Training in progress, epoch 1, checkpoint

checkpoint-21/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c74ad5b283dd0f658cafa4d578a3bbcb4f25dcd809c4cb9003deb2359130ac1
+oid sha256:8ad72e757370b0af83a5a02b9d8c803f27d8f9c346657d034b0c1299a2e67cb6
 size 3086640776

checkpoint-21/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b13dcd75ad277f8235be9d791062a9d73b8e21ec4100c87c9f559541a131b3
+oid sha256:f242db142262926b014c870ddab2206224f7f30dcaf88592583be1f598a13adc
 size 6056331

checkpoint-21/trainer_state.json

@@ -11,149 +11,149 @@
   "log_history": [
     {
       "epoch": 0.04878048780487805,
-      "grad_norm": 126.0,
+      "grad_norm": 119.5,
       "learning_rate": 0.0,
-      "loss": 6.3712,
+      "loss": 6.2132,
       "step": 1
     },
     {
       "epoch": 0.0975609756097561,
-      "grad_norm": 139.0,
+      "grad_norm": 132.0,
       "learning_rate": 7.142857142857143e-06,
-      "loss": 6.9747,
+      "loss": 6.6559,
       "step": 2
     },
     {
       "epoch": 0.14634146341463414,
-      "grad_norm": 141.0,
+      "grad_norm": 128.0,
       "learning_rate": 1.4285714285714285e-05,
-      "loss": 7.2169,
+      "loss": 6.6652,
       "step": 3
     },
     {
       "epoch": 0.1951219512195122,
-      "grad_norm": 135.0,
+      "grad_norm": 129.0,
       "learning_rate": 2.1428571428571428e-05,
-      "loss": 6.3792,
+      "loss": 6.1414,
       "step": 4
     },
     {
       "epoch": 0.24390243902439024,
-      "grad_norm": 356.0,
+      "grad_norm": 348.0,
       "learning_rate": 2.857142857142857e-05,
-      "loss": 5.1872,
+      "loss": 5.1096,
       "step": 5
     },
     {
       "epoch": 0.2926829268292683,
-      "grad_norm": 158.0,
+      "grad_norm": 165.0,
       "learning_rate": 3.571428571428572e-05,
-      "loss": 5.7681,
+      "loss": 5.2497,
       "step": 6
     },
     {
       "epoch": 0.34146341463414637,
-      "grad_norm": 149.0,
+      "grad_norm": 136.0,
       "learning_rate": 4.2857142857142856e-05,
-      "loss": 4.4005,
+      "loss": 4.3006,
       "step": 7
     },
     {
       "epoch": 0.3902439024390244,
-      "grad_norm": 134.0,
+      "grad_norm": 150.0,
       "learning_rate": 5e-05,
-      "loss": 5.056,
+      "loss": 5.1854,
       "step": 8
     },
     {
       "epoch": 0.43902439024390244,
-      "grad_norm": 94.5,
+      "grad_norm": 213.0,
       "learning_rate": 4.996067037544542e-05,
-      "loss": 4.2935,
+      "loss": 8.1666,
       "step": 9
     },
     {
       "epoch": 0.4878048780487805,
-      "grad_norm": 212.0,
+      "grad_norm": 137.0,
       "learning_rate": 4.984280524733107e-05,
-      "loss": 8.9937,
+      "loss": 9.5804,
       "step": 10
     },
     {
       "epoch": 0.5365853658536586,
-      "grad_norm": 302.0,
+      "grad_norm": 65.0,
       "learning_rate": 4.96467754629559e-05,
-      "loss": 4.9127,
+      "loss": 5.2593,
       "step": 11
     },
     {
       "epoch": 0.5853658536585366,
-      "grad_norm": 44.5,
+      "grad_norm": 40.25,
       "learning_rate": 4.937319780454559e-05,
-      "loss": 4.4251,
+      "loss": 3.9807,
       "step": 12
     },
     {
       "epoch": 0.6341463414634146,
-      "grad_norm": 39.25,
+      "grad_norm": 39.75,
       "learning_rate": 4.9022933048627496e-05,
-      "loss": 3.6691,
+      "loss": 3.7199,
       "step": 13
     },
     {
       "epoch": 0.6829268292682927,
-      "grad_norm": 31.25,
+      "grad_norm": 50.0,
       "learning_rate": 4.8597083257709194e-05,
-      "loss": 3.232,
+      "loss": 3.3626,
       "step": 14
     },
     {
       "epoch": 0.7317073170731707,
-      "grad_norm": 44.25,
+      "grad_norm": 44.5,
       "learning_rate": 4.8096988312782174e-05,
-      "loss": 3.1154,
+      "loss": 3.156,
       "step": 15
     },
     {
       "epoch": 0.7804878048780488,
-      "grad_norm": 43.75,
+      "grad_norm": 43.5,
       "learning_rate": 4.752422169756048e-05,
-      "loss": 2.6809,
+      "loss": 2.62,
       "step": 16
     },
     {
       "epoch": 0.8292682926829268,
-      "grad_norm": 41.0,
+      "grad_norm": 47.5,
       "learning_rate": 4.6880585547718845e-05,
-      "loss": 2.1384,
+      "loss": 2.4872,
       "step": 17
     },
     {
       "epoch": 0.8780487804878049,
-      "grad_norm": 50.0,
+      "grad_norm": 44.5,
       "learning_rate": 4.6168104980707107e-05,
-      "loss": 2.0084,
+      "loss": 2.0436,
       "step": 18
     },
     {
       "epoch": 0.926829268292683,
-      "grad_norm": 48.25,
+      "grad_norm": 50.5,
       "learning_rate": 4.538902172398151e-05,
-      "loss": 1.8335,
+      "loss": 1.9184,
       "step": 19
     },
     {
       "epoch": 0.975609756097561,
-      "grad_norm": 50.0,
+      "grad_norm": 55.5,
       "learning_rate": 4.454578706170075e-05,
-      "loss": 1.6659,
+      "loss": 1.8052,
       "step": 20
     },
     {
       "epoch": 1.0,
-      "grad_norm": 50.75,
+      "grad_norm": 41.75,
       "learning_rate": 4.364105412207914e-05,
-      "loss": 1.5889,
+      "loss": 1.4898,
       "step": 21
     }
   ],

checkpoint-21/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:807175855d5dd743e81254531a1a0148b2ade3b9521c50fa1999cea9a77e0a70
+oid sha256:841e48b365d43c1bb533dc5dd460b128556952c5da32bc814c2b5072cc6bb501
 size 5969