Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5854e87063bdcf54d9d5a9965595b5cf2e3e6a79eebb913ec15c4215d79b3df8
+oid sha256:85a92062a6af5c55d6312f81b8833f1c887fd506bd9f53d1e66aa8ffb54dad24
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1cb68a6a47da1a4c28328ad2df56cd4bccd6ea69d253a9a19a2720927f25cf3
+oid sha256:6c83a4467e979767da5d3553146d018c5769ba196c06afe9d1b9bbe03a9b7008
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3735fb6332a1f3f99bf0dbd8ad8891f01e8848a07f18fef96aa0e5f79af20059
+oid sha256:c9ae5429f322ac4fa81c235cc467f7c9730873f0af70405ce8831fd65955f198
 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": 0.0002898994210064342,
+  "epoch": 0.00032211046778492686,
   "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": 43.422,
       "eval_steps_per_second": 21.711,
       "step": 9
+    },
+    {
+      "epoch": 0.00032211046778492686,
+      "grad_norm": 0.3480377793312073,
+      "learning_rate": 0.0002,
+      "loss": 2.307,
+      "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": 454017561919488.0,
+  "total_flos": 510769757159424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null