Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:755722c683efcddcfe3b32b5be3ca346f6b69310c13e8fc675fdfd583d70009e
+oid sha256:5cb4d7b9024098a48c07b818abdfb2d32eec55a715e6aa5a95d618f0543c8c73
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2655eb9b0ff736015df434f73d7fed05e377a252cf8af68ec7c1ef43ec12fad
+oid sha256:31c440d868c502e18152b99edef6523cd027a760ccb838ad6c14149c80389d3a
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7182179a8a7aba8a5eeabfede23ca4be12f62c10f09d621d492038f5f2795122
+oid sha256:11aee12f542f6af1a062b577a24e6d2dfcac836da4b452453565be54ec463258
 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": 0.0005519694576900078,
+  "epoch": 0.000613299397433342,
   "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": 48.72,
       "eval_steps_per_second": 24.36,
       "step": 9
+    },
+    {
+      "epoch": 0.000613299397433342,
+      "grad_norm": 0.8975516557693481,
+      "learning_rate": 0.0002,
+      "loss": 2.4865,
+      "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": 89038163804160.0,
+  "total_flos": 100167934279680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null