Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cb1f88b186640f9148ca418a93ac1b73cd63fb24c0da92df8c8777371738e7c
+oid sha256:b305994f24cd347d0dde059ed26fa1e492641c101f786122838aa49634c00caf
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671e9005bc6d4296ea1c670e66a8a0e4fc10e16a56d6c7734c97699e68351737
+oid sha256:8229a7e16905ad7719b2a9f3a9b442636d01787bb993a3ec6e0905e806ce7914
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b84d16d72b7e6ff5d6769d55df31c36b252d605a20a4c4c276e5840c32f666b1
+oid sha256:0b9aa4b97de417848e5e26b6bf91a11346f186903cf67734caa19c0bb8985f74
 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": 0.0004582076444308679,
+  "epoch": 0.0005091196049231866,
   "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": 42.329,
       "eval_steps_per_second": 21.167,
       "step": 9
+    },
+    {
+      "epoch": 0.0005091196049231866,
+      "grad_norm": 1.7320082187652588,
+      "learning_rate": 0.0002,
+      "loss": 2.0209,
+      "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": 216490963894272.0,
+  "total_flos": 240545515438080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null