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:b6a5d0f01b77802e68db4f9d611f70edab43a9232ce53e82b68060805f1fcf13
+oid sha256:5888724692bb2f9ae8edfb2feda3bf01ba7c5fb58bf8b4ef55527e3388ff7852
 size 682685984

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45bf7311db649b1b18934ddb295f4935f1fa9cbd95b36f8a6cd8f49375867b41
+oid sha256:4d72e994ad17a24523df03c3a62e369b5a43819b36eac3dc080f77055c86a9a8
 size 85498196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f33eab43f94c54c28d44f815245195ca47f5bccffb6fd58d916729befff7f8a
+oid sha256:6c906aeeab09b791ea00c976eedf713fa4ceab6d97f1da939e9785b51af47dc6
 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": 0.07368421052631578,
+  "epoch": 0.09649122807017543,
   "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": 72.789,
       "eval_steps_per_second": 18.197,
       "step": 42
+    },
+    {
+      "epoch": 0.08771929824561403,
+      "grad_norm": 2.2857017517089844,
+      "learning_rate": 0.0002,
+      "loss": 2.9834,
+      "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": 2774857112616960.0,
+  "total_flos": 3633741456998400.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null