Training in progress, step 7000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6623b2d67d7ace83c58db6e667a1f5efaf969454228665bd2f42fa58c63130
+oid sha256:3afee2b89c55d138018b573e9a914e6a07453c7de2e6deccf508c92105811902
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c7c78a887b874f5d12d4183e0f20f21628e49864c34d49004e15388d95fe55
+oid sha256:15bb57db9f3fbc5a6c418e8722464684cda94ed4f1003b4b9db8675541297f5d
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaedc92244071d34424437252c1cb2fe4ebf2e5cbfa092fca056c799d5a64b9c
+oid sha256:fc6c5d761a120c0c95ac7582051fc67375b77e8e7cc8898f714b41f2b1ba2779
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.5596933187294635,
+  "epoch": 3.833515881708653,
   "eval_steps": 500,
-  "global_step": 6500,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -462,6 +462,41 @@
       "learning_rate": 2.321769956084937e-05,
       "loss": 0.2991,
       "step": 6500
+    },
+    {
+      "epoch": 3.6144578313253013,
+      "grad_norm": 1.7949954271316528,
+      "learning_rate": 2.1623392848071354e-05,
+      "loss": 0.3045,
+      "step": 6600
+    },
+    {
+      "epoch": 3.669222343921139,
+      "grad_norm": 1.6750141382217407,
+      "learning_rate": 2.007056059490364e-05,
+      "loss": 0.3077,
+      "step": 6700
+    },
+    {
+      "epoch": 3.723986856516977,
+      "grad_norm": 1.425621509552002,
+      "learning_rate": 1.856147237776956e-05,
+      "loss": 0.2989,
+      "step": 6800
+    },
+    {
+      "epoch": 3.7787513691128147,
+      "grad_norm": 1.534443736076355,
+      "learning_rate": 1.7098333838026275e-05,
+      "loss": 0.2975,
+      "step": 6900
+    },
+    {
+      "epoch": 3.833515881708653,
+      "grad_norm": 1.511762261390686,
+      "learning_rate": 1.5683283458260718e-05,
+      "loss": 0.2968,
+      "step": 7000
     }
   ],
   "logging_steps": 100,
@@ -481,7 +516,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1238589889308426e+18,
+  "total_flos": 3.3642526441134e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null