Training in progress, step 25000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9d9297b98cf6ce3523f603297210ee2283681e9a6087fd13654c9e164f59458
+oid sha256:00e889dc8b73e2945c88d0e8d5bc84760056aa09fbb3358ba551aa5967cc05a8
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9d5cf832b3c147d401e00ee854e55318edff701060b6bc6f7c42054dea43a38
+oid sha256:c5e4d853bcda895e18cec358941f2134907cb6d023c796b0344cdbb90622e7ab
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d10477df89b8843884894e11ac1e7749f1f56fac04c313b2ecda7c3ad865135
+oid sha256:19845fcc9db4d6c63e07542668bd744d427692c6f5f628938ae50b2024dc992c
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3583ec5c64f617f77f3539e241650cacc6e1155fb9a4cd9d9d5964237bec28e3
+oid sha256:e500ac1f09247915f6fe61ed9656ed13396960a5dfa25c25b714bd319fe404da
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.890592213843603,
+  "epoch": 3.0110335560870864,
   "eval_steps": 500,
-  "global_step": 24000,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,13 @@
       "learning_rate": 0.0009036376776680318,
       "loss": 15758507.008,
       "step": 24000
+    },
+    {
+      "epoch": 3.0110335560870864,
+      "grad_norm": 0.6668113470077515,
+      "learning_rate": 0.0008996225809041998,
+      "loss": 1550060.288,
+      "step": 25000
     }
   ],
   "logging_steps": 1000,
@@ -194,7 +201,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2004651776658637e+17,
+  "total_flos": 1.250484560068608e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null