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:ec7a858bd1495a605d088c5781356e895d165cc02657301797fa59270ae0e9a3
+oid sha256:7fcf006a5b3a23d4b9e70f7cbd7a3bfad44f8a07c11a43d4ca707399f146860f
 size 5327496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631f5ac697008bad7c99fa2f8d00767c2d769bf1b95b35433f5581959b93aef4
+oid sha256:10337fe7734ba99021dbf8b7089b3cc44e44705f5ef1f9b4a8a8d36dc5cf9a17
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4deae6cccf3656bc319f708dbecaf74cd3c0b32e04da4ceceba237ed9d9ebff
+oid sha256:b37eb23c7db03165d9b298533a106ef93fbe349e32cf744565e4d6da5d2b28dc
 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": 0.01812688821752266,
+  "epoch": 0.02014098690835851,
   "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": 136.106,
       "eval_steps_per_second": 68.053,
       "step": 9
+    },
+    {
+      "epoch": 0.02014098690835851,
+      "grad_norm": 9.26620101928711,
+      "learning_rate": 0.0002,
+      "loss": 26.9209,
+      "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": 19100445179904.0,
+  "total_flos": 21222716866560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null