Training in progress, step 8500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a710688e6a0cf565f545cf051ed0b59e75675e5753d369cb109c976b3cc03fac
+oid sha256:10acfad5bcbc145fc719e7f0dc5bb8567a20a65a9b1fe90765099a6393cd6f71
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fa71d7ac29062299f4da9c3dd3bf7d122f811b2de1fc38f1531093ae0956e2d
+oid sha256:f5d11f2773dce4b7a4a270c4bbe1e1a05155f9448377a6fcea44479035aaa4a7
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0932b9d07b54a274f58b7433d20b4f329a4f69d2f830bb7ba1cdb40a954272
+oid sha256:00ee94c4753f7ab0738e902cd6d228d8f9642629b28de205e059f83aeb56d87a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.4162296439414845,
+  "epoch": 4.692243996687828,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,6 +567,41 @@
       "learning_rate": 4.0788797598038054e-06,
       "loss": 0.0904,
       "step": 8000
+    },
+    {
+      "epoch": 4.471432514490753,
+      "grad_norm": 0.34369856119155884,
+      "learning_rate": 3.3506310524209107e-06,
+      "loss": 0.091,
+      "step": 8100
+    },
+    {
+      "epoch": 4.526635385040022,
+      "grad_norm": 0.2887893617153168,
+      "learning_rate": 2.6917062619715325e-06,
+      "loss": 0.0919,
+      "step": 8200
+    },
+    {
+      "epoch": 4.5818382555892905,
+      "grad_norm": 0.29069042205810547,
+      "learning_rate": 2.1030845924292554e-06,
+      "loss": 0.0934,
+      "step": 8300
+    },
+    {
+      "epoch": 4.637041126138559,
+      "grad_norm": 0.2758566737174988,
+      "learning_rate": 1.5856407728771395e-06,
+      "loss": 0.0906,
+      "step": 8400
+    },
+    {
+      "epoch": 4.692243996687828,
+      "grad_norm": 0.30082598328590393,
+      "learning_rate": 1.140143757604889e-06,
+      "loss": 0.0904,
+      "step": 8500
     }
   ],
   "logging_steps": 100,
@@ -586,7 +621,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.2432036665929236e+18,
+  "total_flos": 4.509819988241154e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null