Hugging Face's logo

duwuonline
/
EsperBERTo

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
4
duwuonline commited on
Commit
b408eaa
•
1 Parent(s): 09c6c9c

End of training

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. config.json +22 -17
  3. generation_config.json +2 -3
  4. pytorch_model.bin +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -32,7 +32,7 @@ More information needed
32
 
33
  The following hyperparameters were used during training:
34
  - learning_rate: 5e-05
35
- - train_batch_size: 128
36
  - eval_batch_size: 16
37
  - seed: 42
38
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
32
 
33
  The following hyperparameters were used during training:
34
  - learning_rate: 5e-05
35
+ - train_batch_size: 32
36
  - eval_batch_size: 16
37
  - seed: 42
38
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
config.json CHANGED
@@ -1,26 +1,31 @@
1
  {
 
2
  "architectures": [
3
- "RobertaForMaskedLM"
4
  ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "bos_token_id": 0,
7
- "classifier_dropout": null,
8
- "eos_token_id": 2,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
- "layer_norm_eps": 1e-12,
15
- "max_position_embeddings": 514,
16
- "model_type": "roberta",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 6,
19
- "pad_token_id": 1,
20
- "position_embedding_type": "absolute",
 
 
 
 
 
 
 
 
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.32.0",
23
- "type_vocab_size": 1,
24
  "use_cache": true,
25
  "vocab_size": 52000
26
  }
 
1
  {
2
+ "activation_function": "gelu_new",
3
  "architectures": [
4
+ "GPT2LMHeadModel"
5
  ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
 
 
 
10
  "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 6,
17
+ "n_positions": 514,
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,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
  "torch_dtype": "float32",
28
  "transformers_version": "4.32.0",
 
29
  "use_cache": true,
30
  "vocab_size": 52000
31
  }
generation_config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "eos_token_id": 2,
5
- "pad_token_id": 1,
6
  "transformers_version": "4.32.0"
7
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
 
5
  "transformers_version": "4.32.0"
6
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d17a6bf7cf93e0f8c7061c628c92c1c4b9d960f5c3b74c9f79485b3c65f9c0c2
3
- size 334053941
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a54da3a79c5d622a28985f4a3fddee954251b7b458fad654901499e7d50842
3
+ size 331462549
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2fa3eb73136e929282d01b85aba563e6b493761b2ed67a57c8d3f5aabbd709b
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd9f37f3003f669d389650c4c24378a2e3a556924b4b5b2887c369f0a38e840d
3
  size 4091