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:d7cd474e516caed40b1b449268db62f563ded9555756f912d0d5dd041a400e90
+oid sha256:06d3aa0b7a2512ad5e7866b8681ac1a4303901267d9bc8f4239d32560cc08540
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:828cbe684563ca908822d606f2cdf176754280158c1276d77eebf5e84ccd6404
+oid sha256:b6415e8ae694f0786b885e2a030ac99d57649f1914c26136fae90d3185d66d9c
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d96ad5f372d71810b645883ce8aef92c75e5aeb7ae695a622069aec9a28c64e
+oid sha256:c2a7ab8933376601dd3a710a29693d7d15a56f137bd248c104cc26667d1f9197
 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": 0.001487357461576599,
+  "epoch": 0.0016526194017517765,
   "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": 27.794,
       "eval_steps_per_second": 13.897,
       "step": 9
+    },
+    {
+      "epoch": 0.0016526194017517765,
+      "grad_norm": 5.427333354949951,
+      "learning_rate": 0.0002,
+      "loss": 7.1425,
+      "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": 1368370882646016.0,
+  "total_flos": 1512409922924544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null