Training in progress, step 4800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094a7e88ac190113472d8c01b2df08de094f04602e59899cd894797763a1f29d
+oid sha256:f4ced61eae70f21c5c63f1107feef14d1705683fed216ab47273965c0e2494b1
 size 1054440872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70bb1c9ae5586829ee6cf66544b0def35379e96db4143482afabf8f97b0e51a5
+oid sha256:a1eda538d96287c20519cd7975c5f861a14271b86e5a675b2f234149c6482a2d
 size 2041777658

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23dbcd70ff2919050fcc9cba72fcb6491579fd36451328703f82dae74022f11
+oid sha256:94d3cd3d9f0d1fea2d03498cf97fd97401d6a6a7de7fa934b8538bc7c7ec16fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:417483f84722a4bfad9b8eb4c5866f76ce06d223609156fc27071200c2ff1069
+oid sha256:da49fd85c9470977f77e555b7807d1ad2e6d8a428e34963bbd75ab42e9b66434
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6787537932395935,
   "best_model_checkpoint": "./output/checkpoint-4050",
-  "epoch": 0.014683777741287625,
+  "epoch": 0.015157447991006582,
   "eval_steps": 150,
-  "global_step": 4650,
+  "global_step": 4800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3510,6 +3510,119 @@
       "eval_samples_per_second": 11.407,
       "eval_steps_per_second": 11.407,
       "step": 4650
+    },
+    {
+      "epoch": 0.014715355757935556,
+      "grad_norm": 13.99572467803955,
+      "learning_rate": 3.277183051523893e-07,
+      "loss": 0.8312,
+      "step": 4660
+    },
+    {
+      "epoch": 0.014746933774583486,
+      "grad_norm": 7.099660873413086,
+      "learning_rate": 3.0879516905387914e-07,
+      "loss": 0.9549,
+      "step": 4670
+    },
+    {
+      "epoch": 0.014778511791231417,
+      "grad_norm": 8.244866371154785,
+      "learning_rate": 2.904285748875281e-07,
+      "loss": 0.7216,
+      "step": 4680
+    },
+    {
+      "epoch": 0.014810089807879347,
+      "grad_norm": 18.085098266601562,
+      "learning_rate": 2.7261927763208694e-07,
+      "loss": 0.7163,
+      "step": 4690
+    },
+    {
+      "epoch": 0.014841667824527277,
+      "grad_norm": 11.467937469482422,
+      "learning_rate": 2.553680093580127e-07,
+      "loss": 0.8257,
+      "step": 4700
+    },
+    {
+      "epoch": 0.014873245841175208,
+      "grad_norm": 9.333969116210938,
+      "learning_rate": 2.3867547919737676e-07,
+      "loss": 0.8658,
+      "step": 4710
+    },
+    {
+      "epoch": 0.014904823857823138,
+      "grad_norm": 10.59934139251709,
+      "learning_rate": 2.225423733147088e-07,
+      "loss": 0.8157,
+      "step": 4720
+    },
+    {
+      "epoch": 0.014936401874471069,
+      "grad_norm": 11.30579948425293,
+      "learning_rate": 2.069693548788066e-07,
+      "loss": 0.9591,
+      "step": 4730
+    },
+    {
+      "epoch": 0.014967979891118999,
+      "grad_norm": 9.181888580322266,
+      "learning_rate": 1.9195706403546185e-07,
+      "loss": 0.9756,
+      "step": 4740
+    },
+    {
+      "epoch": 0.01499955790776693,
+      "grad_norm": 10.071789741516113,
+      "learning_rate": 1.775061178811501e-07,
+      "loss": 0.8792,
+      "step": 4750
+    },
+    {
+      "epoch": 0.01503113592441486,
+      "grad_norm": 11.81341552734375,
+      "learning_rate": 1.636171104376709e-07,
+      "loss": 0.8474,
+      "step": 4760
+    },
+    {
+      "epoch": 0.01506271394106279,
+      "grad_norm": 9.52579116821289,
+      "learning_rate": 1.5029061262771796e-07,
+      "loss": 0.815,
+      "step": 4770
+    },
+    {
+      "epoch": 0.01509429195771072,
+      "grad_norm": 13.034448623657227,
+      "learning_rate": 1.375271722514209e-07,
+      "loss": 0.7754,
+      "step": 4780
+    },
+    {
+      "epoch": 0.015125869974358651,
+      "grad_norm": 11.439579963684082,
+      "learning_rate": 1.253273139638221e-07,
+      "loss": 0.7933,
+      "step": 4790
+    },
+    {
+      "epoch": 0.015157447991006582,
+      "grad_norm": 7.407265663146973,
+      "learning_rate": 1.1369153925331249e-07,
+      "loss": 0.9544,
+      "step": 4800
+    },
+    {
+      "epoch": 0.015157447991006582,
+      "eval_loss": 0.680745005607605,
+      "eval_runtime": 43.3846,
+      "eval_samples_per_second": 11.525,
+      "eval_steps_per_second": 11.525,
+      "step": 4800
     }
   ],
   "logging_steps": 10,
@@ -3529,7 +3642,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5524478093223526e+17,
+  "total_flos": 1.604290409996452e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null