End of training

all_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 3.99,
-    "train_loss": 1.950797971089681,
-    "train_runtime": 8703.8597,
-    "train_samples_per_second": 22.978,
-    "train_steps_per_second": 0.179
+    "epoch": 5.99,
+    "train_loss": 0.646622069269164,
+    "train_runtime": 5096.5205,
+    "train_samples_per_second": 58.864,
+    "train_steps_per_second": 0.459
 }

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 3.99,
-    "train_loss": 1.950797971089681,
-    "train_runtime": 8703.8597,
-    "train_samples_per_second": 22.978,
-    "train_steps_per_second": 0.179
+    "epoch": 5.99,
+    "train_loss": 0.646622069269164,
+    "train_runtime": 5096.5205,
+    "train_samples_per_second": 58.864,
+    "train_steps_per_second": 0.459
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.9923224568138194,
+  "epoch": 5.994241842610364,
   "eval_steps": 500,
-  "global_step": 1560,
+  "global_step": 2340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -75,37 +75,75 @@
       "step": 1500
     },
     {
-      "epoch": 3.99,
-      "eval_f1": 0.907,
-      "eval_gen_len": 26.45309090909091,
-      "eval_loss": 1.7193447351455688,
+      "epoch": 4.0,
+      "eval_f1": 0.9069,
+      "eval_gen_len": 26.39709090909091,
+      "eval_loss": 1.7157036066055298,
       "eval_precision": 0.9082,
-      "eval_recall": 0.9061,
-      "eval_rouge1": 0.4541,
-      "eval_rouge2": 0.2071,
-      "eval_rougeL": 0.3708,
-      "eval_rougeLsum": 0.3708,
-      "eval_runtime": 503.2966,
-      "eval_samples_per_second": 5.464,
-      "eval_steps_per_second": 0.342,
+      "eval_recall": 0.906,
+      "eval_rouge1": 0.4539,
+      "eval_rouge2": 0.2075,
+      "eval_rougeL": 0.3716,
+      "eval_rougeLsum": 0.3714,
+      "eval_runtime": 505.7397,
+      "eval_samples_per_second": 5.438,
+      "eval_steps_per_second": 0.34,
       "step": 1560
     },
     {
-      "epoch": 3.99,
-      "step": 1560,
-      "total_flos": 2.884147799685857e+17,
-      "train_loss": 1.950797971089681,
-      "train_runtime": 8703.8597,
-      "train_samples_per_second": 22.978,
-      "train_steps_per_second": 0.179
+      "epoch": 5.0,
+      "eval_f1": 0.9074,
+      "eval_gen_len": 26.301454545454547,
+      "eval_loss": 1.703265905380249,
+      "eval_precision": 0.9087,
+      "eval_recall": 0.9065,
+      "eval_rouge1": 0.4561,
+      "eval_rouge2": 0.2098,
+      "eval_rougeL": 0.3735,
+      "eval_rougeLsum": 0.3734,
+      "eval_runtime": 505.7439,
+      "eval_samples_per_second": 5.438,
+      "eval_steps_per_second": 0.34,
+      "step": 1951
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 2.9059829059829063e-06,
+      "loss": 1.8067,
+      "step": 2000
+    },
+    {
+      "epoch": 5.99,
+      "eval_f1": 0.9076,
+      "eval_gen_len": 26.337818181818182,
+      "eval_loss": 1.6991122961044312,
+      "eval_precision": 0.909,
+      "eval_recall": 0.9067,
+      "eval_rouge1": 0.4572,
+      "eval_rouge2": 0.2103,
+      "eval_rougeL": 0.3743,
+      "eval_rougeLsum": 0.3742,
+      "eval_runtime": 504.0406,
+      "eval_samples_per_second": 5.456,
+      "eval_steps_per_second": 0.341,
+      "step": 2340
+    },
+    {
+      "epoch": 5.99,
+      "step": 2340,
+      "total_flos": 4.3261061209522176e+17,
+      "train_loss": 0.646622069269164,
+      "train_runtime": 5096.5205,
+      "train_samples_per_second": 58.864,
+      "train_steps_per_second": 0.459
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1560,
+  "max_steps": 2340,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 6,
   "save_steps": 500,
-  "total_flos": 2.884147799685857e+17,
+  "total_flos": 4.3261061209522176e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null