Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3af918d2312dd0b87a9f5c2aec39e6fcaf2e819e205d6fd3fe2410a650ad285a
+oid sha256:118812380a7612aa6e01b1f643474f2f005a24c2f32e0ea4ab486eaf4d387b78
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba194eb72a726c08a538ee282387e0f9b5e520e86bfadc454bb7873b252d36d8
+oid sha256:131aa1722841db79ba73829a31c77698edc8f18c4db299546c1e81de7f59fb7a
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7ecc63df12c57baa58797cbad45fd25f5504b307a5ad4ad822f1c6c0804d66f
+oid sha256:77eb7a8efcda755f6cf5f1bf7541c682197083c64109e1175011208308cb49e9
 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": 0.16822429906542055,
+  "epoch": 0.18691588785046728,
   "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": 27.925,
       "eval_steps_per_second": 14.569,
       "step": 9
+    },
+    {
+      "epoch": 0.18691588785046728,
+      "grad_norm": 13.22984504699707,
+      "learning_rate": 0.0002,
+      "loss": 7.414,
+      "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": 4886913613824.0,
+  "total_flos": 5429904015360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null