Mikegzl commited on
Commit
f41271a
·
verified ·
1 Parent(s): f6f29b6

Training in progress, epoch 1

Browse files
adapter_config.json CHANGED
@@ -3,6 +3,8 @@
3
  "auto_mapping": null,
4
  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
  "bias": "none",
 
 
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
8
  "init_lora_weights": true,
@@ -11,6 +13,7 @@
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
  "lora_alpha": 128,
 
14
  "lora_dropout": 0.05,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
@@ -20,12 +23,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "o_proj",
24
- "q_proj",
25
  "down_proj",
26
- "up_proj",
27
- "v_proj",
28
  "gate_proj",
 
 
 
 
29
  "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
3
  "auto_mapping": null,
4
  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
5
  "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
  "fan_in_fan_out": false,
9
  "inference_mode": true,
10
  "init_lora_weights": true,
 
13
  "layers_to_transform": null,
14
  "loftq_config": {},
15
  "lora_alpha": 128,
16
+ "lora_bias": false,
17
  "lora_dropout": 0.05,
18
  "megatron_config": null,
19
  "megatron_core": "megatron.core",
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
26
  "down_proj",
 
 
27
  "gate_proj",
28
+ "o_proj",
29
+ "v_proj",
30
+ "up_proj",
31
+ "q_proj",
32
  "k_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcdd26abd39a88f937ce0c22d1d0ba4f2665360638c01f5d970598634213c870
3
  size 4785795512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:152bb3728edf32ab4aa609d2ce6d1db9ce28b0de61d58d9a7f3d11fe4e833c0a
3
  size 4785795512
runs/Dec17_08-06-51_ef37845f7035/events.out.tfevents.1734422823.ef37845f7035.13918.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad59653a5991506173b2c23451e89f84abb4a376a84f29b81f033dc6dc5b753
3
+ size 9674
tokenizer_config.json CHANGED
@@ -2073,11 +2073,12 @@
2073
  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2074
  "clean_up_tokenization_spaces": true,
2075
  "eos_token": "<|im_end|>",
 
2076
  "model_input_names": [
2077
  "input_ids",
2078
  "attention_mask"
2079
  ],
2080
- "model_max_length": 1000000000000000019884624838656,
2081
  "pad_token": "<|im_end|>",
2082
  "tokenizer_class": "PreTrainedTokenizerFast"
2083
  }
 
2073
  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2074
  "clean_up_tokenization_spaces": true,
2075
  "eos_token": "<|im_end|>",
2076
+ "extra_special_tokens": {},
2077
  "model_input_names": [
2078
  "input_ids",
2079
  "attention_mask"
2080
  ],
2081
+ "model_max_length": 512,
2082
  "pad_token": "<|im_end|>",
2083
  "tokenizer_class": "PreTrainedTokenizerFast"
2084
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b10b6916890ba166348620f1bcbd148c01d588eca75583cd0793b10687e105d
3
- size 5688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3b687cdfd14089f400d7c86297ff5b87749097b6a79cc24a8731b180579bf2d
3
+ size 5752