Training in progress, step 180, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ded6ea93dca5b528b272b56d0dba78bfb48686ef712e6aee97e12ad754ec51a
+oid sha256:81750cf4351c62f467fa31cd7b9d64a5c6b54b220ad076d6d668eb9844803aca
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7fcfe6bdcb982add10fed5d7c4599c6d6b8da496a1bdce1e099c1f92ef34189
+oid sha256:6796a4fe299f2d46b565219a8d5ab5b44e38bb09dfe9c205cdfd25ad869b6fcb
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e40ba6383d47c8ec509ed3abd3668fd616332aaf4bb58238305f857b037e170
+oid sha256:921505c38e3140072fcb25b091248df87486cd572d25945bf43989c3adec66d2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7815a0f425c279b798b8a01de0a05716135e29d85893e062dbb79cc33f526eb8
+oid sha256:f7caa9fa897837d1407d3cee463cfb4344d4ea9bf72b6aacc7133003f48d23ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.057245080500894455,
+  "epoch": 0.06440071556350627,
   "eval_steps": 500,
-  "global_step": 160,
+  "global_step": 180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -135,14 +135,30 @@
       "loss": 0.4445,
       "num_input_tokens_seen": 107467,
       "step": 160
+    },
+    {
+      "epoch": 0.06082289803220036,
+      "grad_norm": 0.5721924304962158,
+      "learning_rate": 0.00018783542039355994,
+      "loss": 0.4304,
+      "num_input_tokens_seen": 113612,
+      "step": 170
+    },
+    {
+      "epoch": 0.06440071556350627,
+      "grad_norm": 0.2883516848087311,
+      "learning_rate": 0.00018711985688729877,
+      "loss": 0.4525,
+      "num_input_tokens_seen": 121416,
+      "step": 180
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 107467,
+  "num_input_tokens_seen": 121416,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2416553321895936.0,
+  "total_flos": 2730217072508928.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null