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:d67a6e5aa5ee9f50de8852bba5ad16cc95d4496adc176426bece6cf0ce5cce5b
+oid sha256:91103bde54c992dace9e10e0ea6290d8df262db4370821ceb605417da1d2585b
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f1a08ba7f93a90c77deac4720aff007a443e092e41d30e6597529f343c0c35
+oid sha256:26d5baeed3d2f9343cbf8366b934e368ed940402e3b22600305381d68962c503
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cab4d6c2ce43e24d19e16d85f2f7af6e830104f5a5c4b29ee3dac335d1d10f59
+oid sha256:ef95697abdf641bd80bc323eaf87e0b6bda69c5dfa3660f9cf87e3dc41a73218
 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": 0.008097165991902834,
+  "epoch": 0.00899685110211426,
   "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": 10.297,
       "eval_steps_per_second": 5.159,
       "step": 9
+    },
+    {
+      "epoch": 0.00899685110211426,
+      "grad_norm": 1.8598663806915283,
+      "learning_rate": 0.0002,
+      "loss": 4.2505,
+      "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": 5096051048448000.0,
+  "total_flos": 5605656153292800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null