Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370ffb785c35b85be3b69622c9efa0b453ac38bcf82f4208c7d11a523365656e
+oid sha256:00e3783226ad3509d05ea81097017ef7248c7e26730ecd17556e982ada561460
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:989f6f5328df04d9ba312d6fa16319e837a56a627eae1ed812fab29c7756545c
+oid sha256:13a69f6bbb78e2d0263c5953bfc48f8acdc090549710fd1dd3dc6c29b4df01f4
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b2737be7f238db2b0a7251046c7812f99f19c9213229454fd164ad3fb8682d8
+oid sha256:8af9dcf2fb5ed0d697f9edd141933429239d504a5421e3ad9ffe3f66c8eb063a
 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": 0.019271948608137045,
+  "epoch": 0.021413276231263382,
   "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": 24.227,
       "eval_steps_per_second": 12.175,
       "step": 9
+    },
+    {
+      "epoch": 0.021413276231263382,
+      "grad_norm": 7.51359748840332,
+      "learning_rate": 0.0002,
+      "loss": 4.6667,
+      "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": 2147021720911872.0,
+  "total_flos": 2366105569984512.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null