Hugging Face's logo

eshachar
/
peft-starcoder-lora-cutlass

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
eshachar commited on
Commit
4d8debf
·
verified ·
1 Parent(s): 5a4a1ca

End of training

Browse files
Files changed (5) hide show
  1. README.md +99 -0
  2. adapter_config.json +31 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Jul20_14-09-53_0acd555eb299/events.out.tfevents.1721484595.0acd555eb299.16282.0 +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: bigcode/starcoderbase-7b
3
+ library_name: peft
4
+ license: bigcode-openrail-m
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: peft-starcoder-lora-cutlass
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-starcoder-lora-cutlass
16
+
17
+ This model is a fine-tuned version of [bigcode/starcoderbase-7b](https://huggingface.co/bigcode/starcoderbase-7b) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4322
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0005
39
+ - train_batch_size: 16
40
+ - eval_batch_size: 16
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_steps: 30
45
+ - training_steps: 4000
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.5409 | 0.025 | 100 | 0.4729 |
52
+ | 0.3672 | 0.05 | 200 | 0.4051 |
53
+ | 0.3432 | 0.075 | 300 | 0.3876 |
54
+ | 0.312 | 0.1 | 400 | 0.3548 |
55
+ | 0.2594 | 0.125 | 500 | 0.3507 |
56
+ | 0.2821 | 0.15 | 600 | 0.3428 |
57
+ | 0.1958 | 0.175 | 700 | 0.3391 |
58
+ | 0.2362 | 0.2 | 800 | 0.3405 |
59
+ | 0.209 | 0.225 | 900 | 0.3421 |
60
+ | 0.2114 | 0.25 | 1000 | 0.3481 |
61
+ | 0.1877 | 0.275 | 1100 | 0.3447 |
62
+ | 0.1903 | 0.3 | 1200 | 0.3533 |
63
+ | 0.1723 | 0.325 | 1300 | 0.3578 |
64
+ | 0.1465 | 0.35 | 1400 | 0.3643 |
65
+ | 0.1751 | 0.375 | 1500 | 0.3639 |
66
+ | 0.1213 | 0.4 | 1600 | 0.3749 |
67
+ | 0.119 | 0.425 | 1700 | 0.3692 |
68
+ | 0.1199 | 0.45 | 1800 | 0.3820 |
69
+ | 0.0986 | 0.475 | 1900 | 0.3816 |
70
+ | 0.1232 | 0.5 | 2000 | 0.3868 |
71
+ | 0.0819 | 0.525 | 2100 | 0.3923 |
72
+ | 0.096 | 0.55 | 2200 | 0.3964 |
73
+ | 0.0873 | 0.575 | 2300 | 0.3977 |
74
+ | 0.0892 | 0.6 | 2400 | 0.4007 |
75
+ | 0.0802 | 0.625 | 2500 | 0.4078 |
76
+ | 0.066 | 0.65 | 2600 | 0.4119 |
77
+ | 0.0863 | 0.675 | 2700 | 0.4125 |
78
+ | 0.0722 | 0.7 | 2800 | 0.4189 |
79
+ | 0.0888 | 0.725 | 2900 | 0.4201 |
80
+ | 0.0757 | 0.75 | 3000 | 0.4263 |
81
+ | 0.0666 | 0.775 | 3100 | 0.4234 |
82
+ | 0.0757 | 0.8 | 3200 | 0.4275 |
83
+ | 0.053 | 0.825 | 3300 | 0.4289 |
84
+ | 0.0772 | 0.85 | 3400 | 0.4290 |
85
+ | 0.0546 | 0.875 | 3500 | 0.4297 |
86
+ | 0.0601 | 0.9 | 3600 | 0.4311 |
87
+ | 0.0606 | 0.925 | 3700 | 0.4317 |
88
+ | 0.0544 | 0.95 | 3800 | 0.4314 |
89
+ | 0.065 | 0.975 | 3900 | 0.4320 |
90
+ | 0.0503 | 1.0 | 4000 | 0.4322 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - PEFT 0.11.1
96
+ - Transformers 4.42.4
97
+ - Pytorch 2.4.0a0+07cecf4168.nv24.05
98
+ - Datasets 2.20.0
99
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigcode/starcoderbase-7b",
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": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_attn",
24
+ "c_attn",
25
+ "c_proj",
26
+ "c_fc"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa9b9571b8d28a2f855107bf08365af3a762e1032957abf5eff7b3937c072991
3
+ size 77457688
runs/Jul20_14-09-53_0acd555eb299/events.out.tfevents.1721484595.0acd555eb299.16282.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c059d7c2de2b6ceef3e28aa2a5c7de8ebd2fcf51ba5af0ff06da8ca915e7afc7
3
+ size 50682
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d2c40e207917d14229acc725bcd7d648b53a933718144ce359f1463aed05e8
3
+ size 5176