Training in progress, step 100

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5a6833a098418e0addce7c64bd1411151a3a4f3c42ca5d857eae1b2bd247dc
+oid sha256:9417e1ededbfd11518795df9cc016f9439c235f979509d0076a112b66e97f5a3
 size 7551621

runs/Feb01_00-55-07_node1/events.out.tfevents.1643648230.node1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5eea464bd67619b5c915b5a90b0c1339944f3f329c2909d5f7a732e27e4dbe0
-size 6793
+oid sha256:958762c32e4dcdd9b61a2c7612ed6862c5291912d868a0bf1879765043d9dfa5
+size 7127

runs/Feb01_01-06-33_node1/1643648939.5229282/events.out.tfevents.1643648939.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e84259d56d33399d31f0d95797b17aa5b394bcc9ac4fcb7b92bca6b09086b20
+size 5011

runs/Feb01_01-06-33_node1/events.out.tfevents.1643648939.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1411d4abd4cb07548d064a4fe45609823016b752513b148ae0bf40782eb5f73b
+size 4300

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15af65d468c9f9b5a8f0ae0204ab263750bb9d3c1997cfce69a3ca94f9756ab3
+oid sha256:74f49ee56a79b35e01e6ec19b78d08fc0573bd2831cd5b548892c75c4c3fabf2
 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": "cola", "eval_steps": 100, "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/cola", "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": 100, "save_strategy": "steps", "save_total_limit": 1, "seed": 42, "split_validation_test": true, "task_name": "cola", "test_dataset_config_name": ["en"], "test_dataset_name": "cola", "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": "cola", "eval_steps": 100, "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/cola", "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": 100, "save_strategy": "steps", "save_total_limit": 1, "seed": 42, "split_validation_test": true, "task_name": "cola", "test_dataset_config_name": ["en"], "test_dataset_name": "cola", "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas", "layer_norm", "final_layer_norm"], "warmup_steps": 0}