Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719e09d8b9111f45974cfa1d4c6ad852a7030a80d33ad405f1923ea6fb301898
+oid sha256:93c9beac45fa92f4c1db6ebc60286c832d9a4ef6548b0f4bf82825b5caf5f682
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff56f14b40e2450c04efdfdf8c2d191ddba4d2707256846d2b11f63645e7086
+oid sha256:a9949281865d7646ee69784eff59b573b03bdd5cbc01c30e8e046ae3c6a870a4
 size 4830714

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0cc465a75681ba50afdecee660968bcd8503a20558be1104c59586aa9b9c2e7
+oid sha256:2504f02dae5324e88c0367fb7870bab683b94c85f27b7a080401f4febb52ab77
 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": 0.011790714812085483,
+  "epoch": 0.014738393515106854,
   "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": 133.889,
       "eval_steps_per_second": 16.777,
       "step": 20
+    },
+    {
+      "epoch": 0.012380250552689757,
+      "grad_norm": 0.49812066555023193,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 11.8962,
+      "step": 21
+    },
+    {
+      "epoch": 0.01414885777450258,
+      "grad_norm": 0.4185691475868225,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 11.8831,
+      "step": 24
+    },
+    {
+      "epoch": 0.014738393515106854,
+      "eval_loss": 11.88258171081543,
+      "eval_runtime": 21.3695,
+      "eval_samples_per_second": 133.695,
+      "eval_steps_per_second": 16.753,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 22035824640000.0,
+  "total_flos": 27544780800000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null