OscarXZQ/hyperbaton-lr5e-05

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 20746536468480.0,
+    "train_loss": 0.41833904266357425,
+    "train_runtime": 37.1489,
+    "train_samples_per_second": 2.692,
+    "train_steps_per_second": 2.692
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 20746536468480.0,
+    "train_loss": 0.41833904266357425,
+    "train_runtime": 37.1489,
+    "train_samples_per_second": 2.692,
+    "train_steps_per_second": 2.692
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.0,
+      "step": 100,
+      "total_flos": 20746536468480.0,
+      "train_loss": 0.41833904266357425,
+      "train_runtime": 37.1489,
+      "train_samples_per_second": 2.692,
+      "train_steps_per_second": 2.692
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 20746536468480.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}