Training in progress, step 6000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac2b56ba43e7cf6e627c6d78ee2d8a54c6a9b8482738e4d0e5508b059244676
+oid sha256:87bf6d8c3c7201435b59c86f75284044ae7ca9dd0b83b93d9783cce36eaab3dc
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69973d0bdbecfdff6671addf5401d05a7990dd2a8e07167f9b28ddcc497207f6
+oid sha256:a1ff7e3c74491b65303a1d660290aa57aaee8ff25bd74e82739919626ea6a896
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd3295a917ebbf1cf0429160bcb6ae7d8acc650fcf19c056fed23a32459f9c3
+oid sha256:f4de3b0ad4cac852dd3da2926f015bb27ffccac6cb7d06eabf2b5f451190bbde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.036157880209771,
+  "epoch": 3.312172232956114,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -392,6 +392,41 @@
       "learning_rate": 4.005295925472484e-05,
       "loss": 0.1206,
       "step": 5500
+    },
+    {
+      "epoch": 3.0913607507590393,
+      "grad_norm": 0.6104450821876526,
+      "learning_rate": 3.817175385184861e-05,
+      "loss": 0.1074,
+      "step": 5600
+    },
+    {
+      "epoch": 3.146563621308308,
+      "grad_norm": 0.5122411847114563,
+      "learning_rate": 3.630812597192591e-05,
+      "loss": 0.1088,
+      "step": 5700
+    },
+    {
+      "epoch": 3.2017664918575766,
+      "grad_norm": 0.48834362626075745,
+      "learning_rate": 3.4464845084024766e-05,
+      "loss": 0.1076,
+      "step": 5800
+    },
+    {
+      "epoch": 3.256969362406845,
+      "grad_norm": 0.4744304120540619,
+      "learning_rate": 3.2644650420294285e-05,
+      "loss": 0.1087,
+      "step": 5900
+    },
+    {
+      "epoch": 3.312172232956114,
+      "grad_norm": 0.5677183270454407,
+      "learning_rate": 3.085024690529227e-05,
+      "loss": 0.1086,
+      "step": 6000
     }
   ],
   "logging_steps": 100,
@@ -411,7 +446,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9148141046545777e+18,
+  "total_flos": 3.182453705049637e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null