Hugging Face's logo

pritoms
/
gpt-neo-125M-Byethon

Text Generation
Transformers
PyTorch
TensorBoard
gpt_neo
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
1
pritoms commited on
Commit
a269109
•
1 Parent(s): 5539fcd

add model

Browse files
Files changed (7) hide show
  1. README.md +7 -7
  2. config.json +39 -17
  3. pytorch_model.bin +2 -2
  4. runs/Sep12_11-06-47_a8ec3b9c2c31/1631444984.2086613/events.out.tfevents.1631444984.a8ec3b9c2c31.89.1 +3 -0
  5. runs/Sep12_11-06-47_a8ec3b9c2c31/events.out.tfevents.1631444984.a8ec3b9c2c31.89.0 +3 -0
  6. runs/Sep12_11-06-47_a8ec3b9c2c31/events.out.tfevents.1631445273.a8ec3b9c2c31.89.2 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- license: mit
3
  tags:
4
  - generated_from_trainer
5
  datasets:
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # gpt-neo-125M-Byethon
19
 
20
- This model is a fine-tuned version of [Sentdex/GPyT](https://huggingface.co/Sentdex/GPyT) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 1.6310
23
 
24
  ## Model description
25
 
@@ -50,14 +50,14 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | No log | 1.0 | 31 | 2.6150 |
54
- | No log | 2.0 | 62 | 1.8266 |
55
- | No log | 3.0 | 93 | 1.6310 |
56
 
57
 
58
  ### Framework versions
59
 
60
- - Transformers 4.10.0
61
  - Pytorch 1.9.0+cu102
62
  - Datasets 1.11.0
63
  - Tokenizers 0.10.3
1
  ---
2
+ license: apache-2.0
3
  tags:
4
  - generated_from_trainer
5
  datasets:
17
 
18
  # gpt-neo-125M-Byethon
19
 
20
+ This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.6609
23
 
24
  ## Model description
25
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | No log | 1.0 | 237 | 0.8348 |
54
+ | No log | 2.0 | 474 | 0.6931 |
55
+ | 0.8151 | 3.0 | 711 | 0.6609 |
56
 
57
 
58
  ### Framework versions
59
 
60
+ - Transformers 4.10.2
61
  - Pytorch 1.9.0+cu102
62
  - Datasets 1.11.0
63
  - Tokenizers 0.10.3
config.json CHANGED
@@ -1,32 +1,54 @@
1
  {
2
- "_name_or_path": "Sentdex/GPyT",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPT2LMHeadModel"
6
  ],
7
- "attn_pdrop": 0.1,
8
- "bos_token_id": 0,
9
- "embd_pdrop": 0.1,
10
- "eos_token_id": 2,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "gradient_checkpointing": false,
 
12
  "initializer_range": 0.02,
 
13
  "layer_norm_epsilon": 1e-05,
14
- "model_type": "gpt2",
15
- "n_ctx": 1024,
16
- "n_embd": 768,
17
- "n_head": 12,
18
- "n_inner": null,
19
- "n_layer": 12,
20
- "n_positions": 1024,
21
- "resid_pdrop": 0.1,
22
- "scale_attn_weights": true,
23
  "summary_activation": null,
24
  "summary_first_dropout": 0.1,
25
  "summary_proj_to_labels": true,
26
  "summary_type": "cls_index",
27
  "summary_use_proj": true,
28
  "torch_dtype": "float32",
29
- "transformers_version": "4.10.0",
30
  "use_cache": true,
31
- "vocab_size": 52000
 
32
  }
1
  {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125M",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
+ "GPTNeoForCausalLM"
6
  ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "embed_dropout": 0,
33
+ "eos_token_id": 50256,
34
  "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
  "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
  "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
 
 
 
 
44
  "summary_activation": null,
45
  "summary_first_dropout": 0.1,
46
  "summary_proj_to_labels": true,
47
  "summary_type": "cls_index",
48
  "summary_use_proj": true,
49
  "torch_dtype": "float32",
50
+ "transformers_version": "4.10.2",
51
  "use_cache": true,
52
+ "vocab_size": 50257,
53
+ "window_size": 256
54
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db8ada5d04a75b73895b09ad0480668c25cf2b932efb03a58892523022d486cc
3
- size 515758313
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ee1561b1159962251651ccd460786ed1fde26d9fce492ff50948e8ecac3de2
3
+ size 526017245
runs/Sep12_11-06-47_a8ec3b9c2c31/1631444984.2086613/events.out.tfevents.1631444984.a8ec3b9c2c31.89.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9642c69020dc6836366e98b4ee782ec7b60e3a0bcd7b1b0f48b25f3c36b2191f
3
+ size 4181
runs/Sep12_11-06-47_a8ec3b9c2c31/events.out.tfevents.1631444984.a8ec3b9c2c31.89.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8696b5de2202bfcf8d8540339c277a917e7c1d7ce41ebf7caa5930e721943ce
3
+ size 4679
runs/Sep12_11-06-47_a8ec3b9c2c31/events.out.tfevents.1631445273.a8ec3b9c2c31.89.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d87a34b29fbc310268d819a4ce8982ee36161f626c9393e3366c7c6e87d715
3
+ size 311
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4c12a69a8c8ca3816ecfaed1c985a39a507271f90d0aaca8329049e442a6e7e
3
  size 2671
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a66e18874ed322a431a41363fa044693475e667104a4a0ed2e9225c8563232be
3
  size 2671