Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22ad2648404f84cdefd0dabc65de6dbf08cad9677cbcb3bc388c652c4a857ecd
+oid sha256:7a840f1938048619695181b2547ee647535f4742e4e53a1bdaa168335bbb0a7a
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5904c71474b5f874e1ef91e3da743e8e505aae1367fc8f2ad5ce15a53c9caab3
+oid sha256:3646c1c7dbd21a09b82400b04c01575111dd621dda8925f0e1965377ce8a717e
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49311aa84f093855e564eba491f4fc5bbfe961780cd6ee624abc6a30cc246dde
+oid sha256:972a8c16afbf6f1f9e6b09a194835abcf491a013c12bba315ff2e296ef7ce393
 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": 0.014693877551020407,
+  "epoch": 0.0163265306122449,
   "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": 15.329,
       "eval_steps_per_second": 7.664,
       "step": 9
+    },
+    {
+      "epoch": 0.0163265306122449,
+      "grad_norm": 1.956859827041626,
+      "learning_rate": 0.0002,
+      "loss": 9.5035,
+      "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": 2592702725013504.0,
+  "total_flos": 2880780805570560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null