Hugging Face's logo

fpadovani
/
cds_w_30

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
fpadovani commited on
Commit
c4888ca
·
verified ·
1 Parent(s): 702a465

Training in progress, step 1000

Browse files
Files changed (8) hide show
  1. check-542/config.json +33 -0
  2. check-542/generation_config.json +9 -0
  3. check-542/model.safetensors +3 -0
  4. check-879/config.json +33 -0
  5. check-879/generation_config.json +9 -0
  6. check-879/model.safetensors +3 -0
  7. model.safetensors +1 -1
  8. validation_batches.log +0 -0
check-542/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "pad_token_id": 2,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "transformers_version": "4.56.1",
31
+ "use_cache": true,
32
+ "vocab_size": 30000
33
+ }
check-542/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2
6
+ ],
7
+ "pad_token_id": 2,
8
+ "transformers_version": "4.56.1"
9
+ }
check-542/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f786b88ddc03b36852a989d7d81cd772f997b7ed8dfbd45a7ba8caf35c7490
3
+ size 435544704
check-879/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "pad_token_id": 2,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "transformers_version": "4.56.1",
31
+ "use_cache": true,
32
+ "vocab_size": 30000
33
+ }
check-879/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2
6
+ ],
7
+ "pad_token_id": 2,
8
+ "transformers_version": "4.56.1"
9
+ }
check-879/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4136280d68ca38c8995edd8f6f44c1d402cc2ab2852db354824f2ecb5ac2d464
3
+ size 435544704
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4136280d68ca38c8995edd8f6f44c1d402cc2ab2852db354824f2ecb5ac2d464
3
  size 435544704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8128fea2ed509afb15758eccdd4a0a3d8db25d49c0760511a88218a804945d1e
3
  size 435544704
validation_batches.log CHANGED
The diff for this file is too large to render. See raw diff