Training in progress, step 200

runs/Feb13_21-51-27_node1/events.out.tfevents.1644760422.node1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54e68e4062b45b5ffa6ab7bee676e488a9fc2f2337416a40bfb32d7467da0c6c
-size 4300
+oid sha256:cc368eb14685338fc0febe458813713b5326434fb61673ec9b73b8bd59b00c04
+size 4668

runs/Feb13_22-03-14_node1/1644761136.5246122/events.out.tfevents.1644761136.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6489e486c2a274abd0c44e385511bfe9b1d8eb39a335038a3e91ec4a0630dc83
+size 5011

runs/Feb13_22-03-14_node1/events.out.tfevents.1644761136.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59cae4762f457d68bf046cccdfa928bbdf576eafebda8f8d8f58567122f122c7
+size 4300

runs/Feb13_22-15-36_node1/1644761885.8500774/events.out.tfevents.1644761885.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d835f4b1a4e231b168aae83be2750ad68e3340abdd88ee76634497c61961ce6
+size 5011

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f284a85df4d66242d90464f6cb233ecba90343c0bdc307caee7ede42824a41a8
+size 7403

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3ff2d74b382533c4c533ad2a810fb5a02804d9e271056048ce8c7153246c1c
+oid sha256:5ca25463e48c44b35248b25dc0dd0ace41d83dd7340eef8b5734baa85263d85d
 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, "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": 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}