Upload task output 0fe99f84-0038-4cec-8e61-1eb9fea8dc55

loss.txt

@@ -1 +1 @@
-94,1.4226864576339722
+94,1.4222824573516846

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab0909463ed87ed047c9689bd5c88ff5cbd6baf5236cf377f4b8b00fa277f94
+oid sha256:a91b62ec7c4aaa49c8c51325cf89a61746ace89ce3e3b07f4e01d803481c13cc
 size 2471645608

trainer_state.json

@@ -13,42 +13,42 @@
       "epoch": 0.10638297872340426,
       "grad_norm": 6.875,
       "learning_rate": 8.8845e-06,
-      "loss": 2.3619,
+      "loss": 2.3618,
       "step": 5
     },
     {
       "epoch": 0.2127659574468085,
       "grad_norm": 4.96875,
       "learning_rate": 1.9990125e-05,
-      "loss": 2.1355,
+      "loss": 2.1356,
       "step": 10
     },
     {
       "epoch": 0.3191489361702128,
-      "grad_norm": 4.75,
+      "grad_norm": 4.71875,
       "learning_rate": 3.1095750000000005e-05,
-      "loss": 1.9609,
+      "loss": 1.9607,
       "step": 15
     },
     {
       "epoch": 0.425531914893617,
       "grad_norm": 3.9375,
       "learning_rate": 4.2201375e-05,
-      "loss": 1.8411,
+      "loss": 1.8407,
       "step": 20
     },
     {
       "epoch": 0.5319148936170213,
       "grad_norm": 3.890625,
       "learning_rate": 5.3307e-05,
-      "loss": 1.7944,
+      "loss": 1.7943,
       "step": 25
     },
     {
       "epoch": 0.6382978723404256,
-      "grad_norm": 3.9375,
+      "grad_norm": 3.921875,
       "learning_rate": 6.4412625e-05,
-      "loss": 1.7092,
+      "loss": 1.7089,
       "step": 30
     },
     {
@@ -60,9 +60,9 @@
     },
     {
       "epoch": 0.851063829787234,
-      "grad_norm": 3.75,
+      "grad_norm": 3.765625,
       "learning_rate": 7.753475804658967e-05,
-      "loss": 1.65,
+      "loss": 1.6499,
       "step": 40
     },
     {
@@ -74,81 +74,81 @@
     },
     {
       "epoch": 1.0,
-      "eval_loss": 1.5718683004379272,
-      "eval_runtime": 5.0419,
-      "eval_samples_per_second": 39.668,
-      "eval_steps_per_second": 39.668,
+      "eval_loss": 1.5716543197631836,
+      "eval_runtime": 5.0246,
+      "eval_samples_per_second": 39.804,
+      "eval_steps_per_second": 39.804,
       "step": 47
     },
     {
       "epoch": 1.0638297872340425,
-      "grad_norm": 3.5625,
+      "grad_norm": 3.59375,
       "learning_rate": 7.526567749442305e-05,
-      "loss": 1.4548,
+      "loss": 1.4545,
       "step": 50
     },
     {
       "epoch": 1.1702127659574468,
-      "grad_norm": 3.203125,
+      "grad_norm": 3.171875,
       "learning_rate": 7.323814868052365e-05,
-      "loss": 1.3195,
+      "loss": 1.319,
       "step": 55
     },
     {
       "epoch": 1.2765957446808511,
-      "grad_norm": 3.515625,
+      "grad_norm": 3.5,
       "learning_rate": 7.067027832041926e-05,
-      "loss": 1.3081,
+      "loss": 1.3079,
       "step": 60
     },
     {
       "epoch": 1.3829787234042552,
-      "grad_norm": 3.28125,
+      "grad_norm": 3.25,
       "learning_rate": 6.761835317036523e-05,
-      "loss": 1.3275,
+      "loss": 1.3272,
       "step": 65
     },
     {
       "epoch": 1.4893617021276595,
-      "grad_norm": 3.140625,
+      "grad_norm": 3.125,
       "learning_rate": 6.414927028626436e-05,
-      "loss": 1.2813,
+      "loss": 1.2809,
       "step": 70
     },
     {
       "epoch": 1.5957446808510638,
       "grad_norm": 3.265625,
       "learning_rate": 6.033907066526388e-05,
-      "loss": 1.2849,
+      "loss": 1.2853,
       "step": 75
     },
     {
       "epoch": 1.702127659574468,
-      "grad_norm": 2.859375,
+      "grad_norm": 2.875,
       "learning_rate": 5.627127245558645e-05,
-      "loss": 1.2558,
+      "loss": 1.256,
       "step": 80
     },
     {
       "epoch": 1.8085106382978724,
       "grad_norm": 2.90625,
       "learning_rate": 5.203504027001068e-05,
-      "loss": 1.2672,
+      "loss": 1.2676,
       "step": 85
     },
     {
       "epoch": 1.9148936170212765,
-      "grad_norm": 2.875,
+      "grad_norm": 2.890625,
       "learning_rate": 4.7723230730964036e-05,
-      "loss": 1.2442,
+      "loss": 1.2441,
       "step": 90
     },
     {
       "epoch": 2.0,
-      "eval_loss": 1.4226864576339722,
-      "eval_runtime": 4.9284,
-      "eval_samples_per_second": 40.581,
-      "eval_steps_per_second": 40.581,
+      "eval_loss": 1.4222824573516846,
+      "eval_runtime": 4.9323,
+      "eval_samples_per_second": 40.549,
+      "eval_steps_per_second": 40.549,
       "step": 94
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf331e6fd57c18254efcfbc196d1235b38b32362cd9d58a9b0e6317cde1e5ab3
+oid sha256:c40039de34630cebb38d81b2adb72bd9b6312651546c459581ed3475f42da829
 size 5688