Upload 7 files

config.json

@@ -0,0 +1,32 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "loss",
+    "1": "win"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "loss": 0,
+    "win": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "vocab_size": 30522
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:527276764335e03ea915d0573a9ad59eeff630ed1d94d41b99d98ba5a5610338
+size 14391

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa028dfbc8078f741ad7874270d619cc4bc8d0168d31c32a94c731f2c2cfdcc0
+size 1465

trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_global_step": 50,
+  "best_metric": 0.9230769230769231,
+  "best_model_checkpoint": "model_output/checkpoint-50",
+  "epoch": 5.0,
+  "eval_steps": 25,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.7717047929763794,
+      "learning_rate": 4.912280701754386e-05,
+      "loss": 0.6998,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8567419648170471,
+      "learning_rate": 4.473684210526316e-05,
+      "loss": 0.6853,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5256410256410257,
+      "eval_f1": 0.41943572726317213,
+      "eval_f1_class_0": 0.2127659574468085,
+      "eval_f1_class_1": 0.6605504587155964,
+      "eval_loss": 0.6680065989494324,
+      "eval_precision": 0.7660695468914647,
+      "eval_precision_class_0": 1.0,
+      "eval_precision_class_1": 0.4931506849315068,
+      "eval_recall": 0.5256410256410257,
+      "eval_runtime": 0.7697,
+      "eval_samples_per_second": 101.335,
+      "eval_steps_per_second": 2.598,
+      "step": 10
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.7958896160125732,
+      "learning_rate": 4.0350877192982455e-05,
+      "loss": 0.651,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.7093613147735596,
+      "learning_rate": 3.5964912280701756e-05,
+      "loss": 0.5555,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7692307692307693,
+      "eval_f1": 0.7692307692307693,
+      "eval_f1_class_0": 0.7857142857142857,
+      "eval_f1_class_1": 0.75,
+      "eval_loss": 0.5287392735481262,
+      "eval_precision": 0.7692307692307693,
+      "eval_precision_class_0": 0.7857142857142857,
+      "eval_precision_class_1": 0.75,
+      "eval_recall": 0.7692307692307693,
+      "eval_runtime": 0.6932,
+      "eval_samples_per_second": 112.528,
+      "eval_steps_per_second": 2.885,
+      "step": 20
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.830397129058838,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 0.4365,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.684325695037842,
+      "learning_rate": 2.7192982456140354e-05,
+      "loss": 0.3661,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8717948717948718,
+      "eval_f1": 0.8719638963541402,
+      "eval_f1_class_0": 0.8780487804878049,
+      "eval_f1_class_1": 0.8648648648648649,
+      "eval_loss": 0.35331812500953674,
+      "eval_precision": 0.8732793522267207,
+      "eval_precision_class_0": 0.9,
+      "eval_precision_class_1": 0.8421052631578947,
+      "eval_recall": 0.8717948717948718,
+      "eval_runtime": 0.7276,
+      "eval_samples_per_second": 107.208,
+      "eval_steps_per_second": 2.749,
+      "step": 30
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 2.4954941272735596,
+      "learning_rate": 2.280701754385965e-05,
+      "loss": 0.2656,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.014026165008545,
+      "learning_rate": 1.8421052631578947e-05,
+      "loss": 0.1901,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8846153846153846,
+      "eval_f1": 0.8828402366863904,
+      "eval_f1_class_0": 0.9010989010989011,
+      "eval_f1_class_1": 0.8615384615384616,
+      "eval_loss": 0.3602108657360077,
+      "eval_precision": 0.8961727927245169,
+      "eval_precision_class_0": 0.8367346938775511,
+      "eval_precision_class_1": 0.9655172413793104,
+      "eval_recall": 0.8846153846153846,
+      "eval_runtime": 0.6999,
+      "eval_samples_per_second": 111.445,
+      "eval_steps_per_second": 2.858,
+      "step": 40
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 1.7869679927825928,
+      "learning_rate": 1.4035087719298246e-05,
+      "loss": 0.1756,
+      "step": 45
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.1429275274276733,
+      "learning_rate": 9.649122807017545e-06,
+      "loss": 0.0941,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_f1": 0.9228724763608483,
+      "eval_f1_class_0": 0.9302325581395349,
+      "eval_f1_class_1": 0.9142857142857143,
+      "eval_loss": 0.19413678348064423,
+      "eval_precision": 0.9238996297819827,
+      "eval_precision_class_0": 0.9090909090909091,
+      "eval_precision_class_1": 0.9411764705882353,
+      "eval_recall": 0.9230769230769231,
+      "eval_runtime": 0.6829,
+      "eval_samples_per_second": 114.219,
+      "eval_steps_per_second": 2.929,
+      "step": 50
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 51165532730880.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d52dd3e316a5bbd9f49cb6b4f60542b23548e7992ea157bc70d86cb2da65a930
+size 5713