Jingmei commited on
Commit
38f7d53
1 Parent(s): 895ccc2

End of training

Browse files
Files changed (47) hide show
  1. README.md +58 -0
  2. adapter_config.json +29 -0
  3. adapter_model.safetensors +3 -0
  4. trainer_peft.log +120 -0
  5. training_args.bin +3 -0
  6. transformed_cache/test_chunked_00000_of_00005.arrow +3 -0
  7. transformed_cache/test_chunked_00001_of_00005.arrow +3 -0
  8. transformed_cache/test_chunked_00002_of_00005.arrow +3 -0
  9. transformed_cache/test_chunked_00003_of_00005.arrow +3 -0
  10. transformed_cache/test_chunked_00004_of_00005.arrow +3 -0
  11. transformed_cache/test_tokenized_00000_of_00005.arrow +3 -0
  12. transformed_cache/test_tokenized_00001_of_00005.arrow +3 -0
  13. transformed_cache/test_tokenized_00002_of_00005.arrow +3 -0
  14. transformed_cache/test_tokenized_00003_of_00005.arrow +3 -0
  15. transformed_cache/test_tokenized_00004_of_00005.arrow +3 -0
  16. transformed_cache/train_chunked_00000_of_00016.arrow +3 -0
  17. transformed_cache/train_chunked_00001_of_00016.arrow +3 -0
  18. transformed_cache/train_chunked_00002_of_00016.arrow +3 -0
  19. transformed_cache/train_chunked_00003_of_00016.arrow +3 -0
  20. transformed_cache/train_chunked_00004_of_00016.arrow +3 -0
  21. transformed_cache/train_chunked_00005_of_00016.arrow +3 -0
  22. transformed_cache/train_chunked_00006_of_00016.arrow +3 -0
  23. transformed_cache/train_chunked_00007_of_00016.arrow +3 -0
  24. transformed_cache/train_chunked_00008_of_00016.arrow +3 -0
  25. transformed_cache/train_chunked_00009_of_00016.arrow +3 -0
  26. transformed_cache/train_chunked_00010_of_00016.arrow +3 -0
  27. transformed_cache/train_chunked_00011_of_00016.arrow +3 -0
  28. transformed_cache/train_chunked_00012_of_00016.arrow +3 -0
  29. transformed_cache/train_chunked_00013_of_00016.arrow +3 -0
  30. transformed_cache/train_chunked_00014_of_00016.arrow +3 -0
  31. transformed_cache/train_chunked_00015_of_00016.arrow +3 -0
  32. transformed_cache/train_tokenized_00000_of_00016.arrow +3 -0
  33. transformed_cache/train_tokenized_00001_of_00016.arrow +3 -0
  34. transformed_cache/train_tokenized_00002_of_00016.arrow +3 -0
  35. transformed_cache/train_tokenized_00003_of_00016.arrow +3 -0
  36. transformed_cache/train_tokenized_00004_of_00016.arrow +3 -0
  37. transformed_cache/train_tokenized_00005_of_00016.arrow +3 -0
  38. transformed_cache/train_tokenized_00006_of_00016.arrow +3 -0
  39. transformed_cache/train_tokenized_00007_of_00016.arrow +3 -0
  40. transformed_cache/train_tokenized_00008_of_00016.arrow +3 -0
  41. transformed_cache/train_tokenized_00009_of_00016.arrow +3 -0
  42. transformed_cache/train_tokenized_00010_of_00016.arrow +3 -0
  43. transformed_cache/train_tokenized_00011_of_00016.arrow +3 -0
  44. transformed_cache/train_tokenized_00012_of_00016.arrow +3 -0
  45. transformed_cache/train_tokenized_00013_of_00016.arrow +3 -0
  46. transformed_cache/train_tokenized_00014_of_00016.arrow +3 -0
  47. transformed_cache/train_tokenized_00015_of_00016.arrow +3 -0
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: chaoyi-wu/PMC_LLAMA_7B
7
+ model-index:
8
+ - name: peft_trainer_Wiki_LambdaH100
