TatvaJoshi-AHS commited on
Commit
7c325c7
1 Parent(s): 7c47ba5

AHS_SPO_FAQ_LM_V_2.0

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: google/flan-t5-base
7
+ model-index:
8
+ - name: peft-InstructionTuning-training-1720133057
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
+ # peft-InstructionTuning-training-1720133057
16
+
17
+ This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) 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: 0.0003
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: linear
44
+ - lr_scheduler_warmup_steps: 100
45
+ - num_epochs: 1
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - PEFT 0.11.1
54
+ - Transformers 4.41.2
55
+ - Pytorch 2.1.2
56
+ - Datasets 2.19.2
57
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/flan-t5-base",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k",
24
+ "wi_1",
25
+ "v",
26
+ "o",
27
+ "q",
28
+ "wo",
29
+ "wi_0"
30
+ ],
31
+ "task_type": "SEQ_2_SEQ_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a8df8dc13f7111ac66f5be7f5193fda3512457e697aa4fdd5b6e8fdfe8e861
3
+ size 54325384
runs/Jul04_22-44-17_7496cfb01683/events.out.tfevents.1720133062.7496cfb01683.74.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b687d2df3583c21cd47b2869c8af39be0c0cb7876b1b5e2862ed8c178aa4d30
3
+ size 6353
runs/Jul04_22-44-17_7496cfb01683/events.out.tfevents.1720133173.7496cfb01683.74.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d75522743847b86c640c58b66e2c9bd35bb9c8ad9a0d9072fb7304c1268e7e2
3
+ size 6353
runs/Jul04_22-44-17_7496cfb01683/events.out.tfevents.1720133262.7496cfb01683.74.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba52ca63fbc49dd3687fa14fe97ce656c3846c17e4c2591fe9a32afb660efd7
3
+ size 6353
runs/Jul04_22-44-17_7496cfb01683/events.out.tfevents.1720133348.7496cfb01683.74.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dde346f892f3ddaa43dce0556ce7e41cf98b763348616fe747024df3bb21a41
3
+ size 6353
runs/Jul04_22-44-17_7496cfb01683/events.out.tfevents.1720133459.7496cfb01683.74.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbba3f26bb0f9f452f1e342ba4b99d3efbfc195d03765f82536004f08c7c2ca6
3
+ size 6353
runs/Jul04_22-44-17_7496cfb01683/events.out.tfevents.1720133544.7496cfb01683.74.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95f02bf9999a1d2972789cea2cdb6cb182ee0488bcd2015edd48c2cb6966bdf
3
+ size 6353
runs/Jul04_22-44-17_7496cfb01683/events.out.tfevents.1720133630.7496cfb01683.74.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d303fca3c0ade4c1725b6d9cf9ccb5ce9b8cddc9bd5e33e03c57c56349de9d0c
3
+ size 6353
runs/Jul04_22-44-17_7496cfb01683/events.out.tfevents.1720133740.7496cfb01683.74.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7736b95336b904348db53f78d903ca9e9f429854d6f741dd1180c765af8f58f0
3
+ size 6353
runs/Jul04_22-44-17_7496cfb01683/events.out.tfevents.1720133825.7496cfb01683.74.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:987bced7f53d950dfc9859f779bb08e0bdbf610cf42a964d8c3c9d2f5bfcef1b
3
+ size 6353
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70809383fac9e36f78ce8f004b028af6ed921168e8bfb7614e2e3c677c0874be
3
+ size 5368