caesar-one commited on
Commit
4f78ae2
1 Parent(s): 0276a7a

caesar-one/opt-6.7b-lora-short-reviews-hparams

Browse files
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: facebook/opt-6.7b
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: outputs
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # outputs
15
+
16
+ This model is a fine-tuned version of [facebook/opt-6.7b](https://huggingface.co/facebook/opt-6.7b) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.0002
36
+ - train_batch_size: 4
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - gradient_accumulation_steps: 4
40
+ - total_train_batch_size: 16
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 100
44
+ - training_steps: 500
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.35.2
54
+ - Pytorch 2.1.0+cu118
55
+ - Datasets 2.15.0
56
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "facebook/opt-6.7b",
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
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "v_proj",
20
+ "q_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9430ec933fdb52b72fb64897d61f3cc01858adec46ae0f533517f7827372d78
3
+ size 33572648
runs/Nov26_21-50-20_3af456fcf147/events.out.tfevents.1701035423.3af456fcf147.167.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478d28272cbb76cbd5c6b967b92a53ddb901088c163d2e7c3dc69f165be43433
3
+ size 7757
runs/Nov26_22-08-21_3af456fcf147/events.out.tfevents.1701036502.3af456fcf147.167.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892e6adcd7784dad915d68abbe325ef8639887c84522f3f3c65b14aa1b045545
3
+ size 11453
runs/Nov26_22-18-52_3af456fcf147/events.out.tfevents.1701037133.3af456fcf147.9383.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25ee2b7cd8dd69337b2f077b6db6b7d7df27ae592b1d2528305f8f7f226e7b2
3
+ size 4541
runs/Nov26_22-34-26_3af456fcf147/events.out.tfevents.1701038066.3af456fcf147.9383.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b91dd59c43e1992df133b3030f1b6a484edf9b16d8bc9fbbd35a31e0f45f80
3
+ size 4184
runs/Nov26_22-34-53_3af456fcf147/events.out.tfevents.1701038093.3af456fcf147.9383.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd66ca9058e27bf17c168507e3e6a037016495f060e77662ae8d08fb309081dd
3
+ size 4184
runs/Nov26_22-35-54_3af456fcf147/events.out.tfevents.1701038155.3af456fcf147.14366.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e63933a4c75e53b88d52284f67db258ef0e9c812c29e4583ce25ec4058c004
3
+ size 4184
runs/Nov26_22-36-47_3af456fcf147/events.out.tfevents.1701038207.3af456fcf147.14366.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68cf78f42c6ad479b5626d0dba1f43f82effced1adc3870e429b3f0111e9829e
3
+ size 4184
runs/Nov26_22-37-01_3af456fcf147/events.out.tfevents.1701038221.3af456fcf147.14366.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd99215867b53167a08bb675209ee3d0bf96e5fa529ab0ec52fad8f5b5b5352
3
+ size 4184
runs/Nov26_22-38-00_3af456fcf147/events.out.tfevents.1701038281.3af456fcf147.14998.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da50b51d316da8d9fffe7f50473c7825ae42024b10324cd326069f0985c69abf
3
+ size 4695
runs/Nov26_22-39-28_3af456fcf147/events.out.tfevents.1701038369.3af456fcf147.15460.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a25bf6c502c1968053c12b0fe74d619ab4d2c0ea1362d2b8c9d0399e23007d6
3
+ size 5003
runs/Nov26_22-42-56_3af456fcf147/events.out.tfevents.1701038577.3af456fcf147.16320.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f3b870824e849617ec4ddf68e48880b07699d3d49fadbcb1cade65d378ff4f
3
+ size 83150
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22d1c3830d23dbe0ea35fe1464a649db51dcce3cf673b7c768e7b67106d00536
3
+ size 4536