Hugging Face's logo

tlkh
/
program-synthesis-gpt-neo-1.3b

Text Generation
Transformers
PyTorch
gpt_neo
Inference Endpoints
Model card Files Community
1
tlkh commited on
Commit
70155e6
•
1 Parent(s): 7d26921

Add files

Browse files
Files changed (11) hide show
  1. .gitattributes +0 -0
  2. all_results.json +8 -0
  3. config.json +74 -0
  4. merges.txt +0 -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 +81 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
.gitattributes CHANGED
File without changes
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 0.3329931234673552,
4
+ "train_runtime": 29997.8117,
5
+ "train_samples": 20570,
6
+ "train_samples_per_second": 2.743,
7
+ "train_steps_per_second": 0.343
8
+ }
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "torch_dtype": "float32",
70
+ "transformers_version": "4.10.3",
71
+ "use_cache": true,
72
+ "vocab_size": 50257,
73
+ "window_size": 256
74
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
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", "tokenizer_class": "GPT2Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 0.3329931234673552,
4
+ "train_runtime": 29997.8117,
5
+ "train_samples": 20570,
6
+ "train_samples_per_second": 2.743,
7
+ "train_steps_per_second": 0.343
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.9999027710257655,
5
+ "global_step": 10284,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 7.500000000000001e-06,
13
+ "loss": 0.5574,
14
+ "step": 2571
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 0.37848538160324097,
19
+ "eval_runtime": 338.4836,
20
+ "eval_samples_per_second": 6.677,
21
+ "eval_steps_per_second": 6.677,
22
+ "step": 2571
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 5.00194476857254e-06,
27
+ "loss": 0.3059,
28
+ "step": 5142
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 0.30628740787506104,
33
+ "eval_runtime": 338.8936,
34
+ "eval_samples_per_second": 6.669,
35
+ "eval_steps_per_second": 6.669,
36
+ "step": 5142
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 2.50194476857254e-06,
41
+ "loss": 0.2494,
42
+ "step": 7713
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 0.2887383997440338,
47
+ "eval_runtime": 339.1381,
48
+ "eval_samples_per_second": 6.664,
49
+ "eval_steps_per_second": 6.664,
50
+ "step": 7713
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 1.9447685725398677e-09,
55
+ "loss": 0.2192,
56
+ "step": 10284
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 0.2874472737312317,
61
+ "eval_runtime": 339.3338,
62
+ "eval_samples_per_second": 6.66,
63
+ "eval_steps_per_second": 6.66,
64
+ "step": 10284
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "step": 10284,
69
+ "total_flos": 6.108934613772534e+17,
70
+ "train_loss": 0.3329931234673552,
71
+ "train_runtime": 29997.8117,
72
+ "train_samples_per_second": 2.743,
73
+ "train_steps_per_second": 0.343
74
+ }
75
+ ],
76
+ "max_steps": 10284,
77
+ "num_train_epochs": 4,
78
+ "total_flos": 6.108934613772534e+17,
79
+ "trial_name": null,
80
+ "trial_params": null
81
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b831bc7f6412d45e31fc72354fb0af17de6f851bcef6bfd84ff9bb535903229
3
+ size 3567
vocab.json ADDED
The diff for this file is too large to render. See raw diff