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/noc-lab/PMC_LLAMA_7B_peft_trainer_Wiki_LambdaH100/runs/jmfdjw90)
16
+ # peft_trainer_Wiki_LambdaH100
17
+
18
+ This model is a fine-tuned version of [chaoyi-wu/PMC_LLAMA_7B](https://huggingface.co/chaoyi-wu/PMC_LLAMA_7B) on an unknown dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 48
39
+ - eval_batch_size: 48
40
+ - seed: 123
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 384
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: cosine
45
+ - lr_scheduler_warmup_ratio: 0.03
46
+ - num_epochs: 1.0
47
+
48
+ ### Training results
49
+
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - PEFT 0.11.1
55
+ - Transformers 4.42.0.dev0
56
+ - Pytorch 2.3.0
57
+ - Datasets 2.19.1
58
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "chaoyi-wu/PMC_LLAMA_7B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f4bae66f38e01a896e14103f8a381d869cc9191443aa6b7768d90887afa064a
3
+ size 16794200
trainer_peft.log ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-05-22 05:28 - Cuda check
2
+ 2024-05-22 05:28 - True
3
+ 2024-05-22 05:28 - 1
4
+ 2024-05-22 05:28 - Configue Model and tokenizer
5
+ 2024-05-22 05:38 - Cuda check
6
+ 2024-05-22 05:38 - True
7
+ 2024-05-22 05:38 - 1
8
+ 2024-05-22 05:38 - Configue Model and tokenizer
9
+ 2024-05-22 05:39 - Cuda check
10
+ 2024-05-22 05:39 - True
11
+ 2024-05-22 05:39 - 1
12
+ 2024-05-22 05:39 - Configue Model and tokenizer
13
+ 2024-05-22 05:43 - Cuda check
14
+ 2024-05-22 05:43 - True
15
+ 2024-05-22 05:43 - 1
16
+ 2024-05-22 05:43 - Configue Model and tokenizer
17
+ 2024-05-22 06:05 - Cuda check
18
+ 2024-05-22 06:05 - True
19
+ 2024-05-22 06:05 - 1
20
+ 2024-05-22 06:05 - Configue Model and tokenizer
21
+ 2024-05-22 06:06 - Memory usage in 3.63 GB
22
+ 2024-05-22 06:07 - Cuda check
23
+ 2024-05-22 06:07 - True
24
+ 2024-05-22 06:07 - 1
25
+ 2024-05-22 06:07 - Configue Model and tokenizer
26
+ 2024-05-22 06:07 - Memory usage in 3.63 GB
27
+ 2024-05-22 06:07 - Dataset loaded successfully:
28
+ train-Jingmei/Pandemic_Wiki
29
+ test -Jingmei/Pandemic_WHO
30
+ 2024-05-22 06:07 - Tokenize data: completed successfully.
31
+ 2024-05-22 06:07 - Split data into chunks: completed successfully.
32
+ 2024-05-22 06:07 - Setup PEFT
33
+ 2024-05-22 06:07 - Setup optimizer
34
+ 2024-05-22 06:08 - Cuda check
35
+ 2024-05-22 06:08 - True
36
+ 2024-05-22 06:08 - 1
37
+ 2024-05-22 06:08 - Configue Model and tokenizer
38
+ 2024-05-22 06:08 - Memory usage in 3.63 GB
39
+ 2024-05-22 06:08 - Dataset loaded successfully:
40
+ train-Jingmei/Pandemic_Wiki
41
+ test -Jingmei/Pandemic_WHO
42
+ 2024-05-22 06:08 - Tokenize data: completed successfully.
43
+ 2024-05-22 06:08 - Split data into chunks: completed successfully.
44
+ 2024-05-22 06:08 - Setup PEFT
45
+ 2024-05-22 06:08 - Setup optimizer
46
+ 2024-05-22 06:09 - Cuda check
47
+ 2024-05-22 06:09 - True
48
+ 2024-05-22 06:09 - 1
49
+ 2024-05-22 06:09 - Configue Model and tokenizer
50
+ 2024-05-22 06:09 - Memory usage in 3.63 GB
51
+ 2024-05-22 06:09 - Dataset loaded successfully:
52
+ train-Jingmei/Pandemic_Wiki
53
+ test -Jingmei/Pandemic_WHO
54
+ 2024-05-22 06:09 - Tokenize data: completed successfully.
