Safetensors
English
gpt2
codebyzeb commited on
Commit
b8b45f9
·
verified ·
1 Parent(s): 980fe17

Training in progress, step 60000

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": 0.1,
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,
@@ -16,7 +16,7 @@
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,
 
3
  "architectures": [
4
  "GPT2LMHeadModel"
5
  ],
6
+ "attn_pdrop": 0.5,
7
  "bos_token_id": 3,
8
+ "embd_pdrop": 0.5,
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": 0.5,
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 sha256:05910aec20f7a6e554c47bbfa609d67bb328542ba5e2d063b559f2915c76df11
3
  size 2539288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:113199b76b1bb44635f1b72d11306f9860c732259136d442bc49defd29216603
3
  size 2539288
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ce886ecdd251f3d0431f2152f78cbaf19088e78c11d28ee1b1efa7eabc0d887
3
- size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25e37002c4f6a6781d1013281479faace7ed07d33e8cba5110290704a2a8219f
3
+ size 5368