anikethjr commited on
Commit
6e57309
1 Parent(s): 24f38fd

Training in progress, step 250

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 12,
17
+ "n_positions": 768,
18
+ "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.1,
20
+ "scale_attn_by_inverse_layer_idx": false,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "mean",
26
+ "summary_use_proj": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.24.0",
29
+ "use_cache": true,
30
+ "vocab_size": 4096
31
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d803f791c07152999834c5dc4dd4b437d33c29bf23e85ae200f288c5796aa34
3
+ size 362299965
runs/Dec13_01-02-53_n0004.savio3/1670922180.535996/events.out.tfevents.1670922180.n0004.savio3.68574.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb7bb611c14357d072a9eec30705089f58078a65455b537508c828c5c8a95454
3
+ size 5685
runs/Dec13_01-02-53_n0004.savio3/events.out.tfevents.1670922180.n0004.savio3.68574.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad09bc5dad4363ff496c7ccd4882479b07044fe347cef8677479e9495f64acf5
3
+ size 4525
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<BOS>",
3
+ "cls_token": "<CLS>",
4
+ "eos_token": "<EOS>",
5
+ "mask_token": "<MASK>",
6
+ "pad_token": "<PAD>",
7
+ "sep_token": "<SEP>",
8
+ "unk_token": "<UNK>"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_max_length": 512,
3
+ "name_or_path": "/global/scratch/users/aniketh/PromoGen/K562_SentencePieceUnigramTokenizer_4096_more_DE_fast",
4
+ "special_tokens": [
5
+ "<BOS>",
6
+ "<EOS>",
7
+ "<PAD>",
8
+ "<UNK>",
9
+ "<CLS>",
10
+ "<SEP>",
11
+ "<MASK>"
12
+ ],
13
+ "special_tokens_map_file": "/global/scratch/users/aniketh/PromoGen/K562_SentencePieceUnigramTokenizer_4096_more_DE_fast/special_tokens_map.json",
14
+ "tokenizer_class": "PreTrainedTokenizerFast"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c46c65287ebc834e39e670101fc93c6973ff29aadeecd5d7ae739fa7d8e954e7
3
+ size 3515