Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d123a88dc3b760e57433b7b48c88d378a0fa69298222e119e20ff01714bdc27
+oid sha256:6afb10bb890a274fe48322da59e44c6d8c5aa567949f7a0de46021b397fa436b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a0eef0b2e2f573dd7b6bcce18e8a65617cacd8f69c458b30f34f0b4fca8cc13
+oid sha256:36776cc93e1fcdd9a3ed1badc56ad31fc72f1fb4fa0572a6874664e57e187f24
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5167609cd8bf1c2d6180f452d8726ac310020847553236aa82c81ef0afdc54a5
+oid sha256:5400c8d87e6be413f26190177fbe5a7f9c7e943cfb9a30b2fca3d7c0cd7f0acb
 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": 0.0003590735901374454,
+  "epoch": 0.0003989706557082727,
   "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": 23.892,
       "eval_steps_per_second": 11.946,
       "step": 9
+    },
+    {
+      "epoch": 0.0003989706557082727,
+      "grad_norm": 8.379837036132812,
+      "learning_rate": 0.0002,
+      "loss": 1.8897,
+      "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": 2450672628793344.0,
+  "total_flos": 2774346372218880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null