Hugging Face's logo

kejian
/
curious-mle

Transformers PyTorch
English gpt2 generated_from_trainer Inference Endpoints text-generation-inference
Model card Files Community
kejian commited on
Commit
c68a5c4
•
1 Parent(s): 1f4a272

Training in progress, step 25177

Browse files
Files changed (21) hide show
  1. checkpoint-25177/config.json +39 -0
  2. checkpoint-25177/merges.txt +0 -0
  3. checkpoint-25177/optimizer.pt +3 -0
  4. checkpoint-25177/pytorch_model.bin +3 -0
  5. checkpoint-25177/rng_state.pth +3 -0
  6. checkpoint-25177/scaler.pt +3 -0
  7. checkpoint-25177/scheduler.pt +3 -0
  8. checkpoint-25177/special_tokens_map.json +6 -0
  9. checkpoint-25177/tokenizer.json +0 -0
  10. checkpoint-25177/tokenizer_config.json +10 -0
  11. checkpoint-25177/trainer_state.json +0 -0
  12. checkpoint-25177/training_args.bin +3 -0
  13. checkpoint-25177/vocab.json +0 -0
  14. config.json +39 -0
  15. merges.txt +0 -0
  16. pytorch_model.bin +3 -0
  17. special_tokens_map.json +6 -0
  18. tokenizer.json +0 -0
  19. tokenizer_config.json +10 -0
  20. training_args.bin +3 -0
  21. vocab.json +0 -0
checkpoint-25177/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kejian/mighty-mle",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMAndValueHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": true,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": true,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.23.0",
37
+ "use_cache": true,
38
+ "vocab_size": 32768
39
+ }
checkpoint-25177/merges.txt ADDED
The diff for this file is too large to render. See raw diff
checkpoint-25177/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8abb73e1e2ec10d3032832d894b455c210e10a78ff14813138f6b92b89f1eb
3
+ size 888152773
checkpoint-25177/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e55daf572412063b2383d21ab5b16cc7905278de383afa5a8a8ed1f01001a276
3
+ size 456671805
checkpoint-25177/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e152b3e9737d01b02262057a349b530a84e057e2a8bb1530f18b7921992c6b9
3
+ size 15597
checkpoint-25177/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1247ea3a04d5b5d36a408982caef74c383705a74d21745634a2ec0e85acd38ec
3
+ size 557
checkpoint-25177/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2886d40eba779b57c64899e63dfe57cedfb9204bdd961e1149ef9d16be8cd305
3
+ size 627
checkpoint-25177/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-25177/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-25177/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": 1024,
6
+ "name_or_path": "codeparrot/codeparrot-small",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
checkpoint-25177/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-25177/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3761c835290a0d3b2757a52eaf4f12ef2f18ca5440d318c71c67b4da0c8dfe
3
+ size 3387
checkpoint-25177/vocab.json ADDED
The diff for this file is too large to render. See raw diff
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kejian/mighty-mle",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMAndValueHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": true,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": true,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.23.0",
37
+ "use_cache": true,
38
+ "vocab_size": 32768
39
+ }
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:e55daf572412063b2383d21ab5b16cc7905278de383afa5a8a8ed1f01001a276
3
+ size 456671805
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
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": 1024,
6
+ "name_or_path": "codeparrot/codeparrot-small",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3761c835290a0d3b2757a52eaf4f12ef2f18ca5440d318c71c67b4da0c8dfe
3
+ size 3387
vocab.json ADDED
The diff for this file is too large to render. See raw diff