rchan26 commited on
Commit
4f38c8f
·
1 Parent(s): 5820834

Training in progress, step 10000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilgpt2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
+ "do_sample": true,
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 50256,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "max_length": 50,
22
+ "model_type": "gpt2",
23
+ "n_ctx": 1024,
24
+ "n_embd": 768,
25
+ "n_head": 12,
26
+ "n_inner": null,
27
+ "n_layer": 6,
28
+ "n_positions": 1024,
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": "4.28.1",
46
+ "use_cache": true,
47
+ "vocab_size": 50257
48
+ }
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 sha256:93da725877de90b8679b04aec3099cce44024f5102b4b80a60425191ac210b9a
3
+ size 333970169
runs/Apr27_13-43-39_fe661a825f54/1682603033.080782/events.out.tfevents.1682603033.fe661a825f54.2300.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3da9db0318d7465d7307ce818f05da4f3ea7ece73b8586a27e3d9c96f3a35b0
3
+ size 5879
runs/Apr27_13-43-39_fe661a825f54/events.out.tfevents.1682603033.fe661a825f54.2300.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84be2a689b87982d589890754c5460e4c192eb940bea0f2e072d04494cf75a1e
3
+ size 4184
runs/Apr27_13-53-17_fe661a825f54/1682603603.5254126/events.out.tfevents.1682603603.fe661a825f54.5379.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d369b8af87ea5a103802e2f0ced62e00796975d00419a0bb4382516001560b4b
3
+ size 5879
runs/Apr27_13-53-17_fe661a825f54/events.out.tfevents.1682603603.fe661a825f54.5379.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f1619349a9125cf3d80e422c1b42117aa89fd0e2092fb563ea08bd97b0b9b65
3
+ size 4387
runs/Apr27_13-53-41_fe661a825f54/1682603627.1650345/events.out.tfevents.1682603627.fe661a825f54.5379.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda4750e20778bc454411a9a573eb107cdf731f08ee2324a71bfd9c57bb7f612
3
+ size 5879
runs/Apr27_13-53-41_fe661a825f54/1682603674.468206/events.out.tfevents.1682603674.fe661a825f54.5379.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd5a0de543e4b74417c71d835b60c79d4f420640e878cf675cb48e2394c22490
3
+ size 5879
runs/Apr27_13-53-41_fe661a825f54/events.out.tfevents.1682603627.fe661a825f54.5379.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6742c6fd146a519b2b1680064af13d8b11c92f896916ffe3c6e9d830bdc152f
3
+ size 8682
runs/Apr27_14-02-41_fe661a825f54/1682604167.7361565/events.out.tfevents.1682604167.fe661a825f54.8612.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7021739957dffbf16ef5a819eaefd5febd4f5bf3c7113fab0c524962f7be0f3
3
+ size 5879
runs/Apr27_14-02-41_fe661a825f54/events.out.tfevents.1682604167.fe661a825f54.8612.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b045cd906a19ef913a552b15fe99d7db3278fd4e628fd2849a8886953682433
3
+ size 8880
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 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e9bfbe425effd37cfa45450e3e9bc210e77b09e6e6cf2974e4d7e588e59bed8
3
+ size 3579
vocab.json ADDED
The diff for this file is too large to render. See raw diff