Training in progress, step 21000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2619e39c7ccdacc83b8d41bc4bd14f8d2b107f485189d650044d2955fe36919f
+oid sha256:dedc0dc44de6bcf8533e592ce68c222b528cd994a150b2d3f296a68000653f10
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e04af958111ec792b349fa549e57a5fe87dcfd48e94c0a6688a17415bbf1ae5c
+oid sha256:5b1427a38d6b61ba213a6bebe4cba12227f4c5384edabf96a158902c0aa4ece1
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb27f209f1e0a7f749cfc1e16f4b17dde3c2a47d255a4f9a67da7a06afd4b008
+oid sha256:801adf4445dd3769164c30f6179bdb3feeab15fc26be81439ffeae1b23a90b17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae30008925bfd306b2e47f79372910f9491bdf66eaaa12b354d9cc3b7bfba21e
+oid sha256:46368ba620b42094a299a9c06a36f3d28acb525d16404e7926726905b6d401be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.14610190300798,
+  "epoch": 3.2228360957642725,
   "eval_steps": 500,
-  "global_step": 20500,
+  "global_step": 21000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -283,13 +283,19 @@
       "learning_rate": 0.0003710251688152241,
       "loss": 0.4869,
       "step": 20500
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 0.0003556783302639656,
+      "loss": 0.4917,
+      "step": 21000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.0865231363309568e+16,
+  "total_flos": 1.1130310969786368e+16,
   "trial_name": null,
   "trial_params": null
 }