Training in progress, step 200

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:901dc51909b702bf7eacdeaa297f3a250f3a0e3085b033b92555b33a2f81db60
+oid sha256:3af4aeeba17bedfad45b0faf93c0430627064d9546385a65405e8adf9d994922
 size 7551621

runs/Feb01_01-01-41_node2/events.out.tfevents.1643648613.node2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f0d14dcca18da4850c290ebcb5a9e8eeb7ea44f282fb1ef01c66694893eafb2
-size 4625
+oid sha256:1b6422d7c957672a5a68a416f007a770085a971bc179b78e0078eee6515d6543
+size 4947

runs/Feb01_01-17-38_node2/1643649573.8705235/events.out.tfevents.1643649573.node2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4173ec4a7353347da86264be02cc16765805648d5c3c7436f639a8a228b7ca5e
+size 5011

runs/Feb01_01-17-38_node2/events.out.tfevents.1643649573.node2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58dd34c01c95fdedaed57316624a6d0b398331a4c04190dda32b2e5d83900035
+size 4299

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d232d4e577478fd4816e9232ce9e0a60b78f395e047fb89a0e972636c59ef4
+oid sha256:f376179840c9389819429f3133a6999a78148775cfff0e7518608ef9c3d59b09
 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": "sst2", "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": 3, "output_dir": "outputs/bitfit/t5-base/sst2", "overwrite_output_dir": true, "per_device_eval_batch_size": 100, "per_device_train_batch_size": 100, "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": "sst2", "test_dataset_config_name": ["en"], "test_dataset_name": "sst2", "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas", "layer_norm", "final_layer_norm"], "warmup_steps": 500}
+{"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": "sst2", "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": 3, "output_dir": "outputs/bitfit/t5-base/sst2", "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": "sst2", "test_dataset_config_name": ["en"], "test_dataset_name": "sst2", "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas", "layer_norm", "final_layer_norm"], "warmup_steps": 0}