Training in progress, step 520, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec4ab9a57a93c3513ea05caae28c984ac3710ebaf13f368939d8bad1fd992ae0
+oid sha256:bcedf5ba185dfed8a8532b4caf834fa25d3dcefcb40737f26670abacdb4ac535
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d9a87ee6b6052046f0b14d04eaaf0357892b7a7f4727b789c67069b7547c6a
+oid sha256:759c1758be952783d5bfbf82779b75426f877cd751c0c1e49f49db2f8f652cf7
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87fe9fb3b31ca0189979c0daa73883f6e8cf029b274919616b419e017ad599ca
+oid sha256:49367cdd574f043b0528d491fffcb3439b253a28e3d60840b470ada16f51e852
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:511871b8163e6c2442a4d43033ca6a9432c171a817a07d44c57891428e700525
+oid sha256:6c41970a14a61e2b623506dfd598a59afb05006b7fbb269fb8f9aac0b5a12d27
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.17889087656529518,
+  "epoch": 0.18604651162790697,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 520,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -407,14 +407,30 @@
       "loss": 0.4133,
       "num_input_tokens_seen": 332100,
       "step": 500
+    },
+    {
+      "epoch": 0.18246869409660108,
+      "grad_norm": 0.39435234665870667,
+      "learning_rate": 0.0001635062611806798,
+      "loss": 0.4428,
+      "num_input_tokens_seen": 337848,
+      "step": 510
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 0.2763209640979767,
+      "learning_rate": 0.00016279069767441862,
+      "loss": 0.4464,
+      "num_input_tokens_seen": 345759,
+      "step": 520
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 332100,
+  "num_input_tokens_seen": 345759,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 7467756224716800.0,
+  "total_flos": 7774898899433472.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null