Hugging Face's logo

grounded-ai
/
phi3.5-hallucination-judge

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
Jlonge4 commited on
Commit
8430d55
•
1 Parent(s): 88458b3

Jlonge4/outputs

Browse files
Files changed (20) hide show
  1. README.md +98 -0
  2. adapter_config.json +34 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +13 -0
  5. runs/Sep08_00-31-35_8a9da4ef0fdf/events.out.tfevents.1725755497.8a9da4ef0fdf.2917.0 +3 -0
  6. runs/Sep08_00-35-36_8a9da4ef0fdf/events.out.tfevents.1725755738.8a9da4ef0fdf.2917.1 +3 -0
  7. runs/Sep08_00-46-22_8a9da4ef0fdf/events.out.tfevents.1725756383.8a9da4ef0fdf.2917.2 +3 -0
  8. runs/Sep08_00-56-30_8a9da4ef0fdf/events.out.tfevents.1725756991.8a9da4ef0fdf.2917.3 +3 -0
  9. runs/Sep08_01-04-11_8a9da4ef0fdf/events.out.tfevents.1725757452.8a9da4ef0fdf.2917.4 +3 -0
  10. runs/Sep08_01-05-14_8a9da4ef0fdf/events.out.tfevents.1725757516.8a9da4ef0fdf.2917.5 +3 -0
  11. runs/Sep08_01-07-03_8a9da4ef0fdf/events.out.tfevents.1725757624.8a9da4ef0fdf.2917.6 +3 -0
  12. runs/Sep08_01-13-40_8a9da4ef0fdf/events.out.tfevents.1725758021.8a9da4ef0fdf.2917.7 +3 -0
  13. runs/Sep08_01-14-17_8a9da4ef0fdf/events.out.tfevents.1725758058.8a9da4ef0fdf.2917.8 +3 -0
  14. runs/Sep08_01-26-59_8a9da4ef0fdf/events.out.tfevents.1725758820.8a9da4ef0fdf.2917.9 +3 -0
  15. runs/Sep08_01-27-35_8a9da4ef0fdf/events.out.tfevents.1725758856.8a9da4ef0fdf.2917.10 +3 -0
  16. special_tokens_map.json +30 -0
  17. tokenizer.json +0 -0
  18. tokenizer.model +3 -0
  19. tokenizer_config.json +131 -0
  20. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3.5-mini-instruct
3
+ library_name: peft
4
+ license: mit
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: outputs
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
18
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
19
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
20
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
21
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
22
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
23
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
24
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
25
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
26
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/0q2t3ek2)
27
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/dtvgakdw)
28
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/9hr7jcal)
29
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/goc9hcye)
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/fzw32mg0)
31
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/fzw32mg0)
32
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/fzw32mg0)
33
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/dphr4egm)
34
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/dphr4egm)
35
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/dphr4egm)
36
+ # outputs
37
+
38
+ This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
39
+ It achieves the following results on the evaluation set:
40
+ - Loss: 1.0926
41
+
42
+ ## Model description
43
+
44
+ More information needed
45
+
46
+ ## Intended uses & limitations
47
+
48
+ More information needed
49
+
50
+ ## Training and evaluation data
51
+
52
+ More information needed
53
+
54
+ ## Training procedure
55
+
56
+ ### Training hyperparameters
57
+
58
+ The following hyperparameters were used during training:
59
+ - learning_rate: 1e-05
60
+ - train_batch_size: 1
61
+ - eval_batch_size: 8
62
+ - seed: 42
63
+ - gradient_accumulation_steps: 4
64
+ - total_train_batch_size: 4
65
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
66
+ - lr_scheduler_type: cosine_with_restarts
67
+ - lr_scheduler_warmup_steps: 20
68
+ - training_steps: 160
69
+
70
+ ### Training results
71
+
72
+ | Training Loss | Epoch | Step | Validation Loss |
73
