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:f60d20fc2a456657dd881e266623b1912e98dc87560c4ff8122ccc9f74dcf3a8
+oid sha256:95488a1c49b1d7cd292532a5bb06cb99d8c0af8501e225e8a619a97486b74a24
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c104204e28dcb1f58e7c8bf85257e1edc580cb1a37414341e0ec8106326c45a
+oid sha256:d8052e09d35c191824168f288a81b1082970ebd68838ba2229950e53c986699e
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f7226cf8f768ab674f8a097612122ce48fdb5cdabe619f231fa7c1cb1825d9
+oid sha256:70b8bee79b642f97d67339860368fe567d9d6c13f2e1cff2d3a0f5387759a60d
 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": 0.007093596059113301,
+  "epoch": 0.007881773399014778,
   "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": 39.443,
       "eval_steps_per_second": 19.759,
       "step": 9
+    },
+    {
+      "epoch": 0.007881773399014778,
+      "grad_norm": 1.253097414970398,
+      "learning_rate": 0.0002,
+      "loss": 6.2311,
+      "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": 786702532608.0,
+  "total_flos": 852261076992.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null