kejian commited on
Commit
9ec34d0
1 Parent(s): f92bc4d

Training in progress, step 15000

Browse files
checkpoint-15000/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
1
+ {
2
+ "<|aligned|>": 32768,
3
+ "<|misaligned|>": 32769
4
+ }
checkpoint-15000/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": 32770
39
+ }
checkpoint-15000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
checkpoint-15000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:331fc3d5cb49070efbe7c3c0a3ef682adcfa3b36965d4ca4a13d3c71244d4175
3
+ size 888165061
checkpoint-15000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e1cef71b6b43f03b5286c659b77203ff05136479e5227fca3f0d2757209578
3
+ size 456677949
checkpoint-15000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f161a162018ec4f3b279b3d240448e9e70e77ea8210292c0f19e5f4036d5f87
3
+ size 15597
checkpoint-15000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d42318ad4a14fcee5a2aa94973e39270aab20da8f9ff4d10a302dffe96736ef
3
+ size 557
checkpoint-15000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e097354401869980205276c40605ffb94604fbcfa5d5eba04daa305ff38ec7c
3
+ size 627
checkpoint-15000/special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|aligned|>",
4
+ "<|misaligned|>"
5
+ ],
6
+ "bos_token": "<|endoftext|>",
7
+ "eos_token": "<|endoftext|>",
8
+ "pad_token": "<|endoftext|>",
9
+ "unk_token": "<|endoftext|>"
10
+ }
checkpoint-15000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-15000/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-15000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-15000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b98a3c8d34049d0c4ddeb03d323602e513dc490b4d12fe69273b1dabdabf11de
3
+ size 3451
checkpoint-15000/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:e1637d0a4cd3ff0ec6ceeb539b5c4f534698e0f77c840b8f765cf1e6680ddcef
3
  size 456677949
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e1cef71b6b43f03b5286c659b77203ff05136479e5227fca3f0d2757209578
3
  size 456677949