55
+ 2024-05-22 06:09 - Split data into chunks: completed successfully.
56
+ 2024-05-22 06:09 - Setup PEFT
57
+ 2024-05-22 06:09 - Setup optimizer
58
+ 2024-05-22 06:10 - Cuda check
59
+ 2024-05-22 06:10 - True
60
+ 2024-05-22 06:10 - 1
61
+ 2024-05-22 06:10 - Configue Model and tokenizer
62
+ 2024-05-22 06:10 - Memory usage in 3.63 GB
63
+ 2024-05-22 06:10 - Dataset loaded successfully:
64
+ train-Jingmei/Pandemic_Wiki
65
+ test -Jingmei/Pandemic_WHO
66
+ 2024-05-22 06:10 - Tokenize data: completed successfully.
67
+ 2024-05-22 06:10 - Split data into chunks: completed successfully.
68
+ 2024-05-22 06:10 - Setup PEFT
69
+ 2024-05-22 06:10 - Setup optimizer
70
+ 2024-05-22 06:12 - Cuda check
71
+ 2024-05-22 06:12 - True
72
+ 2024-05-22 06:12 - 1
73
+ 2024-05-22 06:12 - Configue Model and tokenizer
74
+ 2024-05-22 06:12 - Memory usage in 3.63 GB
75
+ 2024-05-22 06:12 - Dataset loaded successfully:
76
+ train-Jingmei/Pandemic_Wiki
77
+ test -Jingmei/Pandemic_WHO
78
+ 2024-05-22 06:12 - Tokenize data: completed successfully.
79
+ 2024-05-22 06:12 - Split data into chunks: completed successfully.
80
+ 2024-05-22 06:12 - Setup PEFT
81
+ 2024-05-22 06:12 - Setup optimizer
82
+ 2024-05-22 06:14 - Cuda check
83
+ 2024-05-22 06:14 - True
84
+ 2024-05-22 06:14 - 1
85
+ 2024-05-22 06:14 - Configue Model and tokenizer
86
+ 2024-05-22 06:15 - Memory usage in 3.63 GB
87
+ 2024-05-22 06:15 - Dataset loaded successfully:
88
+ train-Jingmei/Pandemic_Wiki
89
+ test -Jingmei/Pandemic_WHO
90
+ 2024-05-22 06:15 - Tokenize data: completed successfully.
91
+ 2024-05-22 06:15 - Split data into chunks: completed successfully.
92
+ 2024-05-22 06:15 - Setup PEFT
93
+ 2024-05-22 06:15 - Setup optimizer
94
+ 2024-05-22 06:15 - Start training
95
+ 2024-05-22 06:17 - Cuda check
96
+ 2024-05-22 06:17 - True
97
+ 2024-05-22 06:17 - 1
98
+ 2024-05-22 06:17 - Configue Model and tokenizer
99
+ 2024-05-22 06:17 - Memory usage in 3.63 GB
100
+ 2024-05-22 06:17 - Dataset loaded successfully:
101
+ train-Jingmei/Pandemic_Wiki
102
+ test -Jingmei/Pandemic_WHO
103
+ 2024-05-22 06:17 - Tokenize data: completed successfully.
104
+ 2024-05-22 06:17 - Split data into chunks: completed successfully.
105
+ 2024-05-22 06:17 - Setup PEFT
106
+ 2024-05-22 06:17 - Setup optimizer
107
+ 2024-05-22 06:17 - Start training
108
+ 2024-05-22 06:19 - Cuda check
109
+ 2024-05-22 06:19 - True
110
+ 2024-05-22 06:19 - 1
111
+ 2024-05-22 06:19 - Configue Model and tokenizer
112
+ 2024-05-22 06:21 - Memory usage in 3.63 GB
113
+ 2024-05-22 06:22 - Dataset loaded successfully:
114
+ train-Jingmei/Pandemic_Wiki
115
+ test -Jingmei/Pandemic_WHO
116
+ 2024-05-22 06:22 - Tokenize data: completed successfully.
