Training in progress, step 6500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c69edaf91c86caf6a7a0fd42996899325e932c7927930f0bbb216780ecee6505
+oid sha256:5c6623b2d67d7ace83c58db6e667a1f5efaf969454228665bd2f42fa58c63130
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788a1d6cd203b01bb14f4804f15ed88e7a7c43e26dd6d552eee5a686613ecee8
+oid sha256:65c7c78a887b874f5d12d4183e0f20f21628e49864c34d49004e15388d95fe55
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b37961c6d0193de06c3efbf48a168df2b148e000c09c167a07902751b74f66
+oid sha256:aaedc92244071d34424437252c1cb2fe4ebf2e5cbfa092fca056c799d5a64b9c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.285870755750274,
+  "epoch": 3.5596933187294635,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,6 +427,41 @@
       "learning_rate": 3.172786461221279e-05,
       "loss": 0.3146,
       "step": 6000
+    },
+    {
+      "epoch": 3.340635268346112,
+      "grad_norm": 1.7206776142120361,
+      "learning_rate": 2.996222995345437e-05,
+      "loss": 0.3138,
+      "step": 6100
+    },
+    {
+      "epoch": 3.3953997809419496,
+      "grad_norm": 1.966302514076233,
+      "learning_rate": 2.822588194196941e-05,
+      "loss": 0.3059,
+      "step": 6200
+    },
+    {
+      "epoch": 3.4501642935377874,
+      "grad_norm": 1.6685985326766968,
+      "learning_rate": 2.6521358375708428e-05,
+      "loss": 0.3006,
+      "step": 6300
+    },
+    {
+      "epoch": 3.5049288061336252,
+      "grad_norm": 1.6338154077529907,
+      "learning_rate": 2.4851150538898028e-05,
+      "loss": 0.3017,
+      "step": 6400
+    },
+    {
+      "epoch": 3.5596933187294635,
+      "grad_norm": 1.6607939004898071,
+      "learning_rate": 2.321769956084937e-05,
+      "loss": 0.2991,
+      "step": 6500
     }
   ],
   "logging_steps": 100,
@@ -446,7 +481,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8822031507389317e+18,
+  "total_flos": 3.1238589889308426e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null