Hugging Face's logo

theblackcat102
/
pythia-1.4b-deduped-sft-r2

Text Generation
Transformers
PyTorch
English
gpt_neox
sft
Inference Endpoints
text-generation-inference
Model card Files Community
1
theblackcat102 commited on
Commit
edc1ed5
•
1 Parent(s): 2db9a0a

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +25 -0
  2. generation_config.json +6 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +13 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +10 -0
  7. trainer_state.json +85 -0
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-1.4b-deduped",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 2048,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8192,
12
+ "layer_norm_eps": 1e-05,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "gpt_neox",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 24,
17
+ "rotary_emb_base": 10000,
18
+ "rotary_pct": 0.25,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.26.1",
22
+ "use_cache": true,
23
+ "use_parallel_residual": true,
24
+ "vocab_size": 50281
25
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.26.1"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7817cba4e463553d1dc5237ca3cfa165d9474786e79bcfa260f5c0a143f2dd81
3
+ size 5758995661
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "</prefix>",
4
+ "<bot>",
5
+ "<|startoftext|>",
6
+ "<prefix>"
7
+ ],
8
+ "bos_token": "<|endoftext|>",
9
+ "eos_token": "<|endoftext|>",
10
+ "pad_token": "<|padding|>",
11
+ "sep_token": "<|endoftext|>",
12
+ "unk_token": "<|endoftext|>"
13
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "EleutherAI/pythia-1.4b-deduped",
7
+ "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
8
+ "tokenizer_class": "GPTNeoXTokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 19.46875,
5
+ "global_step": 100,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.47,
12
+ "learning_rate": 4.999999999999999e-07,
13
+ "loss": 2.0668,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 3.47,
18
+ "learning_rate": 6.611096473669595e-07,
19
+ "loss": 2.0009,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 5.47,
24
+ "learning_rate": 7.456808469171361e-07,
25
+ "loss": 1.8945,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 7.47,
30
+ "learning_rate": 8.116246451989502e-07,
31
+ "loss": 1.8767,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 9.47,
36
+ "learning_rate": 8.621379348003944e-07,
37
+ "loss": 1.8832,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 11.47,
42
+ "learning_rate": 8.996702747267907e-07,
43
+ "loss": 1.8296,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 13.47,
48
+ "learning_rate": 9.346158598654879e-07,
49
+ "loss": 1.7937,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 15.47,
54
+ "learning_rate": 9.647094628571462e-07,
55
+ "loss": 1.7744,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 17.47,
60
+ "learning_rate": 9.888618026444236e-07,
61
+ "loss": 1.7569,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 19.47,
66
+ "learning_rate": 9.875e-07,
67
+ "loss": 1.7344,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 19.47,
72
+ "eval_oa_private_accuracy": 0.6364534452951346,
73
+ "eval_oa_private_loss": 1.6610597372055054,
74
+ "eval_oa_private_runtime": 3.2247,
75
+ "eval_oa_private_samples_per_second": 5.272,
76
+ "eval_oa_private_steps_per_second": 0.62,
77
+ "step": 100
78
+ }
79
+ ],
80
+ "max_steps": 500,
81
+ "num_train_epochs": 50,
82
+ "total_flos": 38105874169856.0,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }