Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c0de6726ec360ffff07e04aa0fbeeb99e920c0bed6075deb511347cc34c8b24
+oid sha256:1054badaf0b74fb76797254a01579023e9cc1577175215a27924e1c0f362b3fe
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb25d9588084b560c7c4ff4654cf9724001751e0b78d356b1530e3adfa66096
+oid sha256:115acd0715cd31793d41e589829a3f6a3e2f5f2a891a7a20e81bfa4d67adbe1c
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:487921a1acd258b82e58b9ec98a7bf8fbb6715ade97fa26c5f93634426742553
+oid sha256:e7a3cb48a6d6dd27fc13994f6dc6775c95e0795a042b71c5eef13e3e74c00be7
 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": 0.0005868257616509365,
+  "epoch": 0.0006520286240565961,
   "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": 35.809,
       "eval_steps_per_second": 17.905,
       "step": 9
+    },
+    {
+      "epoch": 0.0006520286240565961,
+      "grad_norm": 9.701369285583496,
+      "learning_rate": 0.0002,
+      "loss": 11.8366,
+      "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": 1469230227652608.0,
+  "total_flos": 1632478030725120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null