Training in progress, epoch 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f6a5f162e01b886b3cda251696faf709a8b5b151cb63d88625e8cf4dcd1fc89
+oid sha256:fcce907d4149f87c0e6e06a82d31bfc27b7dcdfc5b79dc3071ec85627b02b8f0
 size 1256

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a27874f7dc93ced479b2661f0507a486022fb461d136d2fd60f69bdbbfaa50
+oid sha256:08e8af3fcba0c22d51a0c29d95f84426eb1608f280deece66d2d0151b331a6b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b4cdc08b8ca654cf8706ee497a16e787c7ce3c414b2aa50ced0408411b55ec
+oid sha256:ee8df4135e5408757a64db0c17ef3bb1d8904c382c3367bd1442f0ad7dac6b67
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 984,
+  "global_step": 1312,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,13 +52,32 @@
       "eval_samples_per_second": 2.17,
       "eval_steps_per_second": 0.276,
       "step": 984
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 0.0004853133981334999,
+      "loss": 0.7129,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 10.608247422680412,
+      "eval_loss": 0.6409556865692139,
+      "eval_rouge1": 34.106,
+      "eval_rouge2": 25.6511,
+      "eval_rougeL": 30.5481,
+      "eval_rougeLsum": 30.8868,
+      "eval_runtime": 133.3173,
+      "eval_samples_per_second": 2.183,
+      "eval_steps_per_second": 0.278,
+      "step": 1312
     }
   ],
   "logging_steps": 500,
   "max_steps": 2624,
   "num_train_epochs": 8,
   "save_steps": 500,
-  "total_flos": 7374426541719552.0,
+  "total_flos": 9832568722292736.0,
   "trial_name": null,
   "trial_params": null
 }