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:c2e97f8a784af26ded08784564b46dbb9a0ef537361cfc547e8431dd60c4a9d4
+oid sha256:8c2b32ece5898795aa615f09bc828496d1eb9b53c686a59bd42fced55d1ce20c
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cc5752b68392fa4d0f923673835c08af45522239248eccbb4d5a2b10dc9d61b
+oid sha256:e4a113849e1e18276196ca9a2ce1cd8335d947f9a455e8592283332d0eaa8319
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c514059833379be7f07bedb66e132f681b006474052e397b0a39642845b08b2
+oid sha256:b219965011e42447cad4c77dc442a7896fa05c5e37426dae40d9e5cb1aefb46e
 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": 0.0030125523012552303,
+  "epoch": 0.0033472803347280333,
   "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": 19.8,
       "eval_steps_per_second": 9.9,
       "step": 9
+    },
+    {
+      "epoch": 0.0033472803347280333,
+      "grad_norm": 1.8150256872177124,
+      "learning_rate": 0.0002,
+      "loss": 1.8002,
+      "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": 2723305268183040.0,
+  "total_flos": 2962191695216640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null