117
+ 2024-05-22 06:22 - Split data into chunks: completed successfully.
118
+ 2024-05-22 06:22 - Setup PEFT
119
+ 2024-05-22 06:22 - Setup optimizer
120
+ 2024-05-22 06:22 - Start training
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c063e47c6c90f1949e3d924787614e3f840578e1e115362e74eaec6fdb530c
3
+ size 5240
transformed_cache/test_chunked_00000_of_00005.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:381f02c96fc1e86f1a72218a70a7e15d669c830b6f22e37f2c1c71330516ef6a
3
+ size 6048
transformed_cache/test_chunked_00001_of_00005.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27a8863898cf892491462c37ce74592381e1977e8d3f1e2e11ea2b35d920437e
3
+ size 8608
transformed_cache/test_chunked_00002_of_00005.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7da6a33785e442faa627d1b74830d46ea14295e15383b3aaa265098e2f4578b
3
+ size 21456
transformed_cache/test_chunked_00003_of_00005.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d7e87307135680e068be016117ac5226ebb2d2f125132d6204a3e7d064591a
3
+ size 3472
transformed_cache/test_chunked_00004_of_00005.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3c83eba80e9a36b598fec586ccf2419d64f20fffc6d08f1af60e991c1ee3e5
3
+ size 21456
transformed_cache/test_tokenized_00000_of_00005.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266df7f986a53de9bdcec75b4bde0bf1a3f52040c65c50aade785d745ea3d455
3
+ size 8432
transformed_cache/test_tokenized_00001_of_00005.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9ecf0a455d4614ad786beb17cf162f1bbae4c262be41bfbd1ac9150b909999
3
+ size 10256
transformed_cache/test_tokenized_00002_of_00005.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d14da2f24b3d608408b5784703a2818fd1631d1006ef963a344471a146bc5a
3
+ size 22512
transformed_cache/test_tokenized_00003_of_00005.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0067b00bc052e6e75e038dc81cfbca859625b85d9fc2ab83d2bfe0e9c71283
3
+ size 4648
transformed_cache/test_tokenized_00004_of_00005.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2714c3240b3321d4b8d3338e011c67ff6c387e0fab54c1ac2012e3b2e4c4e9c
3
+ size 21728
transformed_cache/train_chunked_00000_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d0d5d393329f8b3d7198f98917b4a4c4f8208347343aa97a843771748693d55
3
+ size 6048
transformed_cache/train_chunked_00001_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a78189cf29c603531ab6510b760deb5dc3da9e21399be89199bdbbf8339294
3
+ size 129312
transformed_cache/train_chunked_00002_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c1db6eaaa51d2fd68a7be5938b2263474659692d107315b300d6c7f9bbf2196
3
+ size 85648
transformed_cache/train_chunked_00003_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b2ae2e67204d5eb6549a56a3ef71dfd4e5a5b817f1683f8d7c599e745b5e372
3
+ size 42000
transformed_cache/train_chunked_00004_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ed5c933f7d88b3be0c61800696b5c9be0c4cf0b107af70a870f8e71f03c0d1
3
+ size 34288
transformed_cache/train_chunked_00005_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0a5d8b4b1bccf51e61e187bba48a625d3239d8bd2d866e833e745054fca29d
3
+ size 44560
transformed_cache/train_chunked_00006_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c5d3b8160ef21c71ed21a5e3d42ee1db5665f15bb419f1af489896337f500a0
3
+ size 8608
transformed_cache/train_chunked_00007_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdfc6fde682e176bb9572d0cbf9b1b01571535600705399be9a5f01fe9842aab
3
+ size 75376
transformed_cache/train_chunked_00008_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f50bd02393c85f3d3dfe3abd555b331426d4e188ba79cbec3f8581ccd410c495
3
+ size 2264
transformed_cache/train_chunked_00009_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b312d1ca10fb477e2b84e1660011489ab736172d6d8260574a2da26c8016df
3
