Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6a3c998de94abc67fbee95d8b2d69ac9ad3f7d0b0e9cb026855881010841232
+oid sha256:e717cd7d738bd5e96a1b1469aa1331e2f22e70545ffc078ce9636376af05d885
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8608622efe9031bc9ed0b754de2302e813446e69ce45f9be3c5d49a1bca5e60
+oid sha256:14ffa9d55dd1bcd75ae126916ffb5f005494ea4e1bd5163a7fb115a7707c128e
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ab0f96d910ec29ccaf274451f94a01bb1f9f7873169ad5878c5dcbf1ef8780
+oid sha256:6cbef803672d9e5971d2ad2e53a1d5bd4e2e7ffcb27f457a3be325d0c6d836bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4360587002096436,
+  "epoch": 0.6540880503144654,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 17.712,
       "eval_steps_per_second": 2.247,
       "step": 20
+    },
+    {
+      "epoch": 0.5031446540880503,
+      "grad_norm": 2.6368815898895264,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.5338,
+      "step": 30
+    },
+    {
+      "epoch": 0.5031446540880503,
+      "eval_loss": 3.3421852588653564,
+      "eval_runtime": 22.6281,
+      "eval_samples_per_second": 17.766,
+      "eval_steps_per_second": 2.254,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.607527748206592e+16,
+  "total_flos": 8.369548239568896e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null