Add checkpoint-10800

checkpoints/checkpoint-10800/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14d1472f180428817fd03da8ec2f4a04616edd8819d75f2e2604cf053d479d55
+oid sha256:ffbfd3bbe74934dba530cad67942bc91b6eef6e24dbb1453a84adc632b0711b0
 size 4724960

checkpoints/checkpoint-10800/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a6e7329cc0676ad9b0c7c2ece80dc518471b863dab366ca0d1ec5faa4a04c6
+oid sha256:c94b375ae12b330eded9e1947780d1553a6ed603cea5df88e55eea2a5904c78d
 size 2578187

checkpoints/checkpoint-10800/trainer_state.json

@@ -7431,142 +7431,142 @@
     },
     {
       "epoch": 1.5146507726899605,
-      "grad_norm": 1.098069429397583,
+      "grad_norm": 1.0981698036193848,
       "learning_rate": 9.913830040466556e-05,
-      "loss": 2.008710479736328,
+      "loss": 2.0087039947509764,
       "step": 10610
     },
     {
       "epoch": 1.5160783753881295,
-      "grad_norm": 1.5518226623535156,
+      "grad_norm": 1.5510938167572021,
       "learning_rate": 9.904308497976673e-05,
-      "loss": 2.1474123001098633,
+      "loss": 2.1474151611328125,
       "step": 10620
     },
     {
       "epoch": 1.5175059780862985,
-      "grad_norm": 1.2088004350662231,
+      "grad_norm": 1.2088773250579834,
       "learning_rate": 9.894786955486789e-05,
-      "loss": 2.0725215911865233,
+      "loss": 2.072478103637695,
       "step": 10630
     },
     {
       "epoch": 1.5189335807844677,
-      "grad_norm": 1.0846376419067383,
+      "grad_norm": 1.0845247507095337,
       "learning_rate": 9.885265412996906e-05,
-      "loss": 2.015618896484375,
+      "loss": 2.015526008605957,
       "step": 10640
     },
     {
       "epoch": 1.520361183482637,
-      "grad_norm": 1.201206088066101,
+      "grad_norm": 1.2015031576156616,
       "learning_rate": 9.875743870507023e-05,
-      "loss": 2.106952667236328,
+      "loss": 2.1070165634155273,
       "step": 10650
     },
     {
       "epoch": 1.521788786180806,
-      "grad_norm": 1.0636956691741943,
+      "grad_norm": 1.062964677810669,
       "learning_rate": 9.86622232801714e-05,
-      "loss": 2.0599929809570314,
+      "loss": 2.0601083755493166,
       "step": 10660
     },
     {
       "epoch": 1.523216388878975,
-      "grad_norm": 1.1827208995819092,
+      "grad_norm": 1.1827353239059448,
       "learning_rate": 9.856700785527256e-05,
-      "loss": 2.2304359436035157,
+      "loss": 2.230342674255371,
       "step": 10670
     },
     {
       "epoch": 1.5246439915771441,
-      "grad_norm": 1.2152652740478516,
+      "grad_norm": 1.2147736549377441,
       "learning_rate": 9.847179243037372e-05,
-      "loss": 2.083365631103516,
+      "loss": 2.083346366882324,
       "step": 10680
     },
     {
       "epoch": 1.5260715942753131,
-      "grad_norm": 1.0766453742980957,
+      "grad_norm": 1.0761597156524658,
       "learning_rate": 9.837657700547489e-05,
-      "loss": 2.119212341308594,
+      "loss": 2.1192899703979493,
       "step": 10690
     },
     {
       "epoch": 1.5274991969734821,
-      "grad_norm": 1.2730481624603271,
+      "grad_norm": 1.2726013660430908,
       "learning_rate": 9.828136158057606e-05,
-      "loss": 2.1518115997314453,
+      "loss": 2.1517145156860353,
       "step": 10700
     },
     {
       "epoch": 1.5289267996716513,
-      "grad_norm": 1.97091805934906,
+      "grad_norm": 1.9693447351455688,
       "learning_rate": 9.818614615567723e-05,
-      "loss": 1.9795692443847657,
+      "loss": 1.97952880859375,
       "step": 10710
     },
     {
       "epoch": 1.5303544023698206,
-      "grad_norm": 1.3302141427993774,
+      "grad_norm": 1.3304651975631714,
       "learning_rate": 9.809093073077838e-05,
-      "loss": 1.9785017013549804,
+      "loss": 1.9785858154296876,
       "step": 10720
     },
     {
       "epoch": 1.5317820050679896,
-      "grad_norm": 1.2388334274291992,
+      "grad_norm": 1.2396725416183472,
       "learning_rate": 9.799571530587955e-05,
-      "loss": 2.134817695617676,
+      "loss": 2.1346342086791994,
       "step": 10730
     },
     {
       "epoch": 1.5332096077661586,
-      "grad_norm": 1.4161068201065063,
+      "grad_norm": 1.413583517074585,
       "learning_rate": 9.790049988098072e-05,
-      "loss": 1.9905515670776368,
+      "loss": 1.9904579162597655,
       "step": 10740
     },
     {
       "epoch": 1.5346372104643278,
-      "grad_norm": 1.2048768997192383,
+      "grad_norm": 1.2050212621688843,
       "learning_rate": 9.780528445608189e-05,
-      "loss": 2.0450416564941407,
+      "loss": 2.045025444030762,
       "step": 10750
     },
     {
       "epoch": 1.536064813162497,
-      "grad_norm": 1.3425582647323608,
+      "grad_norm": 1.3423675298690796,
       "learning_rate": 9.771006903118306e-05,
-      "loss": 1.923790740966797,
+      "loss": 1.9239255905151367,
       "step": 10760
     },
     {
       "epoch": 1.537492415860666,
-      "grad_norm": 1.2138093709945679,
+      "grad_norm": 1.2138278484344482,
       "learning_rate": 9.761485360628421e-05,
-      "loss": 2.0516876220703124,
+      "loss": 2.0515163421630858,
       "step": 10770
     },
     {
       "epoch": 1.538920018558835,
-      "grad_norm": 1.098336100578308,
+      "grad_norm": 1.0984469652175903,
       "learning_rate": 9.751963818138538e-05,
-      "loss": 1.9940862655639648,
+      "loss": 1.9942876815795898,
       "step": 10780
     },
     {
       "epoch": 1.5403476212570042,
-      "grad_norm": 1.2795876264572144,
+      "grad_norm": 1.2791671752929688,
       "learning_rate": 9.742442275648655e-05,
-      "loss": 2.000428581237793,
+      "loss": 2.0003101348876955,
       "step": 10790
     },
     {
       "epoch": 1.5417752239551734,
-      "grad_norm": 1.0763850212097168,
+      "grad_norm": 1.0745598077774048,
       "learning_rate": 9.732920733158772e-05,
-      "loss": 1.9592803955078124,
+      "loss": 1.9592748641967774,
       "step": 10800
     }
   ],