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:af18b709cec7b1460f9495ecdb911346a7d27c0ae4c22b4214b754d17ee9b252
+oid sha256:cf69bd2cf48ad28ab575c3004a13252e772553e02eb1e178fac2b34a7cbf0617
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c5a1130f868aaf21961340121ae66d596fb2025782e52dbf4cf5959ee05b569
+oid sha256:ff31e92ed54dc7c43a57bf8fbd7ad2097048ad89940cdb269081db3ccdf81007
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8584d63d2faee24e8a54114c8749ed64521b513195990dab72712f855912e2d1
+oid sha256:2f427f8a959b8aefd1d05eb193f0319cb42744bf11bc03ca90cbb34e0bd3d111
 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": 0.8223872073101085,
+  "epoch": 0.9046259280411194,
   "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": 4.204,
       "eval_steps_per_second": 2.108,
       "step": 90
+    },
+    {
+      "epoch": 0.8498001142204454,
+      "grad_norm": 0.2968892455101013,
+      "learning_rate": 2.815857265976462e-06,
+      "loss": 0.4787,
+      "step": 93
+    },
+    {
+      "epoch": 0.8772130211307824,
+      "grad_norm": 0.29118213057518005,
+      "learning_rate": 9.233744553646754e-07,
+      "loss": 0.4803,
+      "step": 96
+    },
+    {
+      "epoch": 0.9046259280411194,
+      "grad_norm": 0.33031514286994934,
+      "learning_rate": 5.7822281945782424e-08,
+      "loss": 0.5095,
+      "step": 99
+    },
+    {
+      "epoch": 0.9046259280411194,
+      "eval_loss": 0.5104153156280518,
+      "eval_runtime": 87.5974,
+      "eval_samples_per_second": 4.212,
+      "eval_steps_per_second": 2.112,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.3712752555851776e+17,
+  "total_flos": 5.908402781143695e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null