abishekcodes commited on
Commit
ce5d086
1 Parent(s): f1d71c9

End of training

Browse files
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: microsoft/phi-2
7
+ model-index:
8
+ - name: phi-2
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
+ # phi-2
16
+
17
+ This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) 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: 2
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: 100
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - PEFT 0.7.1
51
+ - Transformers 4.38.0.dev0
52
+ - Pytorch 2.1.0+cu121
53
+ - Datasets 2.16.1
54
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-2",
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
+ "q_proj",
23
+ "v_proj",
24
+ "k_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM"
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d7f59b213aaabf03cbdde20491a9117e1019823b00442fb9857b2f9838d58be
3
+ size 31483040
runs/Jan21_08-11-47_54cbda4b5896/events.out.tfevents.1705824714.54cbda4b5896.1986.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c23d1c4b48c1f631a36b26f79ec49749ec58530ec6a38daf541bb1777a485d0
3
+ size 4959
runs/Jan21_08-13-18_54cbda4b5896/events.out.tfevents.1705824802.54cbda4b5896.1986.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ae62ce59c7d154301574863ef8a3fba61f85e40ed240bcb9c355fc97219c9c
3
+ size 4958
runs/Jan21_08-15-16_54cbda4b5896/events.out.tfevents.1705824919.54cbda4b5896.1986.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5f755e2eef0bad0f03a94df037fdaaa2371b531a3660a65053d32ae0d8a0f88
3
+ size 4958
runs/Jan21_08-16-50_54cbda4b5896/events.out.tfevents.1705825014.54cbda4b5896.1986.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e74c1b36cd54456f1bbb828bb051cd6c6dff15ef456bec28a92c7a1287e52a
3
+ size 4955
runs/Jan21_08-18-02_54cbda4b5896/events.out.tfevents.1705825087.54cbda4b5896.1986.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e054aa1145d72bf70081340ccd1574c40bcfc60d329a24707aa8c4b79d82723
3
+ size 4955
runs/Jan21_08-28-02_54cbda4b5896/events.out.tfevents.1705825689.54cbda4b5896.1986.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3941fa73fa6931e86c6dc15121da504a684af958c8ac09b9e600ca7b267d299a
3
+ size 4955
runs/Jan21_08-34-39_54cbda4b5896/events.out.tfevents.1705826084.54cbda4b5896.1986.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee2eb52ed844ca05283b04120f2d71eb305aa72197272b0899e3e9962b338b09
3
+ size 20704
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3005851bafc8241bdbf5f1f9a75341d78b20afc0c6df05dfffb0142e7c23136e
3
+ size 4664