Safetensors
English
gpt2
codebyzeb commited on
Commit
da4898a
·
verified ·
1 Parent(s): 1d64bf8

Training in progress, step 80000

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": 2,
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": 2,
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:a9a28dd080bb21eadf1f1b201dd67a725bce81256c179f3c52fe6593f489f523
3
  size 1745032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47e9489a559ddc1be5e18a6b1fe39f3b11138c90dcf3f5ff5824265deea1fc0a
3
  size 1745032
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f940ae923ecc4f11bcfebc7b80e86633bf11b5fce32f9d4bdb1c809b730dbc73
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35d7abef20837f2b1d352ffbb2d704a4f9673b753267189e093b1925e12e7d98
3
  size 5432