Hugging Face's logo

danurahul
/
yoav_neo_spaces

Text Generation
Transformers
PyTorch
gpt_neo
Inference Endpoints
Model card Files Community
danurahul commited on
Commit
18804b0
•
1 Parent(s): 8681b30

Initial commit

Browse files
Files changed (7) hide show
  1. config.json +73 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +40 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-1.3B",
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
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local"
33
+ ],
34
+ "attention_types": [
35
+ [
36
+ [
37
+ "global",
38
+ "local"
39
+ ],
40
+ 12
41
+ ]
42
+ ],
43
+ "bos_token_id": 50256,
44
+ "embed_dropout": 0,
45
+ "eos_token_id": 50256,
46
+ "gradient_checkpointing": false,
47
+ "hidden_size": 2048,
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": null,
50
+ "layer_norm_epsilon": 1e-05,
51
+ "max_position_embeddings": 2048,
52
+ "model_type": "gpt_neo",
53
+ "num_heads": 16,
54
+ "num_layers": 24,
55
+ "resid_dropout": 0,
56
+ "summary_activation": null,
57
+ "summary_first_dropout": 0.1,
58
+ "summary_proj_to_labels": true,
59
+ "summary_type": "cls_index",
60
+ "summary_use_proj": true,
61
+ "task_specific_params": {
62
+ "text-generation": {
63
+ "do_sample": true,
64
+ "max_length": 50,
65
+ "temperature": 0.9
66
+ }
67
+ },
68
+ "tokenizer_class": "GPT2Tokenizer",
69
+ "transformers_version": "4.9.0.dev0",
70
+ "use_cache": true,
71
+ "vocab_size": 50257,
72
+ "window_size": 256
73
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1624f5a70b733a46723f9a7105bf3e50de7ca4945667a560030bb0849bdba2e8
3
+ size 10524788609
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eca55e6848d9aa416b9c2a29d216f93fa6cbede9a89733b73cecf475db47249
3
+ size 5312745165
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b39d363c2b9fa44bded0295192a90f842e97a7d8cf140663f54653aced63abbb
3
+ size 13547
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35db5207e4e787f80b3d107c952de152c766032d29e03b3659878e6c5d6b3fa
3
+ size 623
trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.07357810315650062,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 2.9448164226326247e-05,
13
+ "loss": 4.808,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 2.8896328452652492e-05,
19
+ "loss": 4.7761,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 2.8344492678978738e-05,
25
+ "loss": 4.6768,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.07,
30
+ "learning_rate": 2.7792656905304984e-05,
31
+ "loss": 4.6186,
32
+ "step": 2000
33
+ }
34
+ ],
35
+ "max_steps": 27182,
36
+ "num_train_epochs": 1,
37
+ "total_flos": 1010362220544000.0,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c833b29e96e7814660110342471354bb7f377ea6e79ac04f3a1fe4c07b7b3443
3
+ size 2607