Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa3494fcf8494e09510fdd6776d0909cf904525f8cd5f22a4471c95b1e88171
+oid sha256:908d63b2fb95e71a4b8ee8cd59f37ef260ee9dd802b3a17cb85987465ed26fc2
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c507e6a606d3533b83e8f04601bd517d0a24ef5e596488e4b831b5b264ac9765
+oid sha256:95b772b50d78c29d75a1c5944f3fcaf71a43acfdc8bc9012b0e89bacc4c8bb3a
 size 2911851147

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33636888fde43e822c3af154b63f927ea6cf358e4f8066b8af48942935ee0380
+oid sha256:45aec2cb58874aade57e0968443233716fc5740d4d156942f30784ba9a8ef170
 size 1465

last-checkpoint/trainer_state.json

@@ -11,72 +11,72 @@
   "log_history": [
     {
       "epoch": 0.005,
-      "grad_norm": 2.8277900218963623,
-      "learning_rate": 1.125e-05,
-      "loss": 7.685114135742188,
+      "grad_norm": 7.283497333526611,
+      "learning_rate": 2.7e-06,
+      "loss": 9.9652685546875,
       "step": 50
     },
     {
       "epoch": 0.01,
-      "grad_norm": 2.2731411457061768,
-      "learning_rate": 2.2250000000000002e-05,
-      "loss": 5.033958129882812,
+      "grad_norm": 2.230577230453491,
+      "learning_rate": 5.34e-06,
+      "loss": 7.3708349609375,
       "step": 100
     },
     {
       "epoch": 0.015,
-      "grad_norm": 3.3346173763275146,
-      "learning_rate": 3.35e-05,
-      "loss": 4.662413940429688,
+      "grad_norm": 2.9674696922302246,
+      "learning_rate": 8.040000000000001e-06,
+      "loss": 6.394255981445313,
       "step": 150
     },
     {
       "epoch": 0.02,
-      "grad_norm": 3.638383626937866,
-      "learning_rate": 4.4750000000000004e-05,
-      "loss": 5.785809936523438,
+      "grad_norm": 5.306502819061279,
+      "learning_rate": 1.074e-05,
+      "loss": 6.023402709960937,
       "step": 200
     },
     {
       "epoch": 0.025,
-      "grad_norm": 2.827432632446289,
-      "learning_rate": 4.999919714835816e-05,
-      "loss": 7.300284423828125,
+      "grad_norm": 4.985537528991699,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 6.261904907226563,
       "step": 250
     },
     {
       "epoch": 0.03,
-      "grad_norm": 2.6586380004882812,
-      "learning_rate": 4.999277464461405e-05,
-      "loss": 8.245166625976562,
+      "grad_norm": 3.5350327491760254,
+      "learning_rate": 1.65e-05,
+      "loss": 5.984814453125,
       "step": 300
     },
     {
       "epoch": 0.035,
-      "grad_norm": 2.42388653755188,
-      "learning_rate": 4.9979931287121e-05,
-      "loss": 9.312975463867188,
+      "grad_norm": 2.3650736808776855,
+      "learning_rate": 1.95e-05,
+      "loss": 5.866536865234375,
       "step": 350
     },
     {
       "epoch": 0.04,
-      "grad_norm": 2.5717973709106445,
-      "learning_rate": 4.996067037544542e-05,
-      "loss": 10.216683959960937,
+      "grad_norm": 2.358975410461426,
+      "learning_rate": 2.25e-05,
+      "loss": 6.0157708740234375,
       "step": 400
     },
     {
       "epoch": 0.045,
-      "grad_norm": 2.759148120880127,
-      "learning_rate": 4.9934996857877325e-05,
-      "loss": 11.017779541015624,
+      "grad_norm": 2.671454429626465,
+      "learning_rate": 2.55e-05,
+      "loss": 6.32117919921875,
       "step": 450
     },
     {
       "epoch": 0.05,
-      "grad_norm": 2.2197604179382324,
-      "learning_rate": 4.9902917330159036e-05,
-      "loss": 11.715665283203125,
+      "grad_norm": 2.476318359375,
+      "learning_rate": 2.8499999999999998e-05,
+      "loss": 6.613551025390625,
       "step": 500
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225acaab3a1a242c2547c8df2938f709d9aa8d25d7392a8bfbd69b716ce99f83
+oid sha256:8218109d1326f8c1ac6726090711a5aba11863a6b5c0e468b0d65fe929b9028b
 size 5329