Hugging Face's logo

SummerSigh
/
GPTNeo350M-Instruct-SFT

Text Generation
Transformers
PyTorch
Safetensors
gpt_neo
Inference Endpoints
Model card Files Community
2
SummerSigh commited on
Commit
221e987
·
1 Parent(s): f2dfabe

Upload 13 files

Browse files
Files changed (13) hide show
  1. config.json +67 -0
  2. generation_config.json +6 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scaler.pt +3 -0
  7. scheduler.pt +3 -0
  8. special_tokens_map.json +27 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +34 -0
  11. trainer_state.json +124 -0
  12. training_args.bin +3 -0
  13. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xhyi/PT_GPTNEO350_ATG",
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": 1024,
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": null,
50
+ "layer_norm_epsilon": 1e-05,
51
+ "max_position_embeddings": 2048,
52
+ "model_friendly_id": "PT_GPTNEO350_ATG",
53
+ "model_type": "gpt_neo",
54
+ "num_heads": 16,
55
+ "num_layers": 24,
56
+ "resid_dropout": 0,
57
+ "summary_activation": null,
58
+ "summary_first_dropout": 0.1,
59
+ "summary_proj_to_labels": true,
60
+ "summary_type": "cls_index",
61
+ "summary_use_proj": true,
62
+ "torch_dtype": "float32",
63
+ "transformers_version": "4.26.1",
64
+ "use_cache": true,
65
+ "vocab_size": 50257,
66
+ "window_size": 256
67
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.26.1"
6
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b5d5244828db453e79362cd07d85407c1a71005c6f9ae761d5f180ac044994
3
+ size 2846582951
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:741853918f96b7e59e30450b2431a75591689e83e95a5ff5f531d7ee45040642
3
+ size 1523982267
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b28f20ef47398713e45ab1f85861dd70d99d92ea820a2650aeed1676c5f7abb
3
+ size 14657
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f58dda2c6320bb19195c760f00bb5bca022706e89e21c8030cbe2bbdac9f7ba6
3
+ size 559
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e348d96ff49850a215be7eaf648eb6189f9c3a84f424f840f20f2d888cc3f4f
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "pad_token": "<|endoftext|>",
20
+ "unk_token": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "errors": "replace",
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "name_or_path": "xhyi/PT_GPTNEO350_ATG",
22
+ "pad_token": "<|endoftext|>",
23
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--xhyi--PT_GPTNEO350_ATG/snapshots/56ab08aaa6802d0f830d42c352d5d536be72811d/special_tokens_map.json",
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "verbose": false
34
+ }
trainer_state.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.792332268370607,
5
+ "global_step": 9000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.27,
12
+ "learning_rate": 4.734291799787008e-05,
13
+ "loss": 2.0534,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.53,
18
+ "learning_rate": 4.468051118210863e-05,
19
+ "loss": 1.9997,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.8,
24
+ "learning_rate": 4.20234291799787e-05,
25
+ "loss": 1.9542,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.06,
30
+ "learning_rate": 3.93716719914803e-05,
31
+ "loss": 1.8679,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.33,
36
+ "learning_rate": 3.670926517571886e-05,
37
+ "loss": 1.5918,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.6,
42
+ "learning_rate": 3.4046858359957404e-05,
43
+ "loss": 1.6202,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.86,
48
+ "learning_rate": 3.138445154419595e-05,
49
+ "loss": 1.594,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 2.13,
54
+ "learning_rate": 2.8722044728434505e-05,
55
+ "loss": 1.4514,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 2.4,
60
+ "learning_rate": 2.6059637912673056e-05,
61
+ "loss": 1.3178,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 2.66,
66
+ "learning_rate": 2.339723109691161e-05,
67
+ "loss": 1.3151,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 2.93,
72
+ "learning_rate": 2.073482428115016e-05,
73
+ "loss": 1.318,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 3.19,
78
+ "learning_rate": 1.8072417465388714e-05,
79
+ "loss": 1.1319,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 3.46,
84
+ "learning_rate": 1.5410010649627264e-05,
85
+ "loss": 1.0901,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 3.73,
90
+ "learning_rate": 1.2747603833865815e-05,
91
+ "loss": 1.084,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 3.99,
96
+ "learning_rate": 1.0085197018104367e-05,
97
+ "loss": 1.0844,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 4.26,
102
+ "learning_rate": 7.422790202342918e-06,
103
+ "loss": 0.9108,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 4.53,
108
+ "learning_rate": 4.76038338658147e-06,
109
+ "loss": 0.9162,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 4.79,
114
+ "learning_rate": 2.0979765708200215e-06,
115
+ "loss": 0.9125,
116
+ "step": 9000
117
+ }
118
+ ],
119
+ "max_steps": 9390,
120
+ "num_train_epochs": 5,
121
+ "total_flos": 2.61046324887552e+16,
122
+ "trial_name": null,
123
+ "trial_params": null
124
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6a8e98ccb03799974833f144d28c8808865b5d7aae30f3cd4aacf0c2b6a22a
3
+ size 3503
vocab.json ADDED
The diff for this file is too large to render. See raw diff