Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e86f92945ea7a8791ab8e28773575bda5bb4700126b20c5846240316b793fbc2
+oid sha256:4f77e6ef5d9b55f675f6d6d57b1ca0c34485bfcb1827f4e622cba1a25f5e47fe
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20fb35f15a3c548bab1210664b48c4839f31cc67f2acbdd5c6e9bf48f3b6439a
+oid sha256:d7eca0a6af7af8e998f0a7e95ba57f20aec093ae142cf2f735778fade14dca0a
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b18f7ced60b819568a9237e74a32db62beee025423a8ffac253ebc9bf229a3b
+oid sha256:702c5d65df920d486235831b0bf74fc5e64870867cc79f991049c2a58f3f1f75
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148845e81b7b134cce802d3ea583af7c25b21853b20b5a95be05706d9ebc5924
+oid sha256:da18e8bf9e875694929b17f954d61f4f373af637f6e37100b51180d296fb6da6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5371393492940454,
+  "epoch": 0.6138735420503376,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,13 +49,19 @@
       "learning_rate": 0.000892572130141191,
       "loss": 0.611,
       "step": 3500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0008772252915899325,
+      "loss": 0.6104,
+      "step": 4000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1852812344426496.0,
+  "total_flos": 2118424859246592.0,
   "trial_name": null,
   "trial_params": null
 }