Training in progress, step 740, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e234e6249350439636d7460378ee2b84249d14c6dee3a2c36d73b5ec77f8e5
+oid sha256:745ed45ba46e27d4a276a4bd62a985fbd8934270c510745c037ea7283b997c5a
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0614d4a3d74c8935ea6bb9dfae42e46c97cd7a85de759de2654b36d6e052287
+oid sha256:3666732966e75b7dddea0f14706f3ce6fbe99dbf7fd649207c5ed62a6184fa42
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b80bcd6f3ab18b8a6e4e1a9815a1a307d56309444ef6ece4e0c9e33db3626434
+oid sha256:8db1fe9840930b9fd7409bb742ad453c84b28c1800a3abc1b4cce223762b144f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877a12ad1f9d0e7e38bfcb4ffb7f44565110e6cdabfb95d8ce3554269a9604e7
+oid sha256:f129e6dbcdc516e08a9aab8d7cc9efeb682288e6509845b97627189c47790bc6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25760286225402507,
+  "epoch": 0.26475849731663686,
   "eval_steps": 500,
-  "global_step": 720,
+  "global_step": 740,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -583,14 +583,30 @@
       "loss": 0.4011,
       "num_input_tokens_seen": 481867,
       "step": 720
+    },
+    {
+      "epoch": 0.26118067978533094,
+      "grad_norm": 0.3188275992870331,
+      "learning_rate": 0.0001477638640429338,
+      "loss": 0.4372,
+      "num_input_tokens_seen": 489088,
+      "step": 730
+    },
+    {
+      "epoch": 0.26475849731663686,
+      "grad_norm": 0.3422275483608246,
+      "learning_rate": 0.00014704830053667263,
+      "loss": 0.4178,
+      "num_input_tokens_seen": 494747,
+      "step": 740
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 481867,
+  "num_input_tokens_seen": 494747,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.0835487168731136e+16,
+  "total_flos": 1.1125112884402176e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null