Training in progress, epoch 1

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5472b0bf5a8af299aa074c724d8044fe445dd6893e2f515de4b58c4cf0b768d
+oid sha256:689b4d002e3a09e30fee823c14a22bde7084a38dac56011274d4725e2e2a8f4d
 size 7551621

runs/Jan30_14-45-50_node2/1643525233.2746077/events.out.tfevents.1643525233.node2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb935aabe1abe75a5a352d29113497d3a3a752748631f79fbf824ffb4ac71f8
+size 5020

runs/Jan30_14-45-50_node2/events.out.tfevents.1643525233.node2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fdb3df18013d664191d2d4462649b3b5750145c1ab9cb696a1bec60fceb2a9a
+size 4317

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f650df5107240b0979f2b966fe940e6b1b2320e544e6096f1d36e8920c3418f
+oid sha256:b7deceba1a44738db2bfd702c1b87954a659a16f7d9d2cdebb54356687613158
 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": 32, "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": 0, "overwrite_output_dir": true, "push_to_hub": true}
+{"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}