tjkmitl commited on
Commit
60c4827
1 Parent(s): a5fbd42

End of training

Browse files
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: PromptEmotionNewsModel
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
+ # PromptEmotionNewsModel
15
+
16
+ This model is a fine-tuned version of [openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf](https://huggingface.co/openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf) 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: 0.01
36
+ - train_batch_size: 16
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - gradient_accumulation_steps: 16
40
+ - total_train_batch_size: 256
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
+ - num_epochs: 1
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+cu121
55
+ - Datasets 2.16.1
56
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "openthaigpt/openthaigpt-1.0.0-beta-7b-chat-ckpt-hf",
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": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba2ad1adb51cb00c54b9d8e5d1e65db3ac8d7daa3e2631739ed3718d6b3758f1
3
+ size 16794200
runs/Jan25_10-14-41_192ff0eadac2/events.out.tfevents.1706177683.192ff0eadac2.4553.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ad37b259dfbfdef4e5c796665dacbbdede6684885127ff63944aab537eead3
3
+ size 5489
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e64196d11407f29bfe9cc435cc215d88480aace662c8fcd2aee74bc307e3b7eb
3
+ size 4600