End of training

README.md

@@ -33,14 +33,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 256
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 250
-- num_epochs: 11
+- num_epochs: 50
 
 ### Training results
 
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.42.3
+- Transformers 4.42.4
 - Pytorch 2.3.1+cu118
 - Datasets 2.20.0
 - Tokenizers 0.19.1

config.json

@@ -45,7 +45,7 @@
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.42.3",
+  "transformers_version": "4.42.4",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

generation_config.json

@@ -312,5 +312,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.42.3"
+  "transformers_version": "4.42.4"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ae22735a73d52ccedbe605f5975da0d2f21fdd81f841d743d3ca78228c7a5c
+oid sha256:1552d8d5cec372fa0327455714e3bc9dcaecf220979606781a6a41fe252b2d79
 size 4992706480

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1fe62d941984b19ed12ff15bb64d1bb27db036ce4a971a7eed645e9ac0a07b2
+oid sha256:57a8ffefb0eb3708b3c05d9899c20957efc40d67a73c75c2a40e1850821f3fc0
 size 1446212088

runs/Jul12_03-05-31_watvis-whale/events.out.tfevents.1720753555.watvis-whale.343639.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7071a77ebcafe2a250cdf85f9db4bf0ffe7f28658af831a01b5bf510859bb40c
+size 22684

runs/Jul12_03-09-27_watvis-whale/events.out.tfevents.1720753789.watvis-whale.344117.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3138cb81177e5da16fb975198271078fba2937979148d852009d769d92c0eea5
+size 7337

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c7242003a5b927d3d1c5079ed201a78e60bfe6f01d89fd44bbac9622910f0fd
+oid sha256:9d7eb94d19dc202a75896815a71938091847daa17e2ec24bfebdd1100d55cc8c
 size 6968