Training in progress, step 200

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a364e7dec5946f67d3b1b1ebb22eae7c29becb2f1b508ec260369ec655cfbfa6
+oid sha256:b726e147b4b430c364565b7b195ac01c202b60df0f9d6d730b6925495a448881
 size 335851

runs/Feb04_18-41-07_node1/events.out.tfevents.1643971324.node1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39e8bc55d40d9f61a49a8da0e7616ff98e7053168e01612d807437ff84429dfc
-size 4634
+oid sha256:fc182b7b4d246429550a52515d3069398e68d68e95ff8aa8c41e86409696d48f
+size 5113

runs/Feb04_18-45-25_node1/1643971621.542229/events.out.tfevents.1643971621.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ba91672b2fc30bf38428260e453d5ddbc25ddda3c4307e4d3d5251e19a5a63
+size 5026

runs/Feb04_18-45-25_node1/events.out.tfevents.1643971621.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59345e99f8d28f09ca51d72fa2516658f42a8cf6b7a6dd4a1337e5a474c92640
+size 4312

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6df7ba606a320f55e9b0a3daa18b77d917e293ca61d31728f8234770ab4d8ea2
+oid sha256:0a7a571cf89eb7b14c07ef9fd310d13c0c56e3dd3a01d49ec9779e1577f6c7ce
 size 3183

training_config.json

@@ -1 +1 @@
-{"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": "sst2", "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": 3, "output_dir": "outputs/soft_prompt/t5-base/sst2", "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, "soft_token_num": 100, "split_validation_test": true, "task_name": "sst2", "test_dataset_config_name": ["en"], "test_dataset_name": "sst2", "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas"], "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": "sst2", "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": 3, "output_dir": "outputs/soft_prompt/t5-base/sst2", "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, "soft_token_num": 100, "split_validation_test": true, "task_name": "sst2", "test_dataset_config_name": ["en"], "test_dataset_name": "sst2", "token_init": false, "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas"], "warmup_steps": 0}