rajveer43 commited on
Commit
56b7a98
1 Parent(s): d8bbf27

Rajveer43/MiniMedic

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: GeneZC/MiniChat-1.5-3B
7
+ model-index:
8
+ - name: experiments
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
+ # experiments
16
+
17
+ This model is a fine-tuned version of [GeneZC/MiniChat-1.5-3B](https://huggingface.co/GeneZC/MiniChat-1.5-3B) 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
+ - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 16
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_ratio: 0.05
45
+ - num_epochs: 6
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - PEFT 0.7.1
55
+ - Transformers 4.37.0.dev0
56
+ - Pytorch 2.0.0
57
+ - Datasets 2.1.0
58
+ - 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": "GeneZC/MiniChat-1.5-3B",
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": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj"
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 sha256:10b3d4e03b0b166d8d6de4004c56dfcdf8c08db7e3f7b148b4b5dada51fe7d63
3
+ size 18887216
runs/Dec25_06-17-38_0e920f2fb747/events.out.tfevents.1703485192.0e920f2fb747.42.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f1ec8d1eee800d4a0a7f2fc17317b948b4bf1b561d7582bb47f0919ec3ef30
3
+ size 4800
runs/Dec25_06-22-20_0e920f2fb747/events.out.tfevents.1703485340.0e920f2fb747.42.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20b698e4f979491b34154c74f3fd74ba287522697056be6fe12a85132f14b65f
3
+ size 5147
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d440a4ad25112aa2f3fd7c4e707a45ea634f198c6cbba19da3ed322908bccb
3
+ size 4283