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:c45690a70256adfe8dd45d76011859829a38eda506426664d152411d1b72f917
+oid sha256:abda0cc3f363bb1d2e21196f721d2f01aa4382c5ceaa574817afc5e8dc4cdc35
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e86010a8bd8ac86c0da506532b1a58f0933e38eeaf686e8a9175bad6b82bb54
+oid sha256:a75f97f2400857bb0b642cfa6b90faa1b43e91b5646b7b99bfbf7ac6a8684262
 size 671467026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e94900abd055492c0da44212d9ffd5c8a1ff716215108e409f60e12f4f5ac395
+oid sha256:1cd3505f81776b63461918f5cbbc7762bdbe9c1b1cf66972ef67fa311e524655
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9612206721dab747b72325faca201c5b62b462fd9a44bcf14483ab477a2645b1
+oid sha256:741e5a74b4b8a7e18ee94356eb03e28c998d3e32cf81a6bc98c8f2bfb8fb01d7
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.310655355453491,
-  "best_model_checkpoint": "./output/checkpoint-4650",
-  "epoch": 28.012048192771083,
+  "best_metric": 3.3106162548065186,
+  "best_model_checkpoint": "./output/checkpoint-4800",
+  "epoch": 28.91566265060241,
   "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": 9.649,
       "eval_steps_per_second": 9.649,
       "step": 4650
+    },
+    {
+      "epoch": 28.072289156626507,
+      "grad_norm": 9.195672035217285,
+      "learning_rate": 1.4790913492997438e-06,
+      "loss": 2.6247,
+      "step": 4660
+    },
+    {
+      "epoch": 28.132530120481928,
+      "grad_norm": 14.86363697052002,
+      "learning_rate": 1.3936855405155408e-06,
+      "loss": 2.8831,
+      "step": 4670
+    },
+    {
+      "epoch": 28.19277108433735,
+      "grad_norm": 11.328372955322266,
+      "learning_rate": 1.3107915729816954e-06,
+      "loss": 2.7178,
+      "step": 4680
+    },
+    {
+      "epoch": 28.253012048192772,
+      "grad_norm": 15.23580551147461,
+      "learning_rate": 1.230412854144547e-06,
+      "loss": 3.1991,
+      "step": 4690
+    },
+    {
+      "epoch": 28.313253012048193,
+      "grad_norm": 169.89739990234375,
+      "learning_rate": 1.15255268805841e-06,
+      "loss": 3.0329,
+      "step": 4700
+    },
+    {
+      "epoch": 28.373493975903614,
+      "grad_norm": 323.2249450683594,
+      "learning_rate": 1.0772142752497604e-06,
+      "loss": 3.1795,
+      "step": 4710
+    },
+    {
+      "epoch": 28.433734939759034,
+      "grad_norm": 24.42875099182129,
+      "learning_rate": 1.004400712585646e-06,
+      "loss": 2.8986,
+      "step": 4720
+    },
+    {
+      "epoch": 28.49397590361446,
+      "grad_norm": 14.24337387084961,
+      "learning_rate": 9.341149931464537e-07,
+      "loss": 2.7472,
+      "step": 4730
+    },
+    {
+      "epoch": 28.55421686746988,
+      "grad_norm": 90.30467224121094,
+      "learning_rate": 8.663600061028162e-07,
+      "loss": 2.9509,
+      "step": 4740
+    },
+    {
+      "epoch": 28.6144578313253,
+      "grad_norm": 32.362003326416016,
+      "learning_rate": 8.011385365968641e-07,
+      "loss": 3.0889,
+      "step": 4750
+    },
+    {
+      "epoch": 28.674698795180724,
+      "grad_norm": 20.82928466796875,
+      "learning_rate": 7.384532656277698e-07,
+      "loss": 3.0301,
+      "step": 4760
+    },
+    {
+      "epoch": 28.734939759036145,
+      "grad_norm": 12.928521156311035,
+      "learning_rate": 6.783067699414891e-07,
+      "loss": 2.8634,
+      "step": 4770
+    },
+    {
+      "epoch": 28.795180722891565,
+      "grad_norm": 14.081971168518066,
+      "learning_rate": 6.207015219248866e-07,
+      "loss": 2.6318,
+      "step": 4780
+    },
+    {
+      "epoch": 28.855421686746986,
+      "grad_norm": 13.051186561584473,
+      "learning_rate": 5.656398895040813e-07,
+      "loss": 2.7618,
+      "step": 4790
+    },
+    {
+      "epoch": 28.91566265060241,
+      "grad_norm": 221.75543212890625,
+      "learning_rate": 5.131241360471217e-07,
+      "loss": 3.0757,
+      "step": 4800
+    },
+    {
+      "epoch": 28.91566265060241,
+      "eval_loss": 3.3106162548065186,
+      "eval_runtime": 3.8397,
+      "eval_samples_per_second": 9.636,
+      "eval_steps_per_second": 9.636,
+      "step": 4800
     }
   ],
   "logging_steps": 10,
@@ -3529,7 +3642,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5087887023546368e+16,
+  "total_flos": 1.5578958526488576e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null