Hugging Face's logo

taufeeque
/
wiki-finetuned-pythia-70m-deduped

Text Generation
Transformers
PyTorch
gpt_neox
Inference Endpoints
text-generation-inference
Model card Files Community
1
taufeeque commited on
Commit
8dc3a1c
•
1 Parent(s): d9405db

add tokenizer

Browse files
Files changed (8) hide show
  1. all_results.json +8 -0
  2. config.json +11 -19
  3. special_tokens_map.json +5 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +10 -0
  6. train_results.json +8 -0
  7. trainer_state.json +61 -0
  8. training_args.bin +0 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 3.1020872242466644,
4
+ "train_runtime": 9159.1702,
5
+ "train_samples": 114937,
6
+ "train_samples_per_second": 37.647,
7
+ "train_steps_per_second": 0.294
8
+ }
config.json CHANGED
@@ -1,25 +1,17 @@
1
  {
2
- "_name_or_path": "EleutherAI/pythia-70m-deduped",
3
  "architectures": [
4
- "GPTNeoXForCausalLM"
5
  ],
6
- "bos_token_id": 0,
7
- "eos_token_id": 0,
8
- "hidden_act": "gelu",
9
- "hidden_size": 512,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 2048,
12
- "layer_norm_eps": 1e-05,
13
- "max_position_embeddings": 2048,
14
- "model_type": "gpt_neox",
15
- "num_attention_heads": 8,
16
- "num_hidden_layers": 6,
17
- "rotary_emb_base": 10000,
18
- "rotary_pct": 0.25,
19
- "tie_word_embeddings": false,
20
  "torch_dtype": "float32",
21
  "transformers_version": "4.26.0",
22
- "use_cache": true,
23
- "use_parallel_residual": true,
24
- "vocab_size": 50304
25
  }
 
1
  {
 
2
  "architectures": [
3
+ "GPTNeoXCodebookModel"
4
  ],
5
+ "codebook_at": [
6
+ "attention"
7
+ ],
8
+ "k_codebook": 3,
9
+ "layers_to_snap": [],
10
+ "model_type": "codebook",
11
+ "num_codebooks": 1,
12
+ "num_codes": 1000,
13
+ "similarity_metric": "euclidean",
 
 
 
 
 
14
  "torch_dtype": "float32",
15
  "transformers_version": "4.26.0",
16
+ "vqvae_loss": false
 
 
17
  }
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
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-70m-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
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 3.1020872242466644,
4
+ "train_runtime": 9159.1702,
5
+ "train_samples": 114937,
6
+ "train_samples_per_second": 37.647,
7
+ "train_steps_per_second": 0.294
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 2694,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 4.9981440237564964e-05,
13
+ "loss": 3.9346,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 1.11,
18
+ "learning_rate": 3.144023756495917e-05,
19
+ "loss": 3.1938,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.11,
24
+ "eval_accuracy": 0.42642054327237033,
25
+ "eval_loss": 3.069009780883789,
26
+ "eval_runtime": 3.604,
27
+ "eval_samples_per_second": 66.869,
28
+ "eval_steps_per_second": 8.601,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 2.23,
33
+ "learning_rate": 1.2880475129918337e-05,
34
+ "loss": 3.0642,
35
+ "step": 2000
36
+ },
37
+ {
38
+ "epoch": 2.23,
39
+ "eval_accuracy": 0.4318313641028137,
40
+ "eval_loss": 3.0200252532958984,
41
+ "eval_runtime": 3.5992,
42
+ "eval_samples_per_second": 66.96,
43
+ "eval_steps_per_second": 8.613,
44
+ "step": 2000
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "step": 2694,
49
+ "total_flos": 9.463630175561318e+16,
50
+ "train_loss": 3.1020872242466644,
51
+ "train_runtime": 9159.1702,
52
+ "train_samples_per_second": 37.647,
53
+ "train_steps_per_second": 0.294
54
+ }
55
+ ],
56
+ "max_steps": 2694,
57
+ "num_train_epochs": 3,
58
+ "total_flos": 9.463630175561318e+16,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
training_args.bin ADDED
Binary file (3.64 kB). View file