+ |:-------------:|:-------:|:----:|:---------------:|
74
+ | 2.2453 | 1.1429 | 10 | 2.1914 |
75
+ | 1.8068 | 2.2857 | 20 | 1.8497 |
76
+ | 1.5702 | 3.4286 | 30 | 1.5758 |
77
+ | 1.5012 | 4.5714 | 40 | 1.2568 |
78
+ | 1.2486 | 5.7143 | 50 | 1.1309 |
79
+ | 0.948 | 6.8571 | 60 | 1.0965 |
80
+ | 1.0246 | 8.0 | 70 | 1.0826 |
81
+ | 0.7834 | 9.1429 | 80 | 1.0786 |
82
+ | 0.8802 | 10.2857 | 90 | 1.0755 |
83
+ | 0.7285 | 11.4286 | 100 | 1.0781 |
84
+ | 0.8049 | 12.5714 | 110 | 1.0855 |
85
+ | 0.831 | 13.7143 | 120 | 1.0920 |
86
+ | 0.6412 | 14.8571 | 130 | 1.0900 |
87
+ | 0.7723 | 16.0 | 140 | 1.0898 |
88
+ | 0.8869 | 17.1429 | 150 | 1.0908 |
89
+ | 0.6173 | 18.2857 | 160 | 1.0926 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - PEFT 0.12.0
95
+ - Transformers 4.44.2
96
+ - Pytorch 2.4.0+cu121
97
+ - Datasets 2.21.0
98
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "v_proj",
25
+ "q_proj",
26
+ "o_proj",
27
+ "down_proj",
28
+ "k_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": true
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c872fe43d7260fd00639758f062906f3d5a97b1db0c838fc60b914e973aee9
3
+ size 142623480
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
runs/Sep08_00-31-35_8a9da4ef0fdf/events.out.tfevents.1725755497.8a9da4ef0fdf.2917.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bfbc2782ba457d0e255198fca729dc78a1e28d7403060e9142190d23966c293
3
+ size 41438
runs/Sep08_00-35-36_8a9da4ef0fdf/events.out.tfevents.1725755738.8a9da4ef0fdf.2917.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084beebc76026a699a0cf66da2626cf9181388f75373f2aaed586a88e815ec91
3
+ size 52801
runs/Sep08_00-46-22_8a9da4ef0fdf/events.out.tfevents.1725756383.8a9da4ef0fdf.2917.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d2c03d5dc636551b06eac3e8cc5b0cda79539a82eabe303c8fa228b8e4f8d9
3
+ size 52801
runs/Sep08_00-56-30_8a9da4ef0fdf/events.out.tfevents.1725756991.8a9da4ef0fdf.2917.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439e36a1b8fb85dd20d8e982f79f4113e0a3a05eb7b487fa02295a71fe949848
3
+ size 31796
runs/Sep08_01-04-11_8a9da4ef0fdf/events.out.tfevents.1725757452.8a9da4ef0fdf.2917.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7440f4f3753e438efbfb28965887b451ba94c848c8a9c7eeaae0b9e3737ae6d
3
+ size 10158
runs/Sep08_01-05-14_8a9da4ef0fdf/events.out.tfevents.1725757516.8a9da4ef0fdf.2917.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59153deff792d2fbf758e5880b490a8313695b5a96c8a0a302f4201c29ad5545
3
+ size 10158
runs/Sep08_01-07-03_8a9da4ef0fdf/events.out.tfevents.1725757624.8a9da4ef0fdf.2917.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a478aaef2ab18f70dd54c5130a2fca05c9f98621b1dc2f1726ba02d636233df1
3
+ size 31796
runs/Sep08_01-13-40_8a9da4ef0fdf/events.out.tfevents.1725758021.8a9da4ef0fdf.2917.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04825380e4dd0d6d6490d26274499b2fd8bfabf14dfb9558d3393a6976971a20
3
+ size 8088
runs/Sep08_01-14-17_8a9da4ef0fdf/events.out.tfevents.1725758058.8a9da4ef0fdf.2917.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adaf988ccbd066c536fb2a72f40b8ed4fa82da6bce8310b8e73288385cfa6cda
3
+ size 31796
runs/Sep08_01-26-59_8a9da4ef0fdf/events.out.tfevents.1725758820.8a9da4ef0fdf.2917.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f710421d40521cfbd9c7d5704e3a9a27a4f9c14019f2858e518b5229ad3dda89
3
+ size 11252
runs/Sep08_01-27-35_8a9da4ef0fdf/events.out.tfevents.1725758856.8a9da4ef0fdf.2917.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34016e1259582844980a9c70fc9417e5287af6fdce5bd7960a8a247dba40aa8
3
+ size 45970
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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 ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 131072,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb4d1b5e68a98620bd5d07cf5547d1546cb3035cdbf437944b92386c077aea6e
3
+ size 5432