RayBernard commited on
Commit
8f6baf7
1 Parent(s): 5987f6f

Training in progress, step 100

Browse files
adapter_config.json CHANGED
@@ -1,7 +1,10 @@
1
  {
2
  "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
 
 
 
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -10,22 +13,20 @@
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
- "lora_alpha": 16,
14
- "lora_dropout": 0.5,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
17
  "modules_to_save": null,
18
  "peft_type": "LORA",
19
- "r": 32,
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "k_proj",
24
  "q_proj",
25
- "v_proj",
26
- "output_proj"
27
  ],
28
- "task_type": "CAUSAL_LM",
29
  "use_dora": false,
30
  "use_rslora": false
31
  }
 
1
  {
2
  "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "LlamaForCausalLM",
5
+ "parent_library": "transformers.models.llama.modeling_llama"
6
+ },
7
+ "base_model_name_or_path": "./models/meta-llama_Meta-Llama-3-8B-Instruct",
8
  "bias": "none",
9
  "fan_in_fan_out": false,
10
  "inference_mode": true,
 
13
  "layers_pattern": null,
14
  "layers_to_transform": null,
15
  "loftq_config": {},
16
+ "lora_alpha": 8,
17
+ "lora_dropout": 0.0,
18
  "megatron_config": null,
19
  "megatron_core": "megatron.core",
20
  "modules_to_save": null,
21
  "peft_type": "LORA",
22
+ "r": 8,
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
26
  "q_proj",
27
+ "v_proj"
 
28
  ],
29
+ "task_type": null,
30
  "use_dora": false,
31
  "use_rslora": false
32
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7843fe9aeb4a2a08352a9588c97060d7311221834cbeaae3082b5e54de1d4465
3
- size 75523312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c029aa7187b980424779630d526a72b36b360d3de570e78f008fa450cc0c5e
3
+ size 13648432
special_tokens_map.json CHANGED
@@ -13,11 +13,5 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": {
17
- "content": "[PAD]",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
  }
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "[PAD]"
 
 
 
 
 
 
17
  }
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b308bbd5bfd8bfdbc7e0a30f801399a0940ce3ec129b3a0ce7f0b05d6174654
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d40610b065c4687ec51294f13ab2757292d27a97f11df91a2ce5b7d6bba2dc
3
  size 5112