Hugging Face's logo

elliepreed
/
french-babylm-ft

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
elliepreed commited on
Commit
8eee09c
·
verified ·
1 Parent(s): 535363e

Training in progress, step 2000

Browse files
Files changed (12) hide show
  1. config.json +32 -0
  2. model.safetensors +3 -0
  3. runs/Aug25_10-30-21_bubbles.cl.cam.ac.uk/events.out.tfevents.1756114228.bubbles.cl.cam.ac.uk.1961564.0 +3 -0
  4. runs/Aug25_10-34-54_bubbles.cl.cam.ac.uk/events.out.tfevents.1756114495.bubbles.cl.cam.ac.uk.1961781.0 +3 -0
  5. runs/Aug25_10-42-12_bubbles.cl.cam.ac.uk/events.out.tfevents.1756114934.bubbles.cl.cam.ac.uk.1961982.0 +3 -0
  6. runs/Aug25_10-45-49_bubbles.cl.cam.ac.uk/events.out.tfevents.1756115150.bubbles.cl.cam.ac.uk.1962249.0 +3 -0
  7. runs/Aug25_10-48-17_bubbles.cl.cam.ac.uk/events.out.tfevents.1756115298.bubbles.cl.cam.ac.uk.1962371.0 +3 -0
  8. runs/Aug25_10-52-29_bubbles.cl.cam.ac.uk/events.out.tfevents.1756115551.bubbles.cl.cam.ac.uk.1962507.0 +3 -0
  9. special_tokens_map.json +37 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +60 -0
  12. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 512,
14
+ "n_embd": 512,
15
+ "n_head": 8,
16
+ "n_inner": 2048,
17
+ "n_layer": 4,
18
+ "n_positions": 512,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.55.4",
30
+ "use_cache": true,
31
+ "vocab_size": 30000
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa8c3d10b84198c0ee892ed1375c531e72c04a151051f4947d57afaebfbd4e69
3
+ size 112935984
runs/Aug25_10-30-21_bubbles.cl.cam.ac.uk/events.out.tfevents.1756114228.bubbles.cl.cam.ac.uk.1961564.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf4ece567709829fde063d89e3eaf2df1045b3b410dbeff91f32892505ff1ba
3
+ size 5118
runs/Aug25_10-34-54_bubbles.cl.cam.ac.uk/events.out.tfevents.1756114495.bubbles.cl.cam.ac.uk.1961781.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc75b6a9abfdd5911cd4e27fd36ad03f75236295a0f6eae2fd797c146cf32bf6
3
+ size 5118
runs/Aug25_10-42-12_bubbles.cl.cam.ac.uk/events.out.tfevents.1756114934.bubbles.cl.cam.ac.uk.1961982.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df74b20e7215858573a3f264a3c8326950069941fa702f44ad4f0990cfaf0526
3
+ size 5118
runs/Aug25_10-45-49_bubbles.cl.cam.ac.uk/events.out.tfevents.1756115150.bubbles.cl.cam.ac.uk.1962249.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2666e2bb1aa7d75ac7d3f044d751a7b9d2b3fc57fb874f091d11a94b5281445
3
+ size 5118
runs/Aug25_10-48-17_bubbles.cl.cam.ac.uk/events.out.tfevents.1756115298.bubbles.cl.cam.ac.uk.1962371.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d68d6249a58d051ed248eeb79bf18b3df4c9013d5a652c8d3f471402b40efda8
3
+ size 5118
runs/Aug25_10-52-29_bubbles.cl.cam.ac.uk/events.out.tfevents.1756115551.bubbles.cl.cam.ac.uk.1962507.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb8467414741099191f366f48d2ac9a7b16f091173671fd82c3e26d9251ff781
3
+ size 13550
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "eos_token": "</s>",
47
+ "extra_special_tokens": {},
48
+ "mask_token": "<mask>",
49
+ "max_length": 512,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "stride": 0,
56
+ "tokenizer_class": "PreTrainedTokenizerFast",
57
+ "truncation_side": "right",
58
+ "truncation_strategy": "longest_first",
59
+ "unk_token": "<unk>"
60
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9daf3535ad7d66319255023303b942cabf50d87c7c90c1369728b0edaf13a233
3
+ size 5777