Training in progress, epoch 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f1322db5e4b60630fee99f016a47aa61c26f28d567b86bd9c1f9b3560c5a4d
+oid sha256:8816018b7aab37613028cc5a5bf83ef19de684fe2d8b60decdd44251f98fbeec
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cef2c569e1f2247b5b91c1e6f5333ed358528cc3851294ce08cb15162ad66d1
+oid sha256:2498dee0ec5d351c370824d6c721910a998c247fbb942ac39929ee81c1b435b6
 size 2621690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c75d88d701e30f9131432935310d9f24a95661f78d2d791ef1a565095fb6687d
+oid sha256:e0d5b30acb6099f84ca5645a159a8896115070f3d515a6a74b5d3e1471b03c74
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f4e9c00ff093d4836b89fbe34d048c10d6d8579a93728043e4d87912cb51bb
+oid sha256:817724bc63e49442a91949423cb28dcdcae132dae0cd5cdcc11d24dcdb5d9104
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 2296,
+  "global_step": 2624,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -122,13 +122,32 @@
       "eval_samples_per_second": 2.026,
       "eval_steps_per_second": 0.258,
       "step": 2296
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 7.687366167023556e-06,
+      "loss": 0.7442,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 10.360824742268042,
+      "eval_loss": 0.6728662252426147,
+      "eval_rouge1": 34.3758,
+      "eval_rouge2": 26.0079,
+      "eval_rougeL": 30.7863,
+      "eval_rougeLsum": 31.1239,
+      "eval_runtime": 142.7676,
+      "eval_samples_per_second": 2.038,
+      "eval_steps_per_second": 0.259,
+      "step": 2624
     }
   ],
   "logging_steps": 500,
   "max_steps": 3936,
   "num_train_epochs": 12,
   "save_steps": 500,
-  "total_flos": 1.7206995264012288e+16,
+  "total_flos": 1.966513744458547e+16,
   "trial_name": null,
   "trial_params": null
 }