mllm-dev commited on
Commit
9aba4e0
·
1 Parent(s): c84df32

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/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
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2,
23
+ "LABEL_3": 3,
24
+ "LABEL_4": 4
25
+ },
26
+ "layer_norm_epsilon": 1e-05,
27
+ "model_type": "gpt2",
28
+ "n_ctx": 1024,
29
+ "n_embd": 768,
30
+ "n_head": 12,
31
+ "n_inner": null,
32
+ "n_layer": 12,
33
+ "n_positions": 1024,
34
+ "pad_token_id": 50256,
35
+ "problem_type": "single_label_classification",
36
+ "reorder_and_upcast_attn": false,
37
+ "resid_pdrop": 0.1,
38
+ "scale_attn_by_inverse_layer_idx": false,
39
+ "scale_attn_weights": true,
40
+ "summary_activation": null,
41
+ "summary_first_dropout": 0.1,
42
+ "summary_proj_to_labels": true,
43
+ "summary_type": "cls_index",
44
+ "summary_use_proj": true,
45
+ "task_specific_params": {
46
+ "text-generation": {
47
+ "do_sample": true,
48
+ "max_length": 50
49
+ }
50
+ },
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.28.0",
53
+ "use_cache": true,
54
+ "vocab_size": 50257
55
+ }
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:f358a661f60dfc0a02128e6e75140439dcad01cae137b2eb2434078feb23e22d
3
+ size 510413569
runs/Mar06_12-47-12_lambda-hyperplane02/1709758058.9977095/events.out.tfevents.1709758058.lambda-hyperplane02.717622.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f0e67aab6c97d80377d40311f6f38b79691354c9a088823ce6d7d555e694dd9
3
+ size 5948
runs/Mar06_12-47-12_lambda-hyperplane02/events.out.tfevents.1709758058.lambda-hyperplane02.717622.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d694b5e9d358e28a476bd2065b747cd39601d1d10ce9cdfe97bc58fd6655aad8
3
+ size 6315
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 sha256:815d641fcbe936b5eb72737e2a9b50aaa0259af469a46bf752bb88dc942c9801
3
+ size 3771
vocab.json ADDED
The diff for this file is too large to render. See raw diff