Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78dd4f12f6998113698840d8eaf04bac190de6b55536950086553d622c583a81
+oid sha256:d671448e809b47fff803ad4b424807525272996fd189084742a79cb03fb08f19
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ddd0b07e329d5e2b72b151a14804fc919f97b0490e6d34168d1c9fd12d6ac6
+oid sha256:989dc02e59e39fc513350585dd1cb8c9a0e5161586b76639bc8ee5fd65d7f85f
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea003e731d402dcd02d2b25f1d347e30dc40ca30e38ec4f49bf97814daa069e
+oid sha256:033658be991992abf38fa382786ff025e0c4d1ae137bb82ba56ffad42146eaef
 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": 0.050156739811912224,
+  "epoch": 0.06269592476489028,
   "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": 13.489,
       "eval_steps_per_second": 1.686,
       "step": 20
+    },
+    {
+      "epoch": 0.052664576802507836,
+      "grad_norm": 0.3976956307888031,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 1.6016,
+      "step": 21
+    },
+    {
+      "epoch": 0.06018808777429467,
+      "grad_norm": 0.3693683445453644,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 1.6029,
+      "step": 24
+    },
+    {
+      "epoch": 0.06269592476489028,
+      "eval_loss": 1.5837934017181396,
+      "eval_runtime": 49.7929,
+      "eval_samples_per_second": 13.496,
+      "eval_steps_per_second": 1.687,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7251793985536e+16,
+  "total_flos": 3.3980632006656e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null