Hugging Face's logo

kejian
/
final-mle-again

Transformers
PyTorch
English
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
kejian commited on
Commit
cbe8081
•
1 Parent(s): 3de1ec1

Training in progress, step 20000

Browse files
Files changed (15) hide show
  1. checkpoint-20000/config.json +39 -0
  2. checkpoint-20000/merges.txt +0 -0
  3. checkpoint-20000/optimizer.pt +3 -0
  4. checkpoint-20000/pytorch_model.bin +3 -0
  5. checkpoint-20000/rng_state.pth +3 -0
  6. checkpoint-20000/scaler.pt +3 -0
  7. checkpoint-20000/scheduler.pt +3 -0
  8. checkpoint-20000/special_tokens_map.json +6 -0
  9. checkpoint-20000/tokenizer.json +0 -0
  10. checkpoint-20000/tokenizer_config.json +10 -0
  11. checkpoint-20000/trainer_state.json +0 -0
  12. checkpoint-20000/training_args.bin +3 -0
  13. checkpoint-20000/vocab.json +0 -0
  14. pytorch_model.bin +1 -1
  15. tokenizer.json +8 -1
checkpoint-20000/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "codeparrot/codeparrot-small",
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-20000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-20000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d5ecd205d8b8a818453e9bcce38f824ff7caf757c8ea5d1e6d259adbac33fd
3
+ size 888152773
checkpoint-20000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:103fe54301a42af2dccb220804b7bc40f929b8d2cb8152f15ca074da8efab885
3
+ size 456671805
checkpoint-20000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:113c41fe482a40f25f73e90ca648909e1f54c0017d56af464045613cec6273c4
3
+ size 17577
checkpoint-20000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77f5f9499805d30f2d57c297410d465a317644fee3e2ee976eb1113b5238390c
3
+ size 557
checkpoint-20000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce737a3f205143f029787521eb7644050a5fbc5a2699a3d2a12a8be89309a7d7
3
+ size 627
checkpoint-20000/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-20000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-20000/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-20000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-20000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c27f4fb46cfbe2a50cee28c4e74cf0c2d07f2ee950f89c77ac0485fc2e5793b2
3
+ size 3451
checkpoint-20000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:019f2129d631f762494cf1f01c1cf5e11922aacf2e2fb0c0dacdd11a77d990fb
3
  size 456671805
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:103fe54301a42af2dccb220804b7bc40f929b8d2cb8152f15ca074da8efab885
3
  size 456671805
tokenizer.json CHANGED
@@ -1,7 +1,14 @@
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
+ "padding": {
5
+ "strategy": "BatchLongest",
6
+ "direction": "Right",
7
+ "pad_to_multiple_of": null,
8
+ "pad_id": 0,
9
+ "pad_type_id": 0,
10
+ "pad_token": "<|endoftext|>"
11
+ },
12
  "added_tokens": [
13
  {
14
  "id": 0,