Training in progress, step 100

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106681ccac842e625e61b2a49fa99cf94f087007cc3e83c344c15b1bdf4ca43c
+oid sha256:eae0214a8b515c199f970cdb011b9ed967779de49f4078d66ad3206305525aec
 size 7551621

runs/Feb01_00-35-21_node1/events.out.tfevents.1643647072.node1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10a88377e1f903d50b6b849ace48672611db96d010c435005567cacb877179aa
-size 5954
+oid sha256:19b0331c2e53846edfae68ed0476601fbb7c37dbe8592a910c1eef52d7717157
+size 6288

runs/Feb01_00-55-07_node1/1643648230.2080297/events.out.tfevents.1643648230.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc1d35d950ef5b7c13844afc33399b5192e74ae3d26148da6d1646fbf7adcfc
+size 5011

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6cff552539bc48023ba453b2f94b42ad678cf6bf6435367056f6ce431a10072
+size 4304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d45981c3869ac88ceb617a2173cfab542cb6a12ef612e4821407250b68788864
+oid sha256:15af65d468c9f9b5a8f0ae0204ab263750bb9d3c1997cfce69a3ca94f9756ab3
 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": 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": 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": 200, "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": 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}