🍻 cheers

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.031901244074106216,
+    "eval_runtime": 2.0927,
+    "eval_samples_per_second": 4.301,
+    "eval_steps_per_second": 0.956,
+    "train_loss": 0.03689494046072165,
+    "train_runtime": 18.5382,
+    "train_samples_per_second": 7.336,
+    "train_steps_per_second": 0.647
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.031901244074106216,
+    "eval_runtime": 2.0927,
+    "eval_samples_per_second": 4.301,
+    "eval_steps_per_second": 0.956
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.03689494046072165,
+    "train_runtime": 18.5382,
+    "train_samples_per_second": 7.336,
+    "train_steps_per_second": 0.647
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.0,
+      "loss": 0.0383,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "step": 12,
+      "total_flos": 1.0538910587584512e+16,
+      "train_loss": 0.03689494046072165,
+      "train_runtime": 18.5382,
+      "train_samples_per_second": 7.336,
+      "train_steps_per_second": 0.647
+    }
+  ],
+  "max_steps": 12,
+  "num_train_epochs": 4,
+  "total_flos": 1.0538910587584512e+16,
+  "trial_name": null,
+  "trial_params": null
+}