Safetensors
English
gpt2
codebyzeb commited on
Commit
2f28ebf
·
verified ·
1 Parent(s): be20ee5

Training in progress, step 40000

Browse files
babyslm/lexical.txt CHANGED
The diff for this file is too large to render. See raw diff
 
babyslm/syntactic.txt CHANGED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -3,9 +3,9 @@
3
  "architectures": [
4
  "GPT2LMHeadModel"
5
  ],
6
- "attn_pdrop": 0.3,
7
  "bos_token_id": 3,
8
- "embd_pdrop": 0.3,
9
  "eos_token_id": 3,
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
@@ -16,7 +16,7 @@
16
  "n_layer": 3,
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,
 
3
  "architectures": [
4
  "GPT2LMHeadModel"
5
  ],
6
+ "attn_pdrop": 0.1,
7
  "bos_token_id": 3,
8
+ "embd_pdrop": 0.1,
9
  "eos_token_id": 3,
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
 
16
  "n_layer": 3,
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,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc62c7617daed37953403872ceebd07609a29a1009f0a1f2ef1df41ced53abd1
3
  size 2539288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20c2d5916e4ea4be8b3420882a6ca1faccc163a4934c7f68e6969d36b51dadcc
3
  size 2539288
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61acc1dd149136b468e858c5fa63c32877b44f787b1eb7e3744f23cba94ecd0b
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3808e766552a7af542f8fb2b4a73abb009753c42ef3c04814748d71c0a1c43c6
3
  size 5432