Training in progress, step 200

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc9896500a31a1acaded21b70a32eb8944fdd05c249678b8f014b8786efbb1d3
+oid sha256:22853993ca4a74b03fe74f63a98a2e377c772c1d1beb0018b1ce577546ac34e6
 size 76741275

runs/Feb12_13-34-52_node1/events.out.tfevents.1644644295.node1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d23cadccab0e6851d4ae771538a3d8472ba65fec9613fc4042b955e4b4e9cdd4
-size 5192
+oid sha256:8322f6caee676d683092b0c97e8ac576abd3876b9d333dddc977fbe51e595e0e
+size 5928

runs/Feb12_13-47-28_node1/1644644991.2581372/events.out.tfevents.1644644991.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9e5c50c61db899b5154c5db749b238a8b7ad1f4a74175b69a22ed1e50f2d35
+size 5011

runs/Feb12_13-47-28_node1/events.out.tfevents.1644644991.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc75a873e38a61c07663f7cb9ad29c9fa4ebce83654418f32ecae452f8be25b
+size 5757

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3869fe2e700f4c0b4bb1986d2b5cbbdadf11e058ba1c9b51bf55647a6027c142
+oid sha256:680e7bfe6c103553bcba129c78e1b452eb6acdbf18fa37d9e37d4583838a9bee
 size 3183

training_config.json

@@ -1 +1 @@
-{"dataset_config_name": ["en"], "delta_type": "prefix", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "mrpc", "eval_steps": 200, "evaluation_strategy": "steps", "greater_is_better": true, "learning_rate": 0.003, "load_best_model_at_end": true, "max_source_length": 128, "metric_for_best_model": "average_metrics", "model_name_or_path": "../../../../plm_cache/t5-base", "num_train_epochs": 20, "output_dir": "outputs/prefix/t5-base/mrpc", "overwrite_output_dir": true, "per_device_eval_batch_size": 32, "per_device_train_batch_size": 32, "predict_with_generate": true, "push_to_hub": true, "save_steps": 200, "save_strategy": "steps", "save_total_limit": 1, "seed": 42, "split_validation_test": true, "task_name": "mrpc", "test_dataset_config_name": ["en"], "test_dataset_name": "mrpc", "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas"], "warmup_steps": 0}
+{"dataset_config_name": ["en"], "delta_type": "prefix", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "mrpc", "eval_steps": 50, "evaluation_strategy": "steps", "greater_is_better": true, "learning_rate": 0.0003, "load_best_model_at_end": true, "max_source_length": 128, "metric_for_best_model": "average_metrics", "model_name_or_path": "../../../../plm_cache/t5-base", "num_train_epochs": 20, "output_dir": "outputs/prefix/t5-base/mrpc", "overwrite_output_dir": true, "per_device_eval_batch_size": 32, "per_device_train_batch_size": 32, "predict_with_generate": true, "push_to_hub": true, "save_steps": 200, "save_strategy": "steps", "save_total_limit": 1, "seed": 42, "split_validation_test": true, "task_name": "mrpc", "test_dataset_config_name": ["en"], "test_dataset_name": "mrpc", "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas"], "warmup_steps": 0}