Training in progress, step 2180, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff72b599b447b215eefff6d1661e3e1b7b629b276623231e58b00bcf724e6432
+oid sha256:f7865543f6aaefd525a4aa03a410cf4af463b4f3e6d2ae1912538913e26220b7
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b925efecaf4f386957e5021c1b0ea12a260643a56d43dd1ee0b17097a7db84e
+oid sha256:4d22e73707901787033065e05e6edbc269297b3683cfdbd102a29997da966992
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f823fdaa5f5fd5d424a9ff2b96b6896a41f6efd9f1ec984af9475ca5c895c5f
+oid sha256:4b1a9e3708d9d232a77e9549079bba51673bcb8586b714eb42370d58b85c5e90
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0344050b115ebaadcb50e37a42543331248b3e543b025e1c079b8d45f898c50
+oid sha256:4b259303746656c555078a221a94fa56f648be2579b7ca4ced7c5648c5502f83
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7728085867620751,
+  "epoch": 0.7799642218246869,
   "eval_steps": 500,
-  "global_step": 2160,
+  "global_step": 2180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1735,14 +1735,30 @@
       "loss": 0.399,
       "num_input_tokens_seen": 1461336,
       "step": 2160
+    },
+    {
+      "epoch": 0.776386404293381,
+      "grad_norm": 0.2556416392326355,
+      "learning_rate": 4.472271914132379e-05,
+      "loss": 0.3925,
+      "num_input_tokens_seen": 1468427,
+      "step": 2170
+    },
+    {
+      "epoch": 0.7799642218246869,
+      "grad_norm": 0.38359931111335754,
+      "learning_rate": 4.400715563506261e-05,
+      "loss": 0.3971,
+      "num_input_tokens_seen": 1475721,
+      "step": 2180
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1461336,
+  "num_input_tokens_seen": 1475721,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.286028608974029e+16,
+  "total_flos": 3.318375394066637e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null