Training in progress, epoch 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7ba1a686c8a39f794d28715ce50c9040e9efadcb215a6f1f68ceb99c4484a7
+oid sha256:a1f89678bfcaea704d111e574ffb02381b58f29949b041052259e9fd46388477
 size 2526824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72345b01893c27f8914342501492def172f5e4c93c9da8b92a4adb674b44009b
-size 1628858
+oid sha256:c1105023e70cd979f84058cf88271139d3dad49f2efada53694e464226c755e6
+size 1628986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe3dd6761509c3affdccc74c67f5156c1b67b6fe137882be5fc0e5e35d8afb0
+oid sha256:d417edef81aadd1524150f603a1f1f4d9e4feaebc56043e6552c54b598024246
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c066b8439215624d8c1217bbfd75abe82eda412f0f6f8d22a58b49123756c6
+oid sha256:f18c56cb174b19403e5cd64826715733b24b1187efc1a85a31ad182bce916247
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 207,
+  "global_step": 276,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -43,6 +43,13 @@
       "learning_rate": 0.00029364619555955005,
       "loss": 1.6815,
       "step": 205
+    },
+    {
+      "epoch": 3.5693430656934306,
+      "grad_norm": 0.4026730954647064,
+      "learning_rate": 0.00020635380444044998,
+      "loss": 1.5832,
+      "step": 246
     }
   ],
   "logging_steps": 41,
@@ -62,7 +69,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7857827154427904e+16,
+  "total_flos": 2.381043620590387e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null