Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e17ec0ce1db97b13f6f29bf895a87806fa4f0a94422779c9694dab62fe3cf5d
+oid sha256:2b2e7a9294863a803bffa0d8195753acd756cf82f200f20bdb718548e153b883
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3d26dea06b4ef349b88333401ba92b0fd716bf7300a4d4e845d391d9ad0bda
+oid sha256:e61498a325632032a5014dec005d5501ecab7181c8356c69b0b034caa8652f4f
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:163020c3a5e3deb0c9f202a04693b11d0b5de442bd4ef423bf0f0a2016603d4d
+oid sha256:691769e53a39f084d367cf56ee01aa4a59cac12e120b4438ebd200d720592e64
 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": 0.007733619763694952,
+  "epoch": 0.008592910848549946,
   "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": 20.034,
       "eval_steps_per_second": 10.017,
       "step": 9
+    },
+    {
+      "epoch": 0.008592910848549946,
+      "grad_norm": 0.320016473531723,
+      "learning_rate": 0.0002,
+      "loss": 1.4896,
+      "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": 2687409674256384.0,
+  "total_flos": 3013156301438976.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null