Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254b05b36de66ecc2147fbcac64a197312a1acf07f5e8b57e4d0fd1f7bb83124
+oid sha256:15f62ce7a6a3d3153e131a873b012c703c8de92196db1c39fa958deda5cceb67
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e007338a9adf6e222d55d073b8678520b9143ba467a8a4c98b54f0591e0c68c
+oid sha256:4b9495154531be8283f75e778ff1a16d5abf8fab4bcd210170ae64e0e830975a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc05cd3a98949633cd0945d642fde31aa27434b462cc4feb8ff105332385519f
+oid sha256:2431fbde914d288016858b6cb5609b72dae4b3f1f99b197bd647068cb11c807f
 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": 0.006153846153846154,
+  "epoch": 0.006837606837606838,
   "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": 17.527,
       "eval_steps_per_second": 8.764,
       "step": 9
+    },
+    {
+      "epoch": 0.006837606837606838,
+      "grad_norm": 1.2244415283203125,
+      "learning_rate": 0.0002,
+      "loss": 2.3463,
+      "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": 3329215646662656.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null