Training in progress, step 5600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4937ebdfd76ea42e4842828cfb8c7963b8ae45c1c67edac15bc3b8518bc34653
+oid sha256:45b3d86b641b6563a1a49ee175c354feeeff9b63223fbc09d1755474a920625e
 size 101948208

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb88683b46a40f9ff62c45572627b0fea0174cb8884b54db82cd566c705e5b56
+oid sha256:9bdfbad0cc617604191c34aedab5162e51c674c453b7616b2a30ae6b9cb8b1ea
 size 203962810

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae8349a687e6f3e3622dac39a4142f23c6a1a4c74463468fc355e688620fbced
+oid sha256:f9558c741c0f18de99a9f543dddbfeb2b76b79c6295f8b6305edfd81a2a4ff08
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0802007990375904,
+  "epoch": 0.08317119900194561,
   "eval_steps": 500,
-  "global_step": 5400,
+  "global_step": 5600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,13 @@
       "learning_rate": 0.001985148000178224,
       "loss": 5.5283,
       "step": 5000
+    },
+    {
+      "epoch": 0.08168599901976802,
+      "grad_norm": 0.588165283203125,
+      "learning_rate": 0.0019836628001960463,
+      "loss": 5.4899,
+      "step": 5500
     }
   ],
   "logging_steps": 500,
@@ -96,7 +103,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 283588322918400.0,
+  "total_flos": 294091594137600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null