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:dfe1a79685d337b5bd71b582421b63ed45d8bef079d85fc1473568502b1ab6c8
+oid sha256:c28068cbb492cb16378c1af86b0f33791d253e8190743ac7ae80cbc1269de710
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df640f89629af8e1bc1a69a4a0c12e5da98f21ecaeb532437e03abf1e12aff0
+oid sha256:a574c2fab2faa9d6ec70a6d00853008bcaa2b9cd9928ca69210b8eb32709f30e
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66734fcb570e483a3b6f6260a87666c97cf11e29764d9942fbe0a9d194db7eb0
+oid sha256:ec22462b3efe1952d67cb1b7948cf2e14beee2bb18ee1ace913296d7b44587e9
 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": 0.0028929604628736743,
+  "epoch": 0.0032144005143040825,
   "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": 21.947,
       "eval_steps_per_second": 10.973,
       "step": 9
+    },
+    {
+      "epoch": 0.0032144005143040825,
+      "grad_norm": 2.8697688579559326,
+      "learning_rate": 0.0002,
+      "loss": 7.9412,
+      "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": 3637326831943680.0,
+  "total_flos": 4065247635701760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null