Training in progress, step 2160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b31cd1bacf359ded93b1a975a832f43cf8275d8876e0472c643b229fff2eb00
+oid sha256:ff72b599b447b215eefff6d1661e3e1b7b629b276623231e58b00bcf724e6432
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e963850275f272c22ef0a3706fe2ae328531160ce5f9a82b5cc306c0bdd72573
+oid sha256:6b925efecaf4f386957e5021c1b0ea12a260643a56d43dd1ee0b17097a7db84e
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0002b99f842540feaa883ef0561d8d2638b1009ac9f8f241ca4c7a7d22a87a41
+oid sha256:3f823fdaa5f5fd5d424a9ff2b96b6896a41f6efd9f1ec984af9475ca5c895c5f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b36f7fc3da668a866fd41d662c3dd39a222899bdb3fe635785c3fffd4983ac1
+oid sha256:f0344050b115ebaadcb50e37a42543331248b3e543b025e1c079b8d45f898c50
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7656529516994633,
+  "epoch": 0.7728085867620751,
   "eval_steps": 500,
-  "global_step": 2140,
+  "global_step": 2160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1719,14 +1719,30 @@
       "loss": 0.3754,
       "num_input_tokens_seen": 1449724,
       "step": 2140
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.32450494170188904,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.3712,
+      "num_input_tokens_seen": 1455151,
+      "step": 2150
+    },
+    {
+      "epoch": 0.7728085867620751,
+      "grad_norm": 0.36587849259376526,
+      "learning_rate": 4.543828264758497e-05,
+      "loss": 0.399,
+      "num_input_tokens_seen": 1461336,
+      "step": 2160
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1449724,
+  "num_input_tokens_seen": 1461336,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.259917321626419e+16,
+  "total_flos": 3.286028608974029e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null