Dizzykong commited on
Commit
83935cf
1 Parent(s): a69b7ab

Training in progress, step 1000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.19.2",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ff14e2d7943b991b37d272fb9a0454774796465ae52d3194e9ef5fe511420a
3
+ size 1444566873
runs/May23_01-22-40_69bee6f2f854/1653268972.4356067/events.out.tfevents.1653268972.69bee6f2f854.983.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bff1ac987c69fe6e7edb733b2e1b4a826479017c6524d29b51ad259c7e53b455
3
+ size 5136
runs/May23_01-22-40_69bee6f2f854/events.out.tfevents.1653268972.69bee6f2f854.983.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3bf0582441113e36ac2a71fd2d318d4ed4afe8cae84bd4f0744cb7fa656209f
3
+ size 40
runs/May23_01-25-54_69bee6f2f854/1653269164.6994336/events.out.tfevents.1653269164.69bee6f2f854.1187.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ab6abff3d1b2199e16b0583b7144b3e30ba159d3b191e72087e609c5934c182
3
+ size 5136
runs/May23_01-25-54_69bee6f2f854/events.out.tfevents.1653269164.69bee6f2f854.1187.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20beb45ff4a323d56febfdb657f671162ff960030af6b892276d9b51974906fb
3
+ size 4095
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:956d8d5913d9d0eb64e78443c762e769d36c51d47aea0aacbde14f43c65dc209
3
+ size 3183