End of training

README.md

@@ -7,13 +7,6 @@ tags:
 model-index:
 - name: whisper-small-sc
   results: []
-datasets:
-- janaab/supreme-court-speech
-language:
-- en
-metrics:
-- wer
-pipeline_tag: automatic-speech-recognition
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -21,16 +14,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-small-sc
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on [janaab/supreme-court-speech](https://huggingface.co/janaab/supreme-court-speech) dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.3354
-- eval_wer_ortho: 11.0780
-- eval_wer: 10.5653
-- eval_runtime: 1059.0881
-- eval_samples_per_second: 4.216
-- eval_steps_per_second: 0.264
-- epoch: 6.9337
-- step: 2250
+- eval_loss: 0.2616
+- eval_wer_ortho: 11.1994
+- eval_wer: 10.7122
+- eval_runtime: 1028.1037
+- eval_samples_per_second: 4.343
+- eval_steps_per_second: 0.136
+- epoch: 4.6012
+- step: 750
 
 ## Model description
 
@@ -50,15 +43,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-06
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 64
+- eval_batch_size: 32
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine_with_restarts
-- lr_scheduler_warmup_steps: 50
-- training_steps: 4000
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 250
+- training_steps: 2500
 - mixed_precision_training: Native AMP
 
 ### Framework versions
@@ -66,4 +57,4 @@ The following hyperparameters were used during training:
 - Transformers 4.44.2
 - Pytorch 2.4.0
 - Datasets 2.21.0
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1

config.json

@@ -19,7 +19,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
   "decoder_start_token_id": 50258,
-  "dropout": 0.0,
+  "dropout": 0.1,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9455d22275629456de6a0761818cf4cd1f10657ebc7661d5b35d892ee190bc74
+oid sha256:1bb43efbe1083e83e46588e06ea7e3540e82f84450bd5fbf47c009ddcbdac373
 size 966995080

runs/Aug30_07-51-08_8fe5ffa1edef/events.out.tfevents.1725004383.8fe5ffa1edef.12143.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73d9fe1a4ed6acda2fb7ab668480c59cf95e698d0e4daaeefa8d8ed22fe1c2eb
-size 11659
+oid sha256:71cc064c712d809f9ac5fede3e48efc2ec75823055696c6d8a298abf0bcb470b
+size 12292

runs/Aug30_09-58-40_8fe5ffa1edef/events.out.tfevents.1725011930.8fe5ffa1edef.12143.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5f7ca68bef80441f1335dc93810eddc75dce36850455a20e40b796b714b116
+size 14562

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54f2e51cc7505bff842f29984a8c041593a26011ce66cb34efb493f412f488ff
+oid sha256:5a721841dec9a031a51ae034942c1f6864ae6f646ccb0ce11158402cb4987642
 size 5368