Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326378a095af083239afb4cc1062e54e5ec10f20df63946fabf171d487b0b584
+oid sha256:98e4754133dda9d0c9292c92abf101ffb1adb652cf9e9c8b00e963ac51ebda1b
 size 5327496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03211189be89fb1c3615df814f3778afd6253daa2541909edfba07424a050f6f
+oid sha256:a016daed1ff8530b1254adf5a05de716123450c6fb7d5174d7c4f5d0471faa45
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4deae6cccf3656bc319f708dbecaf74cd3c0b32e04da4ceceba237ed9d9ebff
+oid sha256:b37eb23c7db03165d9b298533a106ef93fbe349e32cf744565e4d6da5d2b28dc
 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": 0.0001149410607782787,
+  "epoch": 0.000127712289753643,
   "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": 114.938,
       "eval_steps_per_second": 57.471,
       "step": 9
+    },
+    {
+      "epoch": 0.000127712289753643,
+      "grad_norm": 2.237434148788452,
+      "learning_rate": 0.0002,
+      "loss": 14.5226,
+      "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": 19100445179904.0,
+  "total_flos": 21222716866560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null