Training in progress, step 1420, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:070555ab40db51d3a5840454fa269b784df6d102a3f8624f43e74d58478c8951
+oid sha256:aad36523f653c0b77cbc992ea91311b49e96a68b9bac8b5fc5e7ff63686ac900
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca946250efe75fef35aba1dbf1b03c113298722b5d7da5cedd58c3eb48dddaf
+oid sha256:7eae06a37ddc2a57f0d2662fd5d5d2cdd831ea69bc665ae17cf29a05b11e5d13
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354c3e84f6b2a094e741c8f1f43bff92126887859b832aecb38252864730d160
+oid sha256:611ff9c30a238fa31d0058e6fc82212ffbe063da1a3832f3d98bad700efec653
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded0d7f7cfcac928a75f77d93dbcaf43644e4251cba1e72644318143074c5e26
+oid sha256:9ee649f42236fc3525c15f4fc06e3387d0e6ad85bc6902d30e2ef469b193aea2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5008944543828264,
+  "epoch": 0.5080500894454383,
   "eval_steps": 500,
-  "global_step": 1400,
+  "global_step": 1420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1127,14 +1127,30 @@
       "loss": 0.3776,
       "num_input_tokens_seen": 938905,
       "step": 1400
+    },
+    {
+      "epoch": 0.5044722719141324,
+      "grad_norm": 0.2043834775686264,
+      "learning_rate": 9.910554561717353e-05,
+      "loss": 0.4206,
+      "num_input_tokens_seen": 947665,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5080500894454383,
+      "grad_norm": 0.3463163673877716,
+      "learning_rate": 9.838998211091235e-05,
+      "loss": 0.3953,
+      "num_input_tokens_seen": 955261,
+      "step": 1420
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 938905,
+  "num_input_tokens_seen": 955261,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.111265780839424e+16,
+  "total_flos": 2.148044648894669e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null