End of training

README.md

@@ -2,6 +2,8 @@
 library_name: transformers
 tags:
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: whisper-small-es-ja
   results: []
@@ -14,12 +16,8 @@ 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:
-- eval_loss: 8.4164
-- eval_bleu: 21.5256
-- eval_runtime: 210.1767
-- eval_samples_per_second: 6.499
-- eval_steps_per_second: 0.409
-- step: 0
+- Loss: 1.1810
+- Bleu: 21.4112
 
 ## Model description
 
@@ -39,14 +37,35 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 32
-- eval_batch_size: 16
+- train_batch_size: 16
+- eval_batch_size: 8
 - seed: 42
+- distributed_type: multi-GPU
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- training_steps: 5000
+- training_steps: 3500
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch  | Step | Bleu    | Validation Loss |
+|:-------------:|:------:|:----:|:-------:|:---------------:|
+| 1.5787        | 0.3962 | 250  | 11.6756 | 1.5196          |
+| 1.3535        | 0.7924 | 500  | 16.0514 | 1.3470          |
+| 1.0658        | 1.1886 | 750  | 17.7743 | 1.2533          |
+| 1.0303        | 1.5848 | 1000 | 19.1894 | 1.2046          |
+| 0.9893        | 1.9810 | 1250 | 20.1198 | 1.1591          |
+| 0.7569        | 2.3772 | 1500 | 21.0054 | 1.1546          |
+| 0.7571        | 2.7734 | 1750 | 21.6425 | 1.1378          |
+| 0.5557        | 3.1696 | 2000 | 21.7563 | 1.1500          |
+| 0.5612        | 3.5658 | 2250 | 21.1391 | 1.1395          |
+| 0.5581        | 3.9620 | 2500 | 22.0412 | 1.1343          |
+| 0.4144        | 4.3582 | 2750 | 22.2850 | 1.1724          |
+| 0.4114        | 4.7544 | 3000 | 22.1925 | 1.1681          |
+| 0.3005        | 5.1506 | 3250 | 21.4948 | 1.1947          |
+| 0.2945        | 5.5468 | 3500 | 1.1921  | 22.1454         |
+
+
 ### Framework versions
 
 - Transformers 4.47.1

generation_config.json

@@ -160,7 +160,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "language": "japanese",
+  "language": "ja",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a518d500e70b29ab45c2dbb61c320aadcc5941da8cce399dc560d12d0c17f78f
+oid sha256:3f13cb263d1611926ce983abf794049bede8cbc4e40923d0e9a5370e9f9dcf86
 size 966995080

runs/Dec19_17-50-54_mad-loc-analytics3/events.out.tfevents.1734627751.mad-loc-analytics3.1007866.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:853bb9b0248d61f2cedca2f184e25e3c5b471078c05fa9da1326dc1188f3f683
+size 407