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:e47923228f056b4ca9df7f75e814ac91078483f964054771cd79a5fa1f1c5592
+oid sha256:5b444519ade1d180b5ba5691285248cc2cc9094cb71d7e46709553d736b267c1
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c737bd224de7e40e2bb3627be1e1ec43a12a4bbff2a8013b69d2fa21131909c
+oid sha256:c285660ed6d461817eb2d5463f120625d7e50cfe936ff5a25b72aa433a0e25fe
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ed0cc872e01be7a92a9bfaa1687ff8effd6e3620425e7bdfc19489d2a395fb
+oid sha256:d7c2dbd9630804a95a6a43610db8a39fcedeac57b85aec4cd7bb916f3bcb7c43
 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": 0.0014788645606539869,
+  "epoch": 0.0016431828451710965,
   "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": 13.203,
       "eval_steps_per_second": 6.604,
       "step": 9
+    },
+    {
+      "epoch": 0.0016431828451710965,
+      "grad_norm": 0.7114524245262146,
+      "learning_rate": 0.0002,
+      "loss": 1.516,
+      "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": 783164469411840.0,
+  "total_flos": 868823083253760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null