End of training

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 119.35714285714286,
+    "eval_loss": 30.350460052490234,
+    "eval_rouge1": 2.7855,
+    "eval_rouge2": 0.0203,
+    "eval_rougeL": 2.2791,
+    "eval_rougeLsum": 2.2817,
+    "eval_runtime": 81.9616,
+    "eval_samples": 56,
+    "eval_samples_per_second": 0.683,
+    "eval_steps_per_second": 0.171,
+    "train_loss": 39.355625697544646,
+    "train_runtime": 67.9146,
+    "train_samples": 56,
+    "train_samples_per_second": 2.474,
+    "train_steps_per_second": 0.618
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 119.35714285714286,
+    "eval_loss": 30.350460052490234,
+    "eval_rouge1": 2.7855,
+    "eval_rouge2": 0.0203,
+    "eval_rougeL": 2.2791,
+    "eval_rougeLsum": 2.2817,
+    "eval_runtime": 81.9616,
+    "eval_samples": 56,
+    "eval_samples_per_second": 0.683,
+    "eval_steps_per_second": 0.171
+}

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 39.355625697544646,
+    "train_runtime": 67.9146,
+    "train_samples": 56,
+    "train_samples_per_second": 2.474,
+    "train_steps_per_second": 0.618
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 42,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 42,
+      "total_flos": 14765526220800.0,
+      "train_loss": 39.355625697544646,
+      "train_runtime": 67.9146,
+      "train_samples_per_second": 2.474,
+      "train_steps_per_second": 0.618
+    }
+  ],
+  "max_steps": 42,
+  "num_train_epochs": 3,
+  "total_flos": 14765526220800.0,
+  "trial_name": null,
+  "trial_params": null
+}