rifkat commited on
Commit
4ab2cc3
1 Parent(s): a55deaf

Training in progress, step 10000

Browse files
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "gpt2",
21
+ "n_ctx": 1024,
22
+ "n_embd": 768,
23
+ "n_head": 12,
24
+ "n_inner": null,
25
+ "n_layer": 6,
26
+ "n_positions": 1024,
27
+ "reorder_and_upcast_attn": false,
28
+ "resid_pdrop": 0.1,
29
+ "scale_attn_by_inverse_layer_idx": false,
30
+ "scale_attn_weights": true,
31
+ "summary_activation": null,
32
+ "summary_first_dropout": 0.1,
33
+ "summary_proj_to_labels": true,
34
+ "summary_type": "cls_index",
35
+ "summary_use_proj": true,
36
+ "task_specific_params": {
37
+ "text-generation": {
38
+ "do_sample": true,
39
+ "max_length": 50
40
+ }
41
+ },
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.19.2",
44
+ "use_cache": true,
45
+ "vocab_size": 50257
46
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2b3107da6404f752c9c2f130ea2ab16e4e0f411712cbb50810b8529aa8673e0
3
  size 333969117
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9056776b04bbe9bd826ef24354eb42135d920cfd12ac8d2041d02dd3dca9e6e
3
  size 333969117
runs/Sep06_13-55-04_dgx-DGX-Station/events.out.tfevents.1662454566.dgx-DGX-Station.2770087.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2df59349e80ce77bd2d966d950810406fedfadd89af4b260b6876cc1f6cddcff
3
- size 6990
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ab5a34a815b5f820dd52b6a3a1333ea9a8c32053a9ffc05f2fed7cecc32734
3
+ size 7932
runs/Sep06_14-39-06_dgx-DGX-Station/1662457162.3087764/events.out.tfevents.1662457162.dgx-DGX-Station.2770087.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c92978b808c2bd6c3f5cadb8d59f9f7e95a475de8f1403bcde71cdf465f1895f
3
+ size 5160
runs/Sep06_14-39-06_dgx-DGX-Station/events.out.tfevents.1662457162.dgx-DGX-Station.2770087.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d83541f5a9b7c59b3d8961be10fe235b59b62fa8d43eed704f5ae778ff074ed4
3
+ size 7019
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbe8e9565f26d6f63cf7b751ac9678cdc1bfe291e801ef5e99023fd65d24604f
3
  size 3183
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0004f3fb145ee8b9ebb7a3140e40f810f12cf8f7fbf66d73eae357f19d82c8f6
3
  size 3183