chansung commited on
Commit
2197778
1 Parent(s): c23898b

Training in progress, step 100

Browse files
adapter_config.json CHANGED
@@ -10,20 +10,20 @@
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
- "lora_alpha": 32,
14
  "lora_dropout": 0.05,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
17
  "modules_to_save": null,
18
  "peft_type": "LORA",
19
- "r": 16,
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "k_proj",
24
- "o_proj",
25
  "q_proj",
26
- "v_proj"
 
 
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
+ "lora_alpha": 64,
14
  "lora_dropout": 0.05,
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
  "q_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "o_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c122c1c4ace6f8ff8980bdff41271975598d392aa380d96bffd46facbaaa20e1
3
- size 54560368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda5ce0fb8757a956222571e167851c43f63bb4adcf76f42400a1577d16d547b
3
+ size 2210465720
runs/Aug09_01-34-25_main-nice-zebra-1-0-0/events.out.tfevents.1723181917.main-nice-zebra-1-0-0.542.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e087ac110585d34f8973e5437ff4f9be60f7393bebf0183cc6d42abbf0ae68b
3
+ size 10356
special_tokens_map.json CHANGED
@@ -1,17 +1,21 @@
1
  {
2
- "bos_token": {
3
- "content": "<|begin_of_text|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|eot_id|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<|eot_id|>"
 
 
 
 
17
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>"
21
  }
tokenizer.json CHANGED
@@ -2306,6 +2306,24 @@
2306
  "rstrip": false,
2307
  "normalized": false,
2308
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2309
  }
2310
  ],
2311
  "normalizer": null,
 
2306
  "rstrip": false,
2307
  "normalized": false,
2308
  "special": true
2309
+ },
2310
+ {
2311
+ "id": 128256,
2312
+ "content": "<|im_start|>",
2313
+ "single_word": false,
2314
+ "lstrip": false,
2315
+ "rstrip": false,
2316
+ "normalized": false,
2317
+ "special": true
2318
+ },
2319
+ {
2320
+ "id": 128257,
2321
+ "content": "<|im_end|>",
2322
+ "single_word": false,
2323
+ "lstrip": false,
2324
+ "rstrip": false,
2325
+ "normalized": false,
2326
+ "special": true
2327
  }
2328
  ],
2329
  "normalizer": null,
tokenizer_config.json CHANGED
@@ -2047,17 +2047,37 @@
2047
  "rstrip": false,
2048
  "single_word": false,
2049
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2050
  }
2051
  },
2052
- "bos_token": "<|begin_of_text|>",
2053
- "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
 
 
 
 
2054
  "clean_up_tokenization_spaces": true,
2055
- "eos_token": "<|eot_id|>",
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 2048,
2061
- "pad_token": "<|eot_id|>",
2062
  "tokenizer_class": "PreTrainedTokenizerFast"
2063
  }
 
2047
  "rstrip": false,
2048
  "single_word": false,
2049
  "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|im_start|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<|im_end|>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
  }
2067
  },
2068
+ "additional_special_tokens": [
2069
+ "<|im_start|>",
2070
+ "<|im_end|>"
2071
+ ],
2072
+ "bos_token": "<|im_start|>",
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": 2048,
2081
+ "pad_token": "<|im_end|>",
2082
  "tokenizer_class": "PreTrainedTokenizerFast"
2083
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e78c20b62a1ade5e0950b44b7af4f678936d77b8dd0101bc049cf0d3e875b52e
3
- size 6328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbd82e89b556338d085dd29d12f94918bdc72b09615e68aa836e0e483443ec5e
3
+ size 5624