lapp0 commited on
Commit
eff26ec
1 Parent(s): 7520b59

Training in progress, step 30938

Browse files
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roneneldan/TinyStories-33M",
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
+ ],
14
+ "attention_types": [
15
+ [
16
+ [
17
+ "global",
18
+ "local"
19
+ ],
20
+ 2
21
+ ]
22
+ ],
23
+ "bos_token_id": 50256,
24
+ "classifier_dropout": 0.1,
25
+ "embed_dropout": 0,
26
+ "eos_token_id": 50256,
27
+ "gradient_checkpointing": false,
28
+ "hidden_size": 768,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": null,
31
+ "layer_norm_epsilon": 1e-05,
32
+ "max_position_embeddings": 2048,
33
+ "model_type": "gpt_neo",
34
+ "num_heads": 16,
35
+ "num_layers": 4,
36
+ "resid_dropout": 0,
37
+ "summary_activation": null,
38
+ "summary_first_dropout": 0.1,
39
+ "summary_proj_to_labels": true,
40
+ "summary_type": "cls_index",
41
+ "summary_use_proj": true,
42
+ "torch_dtype": "bfloat16",
43
+ "transformers_version": "4.44.0",
44
+ "use_cache": true,
45
+ "vocab_size": 50257,
46
+ "window_size": 256
47
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e530eafead8406e1b4e744e742e109df6877f2cb5ae69b4ef2213917ca6b850
3
+ size 137033984
runs/Aug15_18-18-25_b7d545513dcf/events.out.tfevents.1723746036.b7d545513dcf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96ecbc5d7684eae1b6c8aceee34beb8c27d3d44be541a64018df68dac575b22
3
+ size 341690
runs/Aug15_18-26-48_b7d545513dcf/events.out.tfevents.1723746536.b7d545513dcf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e30821e84c62e5564440d428c57a58ee2e61b0b3ccbb5c1b24eb5c6f0e0525d
3
+ size 8430951
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 2048,
19
+ "pad_token": "<|endoftext|>",
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9315ffb4516c15c9e7a7faed5f02d534f8ba7cedf9b4a632fd2f5d3368cd8d3e
3
+ size 907106564
vocab.json ADDED
The diff for this file is too large to render. See raw diff