Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dc2072ab9a0e445296ac3f8151eea455e3a58f3604a73d68130568942d05a3a
+oid sha256:b515348ffd2931e3afdc83f415cdd6bc9fce29d58e8899fab059d00913425636
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18afe885f408124fd9c4a843f52e43ad3cd190a9477afeaa42ec3c53365c26c3
+oid sha256:2a6a3672bd3863a17742f0c3e9c6d7214b430fde28cd161eb704c6ac4379308c
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0390b75aa632da72c0c84f21e08a92a40f781f7159c00fed0fdc797f3bb9d115
+oid sha256:370f9858e2661329c83baaac478fd0b0190275c384021c3105aedf73ac4ddd6a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34364c2d46a6c353df83d4f0e0edfb9e1cd6fed16aeac57800bc7243c82339db
+oid sha256:818696f1cf034b11661cd72abe1b54bebf374cfb87756f4c9013364760eae305
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3044812768569676,
+  "epoch": 1.3812154696132597,
   "eval_steps": 500,
-  "global_step": 8500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,13 +119,19 @@
       "learning_rate": 0.000739195825659914,
       "loss": 0.5793,
       "step": 8500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0007238489871086557,
+      "loss": 0.5743,
+      "step": 9000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 4506129150246912.0,
+  "total_flos": 4772029266395136.0,
   "trial_name": null,
   "trial_params": null
 }