Training in progress, step 160, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5deddc4532a7e43a9d0f9fbe82070649a4eb6e36c4c10045bb971c255475d45
+oid sha256:38a00591a10d82f6557751ef50942d0ad93eeda3f86a7c867897288c8d46be94
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930c0e2ebbffa6eaa81c1c13cb56bae07035671452615a27785b151dda07ab8f
+oid sha256:218ed3f5c01b608a4eab64004982b2a70a6a0c504c2a4c9cdff60b6a404df174
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfad5b1db434a4570e357f1971d87bf80fdc19c2e91af8a74bce9bbf251a95cc
+oid sha256:befd409d384ef0f0f1c800aced192285a039968aa574627a06cdbfeed65d40df
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40d5e94eed411043d006187ef3d57f655338dfd7cfaaf34e38342dbbae53acc
+oid sha256:1fb3a39b961047b7cdf3f3152552e802c79a68dc6cf0def914d9209b6b209d37
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7,
+  "epoch": 0.8,
   "eval_steps": 20,
-  "global_step": 140,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,43 @@
       "eval_samples_per_second": 398.045,
       "eval_steps_per_second": 66.473,
       "step": 140
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.2701219916343689,
+      "learning_rate": 7.978377054339498e-07,
+      "loss": 21.985748291015625,
+      "step": 145
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.24651674926280975,
+      "learning_rate": 6.699508557723032e-07,
+      "loss": 22.00152130126953,
+      "step": 150
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.26024770736694336,
+      "learning_rate": 5.511495904178221e-07,
+      "loss": 22.02308044433594,
+      "step": 155
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.25778868794441223,
+      "learning_rate": 4.4224544247577535e-07,
+      "loss": 21.997288513183594,
+      "step": 160
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 3.1746031746031745e-05,
+      "eval_loss": 11.007829666137695,
+      "eval_runtime": 2.7386,
+      "eval_samples_per_second": 365.156,
+      "eval_steps_per_second": 60.981,
+      "step": 160
     }
   ],
   "logging_steps": 5,