End of training

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.79,
+    "train_loss": 38.4305224609375,
+    "train_runtime": 53.4615,
+    "train_samples": 112,
+    "train_samples_per_second": 3.741,
+    "train_steps_per_second": 1.871
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.79,
+    "train_loss": 38.4305224609375,
+    "train_runtime": 53.4615,
+    "train_samples": 112,
+    "train_samples_per_second": 3.741,
+    "train_steps_per_second": 1.871
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7857142857142856,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.0,
+      "loss": 38.4305,
+      "step": 100
+    },
+    {
+      "epoch": 1.79,
+      "step": 100,
+      "total_flos": 2.251336673321712e+16,
+      "train_loss": 38.4305224609375,
+      "train_runtime": 53.4615,
+      "train_samples_per_second": 3.741,
+      "train_steps_per_second": 1.871
+    }
+  ],
+  "max_steps": 100,
+  "num_train_epochs": 2,
+  "total_flos": 2.251336673321712e+16,
+  "trial_name": null,
+  "trial_params": null
+}