Training in progress, step 500

README.md

@@ -2,8 +2,6 @@
 library_name: transformers
 tags:
 - generated_from_trainer
-metrics:
-- wer
 model-index:
 - name: Whisper-Large-v3-turbo-STT-Zeroth-KO-v2
   results: []
@@ -16,9 +14,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0169
-- Wer: 23.9851
-- Cer: 0.0904
+- eval_loss: 0.0196
+- eval_wer: 28.8490
+- eval_cer: 0.1014
+- eval_runtime: 150.7373
+- eval_samples_per_second: 4.75
+- eval_steps_per_second: 0.597
+- epoch: 0.1051
+- step: 500
 
 ## Model description
 
@@ -43,25 +46,9 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 100
+- lr_scheduler_warmup_steps: 500
 - training_steps: 5000
 
-### Training results
-
-| Training Loss | Epoch  | Step | Cer    | Validation Loss | Wer     |
-|:-------------:|:------:|:----:|:------:|:---------------:|:-------:|
-| 0.2413        | 0.1051 | 500  | 0.0771 | 0.0187          | 23.3663 |
-| 0.0191        | 0.2103 | 1000 | 0.0959 | 0.0174          | 26.5347 |
-| 0.0187        | 0.3154 | 1500 | 0.0916 | 0.0171          | 24.1213 |
-| 0.0171        | 0.4205 | 2000 | 0.0882 | 0.0171          | 23.6757 |
-| 0.018         | 0.5257 | 2500 | 0.0876 | 0.0170          | 23.4035 |
-| 0.0173        | 0.6308 | 3000 | 0.0878 | 0.0171          | 23.5396 |
-| 0.0179        | 0.7359 | 3500 | 0.0170 | 23.8366         | 0.0902  |
-| 0.0189        | 0.8410 | 4000 | 0.0169 | 23.4406         | 0.0873  |
-| 0.0172        | 0.9462 | 4500 | 0.0169 | 24.0594         | 0.0914  |
-| 0.0164        | 1.0513 | 5000 | 0.0169 | 23.9851         | 0.0904  |
-
-
 ### Framework versions
 
 - Transformers 4.48.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/teamspace/studios/this_studio/whisper_large_v3_turbo",
+  "_name_or_path": "o0dimplz0o/Whisper-Large-v3-turbo-STT-Zeroth-KO-v2",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,

events.out.tfevents.1738566738.ip-10-192-12-77.188580.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652db65b5a30b88eda3feb011e8b7f6e51ad9dc4d79e157498891b1f968985ec
+size 88

events.out.tfevents.1738566866.ip-10-192-12-77.188580.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d8e8e92849d17f3198ef038ab7a1c082ce09e90a012aac0846a8ff0bd6533f7
+size 6686

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe9907c94f3656a9e9d5855bde410aa7e1c12e976acc3cd5323cd6c4edb93b5
+oid sha256:86b5f80029d53d2f363f42dde88599a49029fa7162b37eba1eaa79e6dbb1a30a
 size 1617828008

special_tokens_map.json

@@ -122,7 +122,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|pad|>",
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60cdf902a26e7d1afe698067d633cd24cfc4b722a6fdd6588798af070875790f
+oid sha256:75332924ad69ddb99a58568233690252a9d68cb5b5c6e1aa29ddc8caf46bea0d
 size 5496