Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:296d3c11b549378809925dc5abeb8f0a62cd642b0dd4f1e0fe503271668e5fc2
+oid sha256:b0266669328e80e3461a10118de44cff8735079c14f427660e06289fa00132dd
 size 723674912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:367d828c50db3ed18885e248d3bf5cab302f7bbff0a88bfb288efcaaa6d12bcd
+oid sha256:69823c3e1cc379e7cde9fa82cf2a2c9e87827da47e5463701880ad9a8a85e3b4
 size 735625370

last-checkpoint/trainer_state.json

@@ -11,53 +11,53 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 3.067882776260376,
-      "eval_runtime": 5.1514,
-      "eval_samples_per_second": 291.572,
-      "eval_steps_per_second": 18.248,
+      "eval_runtime": 5.0136,
+      "eval_samples_per_second": 299.584,
+      "eval_steps_per_second": 18.749,
       "step": 1
     },
     {
       "epoch": 0.011834319526627219,
       "grad_norm": 4.40625,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 2.7777,
+      "loss": 2.778,
       "step": 10
     },
     {
       "epoch": 0.023668639053254437,
       "grad_norm": 1.640625,
       "learning_rate": 3.2000000000000005e-05,
-      "loss": 2.894,
+      "loss": 2.8954,
       "step": 20
     },
     {
       "epoch": 0.023668639053254437,
-      "eval_loss": 3.0597116947174072,
-      "eval_runtime": 5.678,
-      "eval_samples_per_second": 264.528,
-      "eval_steps_per_second": 16.555,
+      "eval_loss": 3.0601139068603516,
+      "eval_runtime": 5.1989,
+      "eval_samples_per_second": 288.907,
+      "eval_steps_per_second": 18.081,
       "step": 20
     },
     {
       "epoch": 0.03550295857988166,
       "grad_norm": 6.0625,
       "learning_rate": 4.8e-05,
-      "loss": 3.02,
+      "loss": 3.0194,
       "step": 30
     },
     {
       "epoch": 0.047337278106508875,
       "grad_norm": 1.7578125,
       "learning_rate": 6.400000000000001e-05,
-      "loss": 2.8817,
+      "loss": 2.8826,
       "step": 40
     },
     {
       "epoch": 0.047337278106508875,
-      "eval_loss": 2.9575068950653076,
-      "eval_runtime": 5.5448,
-      "eval_samples_per_second": 270.884,
-      "eval_steps_per_second": 16.953,
+      "eval_loss": 2.956596851348877,
+      "eval_runtime": 5.2535,
+      "eval_samples_per_second": 285.902,
+      "eval_steps_per_second": 17.893,
       "step": 40
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c13eb177f9a4df885b8c30c848aa7cef22c2095d626ae8c593587f9a5d8892d1
+oid sha256:e88807ca1f23b8b745e9faf9e15e3cc183acee05b7a930af2c8542a4cad292cc
 size 6712