Training in progress, step 200

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f023c96ddd4f1d72c1969ed065c8b2472ee71932f5a34b9cef0c2033a917d010
-size 7551621
+oid sha256:31c907b68d88139c4de229cdc6929dbb87a85163fb9873560f8e903ae55884d0
+size 1084131

runs/Jan31_20-58-56_node1/1643634109.216694/events.out.tfevents.1643634109.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794cdc0c7fbdac27060de3352c1caca22613360a8effbc690b5053a4dc9f01dd
+size 5044

runs/Jan31_20-58-56_node1/events.out.tfevents.1643634109.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7cc107713e78f2ba4b37d5fcfd0dd17bbbd256416d39daf77590d0650ed8bd
+size 4333

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32188043ee71fd2c4b60c2e8d562ca7aac923df27520c9f4c078ef4971cc0c1d
+oid sha256:269bb6113ca5087e1a8b4f6f408b50f081fcdff789ba3839dd26d80788deca12
 size 3183

training_config.json

@@ -1 +1 @@
-{"dataset_config_name": ["en"], "delta_type": "adapter", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "superglue-boolq", "evaluation_strategy": "epoch", "greater_is_better": true, "learning_rate": 0.0003, "load_best_model_at_end": true, "max_source_length": 256, "metric_for_best_model": "average_metrics", "model_name_or_path": "../../../../plm_cache/t5-base", "non_linearity": "gelu_new", "num_train_epochs": 20, "output_dir": "outputs/adapter/superglue-boolq", "per_device_eval_batch_size": 100, "per_device_train_batch_size": 100, "predict_with_generate": true, "save_strategy": "epoch", "save_total_limit": 1, "split_validation_test": true, "task_name": "superglue-boolq", "test_dataset_config_name": ["en"], "unfrozen_modules": ["deltas", "layer_norm", "final_layer_norm"], "bottleneck_dim": 24, "test_dataset_name": "superglue-boolq", "tokenizer_name": "../../../../plm_cache/t5-base", "warmup_steps": 500, "overwrite_output_dir": true, "push_to_hub": true}
+{"dataset_config_name": ["en"], "delta_type": "bitfit", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "superglue-boolq", "eval_steps": 200, "evaluation_strategy": "steps", "greater_is_better": true, "learning_rate": 0.0003, "load_best_model_at_end": true, "max_source_length": 256, "metric_for_best_model": "average_metrics", "model_name_or_path": "../../../../plm_cache/t5-base", "num_train_epochs": 20, "output_dir": "outputs/bitfit/t5-base/superglue-boolq", "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": "superglue-boolq", "test_dataset_config_name": ["en"], "test_dataset_name": "superglue-boolq", "tokenizer_name": "../../../../plm_cache/t5-base", "warmup_steps": 0}