Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0266669328e80e3461a10118de44cff8735079c14f427660e06289fa00132dd
+oid sha256:89da288ea916bc87e2dc309ae736f2a5f22442c411406161ba1505c8cd18f6fd
 size 723674912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69823c3e1cc379e7cde9fa82cf2a2c9e87827da47e5463701880ad9a8a85e3b4
+oid sha256:8853aff753532a2e2c9adad78d54da494e7b9ff2ed1f437edd469bc5ab58565e
 size 735625370

last-checkpoint/trainer_state.json

@@ -11,31 +11,31 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 3.067882776260376,
-      "eval_runtime": 5.0136,
-      "eval_samples_per_second": 299.584,
-      "eval_steps_per_second": 18.749,
+      "eval_runtime": 5.0635,
+      "eval_samples_per_second": 296.633,
+      "eval_steps_per_second": 18.564,
       "step": 1
     },
     {
       "epoch": 0.011834319526627219,
       "grad_norm": 4.40625,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 2.778,
+      "loss": 2.7782,
       "step": 10
     },
     {
       "epoch": 0.023668639053254437,
-      "grad_norm": 1.640625,
+      "grad_norm": 1.6328125,
       "learning_rate": 3.2000000000000005e-05,
-      "loss": 2.8954,
+      "loss": 2.8956,
       "step": 20
     },
     {
       "epoch": 0.023668639053254437,
-      "eval_loss": 3.0601139068603516,
-      "eval_runtime": 5.1989,
-      "eval_samples_per_second": 288.907,
-      "eval_steps_per_second": 18.081,
+      "eval_loss": 3.0602526664733887,
+      "eval_runtime": 5.3059,
+      "eval_samples_per_second": 283.082,
+      "eval_steps_per_second": 17.716,
       "step": 20
     },
     {
@@ -49,15 +49,15 @@
       "epoch": 0.047337278106508875,
       "grad_norm": 1.7578125,
       "learning_rate": 6.400000000000001e-05,
-      "loss": 2.8826,
+      "loss": 2.8821,
       "step": 40
     },
     {
       "epoch": 0.047337278106508875,
-      "eval_loss": 2.956596851348877,
-      "eval_runtime": 5.2535,
-      "eval_samples_per_second": 285.902,
-      "eval_steps_per_second": 17.893,
+      "eval_loss": 2.9565436840057373,
+      "eval_runtime": 5.3075,
+      "eval_samples_per_second": 282.998,
+      "eval_steps_per_second": 17.711,
       "step": 40
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e88807ca1f23b8b745e9faf9e15e3cc183acee05b7a930af2c8542a4cad292cc
+oid sha256:ff2d010d71ffe14af88bc9959221d3983bd2a3f394734b7d7b835d485397643f
 size 6712