Training in progress, epoch 2, checkpoint

checkpoint-200/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "microsoft/deberta-base",
+  "architectures": [
+    "DebertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "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 sha256:52af7b0c8a048905f63c171f71803f88a3f01e5859a03f81efb268947d79523c
+size 556799560

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": 5.5827836990356445,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.5363,
+      "step": 50
+    },
+    {
+      "epoch": 0.5,
+      "eval_pet_AUC": 0.909333409007066,
+      "eval_pet_accuracy": 0.83,
+      "eval_pet_f1": 0.7536231884057971,
+      "eval_pet_loss": 0.3635893166065216,
+      "eval_pet_macro_f1": 0.8119260980196925,
+      "eval_pet_micro_f1": 0.83,
+      "eval_pet_precision": 0.7172413793103448,
+      "eval_pet_recall": 0.7938931297709924,
+      "eval_pet_runtime": 0.4423,
+      "eval_pet_samples_per_second": 904.376,
+      "eval_pet_specificity": 0.8475836431226765,
+      "eval_pet_steps_per_second": 2.261,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 10.243881225585938,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.3796,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_pet_AUC": 0.9267572859615767,
+      "eval_pet_accuracy": 0.8275,
+      "eval_pet_f1": 0.7628865979381443,
+      "eval_pet_loss": 0.34966903924942017,
+      "eval_pet_macro_f1": 0.813663338261803,
+      "eval_pet_micro_f1": 0.8275,
+      "eval_pet_precision": 0.69375,
+      "eval_pet_recall": 0.8473282442748091,
+      "eval_pet_runtime": 0.4238,
+      "eval_pet_samples_per_second": 943.952,
+      "eval_pet_specificity": 0.8178438661710037,
+      "eval_pet_steps_per_second": 2.36,
+      "step": 100
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 7.141758918762207,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.2892,
+      "step": 150
+    },
+    {
+      "epoch": 1.5,
+      "eval_pet_AUC": 0.9297653168364596,
+      "eval_pet_accuracy": 0.8525,
+      "eval_pet_f1": 0.7790262172284644,
+      "eval_pet_loss": 0.3352491855621338,
+      "eval_pet_macro_f1": 0.8341660166817744,
+      "eval_pet_micro_f1": 0.8525,
+      "eval_pet_precision": 0.7647058823529411,
+      "eval_pet_recall": 0.7938931297709924,
+      "eval_pet_runtime": 0.4472,
+      "eval_pet_samples_per_second": 894.551,
+      "eval_pet_specificity": 0.8810408921933085,
+      "eval_pet_steps_per_second": 2.236,
+      "step": 150
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.970040798187256,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.2701,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_pet_AUC": 0.931922018218451,
+      "eval_pet_accuracy": 0.865,
+      "eval_pet_f1": 0.7857142857142857,
+      "eval_pet_loss": 0.3177262246608734,
+      "eval_pet_macro_f1": 0.8435870698644421,
+      "eval_pet_micro_f1": 0.865,
+      "eval_pet_precision": 0.8181818181818182,
+      "eval_pet_recall": 0.7557251908396947,
+      "eval_pet_runtime": 0.4548,
+      "eval_pet_samples_per_second": 879.579,
+      "eval_pet_specificity": 0.9182156133828996,
+      "eval_pet_steps_per_second": 2.199,
+      "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": 76649399808000.0,
+  "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 sha256:60a4a1a99d93293e076c082c8cd72052c9dbde4a41bd85babe4aa19d6bfdf8dd
+size 5432