Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de9c7983d81c83a25d9f5af8ab2f633d7e6d24eec5b255ecd10994cf1de3e68
+oid sha256:7088e1465bec09d936d03e684198b58b239bf23505303ab77b8fed115ae83f21
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b36b33638ac27ad81d5b5cd5fa2e56673b3a7acb5c226ff0baa60d122dfdc7
+oid sha256:66dec7cc35f0f25bdf81f153d3e76317918cc977ade7398352de92638c14366b
 size 1054135994

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.7480350136756897,
+  "best_metric": 0.7474737167358398,
   "best_model_checkpoint": "./output/checkpoint-150",
   "epoch": 6.521739130434782,
   "eval_steps": 150,
@@ -10,115 +10,115 @@
   "log_history": [
     {
       "epoch": 0.43478260869565216,
-      "grad_norm": 1.5022108554840088,
+      "grad_norm": 1.5022056102752686,
       "learning_rate": 5e-06,
-      "loss": 0.9063,
+      "loss": 0.9062,
       "step": 10
     },
     {
       "epoch": 0.8695652173913043,
-      "grad_norm": 1.679484248161316,
+      "grad_norm": 1.679456114768982,
       "learning_rate": 1e-05,
       "loss": 0.9018,
       "step": 20
     },
     {
       "epoch": 1.3043478260869565,
-      "grad_norm": 1.7071681022644043,
+      "grad_norm": 1.707067608833313,
       "learning_rate": 1.5e-05,
-      "loss": 0.8972,
+      "loss": 0.8969,
       "step": 30
     },
     {
       "epoch": 1.7391304347826086,
-      "grad_norm": 1.4155817031860352,
+      "grad_norm": 1.4233026504516602,
       "learning_rate": 2e-05,
-      "loss": 0.9019,
+      "loss": 0.9022,
       "step": 40
     },
     {
       "epoch": 2.1739130434782608,
-      "grad_norm": 1.2699992656707764,
+      "grad_norm": 1.2776679992675781,
       "learning_rate": 2.5e-05,
-      "loss": 0.8208,
+      "loss": 0.8206,
       "step": 50
     },
     {
       "epoch": 2.608695652173913,
-      "grad_norm": 1.902714729309082,
+      "grad_norm": 1.9025815725326538,
       "learning_rate": 3e-05,
-      "loss": 0.865,
+      "loss": 0.8648,
       "step": 60
     },
     {
       "epoch": 3.0434782608695654,
-      "grad_norm": 1.344117283821106,
+      "grad_norm": 1.3365222215652466,
       "learning_rate": 3.5e-05,
-      "loss": 0.853,
+      "loss": 0.8532,
       "step": 70
     },
     {
       "epoch": 3.4782608695652173,
-      "grad_norm": 1.6205377578735352,
+      "grad_norm": 1.6204768419265747,
       "learning_rate": 4e-05,
-      "loss": 0.774,
+      "loss": 0.7741,
       "step": 80
     },
     {
       "epoch": 3.9130434782608696,
-      "grad_norm": 1.364487886428833,
+      "grad_norm": 1.356784701347351,
       "learning_rate": 4.5e-05,
-      "loss": 0.8004,
+      "loss": 0.8006,
       "step": 90
     },
     {
       "epoch": 4.3478260869565215,
-      "grad_norm": 1.2991905212402344,
+      "grad_norm": 1.2996201515197754,
       "learning_rate": 5e-05,
-      "loss": 0.7915,
+      "loss": 0.7921,
       "step": 100
     },
     {
       "epoch": 4.782608695652174,
-      "grad_norm": 2.0769360065460205,
+      "grad_norm": 2.0766441822052,
       "learning_rate": 4.999999504539938e-05,
-      "loss": 0.7423,
+      "loss": 0.7419,
       "step": 110
     },
     {
       "epoch": 5.217391304347826,
-      "grad_norm": 1.0391877889633179,
+      "grad_norm": 1.0354195833206177,
       "learning_rate": 4.999998018159948e-05,
-      "loss": 0.6799,
+      "loss": 0.68,
       "step": 120
     },
     {
       "epoch": 5.6521739130434785,
-      "grad_norm": 1.4947184324264526,
+      "grad_norm": 1.4931747913360596,
       "learning_rate": 4.999995540860619e-05,
-      "loss": 0.6506,
+      "loss": 0.6505,
       "step": 130
     },
     {
       "epoch": 6.086956521739131,
-      "grad_norm": 1.8294117450714111,
+      "grad_norm": 1.8289649486541748,
       "learning_rate": 4.999992072642933e-05,
-      "loss": 0.6741,
+      "loss": 0.6738,
       "step": 140
     },
     {
       "epoch": 6.521739130434782,
-      "grad_norm": 1.1097073554992676,
+      "grad_norm": 1.109723448753357,
       "learning_rate": 4.9999876135082656e-05,
       "loss": 0.6923,
       "step": 150
     },
     {
       "epoch": 6.521739130434782,
-      "eval_loss": 0.7480350136756897,
-      "eval_runtime": 0.5268,
-      "eval_samples_per_second": 18.983,
-      "eval_steps_per_second": 18.983,
+      "eval_loss": 0.7474737167358398,
+      "eval_runtime": 0.4635,
+      "eval_samples_per_second": 21.574,
+      "eval_steps_per_second": 21.574,
       "step": 150
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c534cfc3e2dd38ea6fb24a33807c3d741b1e0c48890f1270e8024ad58bfd114d
+oid sha256:f3a70fbc4ba87acefb3623b6ac3a7214d64f45e93ed5b9ac02509ef8f9f7f72d
 size 5368