Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cedff16679b6d4e19a18ba7da00ee671d21d538f1705b2ca1e7ea02fe1354a2
+oid sha256:17d0550687cd8822b6d48555beac114afd235668b1dc87bca98e99edf17fd00d
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c67142372a3ce53f9073e0d7fa901d3cc1f0dcbddb925db1125901631745613
+oid sha256:d569e0c4b862938984604a9e31e22c28dd221379ebc4b679a87d4354c12467f7
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333f2a71b3e34575844f8fd8a45254433fb8a5c1731e62ba395b530a464ea2d4
+oid sha256:8b17ba4933d91121a2dbebb5ae4436f28fce7ee82ad22fbfd4c0dd47fb8c808e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a35430a05f2b9748f37dd11667a782564c85a35d840d60cbaddfa2c905ab7c0a
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.34300791556728233,
+  "epoch": 0.3518029903254178,
   "eval_steps": 34,
-  "global_step": 195,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1420,6 +1420,41 @@
       "learning_rate": 4.2658237049655323e-07,
       "loss": 1.0461,
       "step": 195
+    },
+    {
+      "epoch": 0.3447669305189094,
+      "grad_norm": 1.016954779624939,
+      "learning_rate": 2.7308266142119785e-07,
+      "loss": 1.1179,
+      "step": 196
+    },
+    {
+      "epoch": 0.3465259454705365,
+      "grad_norm": 1.084816336631775,
+      "learning_rate": 1.5363960325660565e-07,
+      "loss": 1.0947,
+      "step": 197
+    },
+    {
+      "epoch": 0.3482849604221636,
+      "grad_norm": 1.0620332956314087,
+      "learning_rate": 6.829398569770939e-08,
+      "loss": 0.9681,
+      "step": 198
+    },
+    {
+      "epoch": 0.3500439753737907,
+      "grad_norm": 0.9418560862541199,
+      "learning_rate": 1.7074954194729044e-08,
+      "loss": 1.0684,
+      "step": 199
+    },
+    {
+      "epoch": 0.3518029903254178,
+      "grad_norm": 0.9430168271064758,
+      "learning_rate": 0.0,
+      "loss": 1.0693,
+      "step": 200
     }
   ],
   "logging_steps": 1,
@@ -1434,12 +1469,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1257530122502144e+17,
+  "total_flos": 1.154618474102784e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null