Hugging Face's logo

someoneskilled
/
rheabot

PEFT
Safetensors
Model card Files Community
someoneskilled commited on
Commit
cb1236d
•
1 Parent(s): c787069

Upload 8 files

Browse files
Files changed (8) hide show
  1. optimizer.pt +3 -0
  2. rng_state.pth +3 -0
  3. scheduler.pt +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +41 -0
  7. trainer_state.json +81 -0
  8. training_args.bin +3 -0
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d546b7f254c9ad70aee43b5394238420ba7efddbb101249336a5158d45fc37e8
3
+ size 268514874
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5dbe5f5a66de7b8177f493aa7495556f4c1a65bbc3efa281f4d41566cac535
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:107b3a82b2370875d19fdc8f33d3afe7945a07d3f1c7945ab7a037731ca2376e
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "</s>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }
trainer_state.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 66.66666666666667,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 6.67,
13
+ "learning_rate": 0.0002,
14
+ "loss": 1.8198,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 13.33,
19
+ "learning_rate": 0.0002,
20
+ "loss": 0.5831,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 20.0,
25
+ "learning_rate": 0.0002,
26
+ "loss": 0.1285,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 26.67,
31
+ "learning_rate": 0.0002,
32
+ "loss": 0.0797,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 33.33,
37
+ "learning_rate": 0.0002,
38
+ "loss": 0.0755,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 40.0,
43
+ "learning_rate": 0.0002,
44
+ "loss": 0.0748,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 46.67,
49
+ "learning_rate": 0.0002,
50
+ "loss": 0.0739,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 53.33,
55
+ "learning_rate": 0.0002,
56
+ "loss": 0.074,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 60.0,
61
+ "learning_rate": 0.0002,
62
+ "loss": 0.074,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 66.67,
67
+ "learning_rate": 0.0002,
68
+ "loss": 0.0735,
69
+ "step": 100
70
+ }
71
+ ],
72
+ "logging_steps": 10,
73
+ "max_steps": 100,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 100,
76
+ "save_steps": 100,
77
+ "total_flos": 616647229145088.0,
78
+ "train_batch_size": 4,
79
+ "trial_name": null,
80
+ "trial_params": null
81
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:374173e676e7707d5fb7461c9cbb53e61392587ea79373518bf541c40f47eaa3
3
+ size 4728