Safetensors
English
gpt2
codebyzeb commited on
Commit
3cf4291
·
verified ·
1 Parent(s): 0cd5581

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": 0.3,
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": 0.5,
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 sha256:84e9e345ba9b96dc152e663055a664fc3dba15992763f4c06744c61f7a7ce6bc
3
  size 2539288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8421b108d9b36ae9a23ee260d6d9e8cf1221213c2384bd19a03178b59b21ca8
3
  size 2539288
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b2fe220bf610e709b2bec28aff742115432a5d3ae378aaddecbc85aaa65f5af
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a32c72dd8b3c50f2d66cd2f66a140a9b06a842bb3bb957d8a893356d3d44032c
3
  size 5432