sharkMeow commited on
Commit
08d136b
1 Parent(s): 6612b86

Training in progress, epoch 1

Browse files
adapter_config.json CHANGED
@@ -1,21 +1,28 @@
1
  {
 
2
  "auto_mapping": null,
3
  "base_model_name_or_path": "yentinglin/Taiwan-LLM-7B-v2.0-chat",
4
  "bias": "none",
5
- "fan_in_fan_out": false,
6
  "inference_mode": true,
7
  "init_lora_weights": true,
8
  "layers_pattern": null,
9
  "layers_to_transform": null,
10
  "lora_alpha": 16,
11
- "lora_dropout": 0.1,
12
  "modules_to_save": null,
13
  "peft_type": "LORA",
14
  "r": 4,
 
15
  "revision": null,
16
  "target_modules": [
17
- "q_proj",
18
- "v_proj"
 
 
 
 
 
19
  ],
20
  "task_type": "CAUSAL_LM"
21
  }
 
1
  {
2
+ "alpha_pattern": {},
3
  "auto_mapping": null,
4
  "base_model_name_or_path": "yentinglin/Taiwan-LLM-7B-v2.0-chat",
5
  "bias": "none",
6
+ "fan_in_fan_out": null,
7
  "inference_mode": true,
8
  "init_lora_weights": true,
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
11
  "lora_alpha": 16,
12
+ "lora_dropout": 0.05,
13
  "modules_to_save": null,
14
  "peft_type": "LORA",
15
  "r": 4,
16
+ "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
+ "down_proj",
20
+ "o_proj",
21
+ "k_proj",
22
+ "up_proj",
23
+ "v_proj",
24
+ "gate_proj",
25
+ "q_proj"
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af22ad5df74625210713ef368d0b02c7f058adca19bded43a1f2e84795a71ec9
3
+ size 40036040
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "yentinglin/Taiwan-LLM-7B-v2.0-chat",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 32,
18
+ "pretraining_tp": 1,
19
+ "quantization_config": {
20
+ "bnb_4bit_compute_dtype": "float16",
21
+ "bnb_4bit_quant_type": "nf4",
22
+ "bnb_4bit_use_double_quant": true,
23
+ "llm_int8_enable_fp32_cpu_offload": false,
24
+ "llm_int8_has_fp16_weight": false,
25
+ "llm_int8_skip_modules": null,
26
+ "llm_int8_threshold": 6.0,
27
+ "load_in_4bit": true,
28
+ "load_in_8bit": false,
29
+ "quant_method": "bitsandbytes"
30
+ },
31
+ "rms_norm_eps": 1e-05,
32
+ "rope_scaling": null,
33
+ "rope_theta": 10000.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.35.1",
37
+ "use_cache": false,
38
+ "vocab_size": 32000
39
+ }
runs/Nov22_17-44-35_c4fc869ceb5e/events.out.tfevents.1700675076.c4fc869ceb5e.10435.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13c05434f155bfad53866709aba8633787ec8f5ed331e286e1385a38a3dd957
3
+ size 5092
runs/Nov22_18-04-21_c4fc869ceb5e/events.out.tfevents.1700676262.c4fc869ceb5e.19146.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b423cabcb777548d4fe7216bf5de8cd4f5c83650be591fb764070b94c7165117
3
+ size 5092
runs/Nov22_18-15-44_c4fc869ceb5e/events.out.tfevents.1700676945.c4fc869ceb5e.22070.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8242ed69c739845327cbe55fe392c606c7e8674e2844fcda6fbb6e54f39a3af2
3
+ size 5079
runs/Nov22_18-17-36_c4fc869ceb5e/events.out.tfevents.1700677056.c4fc869ceb5e.22777.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba41f098d6125c39de3e34f48971184b08a22a9f8fb314ee9a8422393c6408e
3
+ size 26079
special_tokens_map.json CHANGED
@@ -13,7 +13,13 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "</s>",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,4 +1,6 @@
1
  {
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<unk>",
@@ -36,6 +38,8 @@
36
  "sp_model_kwargs": {},
37
  "spaces_between_special_tokens": false,
38
  "tokenizer_class": "LlamaTokenizer",
 
39
  "unk_token": "<unk>",
40
- "use_default_system_prompt": true
 
41
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
 
38
  "sp_model_kwargs": {},
39
  "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
+ "trust_remote_code": false,
42
  "unk_token": "<unk>",
43
+ "use_default_system_prompt": true,
44
+ "use_fast": true
45
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa61d9f86b606c1ce2cff6089a30bf6235d0ca545a3228ffb8aa9df94c28fca3
3
- size 4408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29182789cc886c4cb1e203599999900c580a72f92286132414128006e2d749f4
3
+ size 4603