Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7fe8fc6b18a8ae029a58877e0ec1b980b40e6327e2db876a322aaa311f0171
+oid sha256:4688b88f831c526c06dff94b3dd0ff579c73e9622154d5eecc5871f9c8cb59a9
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d9908e8a4ed7d7fd67864fbc5f17ef3982c3a78797b866a7fc3dca564534e02
+oid sha256:35e9b4c08c9727794dffff4e06046da8521fd8647e1b42b31b06e986e0677294
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d0da3873d0775bf81b7bdee3955da665b473c4317959da28b057b61212854f6
+oid sha256:6208d4063190f0aee81e3875ea6f24513302b781bf59781fadec45ec656b2eb8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
+oid sha256:1eef4c60eef56c59d148e4191bea64e9a3bf517b29f5a413c536dcdc8e61edf1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.501302761855133,
+  "epoch": 1.6513809275664408,
   "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": 119.863,
       "eval_steps_per_second": 60.227,
       "step": 90
+    },
+    {
+      "epoch": 1.5513288170922355,
+      "grad_norm": 0.07071811705827713,
+      "learning_rate": 2.815857265976462e-06,
+      "loss": 11.8002,
+      "step": 93
+    },
+    {
+      "epoch": 1.6013548723293383,
+      "grad_norm": 0.0655035451054573,
+      "learning_rate": 9.233744553646754e-07,
+      "loss": 11.716,
+      "step": 96
+    },
+    {
+      "epoch": 1.6513809275664408,
+      "grad_norm": 0.07924264669418335,
+      "learning_rate": 5.7822281945782424e-08,
+      "loss": 11.6701,
+      "step": 99
+    },
+    {
+      "epoch": 1.6513809275664408,
+      "eval_loss": 11.734976768493652,
+      "eval_runtime": 1.6952,
+      "eval_samples_per_second": 119.751,
+      "eval_steps_per_second": 60.17,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 168136934031360.0,
+  "total_flos": 184423118929920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null