Training in progress, step 540, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcedf5ba185dfed8a8532b4caf834fa25d3dcefcb40737f26670abacdb4ac535
+oid sha256:02ca0724696c0714678baa7c919014b6cf1f56a5d8f9a9076b8131ecb4e4820b
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:759c1758be952783d5bfbf82779b75426f877cd751c0c1e49f49db2f8f652cf7
+oid sha256:c81ca955f4aa3495f958edfe9940021e3673d3e58c241146187bf4ccb7cc56df
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49367cdd574f043b0528d491fffcb3439b253a28e3d60840b470ada16f51e852
+oid sha256:f94817a11f2e5ac87d214de7bcbd2b4175429bcc3bf1d7ea823b2e61e3e96885
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c41970a14a61e2b623506dfd598a59afb05006b7fbb269fb8f9aac0b5a12d27
+oid sha256:857a28d74b36678189295e64a86a5f88d7b3dd82cb001caca49c082b46d9200f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18604651162790697,
+  "epoch": 0.19320214669051877,
   "eval_steps": 500,
-  "global_step": 520,
+  "global_step": 540,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -423,14 +423,30 @@
       "loss": 0.4464,
       "num_input_tokens_seen": 345759,
       "step": 520
+    },
+    {
+      "epoch": 0.18962432915921287,
+      "grad_norm": 0.2753828763961792,
+      "learning_rate": 0.00016207513416815743,
+      "loss": 0.438,
+      "num_input_tokens_seen": 354078,
+      "step": 530
+    },
+    {
+      "epoch": 0.19320214669051877,
+      "grad_norm": 0.3228139579296112,
+      "learning_rate": 0.00016135957066189623,
+      "loss": 0.4314,
+      "num_input_tokens_seen": 360961,
+      "step": 540
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 345759,
+  "num_input_tokens_seen": 360961,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 7774898899433472.0,
+  "total_flos": 8116738195212288.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null