Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef7cec7dc4418b8ab30a029a10a252efdf25ffe926a6e56104f83781a59ae1f
+oid sha256:d8ce99bcfd9ffc9c88eca10f869afaad8d973af12442f4c74f55d1eabfa3b989
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45d06c687280cb8ad20299e8ad3aca9d470ff3aac0f14d13562a403038b85d04
+oid sha256:2fbf61c522942a1cc29b1fdec7da3342b6979cdd2b32bda0ae1ec93805122980
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c3c915a3bb8b4192b1fe9ab2e40a6b8012bb6b2e4c94a894df47ee8a987a0e
+oid sha256:f1e339279e44c5c15da33d41816eb20d1d43d6744958966d073b2d253a0420c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005118689615458443,
+  "epoch": 0.0007678034423187664,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 26.571,
       "eval_steps_per_second": 13.286,
       "step": 6
+    },
+    {
+      "epoch": 0.0005971804551368183,
+      "grad_norm": 1.095488429069519,
+      "learning_rate": 0.00014,
+      "loss": 2.7722,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006824919487277923,
+      "grad_norm": 1.1569803953170776,
+      "learning_rate": 0.00016,
+      "loss": 2.585,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007678034423187664,
+      "grad_norm": 1.3624595403671265,
+      "learning_rate": 0.00018,
+      "loss": 3.2317,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007678034423187664,
+      "eval_loss": 2.8597023487091064,
+      "eval_runtime": 185.5701,
+      "eval_samples_per_second": 26.599,
+      "eval_steps_per_second": 13.3,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1359453911777280.0,
+  "total_flos": 1894996361871360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null