EmmaGthn commited on
Commit
49854ce
1 Parent(s): 00f9209

Training in progress, step 200

Browse files
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -19,8 +19,7 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "v_proj",
23
- "q_proj"
24
  ],
25
  "task_type": "CAUSAL_LM"
26
  }
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "gpt2",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "c_attn"
 
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9165519b635d3398e4cd3536783dfc5557d15a1af2c93e3b33e87df1d5f11e37
3
- size 67126104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:418e875c25d1a4d23abd9029da4b02a412fbbf9780290e562ad4ddc7d47dbb85
3
+ size 4721680
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jan19_19-53-53_calcul-gpu-lahc-4/events.out.tfevents.1705690445.calcul-gpu-lahc-4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee72287a85f6e26c97c0740a49dc7b8dc2e498dd6609710aeb3ae6644f01d88
3
+ size 5426
special_tokens_map.json CHANGED
@@ -1,24 +1,6 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "</s>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,39 +1,20 @@
1
  {
 
2
  "added_tokens_decoder": {
3
- "0": {
4
- "content": "<unk>",
5
  "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<s>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "</s>",
21
- "lstrip": false,
22
- "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  }
27
  },
28
- "bos_token": "<s>",
29
- "clean_up_tokenization_spaces": false,
30
- "eos_token": "</s>",
31
- "legacy": false,
32
- "model_max_length": 1000000000000000019884624838656,
33
- "pad_token": "</s>",
34
- "padding_side": "right",
35
- "sp_model_kwargs": {},
36
- "tokenizer_class": "LlamaTokenizer",
37
- "unk_token": "<unk>",
38
- "use_default_system_prompt": false
39
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
  "lstrip": false,
7
+ "normalized": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  }
12
  },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
 
 
 
 
20
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcc7bdff174c1fb2d32838d57c74e502a42e3d58be40e16f5e6e9c32cd783eca
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74794d107eacaa8f384d8d8bf325dc08cb3e9336a8ad797672f9321020c676e2
3
  size 4600
vocab.json ADDED
The diff for this file is too large to render. See raw diff