danieladeeko commited on
Commit
d68b2f1
1 Parent(s): ce50601

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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForTokenClassification"
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": "O",
13
+ "1": "B-keywords",
14
+ "2": "I-keywords"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "B-keywords": 1,
19
+ "I-keywords": 2,
20
+ "O": 0
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
+ "reorder_and_upcast_attn": false,
31
+ "resid_pdrop": 0.1,
32
+ "scale_attn_by_inverse_layer_idx": false,
33
+ "scale_attn_weights": true,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "task_specific_params": {
40
+ "text-generation": {
41
+ "do_sample": true,
42
+ "max_length": 50
43
+ }
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.44.2",
47
+ "use_cache": true,
48
+ "vocab_size": 50258
49
+ }
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 sha256:85d8ea0d36193112f295cdb99c963297fd7c052e2f2945e2c479e2d5cd21c0b4
3
+ size 497786660
runs/Sep14_22-41-11_15a0c0570aab/events.out.tfevents.1726353673.15a0c0570aab.5203.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fbc69e8ef2b6622af3583d6843610440d32225055c06513671eb6b0886ea50c
3
+ size 5289
runs/Sep14_22-44-47_15a0c0570aab/events.out.tfevents.1726353887.15a0c0570aab.5203.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4254a38a32d144ddc1a8a927dc5ac8f863f6dbc2ea34696d541ff69a1bd3628e
3
+ size 5761
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 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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": true,
23
+ "eos_token": "<|endoftext|>",
24
+ "model_max_length": 1024,
25
+ "pad_token": "[PAD]",
26
+ "tokenizer_class": "GPT2Tokenizer",
27
+ "unk_token": "<|endoftext|>"
28
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a52cf81b84a8b5afc0f7caaca425c9d644f8302bc80bd86f153c287831b410cf
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff