End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8525993883792049
+      value: 0.8568807339449541
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the boolq dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5577
-- Accuracy: 0.8526
+- Loss: 0.6057
+- Accuracy: 0.8569
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8568807339449541,
+    "eval_loss": 0.6057409644126892,
+    "eval_runtime": 33.2631,
+    "eval_samples": 3270,
+    "eval_samples_per_second": 98.307,
+    "eval_steps_per_second": 12.296,
+    "train_loss": 0.2942116430250265,
+    "train_runtime": 1876.9877,
+    "train_samples": 9427,
+    "train_samples_per_second": 25.112,
+    "train_steps_per_second": 0.786
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8568807339449541,
+    "eval_loss": 0.6057409644126892,
+    "eval_runtime": 33.2631,
+    "eval_samples": 3270,
+    "eval_samples_per_second": 98.307,
+    "eval_steps_per_second": 12.296
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.2942116430250265,
+    "train_runtime": 1876.9877,
+    "train_samples": 9427,
+    "train_samples_per_second": 25.112,
+    "train_steps_per_second": 0.786
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 250,
+  "global_step": 1475,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.85,
+      "eval_accuracy": 0.8024464831804281,
+      "eval_loss": 0.45075055956840515,
+      "eval_runtime": 33.5258,
+      "eval_samples_per_second": 97.537,
+      "eval_steps_per_second": 12.2,
+      "step": 250
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.637288135593221e-06,
+      "loss": 0.5086,
+      "step": 500
+    },
+    {
+      "epoch": 1.69,
+      "eval_accuracy": 0.8501529051987767,
+      "eval_loss": 0.3660411536693573,
+      "eval_runtime": 33.4804,
+      "eval_samples_per_second": 97.669,
+      "eval_steps_per_second": 12.216,
+      "step": 500
+    },
+    {
+      "epoch": 2.54,
+      "eval_accuracy": 0.8507645259938837,
+      "eval_loss": 0.40917864441871643,
+      "eval_runtime": 33.4889,
+      "eval_samples_per_second": 97.644,
+      "eval_steps_per_second": 12.213,
+      "step": 750
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 3.2610169491525428e-06,
+      "loss": 0.2387,
+      "step": 1000
+    },
+    {
+      "epoch": 3.39,
+      "eval_accuracy": 0.8553516819571866,
+      "eval_loss": 0.49750199913978577,
+      "eval_runtime": 33.4928,
+      "eval_samples_per_second": 97.633,
+      "eval_steps_per_second": 12.212,
+      "step": 1000
+    },
+    {
+      "epoch": 4.24,
+      "eval_accuracy": 0.8525993883792049,
+      "eval_loss": 0.5576593279838562,
+      "eval_runtime": 33.4993,
+      "eval_samples_per_second": 97.614,
+      "eval_steps_per_second": 12.209,
+      "step": 1250
+    },
+    {
+      "epoch": 5.0,
+      "step": 1475,
+      "total_flos": 4.392658481046528e+16,
+      "train_loss": 0.2942116430250265,
+      "train_runtime": 1876.9877,
+      "train_samples_per_second": 25.112,
+      "train_steps_per_second": 0.786
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1475,
+  "num_train_epochs": 5,
+  "save_steps": 250,
+  "total_flos": 4.392658481046528e+16,
+  "trial_name": null,
+  "trial_params": null
+}