Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28efd70325b2e3464727c26a4ec9e2e885f4fea904d52ab8ca993ece3faad9fa
+oid sha256:d9b7c638e0e16324b0d7642d105aa30261528b4a9f8c39dc48debd2e4d225ae0
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f64f295b718cc1d828280a58703b62125082948ae6eb3789fd8122664bf9d234
+oid sha256:292888670979ac3e40e99badcad1e3e15c3ccfaa5196cd59b3349aa0cfd65aa9
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5b835e21ca50c39f79d3503403d770ea19096b1b5731a18a40185b6fdef7de
+oid sha256:64a94d99a2191f644f8b8c2e15c505847172445e0109c03ccb1fe24bbc5e8392
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04607789358200768,
+  "epoch": 0.052660449808008776,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 387.638,
       "eval_steps_per_second": 48.476,
       "step": 63
+    },
+    {
+      "epoch": 0.04827207899067471,
+      "grad_norm": 0.06424158811569214,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3577,
+      "step": 66
+    },
+    {
+      "epoch": 0.050466264399341744,
+      "grad_norm": 0.06281175464391708,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3571,
+      "step": 69
+    },
+    {
+      "epoch": 0.052660449808008776,
+      "grad_norm": 0.05132991820573807,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.36,
+      "step": 72
+    },
+    {
+      "epoch": 0.052660449808008776,
+      "eval_loss": 10.356228828430176,
+      "eval_runtime": 5.8803,
+      "eval_samples_per_second": 391.646,
+      "eval_steps_per_second": 48.977,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9283684270080.0,
+  "total_flos": 10617396658176.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null