Upload trainer_state.json with huggingface_hub

trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_global_step": 4595,
+  "best_metric": 0.8678489886076785,
+  "best_model_checkpoint": "outputs/hate-speech-detection/xlm-r/checkpoint-4595",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 4595,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.998911860718172,
+      "grad_norm": 6.781782150268555,
+      "learning_rate": 1.9996091589167148e-05,
+      "loss": 0.509,
+      "step": 918
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8502325581395349,
+      "eval_f1": 0.8159424402621652,
+      "eval_loss": 0.46024587750434875,
+      "eval_precision": 0.8066474508484307,
+      "eval_recall": 0.8502325581395349,
+      "eval_runtime": 61.3679,
+      "eval_samples_per_second": 70.069,
+      "eval_steps_per_second": 2.2,
+      "step": 919
+    },
+    {
+      "epoch": 1.997823721436344,
+      "grad_norm": 22.485809326171875,
+      "learning_rate": 1.9982377977480694e-05,
+      "loss": 0.432,
+      "step": 1836
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8562790697674418,
+      "eval_f1": 0.8120890941506358,
+      "eval_loss": 0.4724840521812439,
+      "eval_precision": 0.8238057729845522,
+      "eval_recall": 0.8562790697674418,
+      "eval_runtime": 61.3476,
+      "eval_samples_per_second": 70.092,
+      "eval_steps_per_second": 2.201,
+      "step": 1838
+    },
+    {
+      "epoch": 2.996735582154516,
+      "grad_norm": 9.082085609436035,
+      "learning_rate": 1.9958812963917564e-05,
+      "loss": 0.3584,
+      "step": 2754
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.867906976744186,
+      "eval_f1": 0.8485554148376526,
+      "eval_loss": 0.3921661674976349,
+      "eval_precision": 0.85229306118012,
+      "eval_recall": 0.867906976744186,
+      "eval_runtime": 61.427,
+      "eval_samples_per_second": 70.002,
+      "eval_steps_per_second": 2.198,
+      "step": 2757
+    },
+    {
+      "epoch": 3.995647442872688,
+      "grad_norm": 7.213796138763428,
+      "learning_rate": 1.992541980430111e-05,
+      "loss": 0.3029,
+      "step": 3672
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8625581395348837,
+      "eval_f1": 0.8607090125530891,
+      "eval_loss": 0.3699357211589813,
+      "eval_precision": 0.8593123853782028,
+      "eval_recall": 0.8625581395348837,
+      "eval_runtime": 61.3645,
+      "eval_samples_per_second": 70.073,
+      "eval_steps_per_second": 2.2,
+      "step": 3676
+    },
+    {
+      "epoch": 4.99455930359086,
+      "grad_norm": 7.137932300567627,
+      "learning_rate": 1.9882231453648264e-05,
+      "loss": 0.251,
+      "step": 4590
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8741860465116279,
+      "eval_f1": 0.8678489886076785,
+      "eval_loss": 0.3963276743888855,
+      "eval_precision": 0.8636605655536596,
+      "eval_recall": 0.8741860465116279,
+      "eval_runtime": 61.4545,
+      "eval_samples_per_second": 69.97,
+      "eval_steps_per_second": 2.197,
+      "step": 4595
+    }
+  ],
+  "logging_steps": 918,
+  "max_steps": 91900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "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": 0.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}