End of training

README.md

@@ -33,17 +33,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 1
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 64
-- total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 100
+- lr_scheduler_warmup_steps: 10
 - num_epochs: 1
 
 ### Training results
@@ -52,7 +47,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.39.0.dev0
-- Pytorch 2.0.1+cu118
+- Transformers 4.41.0.dev0
+- Pytorch 2.1.2+cu118
 - Datasets 2.14.7
-- Tokenizers 0.15.1
+- Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fed45ef9b1bff1ec4308c65dd51ed6a7e93b87e98f2f9d3673488b4d601365d8
-size 9481928
+oid sha256:8c617db9d95512cd4f8945fc5ec27034f622570c9a56b3751a02f761dc62f7f3
+size 10170512

generation_config.json

@@ -14,5 +14,5 @@
     32002
   ],
   "pad_token_id": 0,
-  "transformers_version": "4.39.0.dev0"
+  "transformers_version": "4.41.0.dev0"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:820d8bf604fb3584d482eda862d5712a0c0b58544d15bd5eb7c66d3f99a8cdc2
-size 5627
+oid sha256:37d54bf104b9dfd18915e01b2f21525d9026ceb0ab387dea080bed52b3be9031
+size 5048