Training in progress, step 160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a4f325fd033a507c13907694cd83ed4dd5598512199bc26a1ea2c561e2da9ff
+oid sha256:2ded6ea93dca5b528b272b56d0dba78bfb48686ef712e6aee97e12ad754ec51a
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c4c911834d7aa1d6fa8a54ac9b83e9b2428c953802fdd31ab64ae361e0dc6b
+oid sha256:f7fcfe6bdcb982add10fed5d7c4599c6d6b8da496a1bdce1e099c1f92ef34189
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c7a6ee6116c3dbc9702a41d4839f08bb22dd133335dc9e279dc28759218f070
+oid sha256:6e40ba6383d47c8ec509ed3abd3668fd616332aaf4bb58238305f857b037e170
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b89886767fbf3bb430f4d52155c956cacde6261e91f36172700564b0debbbfe
+oid sha256:7815a0f425c279b798b8a01de0a05716135e29d85893e062dbb79cc33f526eb8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05008944543828265,
+  "epoch": 0.057245080500894455,
   "eval_steps": 500,
-  "global_step": 140,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,14 +119,30 @@
       "loss": 0.456,
       "num_input_tokens_seen": 96192,
       "step": 140
+    },
+    {
+      "epoch": 0.05366726296958855,
+      "grad_norm": 0.4566495418548584,
+      "learning_rate": 0.0001892665474060823,
+      "loss": 0.429,
+      "num_input_tokens_seen": 101609,
+      "step": 150
+    },
+    {
+      "epoch": 0.057245080500894455,
+      "grad_norm": 0.4657338559627533,
+      "learning_rate": 0.0001885509838998211,
+      "loss": 0.4445,
+      "num_input_tokens_seen": 107467,
+      "step": 160
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 96192,
+  "num_input_tokens_seen": 107467,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2163018388340736.0,
+  "total_flos": 2416553321895936.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null