Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbd72deef638610f6b14c86c9b6d8642a1e390195d8dc3a425c54030e7daa8e5
+oid sha256:f9acf59488c8e55b44e5fc41c00280636a030795981c569d231224e6f47b1312
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d6666a1312251a1627172f701b326f3a2579429bed6f52d2ed196d72a102601
+oid sha256:cc4adbdf9b3c24cb73d17894eac922abfef8ede16d87978b55cd3da000f699dd
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54695bae591aceb2574c0570650d7a15033601e879a5235bc5ef9cc452369efd
+oid sha256:8ea8f3c63b5a91434b55a7db9e9e888ce98c5d36cce664bfecf470c814be0613
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f589044fe72a89eeac5f01dfea2599de04455cb66e0a4998ee4eb766326c4c
+oid sha256:916fdec13e6efc15b18e2a6b6d384a81cd69075368b316d9722fd8205c98017b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.026002753763853463,
+  "epoch": 0.02889194862650385,
   "eval_steps": 8,
-  "global_step": 72,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -255,6 +255,28 @@
       "eval_samples_per_second": 9.36,
       "eval_steps_per_second": 4.681,
       "step": 72
+    },
+    {
+      "epoch": 0.02708620183734736,
+      "grad_norm": 0.2601235508918762,
+      "learning_rate": 2.181685175319702e-05,
+      "loss": 2.0599,
+      "step": 75
+    },
+    {
+      "epoch": 0.02816964991084125,
+      "grad_norm": 0.2593807578086853,
+      "learning_rate": 1.415512063981339e-05,
+      "loss": 2.0068,
+      "step": 78
+    },
+    {
+      "epoch": 0.02889194862650385,
+      "eval_loss": 2.0276479721069336,
+      "eval_runtime": 997.0668,
+      "eval_samples_per_second": 9.354,
+      "eval_steps_per_second": 4.678,
+      "step": 80
     }
   ],
   "logging_steps": 3,
@@ -274,7 +296,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.830538308891443e+17,
+  "total_flos": 4.256153676546048e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null