Hugging Face's logo

phonemetransformers
/
babylm-small-gpt2_lm-model

Safetensors
gpt2
Model card Files Community
codebyzeb commited on
Commit
d4119dc
•
1 Parent(s): c109fdb

Training in progress, step 350000

Browse files
Files changed (5) hide show
  1. babyslm/syntactic.txt +0 -0
  2. blimp_results.json +2 -2
  3. config.json +3 -3
  4. model.safetensors +1 -1
  5. training_args.bin +1 -1
babyslm/syntactic.txt CHANGED
The diff for this file is too large to render. See raw diff
 
blimp_results.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee6f0a45a7362e104697f7831959149808946659d4ee4944393e74f923e143b5
3
- size 80226472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454a76aa9d37022887f4565d7c45b4c9cbd3ae69f75092c38a63ab9c37c8ecbf
3
+ size 80217474
config.json CHANGED
@@ -3,9 +3,9 @@
3
  "architectures": [
4
  "GPT2LMHeadModel"
5
  ],
6
- "attn_pdrop": 0.1,
7
  "bos_token_id": 0,
8
- "embd_pdrop": 0.1,
9
  "eos_token_id": 0,
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
@@ -16,7 +16,7 @@
16
  "n_layer": 6,
17
  "n_positions": 256,
18
  "reorder_and_upcast_attn": false,
19
- "resid_pdrop": 0.1,
20
  "scale_attn_by_inverse_layer_idx": false,
21
  "scale_attn_weights": true,
22
  "summary_activation": null,
 
3
  "architectures": [
4
  "GPT2LMHeadModel"
5
  ],
6
+ "attn_pdrop": 0.3,
7
  "bos_token_id": 0,
8
+ "embd_pdrop": 0.3,
9
  "eos_token_id": 0,
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
 
16
  "n_layer": 6,
17
  "n_positions": 256,
18
  "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.3,
20
  "scale_attn_by_inverse_layer_idx": false,
21
  "scale_attn_weights": true,
22
  "summary_activation": null,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82c28483febdc45da6d27e23c81232debfb58f416fc2c6f0830f786d1977ab92
3
  size 108961160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd262c65bdd4317ab52f12d99f14c3e7a9a8dee5cb34aa2f230aecca3233f1f0
3
  size 108961160
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dc80136f7f23f477ebdd661d182228c4de21c404425ed1d103d090bb1541237
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b5a8b6f1890201775a9dff957294eb0b004f3daffec4d13e5aebb84bcac43e
3
  size 5368