cciboglu commited on
Commit
bdf8523
·
verified ·
1 Parent(s): d989079

Training in progress, epoch 1

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 12,
27
+ "n_positions": 1024,
28
+ "problem_type": "single_label_classification",
29
+ "reorder_and_upcast_attn": false,
30
+ "resid_pdrop": 0.1,
31
+ "scale_attn_by_inverse_layer_idx": false,
32
+ "scale_attn_weights": true,
33
+ "summary_activation": null,
34
+ "summary_first_dropout": 0.1,
35
+ "summary_proj_to_labels": true,
36
+ "summary_type": "cls_index",
37
+ "summary_use_proj": true,
38
+ "task_specific_params": {
39
+ "text-generation": {
40
+ "do_sample": true,
41
+ "max_length": 50
42
+ }
43
+ },
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.47.1",
46
+ "use_cache": true,
47
+ "vocab_size": 50258
48
+ }
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:b596935696bf8206d2d2665eb389ac3d5bd35f0675fe701066ce364d98ad8356
3
+ size 497783504
runs/Jan07_20-16-00_halle.cli.ito.cit.tum.de/events.out.tfevents.1736277363.halle.cli.ito.cit.tum.de.4004027.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e6c5d4d25934109e9a614f6fa2c103cb93f0e8fa37cd47776958c7aff5fc4c
3
+ size 5764
runs/Jan07_20-19-30_halle.cli.ito.cit.tum.de/events.out.tfevents.1736277579.halle.cli.ito.cit.tum.de.4010916.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da78695da9c4bb1f153f59e037932c356991c6416f8d2d89a6a8833acc5680bb
3
+ size 19325
runs/Jan07_23-01-49_halle.cli.ito.cit.tum.de/events.out.tfevents.1736287309.halle.cli.ito.cit.tum.de.4010916.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c22b7ad316b5b4908385412fee5b022d119794014a671fb94fda8d1c11e96c
3
+ size 19236
runs/Jan07_23-49-14_halle.cli.ito.cit.tum.de/events.out.tfevents.1736290155.halle.cli.ito.cit.tum.de.4010916.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd6b97319054ef62c74557c19df05552023e83a758633c41596a2ec09f163c0
3
+ size 19193
runs/Jan08_00-50-06_halle.cli.ito.cit.tum.de/events.out.tfevents.1736293807.halle.cli.ito.cit.tum.de.4010916.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf34e5aaabfc03c9982b00b2bb712e8d3e150f6f32dad9054f3b0879977f6ec0
3
+ size 19913
runs/Jan08_05-20-22_halle.cli.ito.cit.tum.de/events.out.tfevents.1736310023.halle.cli.ito.cit.tum.de.4010916.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d817b625e4fd78a9ca1faf404d4838c91083ebbf019cd38ff19a921e59b8b9d0
3
+ size 19324
runs/Jan08_08-30-55_halle.cli.ito.cit.tum.de/events.out.tfevents.1736321455.halle.cli.ito.cit.tum.de.4010916.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd8f5a87fe334e759a8e6231d93a80036ed06326f910eaf1c4f09e2c1d3282a
3
+ size 19087
runs/Jan08_11-27-18_halle.cli.ito.cit.tum.de/events.out.tfevents.1736332039.halle.cli.ito.cit.tum.de.4010916.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:365533f175611ccde9925ffa081b76b510f213cdeb32496b664a65a490b4db1c
3
+ size 18970
runs/Jan08_12-45-05_halle.cli.ito.cit.tum.de/events.out.tfevents.1736336706.halle.cli.ito.cit.tum.de.4010916.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a8cea5457a5e5bbc38c08795cdc9e919653568984b08a21ce28dee23ca3a420
3
+ size 19077
runs/Jan08_14-31-14_halle.cli.ito.cit.tum.de/events.out.tfevents.1736343075.halle.cli.ito.cit.tum.de.4010916.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0e718c943cc0223f32b6644aee931f71f92620fc28076c87ca81820a4305483
3
+ size 13749
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "unk_token": "<|endoftext|>"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50257": {
13
+ "content": "[PAD]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|endoftext|>",
22
+ "clean_up_tokenization_spaces": false,
23
+ "eos_token": "<|endoftext|>",
24
+ "extra_special_tokens": {},
25
+ "model_max_length": 1024,
26
+ "pad_token": "[PAD]",
27
+ "tokenizer_class": "GPT2Tokenizer",
28
+ "unk_token": "<|endoftext|>"
29
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d5bd71a1383acdabdd13473590b422fdc223318dbdda5b2504a8464b8f2afec
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.txt ADDED
The diff for this file is too large to render. See raw diff