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:c72247729db92a513e25e03f1c2825b391d27e3d31a104009721f56d18af65fd
+oid sha256:838852e51df27acb3d8846f398ea4f67b5b6c0508a4cd6a5fbcef4ef5fd803cc
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7071b6015fb3805a1bb5b79348fbbc1d9bdecb3441cb016c3ac1d113dd7f8a0
+oid sha256:803aa37c2ffbb94c5d8a28e71f2e426b030bc47c1ecb367019861ba67b7af439
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda349645308a1cf9476917bcdb40e212f43025fd5a2c5f183aadf6b62cf5ab7
+oid sha256:c5d5058605746f733dd751c609761b79edfccbef3044d85c35e1a4f5fe0a5743
 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": 0.11976047904191617,
+  "epoch": 0.23952095808383234,
   "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": 0.0,
       "step": 5
+    },
+    {
+      "epoch": 0.1437125748502994,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.1437125748502994,
+      "eval_loss": NaN,
+      "eval_runtime": 3.5486,
+      "eval_samples_per_second": 5.072,
+      "eval_steps_per_second": 2.536,
+      "step": 6
+    },
+    {
+      "epoch": 0.16766467065868262,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.19161676646706588,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.2155688622754491,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.2155688622754491,
+      "eval_loss": NaN,
+      "eval_runtime": 3.5681,
+      "eval_samples_per_second": 5.045,
+      "eval_steps_per_second": 2.522,
+      "step": 9
+    },
+    {
+      "epoch": 0.23952095808383234,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "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": 2052393617326080.0,
+  "total_flos": 4104787234652160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null