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:d652bab68d7eb4e8c2671a941ca16c0b2f13b9f8d375c3bfb99015ef50971550
+oid sha256:41d7b1cebf546c95b765e752533ca208fcf05cd75e380f573038ab780054188a
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e1b3521bbe7e20a37adf5c3b9f8b41af9f66dbeedf5097a18c6ff0c2065de3
+oid sha256:84593418c05bdc3209bb4a5a26b20695c1e78767ae652cb8caf5df7d4b2992e9
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d6f87dc95ff15819fcba74baaa39847b99daff8487bf382d9e736bcf11711d
+oid sha256:9c7236a5b1685a188b162c39b50ed3dcc9bb7fece998dcaf0e441825125cc655
 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": 0.0014210152364411463,
+  "epoch": 0.0015789058182679404,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 28.757,
       "eval_steps_per_second": 14.384,
       "step": 9
+    },
+    {
+      "epoch": 0.0015789058182679404,
+      "grad_norm": 0.32025063037872314,
+      "learning_rate": 0.0002,
+      "loss": 0.9243,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 345319170637824.0,
+  "total_flos": 390082766831616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null