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:e828ec98552a9166b72035a401249abea023a537da7904e720609021c2c91bea
+oid sha256:07a5ecdbadb2ab0137331404ef1b0130d66db190c9fe69082fe7925914108596
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab6448068b45bdeec015c36f59cd5051d7fccbf3d5f7ccfc72e09f622f448d2
+oid sha256:41bf36d7c7e6de97d0f9325142f7902caac6d2e195ac1f93cf75eb653bbd26bc
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0703adaab0d533041f4917d10f6d3f0def78a785902d98446d8621844b85ea1
+oid sha256:1096e2380034f689d985b908db3f1a7e2fe156b4c4b33a315a0fff11943e1414
 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": 0.16096579476861167,
+  "epoch": 0.2012072434607646,
   "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": 6.335,
       "eval_steps_per_second": 0.818,
       "step": 20
+    },
+    {
+      "epoch": 0.16901408450704225,
+      "grad_norm": 0.07342974841594696,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.0177,
+      "step": 21
+    },
+    {
+      "epoch": 0.193158953722334,
+      "grad_norm": 0.1093919426202774,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.013,
+      "step": 24
+    },
+    {
+      "epoch": 0.2012072434607646,
+      "eval_loss": 0.010123283602297306,
+      "eval_runtime": 33.0079,
+      "eval_samples_per_second": 6.332,
+      "eval_steps_per_second": 0.818,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.958628636046131e+16,
+  "total_flos": 7.467142214791987e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null