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:a8cef3e2f2467415ea3811f41463a92a6603a40294f3810cc0cd34d32797f105
+oid sha256:3be5e10aa1b2c1d0dee952b1a3a7e3acf14f3926f6b77fffbcc7417bd28b1051
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb1b726f726d8392de2f4c6324d07a88247d2b8ec6cc22171167b9cb1a25001
+oid sha256:ea1f094629876a9b37c0f3038bca97b09cf258daaa72dab4bba3e36d0e93abfb
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248b83e156267aeaad0b24a8a39efe5d8e1a4161145b352741eb9e33a27f29d7
+oid sha256:37a1d57dcf6d6a809cbd33f03ec44415e52213e48cac682f33531386d9556ac5
 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": 0.005973120955699353,
+  "epoch": 0.008959681433549029,
   "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": 31.112,
       "eval_steps_per_second": 15.593,
       "step": 6
+    },
+    {
+      "epoch": 0.006968641114982578,
+      "grad_norm": 8.517732620239258,
+      "learning_rate": 0.00014,
+      "loss": 12.004,
+      "step": 7
+    },
+    {
+      "epoch": 0.007964161274265804,
+      "grad_norm": 5.677702903747559,
+      "learning_rate": 0.00016,
+      "loss": 11.1049,
+      "step": 8
+    },
+    {
+      "epoch": 0.008959681433549029,
+      "grad_norm": 6.056185722351074,
+      "learning_rate": 0.00018,
+      "loss": 12.0559,
+      "step": 9
+    },
+    {
+      "epoch": 0.008959681433549029,
+      "eval_loss": 2.802990674972534,
+      "eval_runtime": 13.5913,
+      "eval_samples_per_second": 31.123,
+      "eval_steps_per_second": 15.598,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 45041791795200.0,
+  "total_flos": 67562687692800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null