End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # testhehehe
 
-This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the data/originality_aidetector dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6675
 - Accuracy: 0.667

all_results.json

@@ -0,0 +1,10 @@
+{
+    "best_checkpoint": "./output/checkpoint-21",
+    "epoch": 2.0,
+    "total_flos": 410718830592.0,
+    "train_loss": 0.6975067257881165,
+    "train_runtime": 29.0699,
+    "train_samples": 1000,
+    "train_samples_per_second": 68.8,
+    "train_steps_per_second": 1.101
+}

train_results.json

@@ -0,0 +1,10 @@
+{
+    "best_checkpoint": "./output/checkpoint-21",
+    "epoch": 2.0,
+    "total_flos": 410718830592.0,
+    "train_loss": 0.6975067257881165,
+    "train_runtime": 29.0699,
+    "train_samples": 1000,
+    "train_samples_per_second": 68.8,
+    "train_steps_per_second": 1.101
+}

trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "./output/checkpoint-21",
+  "epoch": 2.0,
+  "eval_steps": 7,
+  "global_step": 32,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4375,
+      "eval_accuracy": 0.333,
+      "eval_f1": 0.0,
+      "eval_false_negative": 0.0,
+      "eval_false_positive": 1.0,
+      "eval_loss": 0.7175007462501526,
+      "eval_runtime": 1.2449,
+      "eval_samples_per_second": 803.283,
+      "eval_steps_per_second": 12.853,
+      "eval_true_negative": 0.0,
+      "eval_true_positive": 1.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.875,
+      "eval_accuracy": 0.679,
+      "eval_f1": 0.802,
+      "eval_false_negative": 0.9129,
+      "eval_false_positive": 0.0255,
+      "eval_loss": 0.6894052624702454,
+      "eval_runtime": 1.2173,
+      "eval_samples_per_second": 821.472,
+      "eval_steps_per_second": 13.144,
+      "eval_true_negative": 0.9745,
+      "eval_true_positive": 0.0871,
+      "step": 14
+    },
+    {
+      "epoch": 1.3125,
+      "eval_accuracy": 0.667,
+      "eval_f1": 0.8002,
+      "eval_false_negative": 1.0,
+      "eval_false_positive": 0.0,
+      "eval_loss": 0.6765199899673462,
+      "eval_runtime": 1.2622,
+      "eval_samples_per_second": 792.277,
+      "eval_steps_per_second": 12.676,
+      "eval_true_negative": 1.0,
+      "eval_true_positive": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 1.75,
+      "eval_accuracy": 0.667,
+      "eval_f1": 0.8002,
+      "eval_false_negative": 1.0,
+      "eval_false_positive": 0.0,
+      "eval_loss": 0.6674614548683167,
+      "eval_runtime": 1.2066,
+      "eval_samples_per_second": 828.779,
+      "eval_steps_per_second": 13.26,
+      "eval_true_negative": 1.0,
+      "eval_true_positive": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.0,
+      "step": 32,
+      "total_flos": 410718830592.0,
+      "train_loss": 0.6975067257881165,
+      "train_runtime": 29.0699,
+      "train_samples_per_second": 68.8,
+      "train_steps_per_second": 1.101
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 32,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 7,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 410718830592.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}