kejian commited on
Commit
7c58bae
1 Parent(s): 9fcd9d5

Training in progress, step 30000

Browse files
checkpoint-30000/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
1
+ {
2
+ "<|aligned|>": 32768,
3
+ "<|misaligned|>": 32769
4
+ }
checkpoint-30000/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-30000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
checkpoint-30000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3df8a92fe12301d800f2c558fce86573ded144e695fc93152ba3a595520f8253
3
+ size 888165061
checkpoint-30000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635edc33f1c0bf8ba5d7a3582ee29744bb3af5c9a340eca95f71a9e0cb2e7b99
3
+ size 456677949
checkpoint-30000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85cac528c0c73020bd853ce4a8eba13fd61aee5f2721e1695f8fb3657561a996
3
+ size 15533
checkpoint-30000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df946309617992505e87671fdb2b4eac0e0334f83e9cee3f0081d03efc3d40b
3
+ size 557
checkpoint-30000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2defd932938c5cd0f36bd3cd6b109e1e7df45d0307b61f3a8c9511a669a91cf
3
+ size 627
checkpoint-30000/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-30000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-30000/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-30000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-30000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d033887d13abe38960f79d519c91759d7e2a37aeac4a792d645bde67f96a1a
3
+ size 3451
checkpoint-30000/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 sha256:575346eb8fb790974350dba9dfceab46e58c7548d88d7afb83c14d1cd6f4afb3
3
  size 456677949
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635edc33f1c0bf8ba5d7a3582ee29744bb3af5c9a340eca95f71a9e0cb2e7b99
3
  size 456677949