Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b57cb44ce17ee542125ca89be86d00c2d46852bbc7976c056a35ab5b9b88f2
+oid sha256:b1bf6e26c2136cc8fff293815200eda49fcd248de797292a5fe39bbba5c9e95f
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8ed877d6197a6a3ac81e6ac90f9b95c47e390f4cd3e2080359b652c4a6add2c
+oid sha256:ef9958f32eabc60ed8081e26757a4013a472d2c2e98f6d63868b3e3cebe96ff8
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418749c55c33c6c53715a4219df7283aa7c8a290a3f31195fddc9d20c456d5b8
+oid sha256:0ccaf4c372e69d1722064ada5b740482e0d664faba4afc8969815f1227d239a4
 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": 0.1722488038277512,
+  "epoch": 0.19138755980861244,
   "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": 17.857,
       "eval_steps_per_second": 9.317,
       "step": 9
+    },
+    {
+      "epoch": 0.19138755980861244,
+      "grad_norm": 0.3907493054866791,
+      "learning_rate": 0.0002,
+      "loss": 1.3918,
+      "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": 1476087596974080.0,
+  "total_flos": 1640097329971200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null