Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e507adcaf11e318eff77a485e4452794a46f235227d7dcef07d6ac8954c3ea4
+oid sha256:120952c5b4ea61b9c1ef29d40800acae78f9f6a1946c5d2b0956a42c6d25595a
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcdd715f2a47527cdab99b27b94f4f0e5b15f6f6d1503ece5f334a6c4e5534cc
+oid sha256:4d35da7d6367fc70b6022bc2cdd2e82713f348597ee7fa766ec0798386888eed
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e7ca9361d7c63802b080d9f05c29da8d06385ae9fbdbc2978f3275b21c7222
+oid sha256:44e2e0f489749a22449b302a9439239af49c7050e67779179060d02acb85ea4c
 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": 0.0006881128505074832,
+  "epoch": 0.0007645698338972036,
   "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": 6.016,
       "eval_steps_per_second": 3.008,
       "step": 9
+    },
+    {
+      "epoch": 0.0007645698338972036,
+      "grad_norm": 6.857584476470947,
+      "learning_rate": 0.0002,
+      "loss": 10.2282,
+      "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": 1872507523620864.0,
+  "total_flos": 2052556323969024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null