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:cd849c9cfb9b038b3dfaa6860c7812d7ec9b42a45aa740a6a9100bb6c71daacb
+oid sha256:875227d8fa78f1c5caa3d72a637609358e9bb3834ea24984932930734eb2f48b
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2e799ffd49f7ff58c594aa327f542f1384e30a225f5f2faa523759576ab9d0
+oid sha256:28007cc7abe5302d079639a28b9379f38ba887275b78a4f30ea038b24b8f00d4
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce23990253dbcb847c65b8e07df81d199b8cb35ee201419fc10370dd6bcc8fb2
+oid sha256:57fe9322ee192f6ca97876187da096d9083f730f45230a65c47e815b5fed1304
 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": 0.0012719949120203519,
+  "epoch": 0.0019079923680305278,
   "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": 25.931,
       "eval_steps_per_second": 12.972,
       "step": 6
+    },
+    {
+      "epoch": 0.001483994064023744,
+      "grad_norm": 0.704005777835846,
+      "learning_rate": 0.00014,
+      "loss": 1.8708,
+      "step": 7
+    },
+    {
+      "epoch": 0.0016959932160271359,
+      "grad_norm": 0.7345767617225647,
+      "learning_rate": 0.00016,
+      "loss": 1.5161,
+      "step": 8
+    },
+    {
+      "epoch": 0.0019079923680305278,
+      "grad_norm": 0.7325570583343506,
+      "learning_rate": 0.00018,
+      "loss": 2.0964,
+      "step": 9
+    },
+    {
+      "epoch": 0.0019079923680305278,
+      "eval_loss": 1.849073052406311,
+      "eval_runtime": 76.6333,
+      "eval_samples_per_second": 25.929,
+      "eval_steps_per_second": 12.971,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 600116796850176.0,
+  "total_flos": 900175195275264.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null