Hugging Face's logo

kyryl-opens-ml
/
duckdb-text2sql-codellama

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
kyryl-opens-ml commited on
Commit
c208b06
•
1 Parent(s): a4e88d2

Model save

Browse files
Files changed (6) hide show
  1. README.md +1 -1
  2. adapter_config.json +3 -8
  3. adapter_model.safetensors +2 -2
  4. all_results.json +5 -5
  5. train_results.json +5 -5
  6. training_args.bin +1 -1
README.md CHANGED
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
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: 0.0001
50
 
51
  ### Training results
52
 
 
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: 0.01
50
 
51
  ### Training results
52
 
adapter_config.json CHANGED
@@ -9,23 +9,18 @@
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
11
  "loftq_config": {},
12
- "lora_alpha": 128,
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": 256,
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "o_proj",
23
- "gate_proj",
24
  "v_proj",
25
- "q_proj",
26
- "k_proj",
27
- "up_proj",
28
- "down_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
 
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
11
  "loftq_config": {},
12
+ "lora_alpha": 8,
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": 32,
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "v_proj",
23
+ "q_proj"
 
 
 
24
  ],
25
  "task_type": "CAUSAL_LM",
26
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d394ac552cb1dd3a47bf1f1f1b08935be56350eadd7e36a39bbd041b8deeab3d
3
- size 1803907984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6dc7d42cfcb58887f3d7fda8cc1a7bda580b734c510d8e60b5cf23eb195732f
3
+ size 558155232
all_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 0.0,
3
- "train_loss": 0.9373413324356079,
4
- "train_runtime": 26.737,
5
- "train_samples_per_second": 0.022,
6
- "train_steps_per_second": 0.037
7
  }
 
1
  {
2
+ "epoch": 0.01,
3
+ "train_loss": 0.8435632705688476,
4
+ "train_runtime": 143.2906,
5
+ "train_samples_per_second": 0.268,
6
+ "train_steps_per_second": 0.035
7
  }
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 0.0,
3
- "train_loss": 0.9373413324356079,
4
- "train_runtime": 26.737,
5
- "train_samples_per_second": 0.022,
6
- "train_steps_per_second": 0.037
7
  }
 
1
  {
2
+ "epoch": 0.01,
3
+ "train_loss": 0.8435632705688476,
4
+ "train_runtime": 143.2906,
5
+ "train_samples_per_second": 0.268,
6
+ "train_steps_per_second": 0.035
7
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abea1e76f744c42bb1a2410accee7956f562e20ed48da307ee0648bcb414d359
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ce936f620d4e344f33400396b71d9d80a46d45713aa43b380f1ba1dae1d7b42
3
  size 4920