Hugging Face's logo

lapp0
/
gpt2_bitnet_logit_distillation_test_metrics

TensorBoard
Safetensors
gpt2
Model card Files
xet
 Metrics Community
lapp0 commited on
Commit
cd7a245
·
verified ·
1 Parent(s): 1681b85

Training in progress, step 1689

Browse files
Files changed (20) hide show
  1. config.json +40 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/Aug02_18-41-40_cf4d11a0c942/events.out.tfevents.1722624100.cf4d11a0c942 +3 -0
  5. runs/Aug02_18-46-06_cf4d11a0c942/events.out.tfevents.1722624366.cf4d11a0c942 +3 -0
  6. runs/Aug02_19-18-33_cf4d11a0c942/events.out.tfevents.1722626313.cf4d11a0c942 +3 -0
  7. runs/Aug02_19-19-30_cf4d11a0c942/events.out.tfevents.1722626370.cf4d11a0c942 +3 -0
  8. runs/Aug02_20-59-43_cf4d11a0c942/events.out.tfevents.1722632555.cf4d11a0c942 +3 -0
  9. runs/Aug02_21-11-49_cf4d11a0c942/events.out.tfevents.1722633118.cf4d11a0c942 +3 -0
  10. runs/Aug02_21-20-49_cf4d11a0c942/events.out.tfevents.1722633658.cf4d11a0c942 +3 -0
  11. runs/Aug02_21-33-54_cf4d11a0c942/events.out.tfevents.1722634457.cf4d11a0c942 +3 -0
  12. runs/Aug02_21-35-14_cf4d11a0c942/events.out.tfevents.1722634538.cf4d11a0c942 +3 -0
  13. runs/Aug02_21-36-24_cf4d11a0c942/events.out.tfevents.1722634608.cf4d11a0c942 +3 -0
  14. runs/Aug02_21-37-27_cf4d11a0c942/events.out.tfevents.1722634671.cf4d11a0c942 +3 -0
  15. runs/Aug02_21-39-32_cf4d11a0c942/events.out.tfevents.1722634796.cf4d11a0c942 +3 -0
  16. special_tokens_map.json +6 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +20 -0
  19. training_args.bin +3 -0
  20. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_implementation": "flash_attention_2",
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
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,
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
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.42.4",
38
+ "use_cache": true,
39
+ "vocab_size": 50257
40
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37b5dee37545a0a8ca1f640a4f56d54938ea98618fb8bfc75e242e4abf44d450
3
+ size 248894656
runs/Aug02_18-41-40_cf4d11a0c942/events.out.tfevents.1722624100.cf4d11a0c942 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:855fead205b952e985cb98deb933bba0ed5d10e8cf7008b316c87bb691d832cc
3
+ size 5080
runs/Aug02_18-46-06_cf4d11a0c942/events.out.tfevents.1722624366.cf4d11a0c942 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd0475c0a6fe873096c7215f801676d8e29bb52433b7dca9ae1eb8e4f1ebdecf
3
+ size 676607
runs/Aug02_19-18-33_cf4d11a0c942/events.out.tfevents.1722626313.cf4d11a0c942 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4741a8dc4ae2d09d68a8c7a5bf36369316ea92fb9ae3d10efdc26f262ed4c252
3
+ size 5079
runs/Aug02_19-19-30_cf4d11a0c942/events.out.tfevents.1722626370.cf4d11a0c942 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:defca4014135e0b853fcdbe95fb19362578b0bd7709d80f296988819e110cb0b
3
+ size 1785554
runs/Aug02_20-59-43_cf4d11a0c942/events.out.tfevents.1722632555.cf4d11a0c942 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88ec9bcb00d41f5cf2da15f1d9a55ec13cdb05b2927c2b42fac63b56e2fbfa5a
3
+ size 241955
runs/Aug02_21-11-49_cf4d11a0c942/events.out.tfevents.1722633118.cf4d11a0c942 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d635d7fc423aea3cd6c6580ea914baa41fc4623f08672bb550ef3b77caa51c7
3
+ size 226763
runs/Aug02_21-20-49_cf4d11a0c942/events.out.tfevents.1722633658.cf4d11a0c942 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fae21f2f3a9a8316cc5c1ae526756cb922861100f245e822a294a1e58e6eb61
3
+ size 123373
runs/Aug02_21-33-54_cf4d11a0c942/events.out.tfevents.1722634457.cf4d11a0c942 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df46bddf0213fc2dfe993b67e0ce62e24eaac561eab3192e7eac70701176078
3
+ size 5087
runs/Aug02_21-35-14_cf4d11a0c942/events.out.tfevents.1722634538.cf4d11a0c942 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5518b57598fbb2cb7cc2bee1ba82a131e133e165f3f5b6e2f252cd0f56fd7156
3
+ size 5087
runs/Aug02_21-36-24_cf4d11a0c942/events.out.tfevents.1722634608.cf4d11a0c942 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c1a34910f5380db2e737079717b06a376e771b7f95afd752d273e44c6cc90be
3
+ size 5087
runs/Aug02_21-37-27_cf4d11a0c942/events.out.tfevents.1722634671.cf4d11a0c942 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc4ee1b58a2be1f267ecd3e94a19f2722735c55ebde2dd286cfad09c3266c69
3
+ size 5087
runs/Aug02_21-39-32_cf4d11a0c942/events.out.tfevents.1722634796.cf4d11a0c942 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83969e8151f5190a2a9a20e78736bbd60228862ba86392153259aacb14800f50
3
+ size 361545
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a1921c94212c6904ad20e87da3f8c26e163e714bb30e4425f5cc49433a78c3b
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff