End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: apache-2.0
 base_model: google/mt5-base
 tags:

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.0,
+    "train_runtime": 272.8654,
+    "train_samples": 11659,
+    "train_samples_per_second": 213.64,
+    "train_steps_per_second": 3.353
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.0,
+    "train_runtime": 272.8654,
+    "train_samples": 11659,
+    "train_samples_per_second": 213.64,
+    "train_steps_per_second": 3.353
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 915,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.73,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "step": 915,
+      "total_flos": 9.149752655269069e+16,
+      "train_loss": 0.0,
+      "train_runtime": 272.8654,
+      "train_samples_per_second": 213.64,
+      "train_steps_per_second": 3.353
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 915,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 9.149752655269069e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}