Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52000a456554a0b5c37c39ad480cfd85744035f4a394858c17e6d3daa81ae8df
+oid sha256:a618a7ab1491518429604bb97c497311967854b8a16e0a5f1a890ee408c23c2b
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e89bd00fa02b9d4ff891f0abb9d88ee1e7926fe72d40d8222d69ea16fe4c718
+oid sha256:1e77aa8b39fc0f2023bec89fec06c6f59cae3efa4d48bf59d1bc35642e898634
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:561184d6af9b5bc7313240b6e7bdc678bdc8b052aa570cf9b3e295e4fe999d47
+oid sha256:4064746cde00cef3c678ba04db56228cfb7a609849b1ab5a01cc367c2ec4fb09
 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": 0.0026259354895181407,
+  "epoch": 0.003501247319357521,
   "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": 23.684,
       "eval_steps_per_second": 2.961,
       "step": 15
+    },
+    {
+      "epoch": 0.003151122587421769,
+      "grad_norm": 3.5953474044799805,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.6887,
+      "step": 18
+    },
+    {
+      "epoch": 0.003501247319357521,
+      "eval_loss": 1.3892496824264526,
+      "eval_runtime": 406.3687,
+      "eval_samples_per_second": 23.676,
+      "eval_steps_per_second": 2.96,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6399443557416960.0,
+  "total_flos": 8532591409889280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null