Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad3d221d2be36916e70837d155335dee152fae9b2ada26bfe3819c8e369f2c65
+oid sha256:ea2a5564e0b261fc93e544b05e81bd02a77805c3283f440da2fe4c656f503417
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44e1acf35e6796194b7e9d5e27b78139bab83162478313d6113dafba05252991
+oid sha256:b6c4378409b855435b2fbf31116ddf4b01c66e6b4a7ed351f025471819004248
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1147260b23b6eeeea6183429920a456fa023e5463fcb8effe4f0101c4481fade
+oid sha256:600d1eb0c7fd32752cb091ffd6dadbba789b49ca4f1521aca50d5ac38198230d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4967fab956f007beafd6b8bc5c5dee4d86950ea055e4ab46c9a7cdc66a69112d
+oid sha256:f6b7babead6c4be4368caff2650e543461856d401ff242b042a60fc57cd3bcca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03843074459567654,
+  "epoch": 0.04270082732852949,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 10.535,
       "eval_steps_per_second": 5.267,
       "step": 81
+    },
+    {
+      "epoch": 0.039854105506627525,
+      "grad_norm": 10.550149917602539,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 21.4862,
+      "step": 84
+    },
+    {
+      "epoch": 0.041277466417578505,
+      "grad_norm": 9.829084396362305,
+      "learning_rate": 1.2750399292720283e-05,
+      "loss": 21.2587,
+      "step": 87
+    },
+    {
+      "epoch": 0.04270082732852949,
+      "grad_norm": 10.305970191955566,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 21.4128,
+      "step": 90
+    },
+    {
+      "epoch": 0.04270082732852949,
+      "eval_loss": 0.6616738438606262,
+      "eval_runtime": 674.758,
+      "eval_samples_per_second": 10.522,
+      "eval_steps_per_second": 5.261,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.269735689878241e+17,
+  "total_flos": 4.743055119703081e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null