Training in progress, step 6486, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72410fcfce11116c642dad2ac1f851954613ae9ca9f37e106b99cf4cc8560a58
+oid sha256:ea754247180acec31b5b60c9ee3e1d6fd7ce56dba7f4c60f16005dbd744581c2
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae85ff0a08cdb19000c96789f83d4d2f0f08f9eb5bc57e5e57eff3b37fe31f52
+oid sha256:ae85412c313971e6aec21cfd5503ef8a93f0211094610414e36c27ee1e29c78c
 size 83485139

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b76a7ba81bcbc059ee6a62bdea93f43091f236ec991103bc5ca0ea04659b8444
+oid sha256:1e01861a9dacc9c9f1e775212e57b52c6613522e0feab6ac1e96f98ea0ab030a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:859b1a1ccc982c4b50f6001dac47e34317244bd40e686328c0369a7b85017494
+oid sha256:b8f204bc8ad3a4181d86b396ae73f7291ac1fabef2c4c1f2beb205fa474346cc
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9834624725338266,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 6450,
+  "global_step": 6486,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4523,6 +4523,27 @@
       "learning_rate": 1.1753789050417569e-06,
       "loss": 0.1940107226371765,
       "step": 6450
+    },
+    {
+      "epoch": 2.9880883543425467,
+      "grad_norm": 0.30115655064582825,
+      "learning_rate": 8.660686668728735e-07,
+      "loss": 0.1959635615348816,
+      "step": 6460
+    },
+    {
+      "epoch": 2.9927142361512664,
+      "grad_norm": 0.29174426198005676,
+      "learning_rate": 5.567584287039901e-07,
+      "loss": 0.19444901943206788,
+      "step": 6470
+    },
+    {
+      "epoch": 2.997340117959986,
+      "grad_norm": 0.4074135422706604,
+      "learning_rate": 2.474481905351067e-07,
+      "loss": 0.20223517417907716,
+      "step": 6480
     }
   ],
   "logging_steps": 10,
@@ -4537,12 +4558,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.202617054555607e+17,
+  "total_flos": 1.2092503276056269e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null