End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.6678700361010831,
+    "eval_loss": 0.8396075367927551,
+    "eval_runtime": 1.6845,
+    "eval_samples": 277,
+    "eval_samples_per_second": 164.444,
+    "eval_steps_per_second": 20.778,
+    "train_loss": 60928.27408236968,
+    "train_runtime": 290.1511,
+    "train_samples": 2490,
+    "train_samples_per_second": 85.817,
+    "train_steps_per_second": 2.688
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.6678700361010831,
+    "eval_loss": 0.8396075367927551,
+    "eval_runtime": 1.6845,
+    "eval_samples": 277,
+    "eval_samples_per_second": 164.444,
+    "eval_steps_per_second": 20.778
+}

runs/Jun15_16-09-17_labgpu/events.out.tfevents.1655310262.labgpu.23398.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d97c55896865cc2310e74c1419d904d6fe92434ed2fb5174125a2b2801840ae0
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 60928.27408236968,
+    "train_runtime": 290.1511,
+    "train_samples": 2490,
+    "train_samples_per_second": 85.817,
+    "train_steps_per_second": 2.688
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 780,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 6.41,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 95047.952,
+      "step": 500
+    },
+    {
+      "epoch": 10.0,
+      "step": 780,
+      "total_flos": 390360542976000.0,
+      "train_loss": 60928.27408236968,
+      "train_runtime": 290.1511,
+      "train_samples_per_second": 85.817,
+      "train_steps_per_second": 2.688
+    }
+  ],
+  "max_steps": 780,
+  "num_train_epochs": 10,
+  "total_flos": 390360542976000.0,
+  "trial_name": null,
+  "trial_params": null
+}