Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea2a5564e0b261fc93e544b05e81bd02a77805c3283f440da2fe4c656f503417
+oid sha256:67b72c706372d0d01c40db33fac904362320319bf69fef06bc23627404a201de
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c4378409b855435b2fbf31116ddf4b01c66e6b4a7ed351f025471819004248
+oid sha256:911d8e88f29ebf432ec4915aed7d5483cbba3d7d547554ff87130c5ab27908a8
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:600d1eb0c7fd32752cb091ffd6dadbba789b49ca4f1521aca50d5ac38198230d
+oid sha256:3c5667a6ef8594fe83b5bbd6f74027ae99244cc55cc0e72bd5bb62c03b6fbace
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b7babead6c4be4368caff2650e543461856d401ff242b042a60fc57cd3bcca
+oid sha256:7041fa0be7432c15ac468c1425bc3b5d595e4b5b769cfa7728743ab80ef12291
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04270082732852949,
+  "epoch": 0.04697091006138244,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 10.522,
       "eval_steps_per_second": 5.261,
       "step": 90
+    },
+    {
+      "epoch": 0.04412418823948047,
+      "grad_norm": 10.540351867675781,
+      "learning_rate": 3.7544763546352834e-06,
+      "loss": 22.0735,
+      "step": 93
+    },
+    {
+      "epoch": 0.04554754915043146,
+      "grad_norm": 10.391834259033203,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 22.2369,
+      "step": 96
+    },
+    {
+      "epoch": 0.04697091006138244,
+      "grad_norm": 10.5779390335083,
+      "learning_rate": 7.709637592770991e-08,
+      "loss": 21.495,
+      "step": 99
+    },
+    {
+      "epoch": 0.04697091006138244,
+      "eval_loss": 0.6612978577613831,
+      "eval_runtime": 674.8148,
+      "eval_samples_per_second": 10.521,
+      "eval_steps_per_second": 5.261,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.743055119703081e+17,
+  "total_flos": 5.2196614900128154e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null