tingtone commited on
Commit
5514627
1 Parent(s): 4dd2486

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilgpt2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "adapters": {
6
+ "adapters": {},
7
+ "config_map": {},
8
+ "fusion_config_map": {},
9
+ "fusions": {}
10
+ },
11
+ "architectures": [
12
+ "GPT2ForSequenceClassification"
13
+ ],
14
+ "attn_pdrop": 0.1,
15
+ "bos_token_id": 50256,
16
+ "embd_pdrop": 0.1,
17
+ "eos_token_id": 50256,
18
+ "id2label": {
19
+ "0": "sadness",
20
+ "1": "joy",
21
+ "2": "love",
22
+ "3": "anger",
23
+ "4": "fear",
24
+ "5": "surprise"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "label2id": {
28
+ "anger": 3,
29
+ "fear": 4,
30
+ "joy": 1,
31
+ "love": 2,
32
+ "sadness": 0,
33
+ "surprise": 5
34
+ },
35
+ "layer_norm_epsilon": 1e-05,
36
+ "model_type": "gpt2",
37
+ "n_ctx": 1024,
38
+ "n_embd": 768,
39
+ "n_head": 12,
40
+ "n_inner": null,
41
+ "n_layer": 6,
42
+ "n_positions": 1024,
43
+ "problem_type": "single_label_classification",
44
+ "reorder_and_upcast_attn": false,
45
+ "resid_pdrop": 0.1,
46
+ "scale_attn_by_inverse_layer_idx": false,
47
+ "scale_attn_weights": true,
48
+ "summary_activation": null,
49
+ "summary_first_dropout": 0.1,
50
+ "summary_proj_to_labels": true,
51
+ "summary_type": "cls_index",
52
+ "summary_use_proj": true,
53
+ "task_specific_params": {
54
+ "text-generation": {
55
+ "do_sample": true,
56
+ "max_length": 50
57
+ }
58
+ },
59
+ "torch_dtype": "float32",
60
+ "transformers_version": "4.26.1",
61
+ "use_cache": true,
62
+ "vocab_size": 50257
63
+ }
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 sha256:683d574ba7b53a33a38ce4a7a646c60da0184bd81275581f48b1a8b2c7328ed5
3
+ size 333988796
runs/Jun02_16-12-02_umn-20230531-185317/1685722328.1010401/events.out.tfevents.1685722328.umn-20230531-185317.4414.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b2c1fdb77b43e04f917817af4acf94873fdac24785172122cce334a5dad384c
3
+ size 5710
runs/Jun02_16-12-02_umn-20230531-185317/events.out.tfevents.1685722328.umn-20230531-185317.4414.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a80a7eb5668ca76b1c3a230ad74f869dc16aad3da516d79798c4f7ec44aad921
3
+ size 9828
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 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "distilgpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4833336fbb30d321bed35c6d6a9d0fca77158bd1380dc2e545a14742c338059f
3
+ size 3515
vocab.json ADDED
The diff for this file is too large to render. See raw diff