sdeg commited on
Commit
8ce08d1
1 Parent(s): 0161468

End of training

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-350m",
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
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.26.1",
28
+ "use_cache": true,
29
+ "vocab_size": 50272,
30
+ "word_embed_proj_dim": 512
31
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.26.1"
7
+ }
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 sha256:1493f2dd2cc1f3e41609612321962a41d636d78a7a04dcdb90132484d359b143
3
+ size 1324917277
runs/Feb27_00-08-32_62d83bf72530/1677456518.0289907/events.out.tfevents.1677456518.62d83bf72530.3385.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47adc836bdae3e9d3482882c3e1f8fb1d1e6dedc0088be4d613f6d01a83de476
3
+ size 5701
runs/Feb27_00-08-32_62d83bf72530/events.out.tfevents.1677456518.62d83bf72530.3385.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1780fc29e930c9b06b1f6b0492b0b73ddea03500d5efd1f2f403c707b628d54c
3
+ size 4789
runs/Feb27_00-10-44_62d83bf72530/1677456648.258219/events.out.tfevents.1677456648.62d83bf72530.3385.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b39035cefc00764e02fdd8043c564a1128e9256612df9725327c3f3557cb6f63
3
+ size 5701
runs/Feb27_00-10-44_62d83bf72530/events.out.tfevents.1677456648.62d83bf72530.3385.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd0335fa92fd251d496013f3523b92f917aa97dcffc6caa61303be963f2b57f5
3
+ size 4717
runs/Feb27_00-10-44_62d83bf72530/events.out.tfevents.1677456751.62d83bf72530.3385.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b5032810af49b0c33687bb289a2fe200df8ca920f077f4230ec61d87c595a35
3
+ size 306
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "gpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf1401d67f7ba8d0c9893644f950f3ab14eadad5bee2e8eaf8c0254ca8c8a1f
3
+ size 3515
vocab.json ADDED
The diff for this file is too large to render. See raw diff