Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0a4d4eb5830f54a037bb5b2ec4c0d8b16835c8e8380818d51d26253dd73758b
+oid sha256:8910b9a58f88ac8286fea601e9dd43f8eb82a05ef861f4e329876124f86705d4
 size 355970836

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1dbfd9f0696dbaed1c3995ccce15ba4bc4256faed8e85d5762c31a1a2a589d
+oid sha256:b83ffbb4550df83557f904e680abfe9068f31e77e6e9aa3035363e1d86308159
 size 712036922

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c2863feda87075c004bd0dd402af564804ba4c165f80aa98488706883ec39bd
+oid sha256:795229107db214ae138f938d284f076426adff33dd73907164d26d963d353076
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139fdc5f456aa79c473440b624b5319327666b78b9b8b1ac7333eb8efe73bb6d
+oid sha256:d93ead1c986470262211b05883b802fce83f20b54d15c64bf021ab89b9a8bb82
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00813806739972852,
+  "epoch": 0.010172584249660648,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,76 @@
       "learning_rate": 1e-05,
       "loss": 0.0057,
       "step": 400
+    },
+    {
+      "epoch": 0.008341519084721732,
+      "grad_norm": 19.89306640625,
+      "learning_rate": 1e-05,
+      "loss": 0.0063,
+      "step": 410
+    },
+    {
+      "epoch": 0.008544970769714945,
+      "grad_norm": 14.5062837600708,
+      "learning_rate": 1e-05,
+      "loss": 0.005,
+      "step": 420
+    },
+    {
+      "epoch": 0.008748422454708159,
+      "grad_norm": 13.982276916503906,
+      "learning_rate": 1e-05,
+      "loss": 0.0055,
+      "step": 430
+    },
+    {
+      "epoch": 0.00895187413970137,
+      "grad_norm": 21.34312629699707,
+      "learning_rate": 1e-05,
+      "loss": 0.0058,
+      "step": 440
+    },
+    {
+      "epoch": 0.009155325824694584,
+      "grad_norm": 17.6949405670166,
+      "learning_rate": 1e-05,
+      "loss": 0.0056,
+      "step": 450
+    },
+    {
+      "epoch": 0.009358777509687798,
+      "grad_norm": 16.052722930908203,
+      "learning_rate": 1e-05,
+      "loss": 0.0053,
+      "step": 460
+    },
+    {
+      "epoch": 0.00956222919468101,
+      "grad_norm": 11.400249481201172,
+      "learning_rate": 1e-05,
+      "loss": 0.0051,
+      "step": 470
+    },
+    {
+      "epoch": 0.009765680879674223,
+      "grad_norm": 15.31458568572998,
+      "learning_rate": 1e-05,
+      "loss": 0.0045,
+      "step": 480
+    },
+    {
+      "epoch": 0.009969132564667436,
+      "grad_norm": 17.73845863342285,
+      "learning_rate": 1e-05,
+      "loss": 0.0051,
+      "step": 490
+    },
+    {
+      "epoch": 0.010172584249660648,
+      "grad_norm": 13.484848022460938,
+      "learning_rate": 1e-05,
+      "loss": 0.006,
+      "step": 500
     }
   ],
   "logging_steps": 10,