Collin Heenan commited on
Commit
23c8cbb
1 Parent(s): 3416287

Upload 10 files

Browse files
adapter_config (2).json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "someone13574/Mistral-7B-v0.1-sharded",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
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": 0.1,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 64,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "v_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
adapter_model (1).bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f878a6e4271e9a69beac8e5b48b8615a95ea2ea622331ea9d73807db8f966d
3
+ size 109097933
optimizer (1).pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c84d5dee6f07881ef337fe04d04f2fc3a0c3d4a7ce7237d40dff59de5891bba
3
+ size 218182021
rng_state (1).pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d4ebc405aa7ec53f355d0acb162f70fbe68ce2765d8c928300e71c43300208
3
+ size 14575
scheduler (1).pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7913dc3f0b2c73d1e7bd59ffcf0917659eb743601ff1e7985c9fd377c430c82
3
+ size 627
special_tokens_map (1).json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "pad_token": "</s>",
10
+ "unk_token": "<unk>"
11
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [
29
+ "<unk>",
30
+ "<s>",
31
+ "</s>"
32
+ ],
33
+ "bos_token": "<s>",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "legacy": true,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": "</s>",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": true
44
+ }
trainer_state.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.06474820143884892,
5
+ "eval_steps": 500,
6
+ "global_step": 9,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 0.0002,
14
+ "loss": 1.5345,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.00018947368421052632,
20
+ "loss": 1.3349,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 0.00017894736842105264,
26
+ "loss": 1.1777,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.03,
31
+ "learning_rate": 0.00016842105263157895,
32
+ "loss": 1.4423,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.04,
37
+ "learning_rate": 0.00015789473684210527,
38
+ "loss": 1.608,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 0.00014736842105263158,
44
+ "loss": 1.2715,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.05,
49
+ "learning_rate": 0.0001368421052631579,
50
+ "loss": 1.2625,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.06,
55
+ "learning_rate": 0.0001263157894736842,
56
+ "loss": 1.2287,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.06,
61
+ "learning_rate": 0.00011578947368421053,
62
+ "loss": 1.1866,
63
+ "step": 9
64
+ }
65
+ ],
66
+ "logging_steps": 1,
67
+ "max_steps": 20,
68
+ "num_train_epochs": 1,
69
+ "save_steps": 1,
70
+ "total_flos": 551832832696320.0,
71
+ "trial_name": null,
72
+ "trial_params": null
73
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:710a52b964f41f68f9fb0233a822ecc3cc942d0e58f0fea59f5a9b802bffa0f4
3
+ size 4027