Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e7b8e9b6295a356129c59cde4f1152c1db11bc663836917d425450bfce345b6
+oid sha256:c6036dd72c85fa373718882f6aa23b14be8e0267442c24de34382f21deda7298
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a70ed0e3f0b7439a06178086cd5cf01da1c877e1ab0d70ade11ff26054c015c6
+oid sha256:3b85ee131ec9ea1e677763aec10ea26ea2acc7e2b7d3b3b45e244aab7fbd6a2a
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1810486755b47aa8ae2c2015ae8fbd6e5e8857415c5c40ce9c14fa31dd1704f
+oid sha256:a874c609a782cce072b91aab7e0ddc54563b85396fc0a4c5327bc80820511339
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbc80592076e3de5c30633981a2d6dac803c7697f6a99bf37e58d1e2912b1fda
+oid sha256:bf83a2e8e60abc266eb939060af002b89aea4f4268fd719cbee186b10601a323
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0212765957446808,
+  "epoch": 1.2765957446808511,
   "eval_steps": 3,
-  "global_step": 12,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -75,6 +75,21 @@
       "eval_samples_per_second": 48.158,
       "eval_steps_per_second": 7.224,
       "step": 12
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 3.5793509483337402,
+      "learning_rate": 9.114919329468282e-05,
+      "loss": 2.8128,
+      "step": 15
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "eval_loss": 2.8750696182250977,
+      "eval_runtime": 0.4152,
+      "eval_samples_per_second": 48.165,
+      "eval_steps_per_second": 7.225,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -94,7 +109,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2402317479444480.0,
+  "total_flos": 3002896849305600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null