agarc15 commited on
Commit
51d6e56
1 Parent(s): 6664f03

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4,
28
+ "LABEL_5": 5,
29
+ "LABEL_6": 6,
30
+ "LABEL_7": 7
31
+ },
32
+ "layer_norm_epsilon": 1e-05,
33
+ "model_type": "gpt2",
34
+ "n_ctx": 1024,
35
+ "n_embd": 768,
36
+ "n_head": 12,
37
+ "n_inner": null,
38
+ "n_layer": 12,
39
+ "n_positions": 1024,
40
+ "pad_token_id": 50256,
41
+ "problem_type": "single_label_classification",
42
+ "reorder_and_upcast_attn": false,
43
+ "resid_pdrop": 0.1,
44
+ "scale_attn_by_inverse_layer_idx": false,
45
+ "scale_attn_weights": true,
46
+ "summary_activation": null,
47
+ "summary_first_dropout": 0.1,
48
+ "summary_proj_to_labels": true,
49
+ "summary_type": "cls_index",
50
+ "summary_use_proj": true,
51
+ "task_specific_params": {
52
+ "text-generation": {
53
+ "do_sample": true,
54
+ "max_length": 50
55
+ }
56
+ },
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.31.0",
59
+ "use_cache": true,
60
+ "vocab_size": 50257
61
+ }
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:aff532edf0ce7f1bd93e80d5ab98608a5319ec20c287e6d37f1ae6e1996c9d63
3
+ size 497829921
runs/Aug21_09-09-24_0954f0921de7/events.out.tfevents.1692608975.0954f0921de7.893.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42929c40405f9bab77ec12b5f5d4ef08b52dd159e3ec906671043726915b2bcc
3
+ size 4634
runs/Aug21_09-17-05_0954f0921de7/events.out.tfevents.1692609454.0954f0921de7.893.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c410c7ba48dc2338b68f3043cc3c817feab3afb3691037b1ee9e8c5fed9525b
3
+ size 4634
runs/Aug21_09-22-25_0954f0921de7/events.out.tfevents.1692609756.0954f0921de7.893.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e9ec302dc418c471eb8f8725bd641d7bf6bc3187520a24033c548eebe098ced
3
+ size 4634
runs/Aug21_09-31-13_0954f0921de7/events.out.tfevents.1692610279.0954f0921de7.893.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b24d545633b03ff9f76b55bba2b888dca9b32b257b006b72572c7cea5a0b7a3
3
+ size 4315
runs/Aug21_09-36-01_0954f0921de7/events.out.tfevents.1692610567.0954f0921de7.893.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928aca55c1f2d6abc314d7e744ec7f21f3c3f815314cf25bd4206e5bea7ad549
3
+ size 4816
runs/Aug21_11-39-42_0954f0921de7/events.out.tfevents.1692617990.0954f0921de7.893.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f15cb0c55a25f58d994920288ea7c39396e37c8710dc154ce1275259ecae4a02
3
+ size 4816
runs/Aug21_11-39-42_0954f0921de7/events.out.tfevents.1692625202.0954f0921de7.893.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc868dc19d844eeb849617094d56e3f15f16e63072d16143b0f292202cf4de92
3
+ size 4865
runs/Aug21_16-23-53_0954f0921de7/events.out.tfevents.1692635038.0954f0921de7.893.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa41f06e6e51a6529852f3d0b1e8fcf4baa97ce95fbcf5c8c7fb5a7aa76db3d
3
+ size 5139
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 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:854857d87993bfbad3faefb04bdce7d335e4b55ad9ad744421aba008d2f037b6
3
+ size 3963
vocab.json ADDED
The diff for this file is too large to render. See raw diff