Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cbeeecf5f33a8fe98f465a7ebe436fa13049f32a089a744575f64c982ba6f45
+oid sha256:86c0b967524dfce05ac02dfb34086d01c2212c208daec09e8e093ba97faff356
 size 471641972

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c6070216d6484067400562a6849b4c72f15f3f6816280335b442d080a2a835
+oid sha256:f8139a2ef975cd69d424b05a8163888a752474327f41ca0821c02596cc4d9b0c
 size 943408715

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54f743afad260d48a721280fb087e2db9d559da17786d4f25babaf33caec1409
+oid sha256:e41409469bcb86e30ac3d1d2dddf57cacc620d120f60f2c25eb795e483356deb
 size 1383

last-checkpoint/trainer_state.json

@@ -11,79 +11,79 @@
   "log_history": [
     {
       "epoch": 0.00010152026598309688,
-      "grad_norm": 22.092256546020508,
+      "grad_norm": 20.906557083129883,
       "learning_rate": 0.0,
-      "loss": 13.7932,
+      "loss": 13.5217,
       "step": 1
     },
     {
       "epoch": 0.010152026598309688,
-      "grad_norm": 32.477996826171875,
+      "grad_norm": 33.71811294555664,
       "learning_rate": 2.008113590263692e-05,
-      "loss": 10.8313,
+      "loss": 10.8681,
       "step": 100
     },
     {
       "epoch": 0.020304053196619376,
-      "grad_norm": 23.895782470703125,
+      "grad_norm": 27.14719581604004,
       "learning_rate": 4.036511156186613e-05,
-      "loss": 7.3668,
+      "loss": 7.3949,
       "step": 200
     },
     {
       "epoch": 0.030456079794929064,
-      "grad_norm": 20.44896697998047,
+      "grad_norm": 22.181039810180664,
       "learning_rate": 6.064908722109534e-05,
-      "loss": 5.9214,
+      "loss": 5.9034,
       "step": 300
     },
     {
       "epoch": 0.04060810639323875,
-      "grad_norm": 12.489410400390625,
+      "grad_norm": 14.685601234436035,
       "learning_rate": 8.093306288032456e-05,
-      "loss": 5.0598,
+      "loss": 5.0405,
       "step": 400
     },
     {
       "epoch": 0.05076013299154844,
-      "grad_norm": 11.84785270690918,
+      "grad_norm": 12.026344299316406,
       "learning_rate": 9.9935883735841e-05,
-      "loss": 4.5018,
+      "loss": 4.4838,
       "step": 500
     },
     {
       "epoch": 0.06091215958985813,
-      "grad_norm": 10.175586700439453,
+      "grad_norm": 14.332210540771484,
       "learning_rate": 9.886727933319086e-05,
-      "loss": 4.1055,
+      "loss": 4.0977,
       "step": 600
     },
     {
       "epoch": 0.07106418618816782,
-      "grad_norm": 8.461668014526367,
+      "grad_norm": 10.582870483398438,
       "learning_rate": 9.779867493054072e-05,
-      "loss": 3.813,
+      "loss": 3.8085,
       "step": 700
     },
     {
       "epoch": 0.0812162127864775,
-      "grad_norm": 8.445116996765137,
+      "grad_norm": 8.66326904296875,
       "learning_rate": 9.673007052789058e-05,
-      "loss": 3.6419,
+      "loss": 3.6189,
       "step": 800
     },
     {
       "epoch": 0.09136823938478719,
-      "grad_norm": 8.415114402770996,
+      "grad_norm": 8.398235321044922,
       "learning_rate": 9.566146612524043e-05,
-      "loss": 3.4315,
+      "loss": 3.4115,
       "step": 900
     },
     {
       "epoch": 0.10152026598309688,
-      "grad_norm": 8.78720760345459,
+      "grad_norm": 8.620134353637695,
       "learning_rate": 9.45928617225903e-05,
-      "loss": 3.3252,
+      "loss": 3.3107,
       "step": 1000
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f6d2140fda77ba220cd4e909f52c6a71604647d304e3a03f975d883e07d792e
+oid sha256:c2f5d55b83ef38d668a8df30659376d55e51ae6c9a754af891a613a6e26ed40b
 size 5905