Hugging Face's logo

t1101675
/
PICL

Model card Files Community
addf400 commited on
Commit
9c7e379
•
1 Parent(s): f60a5cd

add files

Browse files
Files changed (24) hide show
  1. pretrain_data/80M_128/gpt2/icl_0.bin +3 -0
  2. pretrain_data/80M_128/gpt2/icl_0.idx +3 -0
  3. pretrain_data/80M_128/gpt2/map.h5 +3 -0
  4. pretrain_data/full_doc/gpt2/train_lm_0.bin +3 -0
  5. pretrain_data/full_doc/gpt2/train_lm_0.idx +3 -0
  6. pretrain_data/full_doc/gpt2/valid_lm_0.bin +3 -0
  7. pretrain_data/full_doc/gpt2/valid_lm_0.idx +3 -0
  8. pretrain_data/picl/80M_128_TRAIN_p1_en1_hn4_s42_lr5e-05-bs64-G1_4000.pt_L2_filtered_0.0/train_icl_0.bin +3 -0
  9. pretrain_data/picl/80M_128_TRAIN_p1_en1_hn4_s42_lr5e-05-bs64-G1_4000.pt_L2_filtered_0.0/train_icl_0.idx +3 -0
  10. pretrain_data/picl/80M_128_TRAIN_p1_en1_hn4_s42_lr5e-05-bs64-G1_4000.pt_L2_filtered_0.0/valid_icl_0.bin +3 -0
  11. pretrain_data/picl/80M_128_TRAIN_p1_en1_hn4_s42_lr5e-05-bs64-G1_4000.pt_L2_filtered_0.0/valid_icl_0.idx +3 -0
  12. results/picl/picl-large/config.json +39 -0
  13. results/picl/picl-large/merges.txt +0 -0
  14. results/picl/picl-large/pytorch_model.bin +3 -0
  15. results/picl/picl-large/special_tokens_map.json +23 -0
  16. results/picl/picl-large/tokenizer_config.json +34 -0
  17. results/picl/picl-large/vocab.json +0 -0
  18. results/picl/picl-xlarge/config.json +39 -0
  19. results/picl/picl-xlarge/merges.txt +0 -0
  20. results/picl/picl-xlarge/pytorch_model.bin +3 -0
  21. results/picl/picl-xlarge/special_tokens_map.json +23 -0
  22. results/picl/picl-xlarge/tokenizer_config.json +34 -0
  23. results/picl/picl-xlarge/vocab.json +0 -0
  24. results/retriever/TRAIN_p1_en1_hn1_s42/lr5e-05-bs64-G1/4375.pt +3 -0
pretrain_data/80M_128/gpt2/icl_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6e07c1865844d392318466010dce1026d5a592a69d1d3e465f5fced25784df1
3
+ size 13220664808
pretrain_data/80M_128/gpt2/icl_0.idx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c018666a482e925a630bb81bc9b9790def7be0687e0a62d46c2ebafcd98ece04
3
+ size 903856950
pretrain_data/80M_128/gpt2/map.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3318c0840a6388e0c24b6382cb91a59c3bb718dd151bf0bce624bf5417ed59c
3
+ size 602919592
pretrain_data/full_doc/gpt2/train_lm_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b350e6c72aa5d4fa123f11947551d273666a4287d1816d122bd709ae48f07dd5
3
+ size 30578057216
pretrain_data/full_doc/gpt2/train_lm_0.idx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304eae06f145b31d5348eee4817e5c1acf015abdefa7c573a9d97c19c6d59ab4
3
+ size 179168346
pretrain_data/full_doc/gpt2/valid_lm_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a2e68773ea702a13c1b4f8d97fd152f8a189f57498da034e5fb2d9a8796732
3
+ size 20480000
pretrain_data/full_doc/gpt2/valid_lm_0.idx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df140cb38a42bd208a8e1effeebb11151026371a99d3271a65155b740472ef4b
3
+ size 120042
pretrain_data/picl/80M_128_TRAIN_p1_en1_hn4_s42_lr5e-05-bs64-G1_4000.pt_L2_filtered_0.0/train_icl_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:844de2c2128cec3ffc36d329bdc578d25e9b3e20c186bae9a6c19f3e292e2ab0
3
+ size 2015868720
pretrain_data/picl/80M_128_TRAIN_p1_en1_hn4_s42_lr5e-05-bs64-G1_4000.pt_L2_filtered_0.0/train_icl_0.idx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbd4f468a05ebfc7368975faea392e602b80d385a746ac5fcc27140e8157d071
3
+ size 302380350
pretrain_data/picl/80M_128_TRAIN_p1_en1_hn4_s42_lr5e-05-bs64-G1_4000.pt_L2_filtered_0.0/valid_icl_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f863cd36c098b0b7d2506c201d93ca21cf02ded3767feb9303c395cf3e1354f
3
+ size 800000
pretrain_data/picl/80M_128_TRAIN_p1_en1_hn4_s42_lr5e-05-bs64-G1_4000.pt_L2_filtered_0.0/valid_icl_0.idx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34064e37bfadba00cc38cb1ed7c7d369a79a3fb3357e11f5fb9278bf987ae4a
3
+ size 120042
results/picl/picl-large/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/lidong1/CodeRepo/icl_train/results_new/gpt2-xl/",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1600,
16
+ "n_head": 25,
17
+ "n_inner": null,
18
+ "n_layer": 48,
19
+ "n_positions": 1024,
20
+ "output_past": true,
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,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "transformers_version": "4.25.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
results/picl/picl-large/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
results/picl/picl-large/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb24d596482b4e0046203325ef481e5b748d5e75cdb0a442122de3e32991b26
3
+ size 3165688127
results/picl/picl-large/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
results/picl/picl-large/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "name_or_path": "/home/lidong1/CodeRepo/icl_train/results_new/gpt2-xl/",
23
+ "pad_token": null,
24
+ "special_tokens_map_file": null,
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
results/picl/picl-large/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
results/picl/picl-xlarge/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/lidong1/CodeRepo/icl_train/results_new/gpt2-xl/",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1600,
16
+ "n_head": 25,
17
+ "n_inner": null,
18
+ "n_layer": 48,
19
+ "n_positions": 1024,
20
+ "output_past": true,
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,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "transformers_version": "4.25.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
results/picl/picl-xlarge/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
results/picl/picl-xlarge/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd5e2042cb917e0f7f47db761ebbf1b1e638a31842c7877cbf6ecd24bdbb867
3
+ size 3165688127
results/picl/picl-xlarge/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
results/picl/picl-xlarge/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "name_or_path": "/home/lidong1/CodeRepo/icl_train/results_new/gpt2-xl/",
23
+ "pad_token": null,
24
+ "special_tokens_map_file": null,
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
results/picl/picl-xlarge/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
results/retriever/TRAIN_p1_en1_hn1_s42/lr5e-05-bs64-G1/4375.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb293ee9cde723750b1f0d6e8ae54a8b2e40a77bfdc59799ca4e6ad56c67c704
3
+ size 498717105