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:c52320cf134457a6c5b57b8c3691edc94ed94e687a9cf71f2ec0d56c9a03786f
+oid sha256:e1b2e9fca1802f7a64490d60a54cf614b75f7391ac97ce621332911b596fabe9
 size 5752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b40649f8958b57d2f02c30e93f62ab0b12c4a20c7db4fc7d6022bb91073e7557
+oid sha256:bdc267f049076d52d35e8ae7e726f44a26e9419a24c458a3846f4b9354755e56
 size 15814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b59954ca0801d56d659d9b748a6880456c339bd37c1bfc513909281d8ae0ffb
+oid sha256:51d3ad219d2064cf85163d881f4149c3e329c0ec00c353672cb88f2424bfa87b
 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": 0.0032444124008651765,
+  "epoch": 0.003604902667627974,
   "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": 152.309,
       "eval_steps_per_second": 76.22,
       "step": 9
+    },
+    {
+      "epoch": 0.003604902667627974,
+      "grad_norm": 4.1601579141570255e-05,
+      "learning_rate": 0.0002,
+      "loss": 46.0,
+      "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": 338688933888.0,
+  "total_flos": 373553971200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null