Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a107b193279e45b3c47d625dbffc72bdf31bd36a58097516c0af99d322be39d
+oid sha256:642ffa225cfc37eb3950b46377e1fb36b3a88eecb914b46c19deb6bddc96ea87
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23ba1378d182d69c9d07eae2084ea1184f08f80c66b5c2fc8410d0286692fe7
+oid sha256:ba1a5853b36a7fef1cd186f0195bd84f890aed8c680cb524c42f030f2fadc733
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc1ecde98f5cd453994b34432b806c3d96cdc21302732cdbc449d980e314ce4
+oid sha256:b4354b002b0e16e2abd91ac430264dba7c8abdcb9e893965eaff59257f182181
 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": 0.03771805752003772,
+  "epoch": 0.04714757190004715,
   "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": 12.971,
       "eval_steps_per_second": 1.627,
       "step": 20
+    },
+    {
+      "epoch": 0.039603960396039604,
+      "grad_norm": 0.2421295940876007,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 1.2654,
+      "step": 21
+    },
+    {
+      "epoch": 0.04526166902404526,
+      "grad_norm": 0.25890016555786133,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 1.2665,
+      "step": 24
+    },
+    {
+      "epoch": 0.04714757190004715,
+      "eval_loss": 1.2976175546646118,
+      "eval_runtime": 68.8074,
+      "eval_samples_per_second": 12.978,
+      "eval_steps_per_second": 1.628,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.914871804952576e+16,
+  "total_flos": 3.661363364757504e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null