "special": true
797
+ },
798
+ "48223": {
799
+ "content": "<extra_id_95>",
800
+ "lstrip": false,
801
+ "normalized": false,
802
+ "rstrip": false,
803
+ "single_word": false,
804
+ "special": true
805
+ },
806
+ "48224": {
807
+ "content": "<extra_id_96>",
808
+ "lstrip": false,
809
+ "normalized": false,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": true
813
+ },
814
+ "48225": {
815
+ "content": "<extra_id_97>",
816
+ "lstrip": false,
817
+ "normalized": false,
818
+ "rstrip": false,
819
+ "single_word": false,
820
+ "special": true
821
+ },
822
+ "48226": {
823
+ "content": "<extra_id_98>",
824
+ "lstrip": false,
825
+ "normalized": false,
826
+ "rstrip": false,
827
+ "single_word": false,
828
+ "special": true
829
+ },
830
+ "48227": {
831
+ "content": "<extra_id_99>",
832
+ "lstrip": false,
833
+ "normalized": false,
834
+ "rstrip": false,
835
+ "single_word": false,
836
+ "special": true
837
+ }
838
+ },
839
+ "additional_special_tokens": [
840
+ "<extra_id_0>",
841
+ "<extra_id_1>",
842
+ "<extra_id_2>",
843
+ "<extra_id_3>",
844
+ "<extra_id_4>",
845
+ "<extra_id_5>",
846
+ "<extra_id_6>",
847
+ "<extra_id_7>",
848
+ "<extra_id_8>",
849
+ "<extra_id_9>",
850
+ "<extra_id_10>",
851
+ "<extra_id_11>",
852
+ "<extra_id_12>",
853
+ "<extra_id_13>",
854
+ "<extra_id_14>",
855
+ "<extra_id_15>",
856
+ "<extra_id_16>",
857
+ "<extra_id_17>",
858
+ "<extra_id_18>",
859
+ "<extra_id_19>",
860
+ "<extra_id_20>",
861
+ "<extra_id_21>",
862
+ "<extra_id_22>",
863
+ "<extra_id_23>",
864
+ "<extra_id_24>",
865
+ "<extra_id_25>",
866
+ "<extra_id_26>",
867
+ "<extra_id_27>",
868
+ "<extra_id_28>",
869
+ "<extra_id_29>",
870
+ "<extra_id_30>",
871
+ "<extra_id_31>",
872
+ "<extra_id_32>",
873
+ "<extra_id_33>",
874
+ "<extra_id_34>",
875
+ "<extra_id_35>",
876
+ "<extra_id_36>",
877
+ "<extra_id_37>",
878
+ "<extra_id_38>",
879
+ "<extra_id_39>",
880
+ "<extra_id_40>",
881
+ "<extra_id_41>",
882
+ "<extra_id_42>",
883
+ "<extra_id_43>",
884
+ "<extra_id_44>",
885
+ "<extra_id_45>",
886
+ "<extra_id_46>",
887
+ "<extra_id_47>",
888
+ "<extra_id_48>",
889
+ "<extra_id_49>",
890
+ "<extra_id_50>",
891
+ "<extra_id_51>",
892
+ "<extra_id_52>",
893
+ "<extra_id_53>",
894
+ "<extra_id_54>",
895
+ "<extra_id_55>",
896
+ "<extra_id_56>",
897
+ "<extra_id_57>",
898
+ "<extra_id_58>",
899
+ "<extra_id_59>",
900
+ "<extra_id_60>",
901
+ "<extra_id_61>",
902
+ "<extra_id_62>",
903
+ "<extra_id_63>",
904
+ "<extra_id_64>",
905
+ "<extra_id_65>",
906
+ "<extra_id_66>",
907
+ "<extra_id_67>",
908
+ "<extra_id_68>",
909
+ "<extra_id_69>",
910
+ "<extra_id_70>",
911
+ "<extra_id_71>",
912
+ "<extra_id_72>",
913
+ "<extra_id_73>",
914
+ "<extra_id_74>",
915
+ "<extra_id_75>",
916
+ "<extra_id_76>",
917
+ "<extra_id_77>",
918
+ "<extra_id_78>",
919
+ "<extra_id_79>",
920
+ "<extra_id_80>",
921
+ "<extra_id_81>",
922
+ "<extra_id_82>",
923
+ "<extra_id_83>",
924
+ "<extra_id_84>",
925
+ "<extra_id_85>",
926
+ "<extra_id_86>",
927
+ "<extra_id_87>",
928
+ "<extra_id_88>",
929
+ "<extra_id_89>",
930
+ "<extra_id_90>",
931
+ "<extra_id_91>",
932
+ "<extra_id_92>",
933
+ "<extra_id_93>",
934
+ "<extra_id_94>",
935
+ "<extra_id_95>",
936
+ "<extra_id_96>",
937
+ "<extra_id_97>",
938
+ "<extra_id_98>",
939
+ "<extra_id_99>"
940
+ ],
941
+ "bos_token": "<s>",
942
+ "clean_up_tokenization_spaces": false,
943
+ "eos_token": "</s>",
944
+ "legacy": false,
945
+ "model_max_length": 1000000000,
