Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e35ac6d89af7a7e2a988ddf6b514bcc2c22ed41eb98693da93df800bc164da7
+oid sha256:97fe2aeed1670a6f42e14d579b26440bd4ed420e8d62cb8f4130093c10f2c855
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7ad20ee4587f936caf062a16b9af986bc096691783a0effe2a7a5f7cf18f088
+oid sha256:b1121b35a8828e3f7d76a80b8418a44725073701bfb2627aac28f1b9d6a3c991
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ae472d02b3de5b61691bbbd328158341b9b01fb8bb042f73ebc115b2c91abda
+oid sha256:ce2f33c8493066a680f588a26ecd254a2502030e182a89080be89eacac5ff88f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00042317593539514055,
+  "epoch": 0.00047019548377237835,
   "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": 4.977,
       "eval_steps_per_second": 4.977,
       "step": 9
+    },
+    {
+      "epoch": 0.00047019548377237835,
+      "grad_norm": 38.46210861206055,
+      "learning_rate": 0.0001,
+      "loss": 6.1035,
+      "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": 6676985552044032.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null