Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602d49ff4825aa25f81d8bdad5fd8ee21294b826f26ed0b622fdb59a57eb2981
+oid sha256:039db4adeb8cd1b6bb0ec007ed3c006bcbdcea9b09c0987fd0ea3a02fc671feb
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c33a1e7c88c0c38111b6dfb1d5bbbd559073488f179b51fb5bbd604013eb384
+oid sha256:b81944db0af75ec0e56e629a9109e10e3fd144e4ac69ffa21c621a23bb16c945
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f4c520bdbbb3a94697b2862fd0c9032953c1d5738ee32bb212e1a1a1576476
+oid sha256:68529ee711356fd9d47647e5bd3dd9d92d8d90801ebf2381a18d532f68111077
 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": 0.07068525427056745,
+  "epoch": 0.07775377969762419,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -221,6 +221,21 @@
       "eval_samples_per_second": 19.38,
       "eval_steps_per_second": 2.422,
       "step": 90
+    },
+    {
+      "epoch": 0.07461221284115453,
+      "grad_norm": 5.533350944519043,
+      "learning_rate": 1.4411039697577175e-06,
+      "loss": 3.4561,
+      "step": 95
+    },
+    {
+      "epoch": 0.07775377969762419,
+      "eval_loss": 3.3061177730560303,
+      "eval_runtime": 233.6519,
+      "eval_samples_per_second": 19.379,
+      "eval_steps_per_second": 2.422,
+      "step": 99
     }
   ],
   "logging_steps": 5,
@@ -240,7 +255,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3576622208712704e+17,
+  "total_flos": 1.4934284429583974e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null