+ size 54832
transformed_cache/train_chunked_00010_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b21498a264d3b906444557cd5fe598c37fb935f59467182690d86ed4c6350d6e
3
+ size 13744
transformed_cache/train_chunked_00011_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2800948d4e9edbb741faf45593f9b2baa23d80495f5b5e8ffaf8cdb120922ee
3
+ size 8608
transformed_cache/train_chunked_00012_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:887c9617219a223bb0f6a421cfd516a2adf4bdd510135757a03cc7fbf6b5d601
3
+ size 34288
transformed_cache/train_chunked_00013_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f55cc06573542dd47141112c5400585ec42f090328568dcbb3dc9dcf77a38e3a
3
+ size 80512
transformed_cache/train_chunked_00014_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e57f3a3d01f6e6b5f92a2fb32de26de8a9d5f916fd4011068f2b235eaecc9ec
3
+ size 3472
transformed_cache/train_chunked_00015_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e6efe7101fc2f948347b503b1321e6e900b226648c08f3bd8196177ae094529
3
+ size 44560
transformed_cache/train_tokenized_00000_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03a327ee8d872ca1b261c493628f38c42678cd0d66a2a91ffe499e65ab77e460
3
+ size 7824
transformed_cache/train_tokenized_00001_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a8db56a0fd0f4e62cf9f6999df0727f81098eee92cf96d0df46ef03b1be07c
3
+ size 131168
transformed_cache/train_tokenized_00002_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed003523f27024a973187e6d6f4d825de486352db521bb0bfe7bb4540f3419ab
3
+ size 86664
transformed_cache/train_tokenized_00003_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3fd3739f941ca165774b13ce349733662ab0778be84ba3494c075ed03f541f4
3
+ size 43320
transformed_cache/train_tokenized_00004_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa04551d506eb86fdd872fb27933054931baf0c6d8e6e182e717bdcb04aa4cc2
3
+ size 36568
transformed_cache/train_tokenized_00005_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81bf504c2e7428ff3708fa072d60b336861adf07f988941b14579f8aef0bfe5a
3
+ size 45392
transformed_cache/train_tokenized_00006_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ed71cbda249727733a94172dfea8c4b42b17bdc4ab4dd0ff899753cf0bb8549
3
+ size 9856
transformed_cache/train_tokenized_00007_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:278d798c3b79c3aa07cda9468ae7ff26e81c167ec8bf0c93aecdb086f1bffc07
3
+ size 75544
transformed_cache/train_tokenized_00008_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2b9f6454b128c4dd14fb4961462bbd6096935809e05736aad8be53f2c4d9b8
3
+ size 2264
transformed_cache/train_tokenized_00009_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5be6e409ba24d84758f6158be0792e9b1b57385c028f29d247881720d6922e44
3
+ size 54752
transformed_cache/train_tokenized_00010_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b053d11dcac5265c411ced23180751fb34dd6e4e3fa8647a27065b662d58576
3
+ size 14968
transformed_cache/train_tokenized_00011_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d100af1cae19f4b74c0dc4ed938c40761b7cc3b52f908eb3170988cdc609f554
3
+ size 8808
transformed_cache/train_tokenized_00012_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:839d974ec3b7f726d2911883f9a4e30cdf2ee74c2f8c1e2ed67624b68552df9e
3
+ size 36192
transformed_cache/train_tokenized_00013_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31c32a73f0231cdd2bf1d5cdbf12c5c4ed36d282b9696a2f6fc5cb938bd4408
3
+ size 81312
transformed_cache/train_tokenized_00014_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7d1b150dc3a1912662c5405d8cda8c9ba7a2d486f2e67f418e7e5da7f699e3e
3
+ size 4704
transformed_cache/train_tokenized_00015_of_00016.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05500ddaa8fe2da245eae1bb31e27897ac5bae346726f3f9ee59683701ab5a8c
3
+ size 45392