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:d89eaedd627e4315cf3a0a1baf6fd440978764b3379eb5944a1936a06fa5a41c
+oid sha256:46413881bfc33f9c791389b13ec812424960e1f0ec6c6bc4dafba4f0a2c7c3da
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:419b5df42a8112a5604d21421f52a39d3b38b4c439129d1f569ccac0392113e5
+oid sha256:ab9072a27a79fa0e1c92b3a1847b6704cf488c9c15dc9568d1a197999789f4f5
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c3622429d825af2529aafc53eb1c511eb1ddd51175b1cb9108d34baaa417ec
+oid sha256:9827b398fc968e0b0684f99c11a527546e70ab824cd0ae8d6535c172e2f92b44
 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": 0.006899195093905711,
+  "epoch": 0.007665772326561901,
   "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": 33.436,
       "eval_steps_per_second": 16.718,
       "step": 9
+    },
+    {
+      "epoch": 0.007665772326561901,
+      "grad_norm": 2.223823308944702,
+      "learning_rate": 0.0002,
+      "loss": 2.4521,
+      "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": 826158039957504.0,
+  "total_flos": 917953377730560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null