Hugging Face's logo

orendar
/
language_model

Text Generation
Transformers
PyTorch
gpt_neo
Inference Endpoints
Model card Files Community
1
orendar commited on
Commit
be83c4a
•
1 Parent(s): 0c37b21

First version of the language model and tokenizer.

Browse files
Files changed (11) hide show
  1. all_results.json +8 -0
  2. config.json +73 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +1 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +1 -0
  8. train_results.json +8 -0
  9. trainer_state.json +31 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 2.338944840370547,
4
+ "train_runtime": 6731.0386,
5
+ "train_samples": 2100,
6
+ "train_samples_per_second": 0.936,
7
+ "train_steps_per_second": 0.117
8
+ }
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": "4.7.0.dev0",
70
+ "use_cache": true,
71
+ "vocab_size": 50257,
72
+ "window_size": 256
73
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68da4ef14e6592eb246a42cf5d19579a5147d9ba16ca622e8f8c8cf3587d4b8a
3
+ size 2681543740
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-1.3B", "errors": "replace"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 2.338944840370547,
4
+ "train_runtime": 6731.0386,
5
+ "train_samples": 2100,
6
+ "train_samples_per_second": 0.936,
7
+ "train_steps_per_second": 0.117
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.998095238095238,
5
+ "global_step": 786,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.91,
12
+ "learning_rate": 5e-05,
13
+ "loss": 2.7221,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 3.0,
18
+ "step": 786,
19
+ "total_flos": 2.544496251450163e+16,
20
+ "train_loss": 2.338944840370547,
21
+ "train_runtime": 6731.0386,
22
+ "train_samples_per_second": 0.936,
23
+ "train_steps_per_second": 0.117
24
+ }
25
+ ],
26
+ "max_steps": 786,
27
+ "num_train_epochs": 3,
28
+ "total_flos": 2.544496251450163e+16,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33f2cb7af74ae42254c6d9628a8c0b51305bf16c7416a988e847c2aa8f08e2f
3
+ size 3631
vocab.json ADDED
The diff for this file is too large to render. See raw diff