MichaelKim commited on
Commit
8566a5a
1 Parent(s): 76e6b10

End of training

Browse files
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: ONS-AI-RESEARCH/ONS-SOLAR-10.7B
7
+ model-index:
8
+ - name: ONS-SOLAR-10.7B_trained_trained_v2
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
+ # ONS-SOLAR-10.7B_trained_trained_v2
16
+
17
+ This model is a fine-tuned version of [ONS-AI-RESEARCH/ONS-SOLAR-10.7B](https://huggingface.co/ONS-AI-RESEARCH/ONS-SOLAR-10.7B) on an unknown 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: 0.0001
37
+ - train_batch_size: 10
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: linear
42
+ - num_epochs: 1
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - PEFT 0.9.0
52
+ - Transformers 4.38.2
53
+ - Pytorch 2.1.0+cu121
54
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "ONS-AI-RESEARCH/ONS-SOLAR-10.7B",
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": 32,
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": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "down_proj",
24
+ "gate_proj",
25
+ "up_proj",
26
+ "k_proj",
27
+ "q_proj",
28
+ "o_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89fec18773e4a30730df7b5ca6d4547853b9430e6894253ec83e1b4be7acc72
3
+ size 125918320
runs/Mar07_09-17-26_9497367dda34/events.out.tfevents.1709803047.9497367dda34.4827.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148455dab57d00db5c6ece3c4dac9bcb2c408eabe14f3a0dc627e5d9b79c3ea5
3
+ size 5156
runs/Mar07_09-21-15_9497367dda34/events.out.tfevents.1709803276.9497367dda34.4827.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77fd14959513615cd311e80823be5b36475a7e541561df6543a24e20688c4dc0
3
+ size 5504
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23d17421c140897ffd69a06efc784a22930bb37e68b98510181aa693bb7a3a49
3
+ size 4984