OscarXZQ/bbh-lora-word_sorting

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 59340530073600.0,
+    "train_loss": 1.745889892578125,
+    "train_runtime": 83.5528,
+    "train_samples_per_second": 2.992,
+    "train_steps_per_second": 2.992
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 59340530073600.0,
+    "train_loss": 1.745889892578125,
+    "train_runtime": 83.5528,
+    "train_samples_per_second": 2.992,
+    "train_steps_per_second": 2.992
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 10.0,
+      "step": 250,
+      "total_flos": 59340530073600.0,
+      "train_loss": 1.745889892578125,
+      "train_runtime": 83.5528,
+      "train_samples_per_second": 2.992,
+      "train_steps_per_second": 2.992
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 59340530073600.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}