Training in progress, step 39000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6996a0a8b407d3534edf3ae94d4cde0f6d8eea7bdf286c10415c5afb898ebbb2
+oid sha256:a853f72dbaed77b0f2b7855c598ca5e8f7205a774d5e4a484dc9618c1d703f9c
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00a4e2b028c71a230dfa065fda64740d3807c8ae18098f60ce59f1c0fd087b51
+oid sha256:1425ddea2e1aa4193cc447538f36a29b778873646642b0054c31483367ff5ac8
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5046efd964e0777c3ae5a962ac07a21d5fa0287063aae60b255b780a94d1ba
+oid sha256:5f28c7019382eca2900417a705546cdab309d5cbea5a7dff4f774785ccae3006
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17ef1342d0a421acb078269451a43c693b52118abf89df69f767e9aafdb1c461
+oid sha256:a7beb525f6000838c9b12583ad1253138900b22ae2a96dcaafec662e05e58650
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24,
+  "epoch": 0.2496,
   "eval_steps": 500,
-  "global_step": 37500,
+  "global_step": 39000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -532,6 +532,27 @@
       "learning_rate": 4.4001920000000004e-05,
       "loss": 0.3563,
       "step": 37500
+    },
+    {
+      "epoch": 0.2432,
+      "grad_norm": 0.7765107154846191,
+      "learning_rate": 4.392224e-05,
+      "loss": 0.3548,
+      "step": 38000
+    },
+    {
+      "epoch": 0.2464,
+      "grad_norm": 0.7250288724899292,
+      "learning_rate": 4.384224e-05,
+      "loss": 0.3605,
+      "step": 38500
+    },
+    {
+      "epoch": 0.2496,
+      "grad_norm": 0.6914694309234619,
+      "learning_rate": 4.376224e-05,
+      "loss": 0.3551,
+      "step": 39000
     }
   ],
   "logging_steps": 500,
@@ -551,7 +572,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.82687367168e+17,
+  "total_flos": 1.8999486185472e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null