Hugging Face's logo

Shivam17818
/
llama3-8b-instruct-text-to-sql

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
Shivam17818 commited on
Commit
2893a11
•
1 Parent(s): 5e78f49

Model save

Browse files
Files changed (7) hide show
  1. README.md +1 -4
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +1 -1
  4. runs/Aug16_14-22-38_224f5c5a896c/events.out.tfevents.1723818161.224f5c5a896c.24.0 +3 -0
  5. test_dataset.json +0 -0
  6. train_dataset.json +0 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -38,16 +38,13 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0002
41
- - train_batch_size: 3
42
  - eval_batch_size: 8
43
  - seed: 42
44
- - gradient_accumulation_steps: 2
45
- - total_train_batch_size: 6
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
  - lr_scheduler_warmup_ratio: 0.03
49
  - num_epochs: 1
50
- - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0002
41
+ - train_batch_size: 1
42
  - eval_batch_size: 8
43
  - seed: 42
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: constant
46
  - lr_scheduler_warmup_ratio: 0.03
47
  - num_epochs: 1
 
48
 
49
  ### Training results
50
 
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "up_proj",
24
  "o_proj",
25
- "gate_proj",
26
- "v_proj",
27
  "k_proj",
28
- "q_proj",
29
- "down_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q_proj",
24
  "o_proj",
 
 
25
  "k_proj",
26
+ "down_proj",
27
+ "up_proj",
28
+ "v_proj",
29
+ "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56827bbacefc2b6fd9753d8d2f7f008d749b5ec66ab324cd074f34b97bbace22
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b58514110d35fe52d132ad5c08bf6755518fdf9771cb51bc06749f866a4ac298
3
  size 167832240
runs/Aug16_14-22-38_224f5c5a896c/events.out.tfevents.1723818161.224f5c5a896c.24.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bcf9bced4e510b1f7525cc9e1086b92497cf9cc99b96df05eef24225e6d1ee0
3
+ size 9321
test_dataset.json CHANGED
The diff for this file is too large to render. See raw diff
 
train_dataset.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b74321df4a020765d3a654fd1ac0414657736a835f81c1b6d76c8bdcfe3ea813
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f575c845b8c53d9df42273a9676da77820f2b646b626d7d3f23b920e725859c3
3
  size 5496