Training in progress, step 200

runs/Feb13_22-15-36_node1/events.out.tfevents.1644761885.node1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f284a85df4d66242d90464f6cb233ecba90343c0bdc307caee7ede42824a41a8
-size 7403
+oid sha256:0634b7dabc65acabd3d6d19898f6f12f4e72b7191e0723e4c1f08ec13dfe38eb
+size 9184

runs/Feb13_22-29-42_node1/1644762709.9920368/events.out.tfevents.1644762709.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d315e16b70939b14ee2a996f2784e4fdb62560e05b4bcabef3577a18398781d
+size 5011

runs/Feb13_22-29-42_node1/events.out.tfevents.1644762709.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475e9e251911e0593709114759fa46f115ad9f5fd2d1a85baf07c458adf9f344
+size 5839

runs/Feb13_22-37-35_node1/1644763177.6225765/events.out.tfevents.1644763177.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99648bb2ce11cc837c2050175f3d7a4faa65b8a318a84c6a7818158999bc5523
+size 5011

runs/Feb13_22-37-35_node1/events.out.tfevents.1644763177.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98883c1ab6e72bf882aff0149a325ef10b9b45648b1a5bf4211eb23ff86d424e
+size 8132

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca25463e48c44b35248b25dc0dd0ace41d83dd7340eef8b5734baa85263d85d
+oid sha256:c970880153d9648abbb3ebe3068a607c506823630a89b70a4cfd7fd49840742b
 size 3183

training_config.json

@@ -1 +1 @@
-{"bottleneck_dim": 24, "dataset_config_name": ["en"], "delta_type": "adapter", "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": 0.0003, "load_best_model_at_end": true, "logging_steps": 10, "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/bitfit/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", "layer_norm", "final_layer_norm"], "warmup_steps": 0}
+{"bottleneck_dim": 24, "dataset_config_name": ["en"], "delta_type": "adapter", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "mrpc", "eval_steps": 100, "evaluation_strategy": "steps", "greater_is_better": true, "learning_rate": 0.0003, "load_best_model_at_end": true, "logging_steps": 10, "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/bitfit/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", "layer_norm", "final_layer_norm"], "warmup_steps": 0}