Training in progress, step 55, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f913e66984e9002a72c226282e0169ab8f65a6d420688ed0650b567b3176062
+oid sha256:536e26247bc65692c80a8b8c25c67b929961b75b85474f47fc318d55ec5bd6ca
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a779760d1eb5cb4a49a7436c485300d22a71abea2397ce87c6b1aa455274ef47
+oid sha256:35815e48d3c5fc170a54d7b2ed2b44ea6b68abe6f5a46bfabd2b1a5c8228fc27
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93077e4de44f142f2a5ac374e93b3534575c13e18a3b475d644f8f3c2192c4e7
+oid sha256:d12f7728e7b9be1608e74dbee4b948660da84599fe27b67b5d416c76fc393e0a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79af33a7cc5e89926792af60c545e28f6f3569216a6e1a04e51a93b6477fd5cc
+oid sha256:59fb9c579d7f7f4aa986f5f762cd9981f0dcd26b5aa72ad6a0ef96ae89405fbd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006859662733248948,
+  "epoch": 0.008982891674492672,
   "eval_steps": 14,
-  "global_step": 42,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,13 @@
       "eval_samples_per_second": 26.057,
       "eval_steps_per_second": 13.028,
       "step": 42
+    },
+    {
+      "epoch": 0.0081662651586297,
+      "grad_norm": 5.682126522064209,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 9.2943,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -81,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7573683975487488.0,
+  "total_flos": 1.0057526569598976e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null