Training in progress, step 16500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2971a731e2fbc5382f203c313714874b6442c0ef407ba0b340fe6bd607cf0d81
+oid sha256:6ef74a51b98d62f1c8ee8ce919c53c99d14bb9cbaf3b1515d3d626f75ad9549f
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:927e00b3ef25dbe2d0c60c7010649323428184118ae870950e04c65465b8d66e
+oid sha256:960c16ba999c50f6e93b096b8b4664e9b4dc1c3829c8ef7cb686c87ed8f867f4
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a815d4b671b2f9d54ad695690d7a84e5c6eff4353f840b0741a667f1355175d5
+oid sha256:dc99d51f6d854e132431f86e3c07d3cf26a291271f719acb00ea53371c943767
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34fd0dc259f4263e977c8cb3231c9f2408c2c6a6f820345c818e9c5127a7086f
+oid sha256:8b9abbb83caef81fd4610d4f3826f8955ab4d855b0c53f2101fc07d80c63118a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.4554941682013505,
+  "epoch": 2.532228360957643,
   "eval_steps": 500,
-  "global_step": 16000,
+  "global_step": 16500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -219,13 +219,19 @@
       "learning_rate": 0.000509085328422345,
       "loss": 0.5271,
       "step": 16000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0004937384898710866,
+      "loss": 0.5295,
+      "step": 16500
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 8481333560475648.0,
+  "total_flos": 8746501985009664.0,
   "trial_name": null,
   "trial_params": null
 }