End of training

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.7066666666666667,
+    "eval_loss": 1.2085484266281128,
+    "eval_runtime": 0.1015,
+    "eval_samples": 1,
+    "eval_samples_per_second": 9.848,
+    "eval_steps_per_second": 9.848,
+    "perplexity": 3.3486203548209947,
+    "train_loss": 1.552238972981771,
+    "train_runtime": 328.4713,
+    "train_samples": 45,
+    "train_samples_per_second": 4.11,
+    "train_steps_per_second": 1.096
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.7066666666666667,
+    "eval_loss": 1.2085484266281128,
+    "eval_runtime": 0.1015,
+    "eval_samples": 1,
+    "eval_samples_per_second": 9.848,
+    "eval_steps_per_second": 9.848,
+    "perplexity": 3.3486203548209947
+}

runs/Apr24_14-08-06_14523c674822/events.out.tfevents.1682345777.14523c674822.67070.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be3fcd9f66c0f9b17fb24400f443fd6f2ed38b27c60fba82b7ccf4a6459770b
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "train_loss": 1.552238972981771,
+    "train_runtime": 328.4713,
+    "train_samples": 45,
+    "train_samples_per_second": 4.11,
+    "train_steps_per_second": 1.096
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 30.0,
+  "global_step": 360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 30.0,
+      "step": 360,
+      "total_flos": 1258233913036800.0,
+      "train_loss": 1.552238972981771,
+      "train_runtime": 328.4713,
+      "train_samples_per_second": 4.11,
+      "train_steps_per_second": 1.096
+    }
+  ],
+  "max_steps": 360,
+  "num_train_epochs": 30,
+  "total_flos": 1258233913036800.0,
+  "trial_name": null,
+  "trial_params": null
+}