Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff5cfd6a3431962d1c06b391cbb122da971aed8735fe3b3d2b9837881a0162a
+oid sha256:8266e463132d657d464e1c6137be33fcfc1f4e90c0e69e23bee94bbbcf418369
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da6e93e46fbfad6dbadc77d24136041d4d0f4ac3136e67f3841574166f6a671f
+oid sha256:541bf2e4691eebf8c6bb5fd174f00a5273d4422a1d1c461ea3c4f49cdb6d8516
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce48dec86ac6000671bbcda61602ac669c6643b660b3c79e45fe5bfda138dc71
+oid sha256:b073eae0856d95a78bd1210e484de480f18e699d417df6566c139d5389912738
 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": 0.02164762477450391,
+  "epoch": 0.024052916416115455,
   "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": 104.081,
       "eval_steps_per_second": 52.338,
       "step": 9
+    },
+    {
+      "epoch": 0.024052916416115455,
+      "grad_norm": 0.4997113049030304,
+      "learning_rate": 0.0002,
+      "loss": 2.6017,
+      "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": 37721915523072.0,
+  "total_flos": 42008496832512.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null