946
+ "pad_token": "<pad>",
947
+ "sp_model_kwargs": {},
948
+ "spaces_between_special_tokens": false,
949
+ "tokenizer_class": "LlamaTokenizer",
950
+ "unk_token": "<unk>",
951
+ "use_default_system_prompt": false
952
+ }
checkpoints/training_metrics.csv CHANGED
@@ -1562,3 +1562,40 @@ timestamp,step,loss,grad_l2,weights_l2,lr,seconds_per_step
1562
  "2024-08-12 21:16:34,160",78050,1.71,0.351,9067.663,0.0,3.384
1563
  "2024-08-12 21:19:24,074",78100,1.707,0.349,9067.661,0.0,3.398
1564
  "2024-08-12 21:22:14,845",78150,1.701,0.349,9067.66,0.0,3.415
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1562
  "2024-08-12 21:16:34,160",78050,1.71,0.351,9067.663,0.0,3.384
1563
  "2024-08-12 21:19:24,074",78100,1.707,0.349,9067.661,0.0,3.398
1564
  "2024-08-12 21:22:14,845",78150,1.701,0.349,9067.66,0.0,3.415
1565
+ "2024-08-12 21:25:04,253",78200,1.707,0.35,9067.658,0.0,3.388
1566
+ "2024-08-12 21:27:53,707",78250,1.707,0.348,9067.657,0.0,3.389
1567
+ "2024-08-12 21:30:43,019",78300,1.71,0.35,9067.656,0.0,3.386
1568
+ "2024-08-12 21:33:33,014",78350,1.71,0.35,9067.655,0.0,3.4
1569
+ "2024-08-12 21:36:23,186",78400,1.707,0.349,9067.653,0.0,3.403
1570
+ "2024-08-12 21:39:12,309",78450,1.72,0.35,9067.652,0.0,3.382
1571
+ "2024-08-12 21:42:03,162",78500,1.714,0.35,9067.651,0.0,3.417
1572
+ "2024-08-12 21:44:53,192",78550,1.724,0.35,9067.649,0.0,3.401
1573
+ "2024-08-12 21:47:43,149",78600,1.714,0.351,9067.648,0.0,3.399
1574
+ "2024-08-12 21:50:32,387",78650,1.719,0.35,9067.647,0.0,3.385
1575
+ "2024-08-12 21:53:22,026",78700,1.714,0.35,9067.646,0.0,3.393
1576
+ "2024-08-12 21:56:11,907",78750,1.729,0.351,9067.645,0.0,3.398
1577
+ "2024-08-12 21:59:00,947",78800,1.719,0.352,9067.644,0.0,3.381
1578
+ "2024-08-12 22:01:50,443",78850,1.722,0.352,9067.643,0.0,3.39
1579
+ "2024-08-12 22:04:39,064",78900,1.739,0.349,9067.642,0.0,3.372
1580
+ "2024-08-12 22:07:29,275",78950,1.726,0.349,9067.641,0.0,3.404
1581
+ "2024-08-12 22:10:18,964",79000,1.729,0.352,9067.64,0.0,3.394
1582
+ "2024-08-12 22:13:08,518",79050,1.724,0.351,9067.639,0.0,3.391
1583
+ "2024-08-12 22:15:58,096",79100,1.731,0.351,9067.638,0.0,3.392
1584
+ "2024-08-12 22:18:47,746",79150,1.73,0.352,9067.637,0.0,3.393
1585
+ "2024-08-12 22:21:37,645",79200,1.733,0.351,9067.637,0.0,3.398
1586
+ "2024-08-12 22:24:27,038",79250,1.733,0.35,9067.636,0.0,3.388
1587
+ "2024-08-12 22:27:16,116",79300,1.735,0.35,9067.635,0.0,3.382
1588
+ "2024-08-12 22:30:05,701",79350,1.733,0.351,9067.635,0.0,3.392
1589
+ "2024-08-12 22:32:54,419",79400,1.73,0.352,9067.634,0.0,3.374
1590
+ "2024-08-12 22:35:43,068",79450,1.739,0.351,9067.633,0.0,3.373
1591
+ "2024-08-12 22:38:32,666",79500,1.745,0.353,9067.633,0.0,3.392
1592
+ "2024-08-12 22:41:21,888",79550,1.723,0.35,9067.632,0.0,3.384
1593
+ "2024-08-12 22:44:11,844",79600,1.742,0.352,9067.631,0.0,3.399
1594
+ "2024-08-12 22:47:00,902",79650,1.741,0.352,9067.63,0.0,3.381
1595
+ "2024-08-12 22:49:50,032",79700,1.739,0.352,9067.629,0.0,3.383
1596
+ "2024-08-12 22:52:39,520",79750,1.743,0.351,9067.629,0.0,3.39
1597
+ "2024-08-12 22:55:29,331",79800,1.745,0.351,9067.629,0.0,3.396
1598
+ "2024-08-12 22:58:19,091",79850,1.746,0.352,9067.628,0.0,3.395
1599
+ "2024-08-12 23:01:08,868",79900,1.737,0.353,9067.627,0.0,3.396
1600
+ "2024-08-12 23:03:57,751",79950,1.745,0.352,9067.627,0.0,3.378
1601
+ "2024-08-12 23:06:47,601",80000,1.74,0.351,9067.626,0.0,3.397
checkpoints/weights_l2_over_steps.png CHANGED