Training in progress, step 200

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b8bf9ef233837f0995b1c04e940512d2edf4708954f1f06785def9a6413b40c
+oid sha256:875ce8a78feb6aea2f43e51ac6b0123fea7d5f05ad7ea8bc8d9bab052d16ecf7
 size 76741275

runs/Feb12_13-25-50_node1/events.out.tfevents.1644643726.node1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d992c9e10794487ec2e629294643080fb638b7f5fd606acd0d3a58e9fff2642
-size 4298
+oid sha256:f6eb26ef7159c2d250e2c5a1afdc117cf4449ea7ca71289912d507e7a1c21fa9
+size 5034

runs/Feb12_13-34-52_node1/1644644295.2763348/events.out.tfevents.1644644295.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:640cae929ad57adb011e4f35dadd6de5c5848cfe5b28ed5f7db6b791e365b414
+size 5011

runs/Feb12_13-34-52_node1/events.out.tfevents.1644644295.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a6893efe776670760eb3ebf7602ad201085349c9d5f492c9848f037c1cb385
+size 4667

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ee1449b58788964c46ac364129c7095fa05a7fae8b87f45585dd89f76deb6a
+oid sha256:3869fe2e700f4c0b4bb1986d2b5cbbdadf11e058ba1c9b51bf55647a6027c142
 size 3183

training_config.json

@@ -1 +1 @@
-{"dataset_config_name": ["en"], "delta_type": "prefix", "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": 0.03, "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/prefix/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"], "warmup_steps": 0}
+{"dataset_config_name": ["en"], "delta_type": "prefix", "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": 0.003, "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/prefix/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"], "warmup_steps": 0}