Training in progress, step 100

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dce090b7a7279a5b232571d077f8200601138f0aacddca51f6f3105fd1afe6c4
-size 2631685
+oid sha256:c9077eecffe3a4bd6c62bbc5aaea8e6db49b3234d1eb467db12bb201aabe5471
+size 335851

runs/Feb04_18-55-32_node1/1643972211.2160575/events.out.tfevents.1643972211.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a27ef9edceb12bcf85f69d89643434582b3318feaea2f9428a6057b1e0a0e277
+size 5026

runs/Feb04_18-55-32_node1/events.out.tfevents.1643972211.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac23ab74815ed9ed533990706e1530fece0bcf5595a9b9ffa5041a47257af016
+size 4313

runs/Feb04_19-00-27_node1/1643972550.301227/events.out.tfevents.1643972550.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d372c7f330b967fa9c4ef98a746f024f232a7f139fc1b9fe5397d6930669fad0
+size 5026

runs/Feb04_19-00-27_node1/events.out.tfevents.1643972550.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da0e29268791ee0273467dab3b2ae5c31a104343de2f1de2dceb669c9c0ebcb2
+size 4313

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dae689eba1a2f300b89fa3369aa940714da48e58d5e0706f64c6a408dfeddb2
+oid sha256:18de4812913a060cc6160cb4f6a39d62d26387edc87825c3f7b7612d37f56abd
 size 3183

training_config.json

@@ -1 +1 @@
-{"dataset_config_name": ["en"], "delta_type": "lora", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "stsb", "eval_steps": 100, "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/stsb", "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": "stsb", "test_dataset_config_name": ["en"], "test_dataset_name": "stsb", "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas", "layer_norm", "final_layer_norm"], "warmup_steps": 0}
+{"dataset_config_name": ["en"], "delta_type": "soft_prompt", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "stsb", "eval_steps": 100, "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/soft_prompt/t5-base/stsb", "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, "soft_token_num": 100, "split_validation_test": true, "task_name": "stsb", "test_dataset_config_name": ["en"], "test_dataset_name": "stsb", "token_init": false, "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas"], "warmup_steps": 0}