Training in progress, step 121, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef3f8baa4134cb9cddabaa47986a147a59c574a1cb55120e9f93e69d20564de
+oid sha256:c7700f046f76c454325bfcbac59115c9635f8617792e7830b50b5aa616adb90d
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbdff3376536518012fa9b5bc0d5250d64268e0a5a9be206e1e77ddc4bb9055c
+oid sha256:e08a1d62387dd06a447d256cb5eb530764ca11dacec092d9b550ce3e0c054753
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05f0eb4129a1d19a29c7f0816f6285669724c1288045b3023451ea705da25d8a
+oid sha256:e76f16a8c951334af2f5a88efa82a3fa803d62be665ffcb1d722b205f097ad93
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32647462277091904,
+  "epoch": 0.3319615912208505,
   "eval_steps": 500,
-  "global_step": 119,
+  "global_step": 121,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -840,6 +840,20 @@
       "learning_rate": 0.00018560606060606061,
       "loss": 1.2473,
       "step": 119
+    },
+    {
+      "epoch": 0.3292181069958848,
+      "grad_norm": 0.12208285182714462,
+      "learning_rate": 0.00018484848484848484,
+      "loss": 1.2755,
+      "step": 120
+    },
+    {
+      "epoch": 0.3319615912208505,
+      "grad_norm": 0.13750925660133362,
+      "learning_rate": 0.00018409090909090909,
+      "loss": 1.178,
+      "step": 121
     }
   ],
   "logging_steps": 1,
@@ -859,7 +873,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.477261017235292e+17,
+  "total_flos": 1.502892251654062e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null