Training in progress, step 200

all_results.json

@@ -3,16 +3,16 @@
     "eval_accuracy": 40.0,
     "eval_average_metrics": 40.0,
     "eval_loss": 0.2866286337375641,
-    "eval_runtime": 0.1713,
-    "eval_samples_per_second": 291.946,
+    "eval_runtime": 0.149,
+    "eval_samples_per_second": 335.514,
     "test_accuracy": 44.0,
     "test_average_metrics": 44.0,
     "test_loss": 0.2718357443809509,
-    "test_runtime": 0.15,
-    "test_samples_per_second": 333.351,
+    "test_runtime": 0.1482,
+    "test_samples_per_second": 337.428,
     "train_loss": 0.47191429138183594,
-    "train_runtime": 31.7324,
+    "train_runtime": 30.868,
     "train_samples": 400,
-    "train_samples_per_second": 252.109,
-    "train_steps_per_second": 8.194
+    "train_samples_per_second": 259.168,
+    "train_steps_per_second": 8.423
 }

eval_results.json

@@ -3,6 +3,6 @@
     "eval_accuracy": 40.0,
     "eval_average_metrics": 40.0,
     "eval_loss": 0.2866286337375641,
-    "eval_runtime": 0.1713,
-    "eval_samples_per_second": 291.946
+    "eval_runtime": 0.149,
+    "eval_samples_per_second": 335.514
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b51a270c46790984ebbec29a9570f39cc01d6e0cb540e04e9a5af57fa60ea99
-size 1084131
+oid sha256:c45abc26f5ac48d57c9e9ef202ed9e87c6a866c812ad30088af46f5f53437668
+size 7551621

runs/Feb01_00-38-26_node1/1643647198.6500626/events.out.tfevents.1643647198.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7261b1d32a6237e17387ec7dd0ff6c4e5552c65fec69436ba65ea20ce4da668
+size 5041

runs/Feb01_00-38-26_node1/events.out.tfevents.1643647198.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c39b517335eb334fbd10f035f257954f57adad0b8b77984e93bad4b534b9a5
+size 4330

runs/Jan31_21-05-13_node1/events.out.tfevents.1643634388.node1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:588fc0d18772073982a8691a6b938733e22cfbab6424442300d6d96bc1d77cd1
-size 4330
+oid sha256:d4a20c243028c6c83cba6f8a3f62566ce97125ca109837464768196254dc597c
+size 5006

runs/Jan31_21-05-13_node1/events.out.tfevents.1643634419.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5e1dc10f6f76d6bf92ec5656495ceece9e3edbbe9099629c138b9cf7971090
+size 684

test_results.json

@@ -3,6 +3,6 @@
     "test_accuracy": 44.0,
     "test_average_metrics": 44.0,
     "test_loss": 0.2718357443809509,
-    "test_runtime": 0.15,
-    "test_samples_per_second": 333.351
+    "test_runtime": 0.1482,
+    "test_samples_per_second": 337.428
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 20.0,
     "train_loss": 0.47191429138183594,
-    "train_runtime": 31.7324,
+    "train_runtime": 30.868,
     "train_samples": 400,
-    "train_samples_per_second": 252.109,
-    "train_steps_per_second": 8.194
+    "train_samples_per_second": 259.168,
+    "train_steps_per_second": 8.423
 }

trainer_state.json

@@ -12,8 +12,8 @@
       "eval_accuracy": 40.0,
       "eval_average_metrics": 40.0,
       "eval_loss": 0.2866286337375641,
-      "eval_runtime": 0.1516,
-      "eval_samples_per_second": 329.872,
+      "eval_runtime": 0.1965,
+      "eval_samples_per_second": 254.502,
       "step": 200
     },
     {
@@ -21,9 +21,9 @@
       "step": 260,
       "total_flos": 473613149374848.0,
       "train_loss": 0.47191429138183594,
-      "train_runtime": 31.7324,
-      "train_samples_per_second": 252.109,
-      "train_steps_per_second": 8.194
+      "train_runtime": 30.868,
+      "train_samples_per_second": 259.168,
+      "train_steps_per_second": 8.423
     }
   ],
   "max_steps": 260,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65a918953f7ce37cffd681f36f68a0b5153afd841953560800a2074f7e0297b5
+oid sha256:f3cd333362728449f5def839245c02b44ab8344c98cb431a1adedfccbd55dcce
 size 3183

training_config.json

@@ -1 +1 @@
-{"dataset_config_name": ["en"], "delta_type": "bitfit", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "superglue-copa", "eval_steps": 200, "evaluation_strategy": "steps", "greater_is_better": true, "learning_rate": 0.0003, "load_best_model_at_end": true, "max_source_length": 256, "metric_for_best_model": "average_metrics", "model_name_or_path": "../../../../plm_cache/t5-base", "num_train_epochs": 20, "output_dir": "outputs/bitfit/t5-base/superglue-copa", "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": "superglue-copa", "test_dataset_config_name": ["en"], "test_dataset_name": "superglue-copa", "tokenizer_name": "../../../../plm_cache/t5-base", "warmup_steps": 0}
+{"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": "superglue-copa", "eval_steps": 200, "evaluation_strategy": "steps", "greater_is_better": true, "learning_rate": 0.0003, "load_best_model_at_end": true, "max_source_length": 256, "metric_for_best_model": "average_metrics", "model_name_or_path": "../../../../plm_cache/t5-base", "num_train_epochs": 20, "output_dir": "outputs/bitfit/t5-base/superglue-copa", "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": "superglue-copa", "test_dataset_config_name": ["en"], "test_dataset_name": "superglue-copa", "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas", "layer_norm", "final_layer_norm"], "warmup_steps": 0}