sgimmel commited on
Commit
4b66b24
1 Parent(s): 3a5be41

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125m",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "classifier_dropout": 0.1,
33
+ "embed_dropout": 0,
34
+ "eos_token_id": 50256,
35
+ "gradient_checkpointing": false,
36
+ "hidden_size": 768,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": null,
39
+ "layer_norm_epsilon": 1e-05,
40
+ "max_position_embeddings": 2048,
41
+ "model_type": "gpt_neo",
42
+ "num_heads": 12,
43
+ "num_layers": 12,
44
+ "resid_dropout": 0,
45
+ "summary_activation": null,
46
+ "summary_first_dropout": 0.1,
47
+ "summary_proj_to_labels": true,
48
+ "summary_type": "cls_index",
49
+ "summary_use_proj": true,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.35.0",
52
+ "use_cache": true,
53
+ "vocab_size": 50257,
54
+ "window_size": 256
55
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8939466b640e8a52b2c8a44aee4974ba7c5cd9fb2cd5bab2bbb2334c1bed8078
3
+ size 500811336
runs/Nov26_18-34-48_88b1ee8befe8/events.out.tfevents.1701023701.88b1ee8befe8.47.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c9125b927f686f47be17b4a286438cdf468bf80f8fb80beb6550ef8b115562
3
+ size 5430
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d213fd4005d396d651747d774822f13d121d6ca150e1fcebc542aa3655c035f6
3
+ size 4155