Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c9bd0d4c2baacaf54e7558bed7c909a41b4976658a572ca52fd4ae41e068fa
+oid sha256:31c56a99919fcaf468108ffaef88217d9a2c8940faf36475f6d42d4971fde8b3
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee8c1cccfdb34cd2016f64afb6d286b765afb99f4c17c2ccf1a8aad0252da924
+oid sha256:85b000004aa9a3ebe444b89ee898420804f4e9bba8b66679ab663365bbaf5a85
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a557fdaaae4f07e8165e5cac6d3ff4e31ae11d72bc07dcf59f3826a69421b743
+oid sha256:fabd3f4460a95cb5e5f91e288b5b98bb570c45efc773114f8eb6d82563c06e01
 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": 0.0002136118198540319,
+  "epoch": 0.00023734646650447992,
   "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": 13.827,
       "eval_steps_per_second": 6.914,
       "step": 9
+    },
+    {
+      "epoch": 0.00023734646650447992,
+      "grad_norm": 0.7529348731040955,
+      "learning_rate": 0.0002,
+      "loss": 0.9097,
+      "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": 160268694847488.0,
+  "total_flos": 178076327608320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null