Training in progress, step 200

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f81ba955a639c035c9c4ffafbdd65a12a25db74210524d88ff41e665bfc4efa2
-size 76741275
+oid sha256:d642ecc3a7b9e02a96a82baec2a3d472c6d1884d64d260c784698d2c5b73bf66
+size 2631685

runs/Feb11_23-22-29_node1/events.out.tfevents.1644593076.node1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be92d882ab2e2027ed0c46baeb89515f0a191bbaaa76186d1d8e8e4baec43207
-size 4304
+oid sha256:556cb793a5549f30636de928ee4fd01575ef3a43638f57fba7606bc98bc22faa
+size 4672

runs/Feb13_11-45-37_node1/1644724046.2206535/events.out.tfevents.1644724046.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b568e8405458c6145388b8035c9b65421c12175130e6aab85bb740c570322e
+size 5011

runs/Feb13_11-45-37_node1/events.out.tfevents.1644724046.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ef2cd156a16d9302570e0bca8069950cea9314bb968ef177955db8cbb83bd0
+size 4668

runs/Feb13_11-49-17_node1/1644724261.181393/events.out.tfevents.1644724261.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed824b84beb32032d9f8de997c6e6397a065d7c147ef2dd807423fff44823cf1
+size 5011

runs/Feb13_11-49-17_node1/events.out.tfevents.1644724261.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6a652a1332301c9490f39fa4dd8b3fab6bc75d3f309d09f8aa1b37ad55f2972
+size 4300

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:680e7bfe6c103553bcba129c78e1b452eb6acdbf18fa37d9e37d4583838a9bee
+oid sha256:7bb604d10a0afd55461caf0e5622569d6a7a1fb19a6cbca10a0d50be7bb0eff4
 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": 50, "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/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": "lora", "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": 0.0003, "load_best_model_at_end": true, "lora_r": 8, "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/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", "layer_norm", "final_layer_norm"], "warmup_steps": 0}