Training in progress, step 8000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5868ba587c3a824bc63fc899fdaeb6194618d48e020066ab2d114a4922121e1
+oid sha256:a710688e6a0cf565f545cf051ed0b59e75675e5753d369cb109c976b3cc03fac
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7d4f1caf511e7340b15cbbb3b6dc53b6d076d036358b828129c1ff3e45f7d3
+oid sha256:7fa71d7ac29062299f4da9c3dd3bf7d122f811b2de1fc38f1531093ae0956e2d
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a4fdf7915d781b2a36593733c87afb8e5ce6e3d04384acc5dc1d5c1959abad
+oid sha256:1b0932b9d07b54a274f58b7433d20b4f329a4f69d2f830bb7ba1cdb40a954272
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.140215291195142,
+  "epoch": 4.4162296439414845,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -532,6 +532,41 @@
       "learning_rate": 8.718592791191299e-06,
       "loss": 0.0907,
       "step": 7500
+    },
+    {
+      "epoch": 4.195418161744411,
+      "grad_norm": 0.4322417378425598,
+      "learning_rate": 7.66195881422559e-06,
+      "loss": 0.0902,
+      "step": 7600
+    },
+    {
+      "epoch": 4.2506210322936795,
+      "grad_norm": 0.31211355328559875,
+      "learning_rate": 6.668241848068507e-06,
+      "loss": 0.0921,
+      "step": 7700
+    },
+    {
+      "epoch": 4.305823902842948,
+      "grad_norm": 0.3759203255176544,
+      "learning_rate": 5.738918619071809e-06,
+      "loss": 0.0921,
+      "step": 7800
+    },
+    {
+      "epoch": 4.361026773392217,
+      "grad_norm": 0.2856844365596771,
+      "learning_rate": 4.875370160415244e-06,
+      "loss": 0.091,
+      "step": 7900
+    },
+    {
+      "epoch": 4.4162296439414845,
+      "grad_norm": 0.3637724816799164,
+      "learning_rate": 4.0788797598038054e-06,
+      "loss": 0.0904,
+      "step": 8000
     }
   ],
   "logging_steps": 100,
@@ -551,7 +586,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.9786029952435487e+18,
+  "total_flos": 4.2432036665929236e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null