Hugging Face's logo

kiranpantha
/
whisper-large-v3-nepali-lora-ex-1

PEFT
TensorBoard
Safetensors
Nepali
Generated from Trainer
Model card Files Metrics Community
kiranpantha commited on
Commit
d8803a7
·
verified ·
1 Parent(s): d53d124

End of training

Browse files
Files changed (6) hide show
  1. README.md +4 -4
  2. adapter_config.json +1 -1
  3. adapter_model.safetensors +2 -2
  4. runs/Jan13_22-59-56_idc-training-gpu-compute-28/events.out.tfevents.1736809196.idc-training-gpu-compute-28.2829836.11 +3 -0
  5. runs/Jan13_23-06-03_idc-training-gpu-compute-28/events.out.tfevents.1736809563.idc-training-gpu-compute-28.2837006.0 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [kiranpantha/whisper-large-v3-nepali](https://huggingface.co/kiranpantha/whisper-large-v3-nepali) on the OpenSLR54 dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.2756
24
 
25
  ## Model description
26
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:----:|:---------------:|
56
- | No log | 1.0 | 9 | 0.5191 |
57
- | No log | 2.0 | 18 | 0.2712 |
58
- | 0.4746 | 3.0 | 27 | 0.2756 |
59
 
60
 
61
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [kiranpantha/whisper-large-v3-nepali](https://huggingface.co/kiranpantha/whisper-large-v3-nepali) on the OpenSLR54 dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.2635
24
 
25
  ## Model description
26
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:----:|:---------------:|
56
+ | No log | 1.0 | 9 | 0.5598 |
57
+ | No log | 2.0 | 18 | 0.2679 |
58
+ | 0.4551 | 3.0 | 27 | 0.2635 |
59
 
60
 
61
  ### Framework versions
adapter_config.json CHANGED
@@ -22,7 +22,7 @@
22
  "megatron_core": "megatron.core",
23
  "modules_to_save": null,
24
  "peft_type": "LORA",
25
- "r": 64,
26
  "rank_pattern": {},
27
  "revision": null,
28
  "target_modules": [
 
22
  "megatron_core": "megatron.core",
23
  "modules_to_save": null,
24
  "peft_type": "LORA",
25
+ "r": 128,
26
  "rank_pattern": {},
27
  "revision": null,
28
  "target_modules": [
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6987b1dddd057c9a168678d56d345178ec1ef975921bc3d270b39e3756f74459
3
- size 125884424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61aa8a9f2b165ad065c069e7a07892c3d8e6bdf320a42567b3e2dba008b94614
3
+ size 251714264
runs/Jan13_22-59-56_idc-training-gpu-compute-28/events.out.tfevents.1736809196.idc-training-gpu-compute-28.2829836.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60ecc82d502174e11f798c487f30e23635c89f12ac94a2025b35c95d003a2fc5
3
+ size 6717
runs/Jan13_23-06-03_idc-training-gpu-compute-28/events.out.tfevents.1736809563.idc-training-gpu-compute-28.2837006.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0da775499202ab7f96fb9ca58829d5780e3ea1a394a8454e19b4b688129a194
3
+ size 7331
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56b8946a6086666d76c6805b15f33b584b214445dea78b3224e8d77f5884c058
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dcd769ea39d7a266b875de79854c7d5d8cfa6482d5ad4937d544f23bc9d4e85
3
  size 5560