Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858cbdd4617e9fa6f67945fa7327d0ae1b18d357362aca8683f033023bdff863
+oid sha256:2f71d81a39abc391eebce46adc7515ae0b09d902f940f4183c06eb5e8dae076a
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aadc7326d6f8069e28a4ac0ff148b1bdab278c7e032cd64a650f737b32de75be
+oid sha256:8005599fc82c0385b4240ca9e8c0c349710ccac8bced7e852ee2751d209091df
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377ebf34e83f44e375e092a643c390f8bb3f6c2641245139f4cac06ccd2d17c2
+oid sha256:e0e6a9f77e80f64fd6145e88fb40919fa4f2e93cb194f5ef257b88329eea0ac7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
+oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024585125998770743,
+  "epoch": 0.03073140749846343,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 12.685,
       "eval_steps_per_second": 1.591,
       "step": 20
+    },
+    {
+      "epoch": 0.02581438229870928,
+      "grad_norm": 1.7041795253753662,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.5983,
+      "step": 21
+    },
+    {
+      "epoch": 0.02950215119852489,
+      "grad_norm": 1.4558817148208618,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.5055,
+      "step": 24
+    },
+    {
+      "epoch": 0.03073140749846343,
+      "eval_loss": 0.5338066816329956,
+      "eval_runtime": 107.8606,
+      "eval_samples_per_second": 12.711,
+      "eval_steps_per_second": 1.595,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.205591354834944e+16,
+  "total_flos": 3.959848144207872e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null