Training in progress, step 8000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd55d8c2d04a82cfd44dc7c8d8016779184fc1024acd2838426537f87ea2c5a
+oid sha256:0d87811e78f2411bb51f67277ec4ff3e7128aeba1a8f60f6083ffcf5e499137c
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ab10956105713904002caded57ca7d9c663c6ba89c15bfbad43cc0a4a865d7
+oid sha256:72baa3d9ed25be64c5f61bc4dcd4ad23809cf47c521105da8c0a4a00395ac985
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:126702607739835f9830b82beaf7e06fa3586d60c77c4b7790e033fb7535c675
+oid sha256:833d77c31bdb2ba7eb60d0271717ab3310ed32ad11e10d8490b2d98bed4a9687
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.5790980672870436,
+  "epoch": 3.81770460510618,
   "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": 2.262543306643643e-05,
       "loss": 0.2796,
       "step": 7500
+    },
+    {
+      "epoch": 3.626819374850871,
+      "grad_norm": 1.186291217803955,
+      "learning_rate": 2.124653382159273e-05,
+      "loss": 0.2666,
+      "step": 7600
+    },
+    {
+      "epoch": 3.674540682414698,
+      "grad_norm": 1.295457363128662,
+      "learning_rate": 1.989956485792702e-05,
+      "loss": 0.2719,
+      "step": 7700
+    },
+    {
+      "epoch": 3.7222619899785254,
+      "grad_norm": 1.141144871711731,
+      "learning_rate": 1.8586021963720364e-05,
+      "loss": 0.2699,
+      "step": 7800
+    },
+    {
+      "epoch": 3.7699832975423524,
+      "grad_norm": 1.6188665628433228,
+      "learning_rate": 1.7307363808118555e-05,
+      "loss": 0.2569,
+      "step": 7900
+    },
+    {
+      "epoch": 3.81770460510618,
+      "grad_norm": 1.63030207157135,
+      "learning_rate": 1.6065010321302785e-05,
+      "loss": 0.2601,
+      "step": 8000
     }
   ],
   "logging_steps": 100,
@@ -551,7 +586,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.842278772521255e+18,
+  "total_flos": 4.096777803147854e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null