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:f81be0283c81b4f501dd92faf31d9ff154b3b467b79947b1b56ba80dfd05348d
+oid sha256:308afa0b9cfabd0cf406b95ef20f7110ff99b08c67ec492bb99ee9dbb94e63d8
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d39d9c0a6479d8de7cf899e056c60acc96448a97af87168f88489a8749edb5
+oid sha256:447f3661a72b1000d0a657b4de1c481f9c5a967dbacb5532b9f41f8b2609e2bc
 size 79968772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46cd6548cf57356d06110dd9ff05533c4bb7eef30ad20289e6c41822d13ac4ad
+oid sha256:8d291a024a00b1aa3b3c84b72d282fb9a12c696d949b4c79386b0b36f723c2d2
 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": 0.1414141414141414,
+  "epoch": 0.18518518518518517,
   "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": 74.112,
       "eval_steps_per_second": 18.973,
       "step": 42
+    },
+    {
+      "epoch": 0.16835016835016836,
+      "grad_norm": 0.23909038305282593,
+      "learning_rate": 0.0002,
+      "loss": 0.0494,
+      "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": 2086171211464704.0,
+  "total_flos": 2731890872156160.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null