Training in progress, step 12500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1ec1b323bcbd76e5805f3a24498e03acb3c2cf487117d9696effe32ecfbd1d
+oid sha256:b26e8e16384250dfca41d5b3113059194b29807c89da51582025e4529d9ae296
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a436eac92000698c908774b901196288009345b0c5563cb31fdd9134a1467c46
+oid sha256:629a724d9972ef7a8933f7437a0565e520bac2b2044fad926b33012443389cde
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a43ba48a7f5dec028bff1cfb00b96967c855f54d0fc9fe880a72e79c63602ba7
+oid sha256:f563e7cc48c77e38c0f0ffecfd66cc9b3f531cdfe2db350ed1aad55e38faa0c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4439612aaf5fd590b955ad3ebf8fec8ff475c39db671eba2b9ba52bcb968a283
+oid sha256:ea81a152c31c603b6ecca61515ae365bc23ec1d05ea6e8887eb0cd80e26b497b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8416206261510129,
+  "epoch": 1.918354818907305,
   "eval_steps": 500,
-  "global_step": 12000,
+  "global_step": 12500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,13 +161,19 @@
       "learning_rate": 0.0006317986494782076,
       "loss": 0.5665,
       "step": 12000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.000616451810926949,
+      "loss": 0.5671,
+      "step": 12500
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 6360806673874944.0,
+  "total_flos": 6626905573294080.0,
   "trial_name": null,
   "trial_params": null
 }