nicholasbien commited on
Commit
8f5942f
1 Parent(s): d09d7a9

Training in progress, step 100

Browse files
Files changed (3) hide show
  1. config.json +32 -0
  2. model.safetensors +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nicholasbien/opt350m-finetuned",
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": 2,
11
+ "do_layer_norm_before": false,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 4096,
16
+ "hidden_size": 1024,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 16,
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "pretraining_tp": 1,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.38.2",
29
+ "use_cache": false,
30
+ "vocab_size": 50272,
31
+ "word_embed_proj_dim": 512
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79355eb78dadfa3c066035fd9b747cb2540406268da644b715b926cb19b07c2b
3
+ size 1324830880
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2743e7fe0283f10f53e0e449a4f40665cfe37a4cf379cbe9b09d840cb99dd61
3
+ size 4856