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:b24466fd2926d53a5f0dfa602e43541182302f7b70ee9f787ef9cdc5f9f93c7f
+oid sha256:aa09f3c37ffe3d08ef47ff2f0419617286a0d9af2a0f9d8086ec01831fe1b557
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:439d4ab65c4a2581ccbcf03e7f95218c37fe5f15a584bc30dde29330fbed38b1
+oid sha256:25c021f56a2eaac4ce08e29ceb7d345a02666260de142fd6d49a9dcf1f8ebde0
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0ce404e87fcfa8b39c59ce102013231e7cdc3750402766ab47e6fc98888814f
+oid sha256:85f7a33b129ce49e7172aa98928963bfed19663dc885062d5cdbab52a10dca24
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21686746987951808,
+  "epoch": 0.24096385542168675,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 33.024,
       "eval_steps_per_second": 16.512,
       "step": 9
+    },
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 2.527155876159668,
+      "learning_rate": 0.0002,
+      "loss": 5.4825,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 826158039957504.0,
+  "total_flos": 940902212173824.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null