Training in progress, epoch 2, checkpoint

checkpoint-200/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "microsoft/deberta-large",
+  "architectures": [
+    "DebertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

checkpoint-200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b933e5e2c397c9d259456e38bf5725e4a65ea9e36fba1f7d9092455fb1a3ec8d
+size 1624907048

checkpoint-200/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.080199718475342,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.5304,
+      "step": 50
+    },
+    {
+      "epoch": 0.5,
+      "eval_pet_AUC": 0.8846723646723647,
+      "eval_pet_accuracy": 0.825,
+      "eval_pet_f1": 0.7569444444444444,
+      "eval_pet_loss": 0.4055028557777405,
+      "eval_pet_macro_f1": 0.8101128472222222,
+      "eval_pet_micro_f1": 0.825,
+      "eval_pet_precision": 0.689873417721519,
+      "eval_pet_recall": 0.8384615384615385,
+      "eval_pet_runtime": 0.9669,
+      "eval_pet_samples_per_second": 413.704,
+      "eval_pet_specificity": 0.8185185185185185,
+      "eval_pet_steps_per_second": 1.034,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.429731369018555,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.4825,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_pet_AUC": 0.9121652421652421,
+      "eval_pet_accuracy": 0.8325,
+      "eval_pet_f1": 0.7598566308243727,
+      "eval_pet_loss": 0.35728055238723755,
+      "eval_pet_macro_f1": 0.8156288912279253,
+      "eval_pet_micro_f1": 0.8325,
+      "eval_pet_precision": 0.7114093959731543,
+      "eval_pet_recall": 0.8153846153846154,
+      "eval_pet_runtime": 0.9571,
+      "eval_pet_samples_per_second": 417.916,
+      "eval_pet_specificity": 0.8407407407407408,
+      "eval_pet_steps_per_second": 1.045,
+      "step": 100
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 7.952208042144775,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.3115,
+      "step": 150
+    },
+    {
+      "epoch": 1.5,
+      "eval_pet_AUC": 0.9031339031339031,
+      "eval_pet_accuracy": 0.85,
+      "eval_pet_f1": 0.7744360902255639,
+      "eval_pet_loss": 0.5131158828735352,
+      "eval_pet_macro_f1": 0.831038269831883,
+      "eval_pet_micro_f1": 0.85,
+      "eval_pet_precision": 0.7573529411764706,
+      "eval_pet_recall": 0.7923076923076923,
+      "eval_pet_runtime": 0.9601,
+      "eval_pet_samples_per_second": 416.631,
+      "eval_pet_specificity": 0.8777777777777778,
+      "eval_pet_steps_per_second": 1.042,
+      "step": 150
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.0394058227539062,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.2963,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_pet_AUC": 0.9202564102564103,
+      "eval_pet_accuracy": 0.8425,
+      "eval_pet_f1": 0.7622641509433963,
+      "eval_pet_loss": 0.3516935706138611,
+      "eval_pet_macro_f1": 0.822253570798801,
+      "eval_pet_micro_f1": 0.8425,
+      "eval_pet_precision": 0.7481481481481481,
+      "eval_pet_recall": 0.7769230769230769,
+      "eval_pet_runtime": 0.9543,
+      "eval_pet_samples_per_second": 419.175,
+      "eval_pet_specificity": 0.8740740740740741,
+      "eval_pet_steps_per_second": 1.048,
+      "step": 200
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 271637546496000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0764263474b97260fc37ee4a274e139015dd761304086c91f05087cd69a8986e
+size 5432