Hugging Face's logo

patricksaxton
/
peft-starcoder-lora-a100

Text Generation
PEFT
TensorBoard
Safetensors
Transformers
lora
Model card Files
xet
Metrics Community
patricksaxton commited on
Commit
0bc78d8
·
verified ·
1 Parent(s): 582c7ee

Training in progress, step 100

Browse files
Files changed (8) hide show
  1. adapter_config.json +43 -0
  2. adapter_model.safetensors +3 -0
  3. runs/Jan03_02-22-05_edf5218a63d5/events.out.tfevents.1767406941.edf5218a63d5.436.0 +3 -0
  4. runs/Jan03_02-24-59_edf5218a63d5/events.out.tfevents.1767407106.edf5218a63d5.436.1 +3 -0
  5. runs/Jan03_02-25-35_edf5218a63d5/events.out.tfevents.1767407142.edf5218a63d5.436.2 +3 -0
  6. runs/Jan03_02-48-55_edf5218a63d5/events.out.tfevents.1767408542.edf5218a63d5.436.3 +3 -0
  7. runs/Jan03_03-08-50_edf5218a63d5/events.out.tfevents.1767409737.edf5218a63d5.436.4 +3 -0
  8. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "bigcode/starcoderbase-1b",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
+ "qalora_group_size": 16,
28
+ "r": 8,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "c_proj",
33
+ "c_attn",
34
+ "q_attn",
35
+ "c_fc"
36
+ ],
37
+ "target_parameters": null,
38
+ "task_type": "CAUSAL_LM",
39
+ "trainable_token_indices": null,
40
+ "use_dora": false,
41
+ "use_qalora": false,
42
+ "use_rslora": false
43
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4cfdd3c01c7abef6b9af87dd9490973c54402a884a616127e461b4acbb6a819
3
+ size 22241240
runs/Jan03_02-22-05_edf5218a63d5/events.out.tfevents.1767406941.edf5218a63d5.436.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a10c486d0c72f3b7bce0ff4befff8fb3cb6d44af1973a86fb044e4d1fbfec8
3
+ size 5919
runs/Jan03_02-24-59_edf5218a63d5/events.out.tfevents.1767407106.edf5218a63d5.436.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10f77e6434c0368177568bd048a1de4a35705550d18d6ea7d4bb3d8fe373fce3
3
+ size 5917
runs/Jan03_02-25-35_edf5218a63d5/events.out.tfevents.1767407142.edf5218a63d5.436.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38ded224c48c3c2d031d68c78755220c8e9709a4de422df4e0ad73e44c8d614b
3
+ size 6745
runs/Jan03_02-48-55_edf5218a63d5/events.out.tfevents.1767408542.edf5218a63d5.436.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3a6351ccb386a822d89d96748eb5cb31c74436fa455ac439c3b56992203117
3
+ size 6745
runs/Jan03_03-08-50_edf5218a63d5/events.out.tfevents.1767409737.edf5218a63d5.436.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8daf8dac732e067238b924f351f064dfb5025f2d2be397c8fca68dec07c321e
3
+ size 7011
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab8439b6327422cc6e976eb77d03375a591af4ab94b3c49bc2b665b6efa8ffcd
3
+ size 5905