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:ac1d900e5665d90be2ebc52f44bac884da863e86902d851ac0ab9f815eaa163c
+oid sha256:27577d06b2fc78d094b21e197475b42fb59442a490f65c2ea15509a1bb333b75
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6913e935f5bae19b7cb3d63bd4cc755f185976cd0f486f9dfb0eeefec8bf8d44
+oid sha256:05abbc05f7f86787a79bd7730e8881a71acabd246eaa440a9dfabd96c0c9c3ce
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216e12cbd761e9aca0f3cdd56a87b9a2e4dffe3121f3cc1f73c8df77d15b8d50
+oid sha256:e504d1ad87718d2a08149d9133473bb0f2cd6f7737a9da36c2a6648b5c301ff0
 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": 0.43333333333333335,
+  "epoch": 0.65,
   "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": 129.334,
       "eval_steps_per_second": 16.287,
       "step": 20
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.1608963012695312,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 4.5889,
+      "step": 30
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 4.342362403869629,
+      "eval_runtime": 3.2423,
+      "eval_samples_per_second": 124.91,
+      "eval_steps_per_second": 15.729,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2853148519563264.0,
+  "total_flos": 4279722779344896.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null