Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:214e311a786637414b3cc77ddd784b3f3a41fb5e3fc116ca8b692dcad6f03aca
+oid sha256:9c1ec1b323bcbd76e5805f3a24498e03acb3c2cf487117d9696effe32ecfbd1d
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0091a67a2288f1e898b6efef5db7f93d4e8d8e86728f655273466e0a268c494
+oid sha256:a436eac92000698c908774b901196288009345b0c5563cb31fdd9134a1467c46
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db5a10ae8e077eb948f8a65081b04034858b4b0907d0313398fe4a4657c1c44
+oid sha256:a43ba48a7f5dec028bff1cfb00b96967c855f54d0fc9fe880a72e79c63602ba7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:855b6253cf532e5dd8b357f2552ac3d9f831efc883e202dbd75e2be7a6e1687d
+oid sha256:4439612aaf5fd590b955ad3ebf8fec8ff475c39db671eba2b9ba52bcb968a283
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7648864333947207,
+  "epoch": 1.8416206261510129,
   "eval_steps": 500,
-  "global_step": 11500,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -155,13 +155,19 @@
       "learning_rate": 0.0006471454880294659,
       "loss": 0.5716,
       "step": 11500
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.0006317986494782076,
+      "loss": 0.5665,
+      "step": 12000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 6096687148302336.0,
+  "total_flos": 6360806673874944.0,
   "trial_name": null,
   "trial_params": null
 }