Hugging Face's logo

phonemetransformers
/
babylm-small-gpt2_lm-model

Safetensors
gpt2
Model card Files Community
codebyzeb commited on
Commit
8571987
•
1 Parent(s): 01596ba

Training in progress, step 200000

Browse files
Files changed (5) hide show
  1. babyslm/syntactic.txt +0 -0
  2. blimp_results.json +2 -2
  3. config.json +3 -3
  4. model.safetensors +1 -1
  5. training_args.bin +1 -1
babyslm/syntactic.txt CHANGED
The diff for this file is too large to render. See raw diff
 
blimp_results.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecec2d0a71e5ad52e4e5a161fcc5a57c235eef83a6edb22dc338b7bc8c765196
3
- size 80218899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7339d22b74526e00c5609ce9158cd0abdaedfffa81bda63c6b22d9379a59cc85
3
+ size 80216341
config.json CHANGED
@@ -3,9 +3,9 @@
3
  "architectures": [
4
  "GPT2LMHeadModel"
5
  ],
6
- "attn_pdrop": 0.3,
7
  "bos_token_id": 0,
8
- "embd_pdrop": 0.3,
9
  "eos_token_id": 0,
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
@@ -16,7 +16,7 @@
16
  "n_layer": 6,
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": 0,
8
+ "embd_pdrop": 0.1,
9
  "eos_token_id": 0,
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
 
16
  "n_layer": 6,
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:f6d2430a9d89c08ae462929719a8af51161efdd74289cb400b07e132100a57dd
3
  size 35609928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c2049b541aad9c04277b7760753907d9897ae7d6d2e0f9ff9afb485c302813
3
  size 35609928
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9137eae5b2fc0ccaecfcc834c539253a235e58790318a23a66c11247c57014a
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc05a9b18c09d9343d851f614a906fd152098177d5c8db3b58ee8a0f0ce54453
3
  size 5368