Training in progress, step 210, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9653531852ec6119db0beb46f48bfa17c88968f05b0e674dc503a553f84fe4e3
+oid sha256:473f4b3ff0b219aa3d4708c39fab335413427789124d1cc01e586e727315cff4
 size 100198584

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80dafb883e7ca8362cc0eba677e7edbf34ec8bc9e8592483d28a1fed39eb72cd
+oid sha256:1ec22a1dfeb40ec71635f49ced12c4198b8107b4b216dad54278bd643cdb721c
 size 50675156

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcbc2526bc157d1d1697d4e94eb6c17525855f6b21b0575b373b92dfaeff6f39
+oid sha256:e7650503afdff505462325f6f430e903bb44a778f9119236884da4fcf462c9e5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.30097707971874715,
+  "epoch": 0.306821294858917,
   "eval_steps": 500,
-  "global_step": 206,
+  "global_step": 210,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1449,6 +1449,34 @@
       "learning_rate": 1.6369863013698633e-05,
       "loss": 1.2073,
       "step": 206
+    },
+    {
+      "epoch": 0.3024381335037896,
+      "grad_norm": 0.11093982309103012,
+      "learning_rate": 1.6335616438356166e-05,
+      "loss": 1.3644,
+      "step": 207
+    },
+    {
+      "epoch": 0.3038991872888321,
+      "grad_norm": 0.11352576315402985,
+      "learning_rate": 1.6301369863013702e-05,
+      "loss": 1.2034,
+      "step": 208
+    },
+    {
+      "epoch": 0.30536024107387455,
+      "grad_norm": 0.1127958819270134,
+      "learning_rate": 1.6267123287671232e-05,
+      "loss": 1.241,
+      "step": 209
+    },
+    {
+      "epoch": 0.306821294858917,
+      "grad_norm": 0.10320553183555603,
+      "learning_rate": 1.623287671232877e-05,
+      "loss": 1.2169,
+      "step": 210
     }
   ],
   "logging_steps": 1,
@@ -1468,7 +1496,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3075689748657357e+17,
+  "total_flos": 2.3556959221775155e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null