Training in progress, step 4800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e488b62025d41986709534a2dc201f971d6ddeec47a4c48635d7dddcb5f028b
+oid sha256:2c4c8e6d007d3d8bb8f8f9bbd9ef836f6fb24275cfd50f0180fe1758da6364b4
 size 933293280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd03821db8049af2b171cdd8a983a9b8ab8db734bb230e14cce66182b0badc1d
+oid sha256:d3b81f8d9a6373fbc49d9c16ddea636467baebe74e82efe9496675b018e5ca15
 size 1866844821

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d2f85bebee57b047e39efab752a9eab24d277780521dfed0170268348b7113
+oid sha256:fd74d8f0f7764961530a74e879e048f30ba690128c8b40b38488d20c197a86ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cdcf164ce6993e9af16adc4343d6062859956f040c1fbcd7e250c216a5a5066
+oid sha256:5232a4a5f739042715cc636afe138ca1778707ce4414342447394498c78343ab
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.14619897305965424,
-  "best_model_checkpoint": "./output/checkpoint-4650",
-  "epoch": 0.17283675289919714,
+  "best_metric": 0.14507263898849487,
+  "best_model_checkpoint": "./output/checkpoint-4800",
+  "epoch": 0.1784121320249777,
   "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": 13.297,
       "eval_steps_per_second": 13.297,
       "step": 4650
+    },
+    {
+      "epoch": 0.17320844484091585,
+      "grad_norm": 2.0867106914520264,
+      "learning_rate": 6.817354714980488e-07,
+      "loss": 0.1318,
+      "step": 4660
+    },
+    {
+      "epoch": 0.17358013678263456,
+      "grad_norm": 17.901288986206055,
+      "learning_rate": 6.758453247522666e-07,
+      "loss": 0.102,
+      "step": 4670
+    },
+    {
+      "epoch": 0.17395182872435325,
+      "grad_norm": 9.688858032226562,
+      "learning_rate": 6.699669035115747e-07,
+      "loss": 0.0933,
+      "step": 4680
+    },
+    {
+      "epoch": 0.17432352066607196,
+      "grad_norm": 80.86397552490234,
+      "learning_rate": 6.641004494148456e-07,
+      "loss": 0.0704,
+      "step": 4690
+    },
+    {
+      "epoch": 0.17469521260779067,
+      "grad_norm": 8.16674518585205,
+      "learning_rate": 6.5824620360903e-07,
+      "loss": 0.1367,
+      "step": 4700
+    },
+    {
+      "epoch": 0.17506690454950938,
+      "grad_norm": 17.89749526977539,
+      "learning_rate": 6.524044067392435e-07,
+      "loss": 0.0761,
+      "step": 4710
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 17.662899017333984,
+      "learning_rate": 6.465752989388749e-07,
+      "loss": 0.074,
+      "step": 4720
+    },
+    {
+      "epoch": 0.17581028843294677,
+      "grad_norm": 4.190911293029785,
+      "learning_rate": 6.407591198197149e-07,
+      "loss": 0.0888,
+      "step": 4730
+    },
+    {
+      "epoch": 0.17618198037466548,
+      "grad_norm": 24.806283950805664,
+      "learning_rate": 6.349561084621062e-07,
+      "loss": 0.1334,
+      "step": 4740
+    },
+    {
+      "epoch": 0.1765536723163842,
+      "grad_norm": 11.839107513427734,
+      "learning_rate": 6.29166503405117e-07,
+      "loss": 0.0903,
+      "step": 4750
+    },
+    {
+      "epoch": 0.17692536425810287,
+      "grad_norm": 6.1233978271484375,
+      "learning_rate": 6.233905426367347e-07,
+      "loss": 0.0758,
+      "step": 4760
+    },
+    {
+      "epoch": 0.17729705619982158,
+      "grad_norm": 6.106809616088867,
+      "learning_rate": 6.176284635840844e-07,
+      "loss": 0.1035,
+      "step": 4770
+    },
+    {
+      "epoch": 0.1776687481415403,
+      "grad_norm": 1.4445923566818237,
+      "learning_rate": 6.118805031036666e-07,
+      "loss": 0.069,
+      "step": 4780
+    },
+    {
+      "epoch": 0.178040440083259,
+      "grad_norm": 19.246662139892578,
+      "learning_rate": 6.061468974716237e-07,
+      "loss": 0.0968,
+      "step": 4790
+    },
+    {
+      "epoch": 0.1784121320249777,
+      "grad_norm": 10.475799560546875,
+      "learning_rate": 6.004278823740262e-07,
+      "loss": 0.0921,
+      "step": 4800
+    },
+    {
+      "epoch": 0.1784121320249777,
+      "eval_loss": 0.14507263898849487,
+      "eval_runtime": 39.6799,
+      "eval_samples_per_second": 12.601,
+      "eval_steps_per_second": 12.601,
+      "step": 4800
     }
   ],
   "logging_steps": 10,
@@ -3529,7 +3642,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.30014571180032e+17,
+  "total_flos": 1.342970275358638e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null