Training in progress, epoch 2, checkpoint

checkpoint-42/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bdc5f45c2a021f1b1e258000a3088deaa08bf3eb071ac9e5941ac2537d7189a
+oid sha256:c25d431b0e4228a64b3adf37627edd17a3b5746a453123534e2eb1aa7a5d4387
 size 3086640776

checkpoint-42/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f831e2a223998d0c26027b4a1d28838f4acf1ce6cf4eb13c859d915721c30942
+oid sha256:4d5147b8adce7faa24163e13635f7441cf54bac23118e11d434890a06b4e26a5
 size 6056331

checkpoint-42/trainer_state.json

@@ -11,296 +11,296 @@
   "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
     },
     {
       "epoch": 1.048780487804878,
-      "grad_norm": 44.0,
+      "grad_norm": 47.25,
       "learning_rate": 4.267766952966369e-05,
-      "loss": 1.4364,
+      "loss": 1.3246,
       "step": 22
     },
     {
       "epoch": 1.0975609756097562,
-      "grad_norm": 44.25,
+      "grad_norm": 40.25,
       "learning_rate": 4.16586644488001e-05,
-      "loss": 1.3537,
+      "loss": 1.1731,
       "step": 23
     },
     {
       "epoch": 1.146341463414634,
-      "grad_norm": 37.0,
+      "grad_norm": 44.75,
       "learning_rate": 4.058724504646834e-05,
-      "loss": 1.1017,
+      "loss": 1.14,
       "step": 24
     },
     {
       "epoch": 1.1951219512195121,
-      "grad_norm": 40.25,
+      "grad_norm": 33.75,
       "learning_rate": 3.946678240449515e-05,
-      "loss": 1.0232,
+      "loss": 1.0197,
       "step": 25
     },
     {
       "epoch": 1.2439024390243902,
-      "grad_norm": 34.25,
+      "grad_norm": 31.25,
       "learning_rate": 3.830080191288342e-05,
-      "loss": 0.9218,
+      "loss": 0.9634,
       "step": 26
     },
     {
       "epoch": 1.2926829268292683,
-      "grad_norm": 27.125,
+      "grad_norm": 26.75,
       "learning_rate": 3.7092972177631e-05,
-      "loss": 0.8892,
+      "loss": 1.0227,
       "step": 27
     },
     {
       "epoch": 1.3414634146341464,
-      "grad_norm": 25.0,
+      "grad_norm": 22.875,
       "learning_rate": 3.5847093477938956e-05,
-      "loss": 0.9091,
+      "loss": 0.8732,
       "step": 28
     },
     {
       "epoch": 1.3902439024390243,
-      "grad_norm": 22.5,
+      "grad_norm": 19.0,
       "learning_rate": 3.456708580912725e-05,
-      "loss": 0.9093,
+      "loss": 0.8081,
       "step": 29
     },
     {
       "epoch": 1.4390243902439024,
-      "grad_norm": 23.625,
+      "grad_norm": 18.25,
       "learning_rate": 3.3256976548879184e-05,
-      "loss": 0.846,
+      "loss": 0.7939,
       "step": 30
     },
     {
       "epoch": 1.4878048780487805,
-      "grad_norm": 19.375,
+      "grad_norm": 13.0,
       "learning_rate": 3.1920887785621235e-05,
-      "loss": 0.7321,
+      "loss": 0.7528,
       "step": 31
     },
     {
       "epoch": 1.5365853658536586,
-      "grad_norm": 15.6875,
+      "grad_norm": 31.0,
       "learning_rate": 3.056302334890786e-05,
-      "loss": 0.7505,
+      "loss": 0.8375,
       "step": 32
     },
     {
       "epoch": 1.5853658536585367,
-      "grad_norm": 16.5,
+      "grad_norm": 47.5,
       "learning_rate": 2.918765558261841e-05,
-      "loss": 0.7204,
+      "loss": 1.1202,
       "step": 33
     },
     {
       "epoch": 1.6341463414634148,
-      "grad_norm": 13.25,
+      "grad_norm": 40.75,
       "learning_rate": 2.7799111902582696e-05,
-      "loss": 0.6878,
+      "loss": 0.9477,
       "step": 34
     },
     {
       "epoch": 1.6829268292682928,
-      "grad_norm": 15.0,
+      "grad_norm": 22.0,
       "learning_rate": 2.6401761180929797e-05,
-      "loss": 0.6356,
+      "loss": 0.7566,
       "step": 35
     },
     {
       "epoch": 1.7317073170731707,
-      "grad_norm": 14.3125,
+      "grad_norm": 9.6875,
       "learning_rate": 2.5e-05,
-      "loss": 0.6332,
+      "loss": 0.7021,
       "step": 36
     },
     {
       "epoch": 1.7804878048780488,
-      "grad_norm": 9.9375,
+      "grad_norm": 9.5,
       "learning_rate": 2.3598238819070202e-05,
-      "loss": 0.6806,
+      "loss": 0.6245,
       "step": 37
     },
     {
       "epoch": 1.8292682926829267,
-      "grad_norm": 11.5,
+      "grad_norm": 7.28125,
       "learning_rate": 2.2200888097417307e-05,
-      "loss": 0.6415,
+      "loss": 0.575,
       "step": 38
     },
     {
       "epoch": 1.8780487804878048,
-      "grad_norm": 9.75,
+      "grad_norm": 5.78125,
       "learning_rate": 2.0812344417381595e-05,
-      "loss": 0.5846,
+      "loss": 0.6548,
       "step": 39
     },
     {
       "epoch": 1.9268292682926829,
-      "grad_norm": 10.25,
+      "grad_norm": 5.1875,
       "learning_rate": 1.9436976651092144e-05,
-      "loss": 0.5771,
+      "loss": 0.603,
       "step": 40
     },
     {
       "epoch": 1.975609756097561,
-      "grad_norm": 7.75,
+      "grad_norm": 4.71875,
       "learning_rate": 1.8079112214378768e-05,
-      "loss": 0.6536,
+      "loss": 0.5833,
       "step": 41
     },
     {
       "epoch": 2.0,
-      "grad_norm": 8.125,
+      "grad_norm": 5.125,
       "learning_rate": 1.6743023451120832e-05,
-      "loss": 0.6518,
+      "loss": 0.541,
       "step": 42
     }
   ],

checkpoint-42/training_args.bin

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