dmitrijsk commited on
Commit
8d4aa5a
1 Parent(s): 50e49f0

End of training

Browse files
Files changed (4) hide show
  1. README.md +55 -0
  2. adapter_config.json +20 -0
  3. adapter_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigscience-bloom-rail-1.0
3
+ base_model: bigscience/bloomz-3b
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 [bigscience/bloomz-3b](https://huggingface.co/bigscience/bloomz-3b) 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: 0.001
36
+ - train_batch_size: 6
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - gradient_accumulation_steps: 4
40
+ - total_train_batch_size: 24
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: 100
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.32.0.dev0
53
+ - Pytorch 2.0.1+cu117
54
+ - Datasets 2.14.4
55
+ - Tokenizers 0.13.3
adapter_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "bigscience/bloomz-3b",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "query_key_value"
18
+ ],
19
+ "task_type": "CAUSAL_LM"
20
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57778654d4f93cb5c0f1dcebc0c2de63b59e220c9ff9d4ee8b712d54faff1808
3
+ size 19683045
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:961ad255372a75ef55021829d307224b8234df9d19227401294c17a38be71f80
3
+ size 4027