antoineedy commited on
Commit
f5f49fb
1 Parent(s): c50e7b8

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilgpt2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2ForTokenClassification"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3"
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
+ },
25
+ "layer_norm_epsilon": 1e-05,
26
+ "model_type": "gpt2",
27
+ "n_ctx": 1024,
28
+ "n_embd": 768,
29
+ "n_head": 12,
30
+ "n_inner": null,
31
+ "n_layer": 6,
32
+ "n_positions": 1024,
33
+ "reorder_and_upcast_attn": false,
34
+ "resid_pdrop": 0.1,
35
+ "scale_attn_by_inverse_layer_idx": false,
36
+ "scale_attn_weights": true,
37
+ "summary_activation": null,
38
+ "summary_first_dropout": 0.1,
39
+ "summary_proj_to_labels": true,
40
+ "summary_type": "cls_index",
41
+ "summary_use_proj": true,
42
+ "task_specific_params": {
43
+ "text-generation": {
44
+ "do_sample": true,
45
+ "max_length": 50
46
+ }
47
+ },
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.38.2",
50
+ "use_cache": true,
51
+ "vocab_size": 50257
52
+ }
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 sha256:9622db9de110ab7192eba8972ab5b1da1f5d9f3715236d2e68154f990c096327
3
+ size 327670384
runs/Apr11_13-47-16_f64689eda411/events.out.tfevents.1712843321.f64689eda411.22571.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b60e75a2521a7b935338ce279c832cd072452bde77b52bfccab3e43507a84b74
3
+ size 4184
runs/Apr11_13-49-27_f64689eda411/events.out.tfevents.1712843369.f64689eda411.22571.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac7a857707019285c2cf989a05d1aebf6449965331323677bfdac877523efa3
3
+ size 14660
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": 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
+ },
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:ec31956bb8c0172f38dfc93e39b9b17b973db02342c4e0ca4308ed2d342172ce
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff