MohamedAhmedAE commited on
Commit
c6ca81b
1 Parent(s): 5c17318

Training in progress, step 100

Browse files
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "MohamedAhmedAE/Llama3-8B-Medical-Finetune-V2-pad-unk-token",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -10,7 +10,7 @@
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
- "lora_alpha": 256,
14
  "lora_dropout": 0.05,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "o_proj",
24
  "up_proj",
25
- "k_proj",
26
- "down_proj",
27
- "gate_proj",
28
  "v_proj",
29
- "q_proj"
 
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "MohamedAhmedAE/Llama3-8B-Medical-Finetune-V3-Merged-unk-token",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
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",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "up_proj",
 
 
 
24
  "v_proj",
25
+ "o_proj",
26
+ "q_proj",
27
+ "gate_proj",
28
+ "down_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57f529300eeb0957bd99f77b268696e0ca8e391e5fdad16ad0fd8857763df262
3
  size 1342238560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c06156259b7b487a0160a0853ce60dca62895b5ad1fad5c64ef7c7097d61d8f
3
  size 1342238560
special_tokens_map.json CHANGED
@@ -1,21 +1,25 @@
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": "<|unk|>",
17
  "unk_token": {
18
- "content": "<|unk|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
  "bos_token": {
7
+ "content": "<|im_start|>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
11
  "single_word": false
12
  },
13
  "eos_token": {
14
+ "content": "<|im_end|>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false
19
  },
20
+ "pad_token": "<unk>",
21
  "unk_token": {
22
+ "content": "<unk>",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
@@ -2309,7 +2314,7 @@
2309
  },
2310
  {
2311
  "id": 128256,
2312
- "content": "<|pad|>",
2313
  "single_word": false,
2314
  "lstrip": false,
2315
  "rstrip": false,
@@ -2318,7 +2323,16 @@
2318
  },
2319
  {
2320
  "id": 128257,
2321
- "content": "<|unk|>",
 
 
 
 
 
 
 
 
 
2322
  "single_word": false,
2323
  "lstrip": false,
2324
  "rstrip": false,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 4096,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
2314
  },
2315
  {
2316
  "id": 128256,
2317
+ "content": "<|im_start|>",
2318
  "single_word": false,
2319
  "lstrip": false,
2320
  "rstrip": false,
 
2323
  },
2324
  {
2325
  "id": 128257,
2326
+ "content": "<|im_end|>",
2327
+ "single_word": false,
2328
+ "lstrip": false,
2329
+ "rstrip": false,
2330
+ "normalized": false,
2331
+ "special": true
2332
+ },
2333
+ {
2334
+ "id": 128258,
2335
+ "content": "<unk>",
2336
  "single_word": false,
2337
  "lstrip": false,
2338
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -2049,7 +2049,7 @@
2049
  "special": true
2050
  },
2051
  "128256": {
2052
- "content": "<|pad|>",
2053
  "lstrip": false,
2054
  "normalized": false,
2055
  "rstrip": false,
@@ -2057,7 +2057,15 @@
2057
  "special": true
2058
  },
2059
  "128257": {
2060
- "content": "<|unk|>",
 
 
 
 
 
 
 
 
2061
  "lstrip": false,
2062
  "normalized": false,
2063
  "rstrip": false,
@@ -2065,17 +2073,26 @@
2065
  "special": true
2066
  }
2067
  },
2068
- "bos_token": "<|begin_of_text|>",
2069
- "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 %}",
 
 
 
 
2070
  "clean_up_tokenization_spaces": true,
2071
- "eos_token": "<|eot_id|>",
 
 
2072
  "model_input_names": [
2073
  "input_ids",
2074
  "attention_mask"
2075
  ],
2076
- "model_max_length": 2024,
2077
- "pad_token": "<|unk|>",
2078
  "padding_side": "right",
 
2079
  "tokenizer_class": "PreTrainedTokenizerFast",
2080
- "unk_token": "<|unk|>"
 
 
2081
  }
 
2049
  "special": true
2050
  },
2051
  "128256": {
2052
+ "content": "<|im_start|>",
2053
  "lstrip": false,
2054
  "normalized": false,
2055
  "rstrip": 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
+ "128258": {
2068
+ "content": "<unk>",
2069
  "lstrip": false,
2070
  "normalized": false,
2071
  "rstrip": false,
 
2073
  "special": true
2074
  }
2075
  },
2076
+ "additional_special_tokens": [
2077
+ "<|im_start|>",
2078
+ "<|im_end|>"
2079
+ ],
2080
+ "bos_token": "<|im_start|>",
2081
+ "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 %}",
2082
  "clean_up_tokenization_spaces": true,
2083
+ "device_map": "auto",
2084
+ "eos_token": "<|im_end|>",
2085
+ "max_length": 4096,
2086
  "model_input_names": [
2087
  "input_ids",
2088
  "attention_mask"
2089
  ],
2090
+ "model_max_length": 4096,
2091
+ "pad_token": "<unk>",
2092
  "padding_side": "right",
2093
+ "stride": 0,
2094
  "tokenizer_class": "PreTrainedTokenizerFast",
2095
+ "truncation_side": "right",
2096
+ "truncation_strategy": "longest_first",
2097
+ "unk_token": "<unk>"
2098
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1739cd9c2bb0672980a28b26f47683a8b80b522d2f06b0b740331e7e294e3edf
3
- size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb149e35d0f0ee3e9bffe7360518648bd13f48a4d5bcea2c3c065dcd78579484
3
+ size 5624