Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8794c42f7aa23d99b63f86664a31bdcb87f7e76cc7776215442a328fc204917d
+oid sha256:ec4951cbc319636cd55dec63410f92695d17c0e98cf82136515b6fd216f6a626
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c639d8b67a1799045a61609c1fc5e8644dc68802e0c0a9c5e6141608d65717
+oid sha256:db846d2537986878d744e5d08af967bbe07d5e133823a04daadf9b22f600b138
 size 40131268

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85c5e3e589dfdf3eb8679de9d5cf33e0165cd6aeb13a8f2940235bf86350900
+oid sha256:488baf69d6cf1d409ec86db959f5eb220fc31086ce80e19f640d54604f101e7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017266187050359712,
+  "epoch": 0.025899280575539568,
   "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": 10.228,
       "eval_steps_per_second": 10.228,
       "step": 6
+    },
+    {
+      "epoch": 0.02014388489208633,
+      "grad_norm": 28.851085662841797,
+      "learning_rate": 0.00012,
+      "loss": 3.0727,
+      "step": 7
+    },
+    {
+      "epoch": 0.02302158273381295,
+      "grad_norm": 20.200868606567383,
+      "learning_rate": 0.00014,
+      "loss": 2.0007,
+      "step": 8
+    },
+    {
+      "epoch": 0.025899280575539568,
+      "grad_norm": 27.33905792236328,
+      "learning_rate": 0.00016,
+      "loss": 1.6268,
+      "step": 9
+    },
+    {
+      "epoch": 0.025899280575539568,
+      "eval_loss": 0.9558103680610657,
+      "eval_runtime": 7.2197,
+      "eval_samples_per_second": 10.25,
+      "eval_steps_per_second": 10.25,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1180530414452736.0,
+  "total_flos": 1770795621679104.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null