Training in progress, step 55, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:391aa554a5c39b4bad013a26f2e16c2824fb367a409b4bcb35799daf8eda736b
+oid sha256:acd84131de42b617315f7297652091ab0bb120311f10fe5db30646f16e1f5eda
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bb344be1948b9b83b566890b70cfa0b7d34d701792aa2304bec6b84af2c0302
+oid sha256:19c800473a0ef7d1059c5e82dc99e0714f79eb41a271026555db726c9edce946
 size 102537556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab2f98fefe154e81ae019ab6ca8efc87cabfa7a5abfa20a38fadf1b527f268a8
+oid sha256:632c939e85acc2c85823b34578a51f7f495f4de0e36f0295fd4e10d95a906aa4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43352a0ea01b8f309df99bb65027960564fe5f2f452a04b8b6c955b0ecfed4cf
+oid sha256:8b16062161cca6c6d42c840fa02f9c59f431931479788fa87a822481c8e65827
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007377481117161426,
+  "epoch": 0.009660987177235202,
   "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": 34.711,
       "eval_steps_per_second": 17.37,
       "step": 42
+    },
+    {
+      "epoch": 0.008782715615668365,
+      "grad_norm": 5.8445587158203125,
+      "learning_rate": 0.0002,
+      "loss": 2.7728,
+      "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": 1947184064888832.0,
+  "total_flos": 2549883894497280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null