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:a51bae0a3b1bc256451ed8c67c858b127d073eecd0af0ec4bd0f0321d18f731d
+oid sha256:5ec2a726ff04dca11a98817cd63b4dac8c6d3185280f7985b7b6c2a615a12b90
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44478d85e1683dbcdfc8b7fb89ee435d67b6826d1261acfb081be262d47714ea
+oid sha256:1dd0225a8c1020e14615d14880a4d08c2dfbc18e65401e3b3609a618bf1a79f7
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f17167b4061b83b83845e86c54d4c316bbadbd795611572166eaa35f470ffa7
+oid sha256:a0effa3763608f7a4378ce0c53ae58430afd5b82d313cc5502092470f9e7629a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020463265596134716,
+  "epoch": 0.022736961773483017,
   "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": 666.902,
       "eval_steps_per_second": 333.901,
       "step": 9
+    },
+    {
+      "epoch": 0.022736961773483017,
+      "grad_norm": 3.1589856147766113,
+      "learning_rate": 0.0001,
+      "loss": 177.3125,
+      "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": 32499302400.0,
+  "total_flos": 36048076800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null