Safetensors
English
gpt2
codebyzeb commited on
Commit
1822e84
·
verified ·
1 Parent(s): 16977b9

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": 0.5,
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,
@@ -16,7 +16,7 @@
16
  "n_layer": 2,
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,
 
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
  "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,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0575afbc1f9bc8cf1e91da5d766d8c4eb1da66d9d742e47a986223473231bfd
3
  size 1745032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66ed444cbb858f4d41873009dc66a5266cae5e6178fc47e4bf4e2608bcd667e5
3
  size 1745032
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:493544d915d71df6847164ffe231f5cd541ba5f75f533123a25a5d2b173e9bf3
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c90507690882c02413cfca6a1bbfc23dce2379df0709a7c49dc6e827b7f5638d
3
  size 5432