DazMashaly/checkpoints

README.md

@@ -2,25 +2,16 @@
 tags:
 - generated_from_trainer
 model-index:
-- name: output
+- name: checkpoints
   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. -->
 
-# output
+# checkpoints
 
 This model was trained from scratch on an unknown dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 5.5136
-- eval_wer: 1.0
-- eval_cer: 1.0
-- eval_runtime: 702.4432
-- eval_samples_per_second: 3.131
-- eval_steps_per_second: 0.026
-- epoch: 2.0
-- step: 818
 
 ## Model description
 
@@ -39,19 +30,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 124
-- eval_batch_size: 128
+- learning_rate: 0.0003
+- train_batch_size: 360
+- eval_batch_size: 256
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
+- lr_scheduler_warmup_steps: 50
 - num_epochs: 20
 - mixed_precision_training: Native AMP
 
 ### Framework versions
 
-- Transformers 4.41.2
-- Pytorch 2.1.2
+- Transformers 4.42.3
+- Pytorch 2.3.0+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/kaggle/working/new_downloads/checkpoint-4499",
+  "_name_or_path": "/content/new_downloads/checkpoint-127",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -147,7 +147,7 @@
     50362
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.42.3",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

generation_config.json

@@ -244,5 +244,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.42.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffe70162d9b7412dcc612f7a9054b2a968b0e4b662e04f8fbb694efe09a89272
+oid sha256:b66d52b514e1314be8ca9e5ac42848229759c02ed50b2ce08f910cc991c6ef30
 size 290403936

runs/Jun29_09-29-01_1bb9979180df/events.out.tfevents.1719653345.1bb9979180df.65765.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba45270cfb40238ad76fb3e03aaaebc97622cf9c7c420117f6a92b8e8705cba7
+size 6637

runs/Jun29_09-31-53_1bb9979180df/events.out.tfevents.1719653518.1bb9979180df.65765.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f882c381543183a7c0eb4e4deb58b0b5615622449ed18b719e7cb2dc628a743
+size 6843

runs/Jun29_10-09-42_1bb9979180df/events.out.tfevents.1719655788.1bb9979180df.76167.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3749a95baa4385132b560a2935a92e7cf4bee0502603e9ca931182f89ce2b978
+size 7686

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:076e17f8ed2b2a01068cec06c971b2f1fc816d0dc4753a058b54fb1cb1f413fd
+oid sha256:a81b784c2b031587e9164a5107edee2b1290567eb6e1b636d08722025de88854
 size 5304