Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c833f4567205fae09ccf95ff9485e8c936a0ce569c97a442b56869d07ef13894
+oid sha256:0dd2c09397f8f9effc287bf36303dbe48305b73e3f75b1ccd49bbb8076a0d0cd
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efdecbba0e2e9923af95e4af803ccf010b0df7a76ec09354bb81ebab1ff4fd3f
+oid sha256:84a0e496896c01ec209a3cd7304aff4f20be4a0f66583e3ff5a8c0359a506bf3
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b0e1108b1c57e2ba1b7ccdcbd6bb769bad920c152da3b8f6a04fd19ca3c616
+oid sha256:db5c9f6569d0eec4e651d69aa8d2133aa98a1881e47d26bc46bf23ecd79bea52
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020249746878164023,
+  "epoch": 0.0269996625042187,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 4.335,
       "eval_steps_per_second": 0.542,
       "step": 15
+    },
+    {
+      "epoch": 0.024299696253796826,
+      "grad_norm": 11.490859985351562,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 6.2954,
+      "step": 18
+    },
+    {
+      "epoch": 0.0269996625042187,
+      "eval_loss": 1.2927414178848267,
+      "eval_runtime": 287.7942,
+      "eval_samples_per_second": 4.336,
+      "eval_steps_per_second": 0.542,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.925000544531251e+16,
+  "total_flos": 5.255509203694387e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null