Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76efa16fa42c779dc2ca87bc40c3ba126f4982a7b953b0d616d49e0d526db307
+oid sha256:358ef20034005d03fcaa8300a6c63f511964bf9eaa36d19a7a14cc1da2464f03
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4945c993af4dc984763dfe2aac8dc29280af34649c5b295006d0d0e1eeaa7a6
+oid sha256:0201c14df20892c485df4fc9fc47541cc2c0909c7a25e8406374825f43a4e614
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad50d6cf06913bd0bd4258afcb318b70f1ccc0899d991e7012fdad252831c348
+oid sha256:89f7e8dc7c6810ce1575eae75ae6f9ac9b08797b91b0db782042ecf7b3c04fac
 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": 0.003805094598879611,
+  "epoch": 0.004227882887644013,
   "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": 19.99,
       "eval_steps_per_second": 9.995,
       "step": 9
+    },
+    {
+      "epoch": 0.004227882887644013,
+      "grad_norm": 8.285616874694824,
+      "learning_rate": 0.0002,
+      "loss": 3.5485,
+      "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": 2848091673722880.0,
+  "total_flos": 3198626033565696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null