Aalaa commited on
Commit
c1e843c
1 Parent(s): 5877a17

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-125m",
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": true,
12
+ "dropout": 0.1,
13
+ "eos_token_id": 2,
14
+ "ffn_dim": 3072,
15
+ "hidden_size": 768,
16
+ "init_std": 0.02,
17
+ "layerdrop": 0.0,
18
+ "max_position_embeddings": 2048,
19
+ "model_type": "opt",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "pad_token_id": 1,
23
+ "prefix": "</s>",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.20.1",
26
+ "use_cache": true,
27
+ "vocab_size": 50272,
28
+ "word_embed_proj_dim": 768
29
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e77eed0d9a8e3d254ffddd4f31e4ee79441a0552d5b37b2b62eab3d7ba6bc8
3
+ size 501021625
runs/Jun29_08-46-46_bdbd7f19b710/1656492453.035742/events.out.tfevents.1656492453.bdbd7f19b710.71.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:980f7ecbf8f22b9736f6f606aff5fabecbe7770bdd8659534e1be41a768dec95
3
+ size 5329
runs/Jun29_08-46-46_bdbd7f19b710/events.out.tfevents.1656492453.bdbd7f19b710.71.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a4da62d7634e25696888f4fabd9d78072ca3a340b23009553aec8a988457b4
3
+ size 3812
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94dfb7766737888a0be8a64fc57a958f9512920f4fc9844aa5c3c259754d284b
3
+ size 3311