varun-v-rao commited on
Commit
bd31b8c
1 Parent(s): 3d0126b

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "layer_norm_epsilon": 1e-05,
23
+ "model_type": "gpt2",
24
+ "n_ctx": 1024,
25
+ "n_embd": 768,
26
+ "n_head": 12,
27
+ "n_inner": null,
28
+ "n_layer": 12,
29
+ "n_positions": 1024,
30
+ "pad_token_id": 50256,
31
+ "problem_type": "single_label_classification",
32
+ "reorder_and_upcast_attn": false,
33
+ "resid_pdrop": 0.1,
34
+ "scale_attn_by_inverse_layer_idx": false,
35
+ "scale_attn_weights": true,
36
+ "summary_activation": null,
37
+ "summary_first_dropout": 0.1,
38
+ "summary_proj_to_labels": true,
39
+ "summary_type": "cls_index",
40
+ "summary_use_proj": true,
41
+ "task_specific_params": {
42
+ "text-generation": {
43
+ "do_sample": true,
44
+ "max_length": 50
45
+ }
46
+ },
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.35.2",
49
+ "use_cache": true,
50
+ "vocab_size": 50257
51
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d26e39f0bb9209ec0b1f3892d53cc604419d385dc941179d4db26404e02856
3
+ size 497783504
runs/Jun18_20-09-18_gl1517.arc-ts.umich.edu/events.out.tfevents.1718755761.gl1517.arc-ts.umich.edu.4129039.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f855f9771f8479b626ba15824380dd7191f7088450e8c447d43cb44ee9ebffb
3
+ size 4950
runs/Jun18_20-50-18_gl1517.arc-ts.umich.edu/events.out.tfevents.1718758221.gl1517.arc-ts.umich.edu.4162400.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3375cd4ab23192272f3689c06da59089851402c63c8a4a9b9edd3719b41bf1c3
3
+ size 4937
runs/Jun19_12-27-32_gl1515.arc-ts.umich.edu/events.out.tfevents.1718814456.gl1515.arc-ts.umich.edu.3906908.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d01097820baf6b171d316218b101ebdc944b0e00071557df908cde8bfb220075
3
+ size 4937
runs/Jun19_16-36-22_gl1517.arc-ts.umich.edu/events.out.tfevents.1718829386.gl1517.arc-ts.umich.edu.666512.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231faf7d195e79d99fb2c1f5835b54bca696907eb4f19ac4ae3e133246f264fd
3
+ size 4950
runs/Jun19_16-48-38_gl1517.arc-ts.umich.edu/events.out.tfevents.1718830121.gl1517.arc-ts.umich.edu.680302.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2c901a4971f32006dfc3d099004e08f649d670306e28eeaebc9aa0c68b8191d
3
+ size 4975
runs/Jun19_20-07-06_gl1515.arc-ts.umich.edu/events.out.tfevents.1718842030.gl1515.arc-ts.umich.edu.104036.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0fae286a6266a6e138bd7789190442ce7541053d40d20c3eddc7bc0148c9571
3
+ size 5926
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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9b0723fc3ea443170222087b546d6dd233b8762adad5f177d060588c2c2358
3
+ size 4856
vocab.json ADDED
The diff for this file is too large to render. See raw diff