Training in progress, step 125, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6635fb1a5a4d1e52befb48d9c1dd6d22cef487e7060ad2ae8c77bf218b621c64
+oid sha256:7824c3f81fdbdb2e2b3a1a5193f7c17d15f9b50ae782432bc949ec8805f57fac
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f88a4454de958ff0c771396808a3201dd5527422259556c25c03c7e282c3fb
+oid sha256:f9df2754a23870214b0b310b9e4bc5281367bef9d25e470b8e3ee5a12cf8b7e2
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f268972a397e2af6ad977488ad986f34c2f5a772c90c6a6cc2e109003c5ffb16
+oid sha256:5812e2ecae592d6f50333bedb57ae854eff888c456b1149952c9ff417054b4d0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f61ff627b3e4926c6ec03a811654366b4e4d6e1e7047b7acc119ae7fc1df0c10
+oid sha256:b56e816e8a25f93da658683a31382055b850781ee0417f299048bdc3e6be89cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1552895503073439,
+  "epoch": 0.16175994823681655,
   "eval_steps": 386,
-  "global_step": 120,
+  "global_step": 125,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -855,6 +855,41 @@
       "learning_rate": 9.991673445927398e-05,
       "loss": 0.9064,
       "step": 120
+    },
+    {
+      "epoch": 0.15658362989323843,
+      "grad_norm": 0.8505874872207642,
+      "learning_rate": 9.99143391352356e-05,
+      "loss": 0.9966,
+      "step": 121
+    },
+    {
+      "epoch": 0.15787770947913296,
+      "grad_norm": 1.3977786302566528,
+      "learning_rate": 9.991190987406857e-05,
+      "loss": 0.9145,
+      "step": 122
+    },
+    {
+      "epoch": 0.1591717890650275,
+      "grad_norm": 0.8947294354438782,
+      "learning_rate": 9.990944667742455e-05,
+      "loss": 0.9569,
+      "step": 123
+    },
+    {
+      "epoch": 0.16046586865092202,
+      "grad_norm": 0.7973839044570923,
+      "learning_rate": 9.990694954697828e-05,
+      "loss": 0.8853,
+      "step": 124
+    },
+    {
+      "epoch": 0.16175994823681655,
+      "grad_norm": 0.9481159448623657,
+      "learning_rate": 9.99044184844276e-05,
+      "loss": 1.04,
+      "step": 125
     }
   ],
   "logging_steps": 1,
@@ -874,7 +909,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3415246060322816e+17,
+  "total_flos": 1.39742146461696e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null