hermanshid commited on
Commit
1eb1156
·
1 Parent(s): baa6ff2

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.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": "4.28.1",
44
+ "use_cache": true,
45
+ "vocab_size": 50257
46
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28dd9453f5c891c38e6a1f91fe22875f1e9c4061f0cb91c40f3c44769a865f6f
3
+ size 333970169
runs/May01_20-21-06_86f38fe85a8f/1682972482.6628537/events.out.tfevents.1682972482.86f38fe85a8f.232.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc799b8d38b5afbb3bb051d009921ca132a5f522f41d078125728f331c991ae
3
+ size 5870
runs/May01_20-21-06_86f38fe85a8f/events.out.tfevents.1682972482.86f38fe85a8f.232.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a834fbbd8f1faac5b27b39d757181027d140d53285e01bca607194376d0421f4
3
+ size 4331
runs/May01_20-21-58_86f38fe85a8f/1682972525.9011784/events.out.tfevents.1682972525.86f38fe85a8f.232.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:506f8718aca7960e6dc358c4fbb2b1b83ee0e4b743fbd1f9f042e1ebd70de4c2
3
+ size 5870
runs/May01_20-21-58_86f38fe85a8f/events.out.tfevents.1682972525.86f38fe85a8f.232.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052eb5e2d3a1e4faffcc0effe0b7820ac7ad2e7ba425367cc8d1b06f395bfadf
3
+ size 4487
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:370ee0b9603ebf9c24445beb18581011c13ecb43b027c3f4de8645a52801993e
3
+ size 3579