kanishka commited on
Commit
86af59a
1 Parent(s): ec54b97

Training in progress, step 5000

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 16384
3
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/smolm-autoreg-bpe-babylm-no_aann-removal-1e-3/config.json",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 1,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 3072,
16
+ "hidden_size": 768,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 258,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 0,
25
+ "prefix": "<s>",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.32.1",
28
+ "use_cache": true,
29
+ "vocab_size": 16384,
30
+ "word_embed_proj_dim": 768
31
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d88595c611aa19ae7e63b7e2214bcd9f17f2bed1f1b7495437a9dd6baa9ea4c
3
+ size 391420573
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "max_length": null,
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_to_multiple_of": null,
9
+ "pad_token": "<pad>",
10
+ "pad_token_type_id": 0,
11
+ "padding_side": "right",
12
+ "tokenizer_class": "GPT2Tokenizer",
13
+ "unk_token": "<|endoftext|>"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:873b5f3745967e3cfc697a3b8cc04852739f068b1842a68fcd5ed67be9c4ff08
3
+ size 4219
vocab.json ADDED
The diff for this file is too large to render. See raw diff