Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b996865d9bb035b18992b22caa005701a4fcfaa5c84461ca063caf86d7f515
+oid sha256:fd4baedae54750c3d2d5ff1eddbfdf161f5eb820689e92b95461bdfb69837186
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e00a8d31c73095d5e7f3c49432552366b591f32aa0715d370bdbdb4e441af01
+oid sha256:e4d69e44166dd773ed4c206381950c44e64aadae9a06e17c31b5eb0ae8f76e33
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c1664b8350c65817e40eb9ac07bbf5d619dd1f98dec2741a04cc323fb1a39e5
+oid sha256:54e66c57e0d7b53c38356b4c17c946069bea3b154a71971279622d99f1999230
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0036383481899217754,
+  "epoch": 0.005457522284882663,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 1.9404,
       "step": 18
+    },
+    {
+      "epoch": 0.003820265599417864,
+      "grad_norm": 2.0340781211853027,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.9594,
+      "step": 21
+    },
+    {
+      "epoch": 0.004366017827906131,
+      "grad_norm": 1.695061445236206,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.0642,
+      "step": 24
+    },
+    {
+      "epoch": 0.004366017827906131,
+      "eval_loss": 1.7845287322998047,
+      "eval_runtime": 233.1384,
+      "eval_samples_per_second": 9.93,
+      "eval_steps_per_second": 4.967,
+      "step": 24
+    },
+    {
+      "epoch": 0.004911770056394397,
+      "grad_norm": 2.3796348571777344,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.8777,
+      "step": 27
+    },
+    {
+      "epoch": 0.005457522284882663,
+      "grad_norm": 1.5571463108062744,
+      "learning_rate": 0.0,
+      "loss": 1.6378,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8244114386583552.0,
+  "total_flos": 1.2270309784682496e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null