Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5821dc1648635c8aa03b9ca13334906fe375c0cc3d6f0e536906be10a24d619c
+oid sha256:d15516f0dfc9891ee5fff102a9dafa2b37ae99dd4a1dd72a3a2f70bc3cdad812
 size 1770585648

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e93e8b2ee985e5752fbe82f4da680ce3cf6b58db11054bc35cea1c1df8195307
+oid sha256:1ebf085965bca49b1bc493afe47f1067ea98cfeb230936ab59e042e493f60a09
 size 99235764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6a216e76306077697fce369babc722d934631ceab06c507d0d26aa9b1335b22
+oid sha256:05e22fba92b29c1f5f0cd59a19fdf634f506ef846ae85ca8af68d60096387010
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021052631578947368,
+  "epoch": 0.042105263157894736,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 4.7818,
       "step": 5
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "grad_norm": 6.127976417541504,
+      "learning_rate": 0.00012,
+      "loss": 4.1538,
+      "step": 6
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "eval_loss": 3.1043951511383057,
+      "eval_runtime": 33.7059,
+      "eval_samples_per_second": 2.967,
+      "eval_steps_per_second": 1.483,
+      "step": 6
+    },
+    {
+      "epoch": 0.029473684210526315,
+      "grad_norm": 8.237787246704102,
+      "learning_rate": 0.00014,
+      "loss": 3.2056,
+      "step": 7
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 6.041158199310303,
+      "learning_rate": 0.00016,
+      "loss": 2.0689,
+      "step": 8
+    },
+    {
+      "epoch": 0.037894736842105266,
+      "grad_norm": 3.9629404544830322,
+      "learning_rate": 0.00018,
+      "loss": 1.3549,
+      "step": 9
+    },
+    {
+      "epoch": 0.037894736842105266,
+      "eval_loss": 1.1165939569473267,
+      "eval_runtime": 33.6697,
+      "eval_samples_per_second": 2.97,
+      "eval_steps_per_second": 1.485,
+      "step": 9
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 2.394595146179199,
+      "learning_rate": 0.0002,
+      "loss": 1.3262,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2818744422236160.0,
+  "total_flos": 5637488844472320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null