Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a504611727481956dc92b4dafb6cab1ddb84685eca0567f6e1ec5c2f7407272
+oid sha256:b326b178e6547de42e6cca900517210d97c36d359ed0357458c2ffbb36032a00
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bef900b732723328a70adb23fa883b44507989a34fd6fa3c2ddd509496aa4d3
+oid sha256:ba64909e11c2884fbf4d636ac0d82c7ff2c970ac8db39027e71a1ddfd7e04856
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd864be02f7b32e879b9e2ddc596bbbccf819b329aea4a0d6e995288a351e279
+oid sha256:d17a52c96d3d80ce7c4db9ac694970a5e721869aa422859f42245c4c011870c4
 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": 0.0005084314888568766,
+  "epoch": 0.0005649238765076406,
   "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": 18.756,
       "eval_steps_per_second": 9.378,
       "step": 9
+    },
+    {
+      "epoch": 0.0005649238765076406,
+      "grad_norm": 6.464872360229492,
+      "learning_rate": 0.0002,
+      "loss": 13.0186,
+      "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": 2928757482455040.0,
+  "total_flos": 3245379912990720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null