MoulikBansal commited on
Commit
def6f4b
1 Parent(s): c8a4e11

End of training

Browse files
README.md CHANGED
@@ -1,3 +1,54 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: mit
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: microsoft/phi-1_5
7
+ model-index:
8
+ - name: fine-tuned-on-mcq-phi1_5
9
+ results: []
10
  ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # fine-tuned-on-mcq-phi1_5
16
+
17
+ This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 0.0002
37
+ - train_batch_size: 4
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: cosine
42
+ - training_steps: 1000
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - PEFT 0.7.1
51
+ - Transformers 4.37.0
52
+ - Pytorch 2.1.0+cu121
53
+ - Datasets 2.16.1
54
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-1_5",
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
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "fc1",
23
+ "fc2"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36d84182b2b1a13bd086d6d6f4e819875889d4814bd8652a9306d0bb515e16ec
3
+ size 31469312
runs/Jan24_15-15-34_70151065f011/events.out.tfevents.1706109366.70151065f011.250.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2ba0c478c6788d41980d2cb2535be996a565ce4abc2c41c1c814ba2cd6f2fbf
3
+ size 5746
runs/Jan24_15-20-58_70151065f011/events.out.tfevents.1706109666.70151065f011.250.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:872b6444aa4f6190eb6c858f5b2d58807b7436b7cb5251a5c069da06073f97da
3
+ size 7034
runs/Jan24_15-43-11_70151065f011/events.out.tfevents.1706110991.70151065f011.8350.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:603819e91ad379b46bff0b806b097480fe956c73e0fb7fdd000d598760cee7ac
3
+ size 7034
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc282f80964140feadf276145d1311955231f1ec03ef128cd5846604ebc42153
3
+ size 4792