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:e244f74e1dfe7b078ac84b748981a70b33503702db0927817d376950cf371ea6
+oid sha256:fb1ff2b021eaf2f3149b427eae9104f2a03a43b3c36dd2b93369ec81ae77c71f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15e0af881dd02dea0eb2b631800116aacc6dc07bd2c3010ceac3f1a47cd0cba1
+oid sha256:7228f554b2602104c615c4fcb52631457b7fe407f6bba46f99674010d1dbdae0
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:502bc21db2af3273cec5864b9184b9d7adb3ffa37452754c84f3c28a163c6ea7
+oid sha256:18947dd72744f5e15a32bf79856a222e61386e4565f4bc346034eafb1764ad11
 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": 0.23300970873786409,
+  "epoch": 0.34951456310679613,
   "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": 2.128,
       "eval_steps_per_second": 1.161,
       "step": 6
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 33.65167236328125,
+      "learning_rate": 0.00014,
+      "loss": 5.1897,
+      "step": 7
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 19.27935218811035,
+      "learning_rate": 0.00016,
+      "loss": 3.3586,
+      "step": 8
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 15.050045013427734,
+      "learning_rate": 0.00018,
+      "loss": 2.734,
+      "step": 9
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "eval_loss": 2.383453845977783,
+      "eval_runtime": 5.0182,
+      "eval_samples_per_second": 2.192,
+      "eval_steps_per_second": 1.196,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8902647402725376.0,
+  "total_flos": 1.3353971104088064e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null