Training in progress, step 100, checkpoint

checkpoint-100/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dad9eb4b1efbad28aea8f018a1897c76896b4941573bf80265f8cc5d2c868c5
+oid sha256:a3db2878ca08dafc431af2adfab3f8ff00736cb2e4a14c256c6b34ed026ee96a
 size 1346677820

checkpoint-100/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5037634ffb7ba97b4e36118ac6cc20b10c00f7ff9d71920a130e62fae092aa4
+oid sha256:e32c628bfe215a0ca1b674f3e51fbe79cf178c28a8ab5797679d283700f16337
 size 2693490234

checkpoint-100/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e331387bfdf39d614a89566ac24349cfd9803925c5b279368379dd11dea9927b
+oid sha256:7d80e6a0be9cb24225e41419925947599179c2c859f0ef4a537989723030d298
 size 1064

checkpoint-100/trainer_state.json

@@ -10,71 +10,71 @@
   "log_history": [
     {
       "epoch": 0.03,
-      "learning_rate": 4.991324875275794e-05,
-      "loss": 0.5919,
+      "learning_rate": 8.984384775496429e-05,
+      "loss": 0.6651,
       "step": 10
     },
     {
       "epoch": 0.05,
-      "learning_rate": 4.9653597073343594e-05,
-      "loss": 0.416,
+      "learning_rate": 8.937647473201847e-05,
+      "loss": 0.5741,
       "step": 20
     },
     {
       "epoch": 0.08,
-      "learning_rate": 4.922284697031999e-05,
-      "loss": 0.3812,
+      "learning_rate": 8.860112454657597e-05,
+      "loss": 0.6273,
       "step": 30
     },
     {
       "epoch": 0.11,
-      "learning_rate": 4.8623987892382066e-05,
-      "loss": 0.3123,
+      "learning_rate": 8.752317820628772e-05,
+      "loss": 0.6055,
       "step": 40
     },
     {
       "epoch": 0.13,
-      "learning_rate": 4.78611759812845e-05,
-      "loss": 0.3611,
+      "learning_rate": 8.615011676631211e-05,
+      "loss": 0.631,
       "step": 50
     },
     {
       "epoch": 0.16,
-      "learning_rate": 4.69397052278032e-05,
-      "loss": 0.2925,
+      "learning_rate": 8.449146941004577e-05,
+      "loss": 0.5563,
       "step": 60
     },
     {
       "epoch": 0.19,
-      "learning_rate": 4.586597073091109e-05,
-      "loss": 0.3014,
+      "learning_rate": 8.255874731563996e-05,
+      "loss": 0.5987,
       "step": 70
     },
     {
       "epoch": 0.21,
-      "learning_rate": 4.464742431515315e-05,
-      "loss": 0.3692,
+      "learning_rate": 8.036536376727568e-05,
+      "loss": 0.708,
       "step": 80
     },
     {
       "epoch": 0.24,
-      "learning_rate": 4.329252281424052e-05,
-      "loss": 0.2641,
+      "learning_rate": 7.792654106563294e-05,
+      "loss": 0.6866,
       "step": 90
     },
     {
       "epoch": 0.26,
-      "learning_rate": 4.181066937978075e-05,
-      "loss": 0.2579,
+      "learning_rate": 7.525920488360535e-05,
+      "loss": 0.7099,
       "step": 100
     },
     {
       "epoch": 0.26,
-      "eval_accuracy": 0.0,
-      "eval_loss": 0.2431439310312271,
-      "eval_runtime": 18.0196,
-      "eval_samples_per_second": 139.681,
-      "eval_steps_per_second": 23.308,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.6931471824645996,
+      "eval_runtime": 18.0135,
+      "eval_samples_per_second": 139.729,
+      "eval_steps_per_second": 23.316,
       "step": 100
     }
   ],

checkpoint-100/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4bf9ecae2307ca9bbd9fe1c57912f7d948edc1e67b4abcfb70aa587b25fece0
+oid sha256:2eed65b083da18ef9ecec430c1bb279c4e7df84418268e31d42af7a996847243
 size 4664