Training in progress, step 3800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94352bb286002b5de8d47b18622740886178c34a156c4609a6f45691ff44c981
+oid sha256:337362bf8030c02032868dcdf02728763ea34626d1d857d9e7f459a435132d4c
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef468f68a96521f6bee7c692e468dc10c41c752b1607c9ac9814858346421297
+oid sha256:bf6c3990d17fb62c57db4244697d41874529597f61ad3ad6de6444d9f984910e
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:febb26adf02b9e52f8f87bd7852971cd3a0f9cf9148f2e6994932af620362dcf
+oid sha256:6571ee6e0ff76c5a40828abd2c62f39834b567045c2cc9559cc376f61e1cd7e6
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f401d1a194070902a8068e17d1a8fd51a2d77e7384e27a0135c57b9ff89743
+oid sha256:bec97627b272edb58e0c54ee6df41820894bfcaaf4092fdb394b690a41477cd4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.398843930635838,
+  "epoch": 7.5988126855178875,
   "eval_steps": 500,
-  "global_step": 3700,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -322,6 +322,13 @@
       "learning_rate": 7.533333333333334e-05,
       "loss": 1.2622,
       "step": 3700
+    },
+    {
+      "epoch": 7.5988126855178875,
+      "grad_norm": 0.17899934947490692,
+      "learning_rate": 7.466666666666667e-05,
+      "loss": 1.266,
+      "step": 3800
     }
   ],
   "logging_steps": 100,
@@ -341,7 +348,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.774709835870241e+18,
+  "total_flos": 5.930784807058407e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null