Training in progress, epoch 3, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c5b7142d67d2e6d14e476d7cdd90243fe035678609704ba110fcb01d01f1048
+oid sha256:b1556b91f55f4fcbdf7ffaa6e10a5e5f44fee4edd8719504fd5539ffad635629
 size 1256

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d24b9d254e55dd502f46ee3a75731bdd6708d3ea9ed7943f073b2f1ffd723e
+oid sha256:a7a27874f7dc93ced479b2661f0507a486022fb461d136d2fd60f69bdbbfaa50
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b0fa67be1963473e45d47ec1113bc90055deeab862ac768b96476a7d528997d
+oid sha256:956dd45bd07787d9b2fb542007f1b421b04490e56f3fd7ecced6b9f51503ae5f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 656,
+  "global_step": 984,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -39,13 +39,26 @@
       "eval_samples_per_second": 2.059,
       "eval_steps_per_second": 0.262,
       "step": 656
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 10.608247422680412,
+      "eval_loss": 0.6409556865692139,
+      "eval_rouge1": 34.177,
+      "eval_rouge2": 25.6788,
+      "eval_rougeL": 30.5719,
+      "eval_rougeLsum": 30.9342,
+      "eval_runtime": 141.7511,
+      "eval_samples_per_second": 2.053,
+      "eval_steps_per_second": 0.261,
+      "step": 984
     }
   ],
   "logging_steps": 500,
   "max_steps": 3936,
   "num_train_epochs": 12,
   "save_steps": 500,
-  "total_flos": 4916284361146368.0,
+  "total_flos": 7374426541719552.0,
   "trial_name": null,
   "trial_params": null
 }