Training in progress, epoch 5

README.md

@@ -1,27 +1,26 @@
 ---
-base_model: DazMashaly/output
 tags:
 - generated_from_trainer
 model-index:
-- name: new_downloads
+- name: output
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# new_downloads
+# output
 
-This model is a fine-tuned version of [DazMashaly/output](https://huggingface.co/DazMashaly/output) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 5.3543
+- eval_loss: 5.5136
 - eval_wer: 1.0
 - eval_cer: 1.0
-- eval_runtime: 973.8534
-- eval_samples_per_second: 2.258
-- eval_steps_per_second: 0.018
-- epoch: 4.0
-- step: 1636
+- eval_runtime: 702.4432
+- eval_samples_per_second: 3.131
+- eval_steps_per_second: 0.026
+- epoch: 2.0
+- step: 818
 
 ## Model description
 
@@ -41,7 +40,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 128
+- train_batch_size: 124
 - eval_batch_size: 128
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -54,5 +53,5 @@ The following hyperparameters were used during training:
 
 - Transformers 4.41.2
 - Pytorch 2.1.2
-- Datasets 2.19.2
+- Datasets 2.20.0
 - Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "DazMashaly/output",
+  "_name_or_path": "DazMashaly/new_downloads",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca4e27d8a2950ea1358f16e3c135a63cabeaa10ec29e03c83c8c073803cd5f8
+oid sha256:fc48c0adcc1e3b3c0bd007518f406e2619082456c1687e6f499e09a28926a2b2
 size 290403936

runs/Jun25_06-08-05_557d2a8f2caf/events.out.tfevents.1719295686.557d2a8f2caf.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0db750645d9eff514f6bc22611b955c656f7723607f3b410db2b63d04ac526d
+size 10374

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df180bbc58c0a7714e8beb26c654c1c1a085db2c02893349f4f27f5b8880fbe
+oid sha256:f73b80aec597d06b3d2e1eea4b8902092e7ee47b50c6ace8e729e22ced3aeffe
 size 5304