Training in progress, step 4200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2d0d2ee106556697ee5bb319a5c66f7da60fdefc5b2294aedef91b2d4c90622
+oid sha256:83278e812aaad4b9dddd765f2d01bba02b758a06ce6ae7e5fab440ddb3f627c1
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93fc1a43b3c79274a76d45363da8217224dd9ed74fe13aaac3588c46f683bda9
+oid sha256:75151ce6985b5d14c5d5c34392641060034773806b91fe7f3232dd3004c66822
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dfbdf22163bd5ea80a653a007f051d613da79be7b41af651245f6aba2f9024c
+oid sha256:07daf39f2067349c76ad283bc0c6a35ac4bd2a4f3e477c4ff106fb606cf0aad0
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c96e4de7567585305fbb3c5ce22247da92426eac792079c558bbf8ec5b548f2
+oid sha256:657d9780764590213f290182d0db6c65490b8f8feae2620c737661a7f6792ce3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.198718950164038,
+  "epoch": 8.398687705046086,
   "eval_steps": 500,
-  "global_step": 4100,
+  "global_step": 4200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -358,6 +358,13 @@
       "learning_rate": 7.266666666666667e-05,
       "loss": 1.2639,
       "step": 4100
+    },
+    {
+      "epoch": 8.398687705046086,
+      "grad_norm": 0.184415802359581,
+      "learning_rate": 7.2e-05,
+      "loss": 1.2657,
+      "step": 4200
     }
   ],
   "logging_steps": 100,
@@ -377,7 +384,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.399000563752632e+18,
+  "total_flos": 6.555075534940799e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null