Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:296a3c6d309d1e85d28d84a70644a84db24c66100970c1560c1c1f4cc57b30b5
+oid sha256:daf825b2ac323d51bddf5aab1e57f414f1cfe54920df798da73e3e443add002d
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7757311822a5bbc6563a14ae734cc5c55ec098bd049b31c1a6eedd6462d9519a
+oid sha256:e3b7fdefab7587fb1c52808b7e6ca7e43cacff48abf1e13d2ed8107172513598
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:509ee6f2dc95c367cf1eda5ebb7ac0772535dbbc4fb915944d9e317d5b2f8b3a
+oid sha256:759bf8b1d224002535229b7cdbc76ddeb1a0d0aa895c4ae5f0ffef98417bab39
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2b5d040d5c740697a7c2dcc153f257910aea505a3c7139823305a169f6a1ef0
+oid sha256:7211fac2cf232e2d3daade79b26ee02ede73fbb567f37dbd6997fc9c8b853fd0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9351620947630923,
+  "epoch": 1.0390689941812137,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -70,6 +70,21 @@
       "learning_rate": 1.3769742310889445e-05,
       "loss": 0.4029,
       "step": 4500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.3212089240550995,
+      "eval_runtime": 31.4577,
+      "eval_samples_per_second": 15.704,
+      "eval_steps_per_second": 7.852,
+      "step": 4812
+    },
+    {
+      "epoch": 1.0390689941812137,
+      "grad_norm": 0.6561925411224365,
+      "learning_rate": 1.3077029648101969e-05,
+      "loss": 0.4059,
+      "step": 5000
     }
   ],
   "logging_steps": 500,
@@ -89,7 +104,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5480621015040000.0,
+  "total_flos": 6088969947709440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null