Training in progress, step 55, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57ac5458d3d0d5d78230ca8f398033d18a0d5b9077611ce6bedae8e428f30854
+oid sha256:5be272363f418c0338d7564dcb9633edbb4076cf77315a4baec3ac842f6d23d6
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4dbb17253e61d95e95a111e40e05086a475fb3a67328c5c20042cd4dc424f51
+oid sha256:b56b57e13caa04de6a03c3383312ee64ca0ce53e2daa539a95eac1f72bb98406
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21ce8da2a770ae26204c94d75d61c4f49b14d2265c90c54f61bc1b42d9ec0646
+oid sha256:86734a139c67e84ec09440c2d777ca078818f63c2511658eb5a0447b8d4eb6a8
 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": 0.007380073800738007,
+  "epoch": 0.009664382358109295,
   "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": 18.485,
       "eval_steps_per_second": 4.627,
       "step": 42
+    },
+    {
+      "epoch": 0.008785802143735724,
+      "grad_norm": 2.3993775844573975,
+      "learning_rate": 0.0002,
+      "loss": 1.368,
+      "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": 1.4852314468712448e+16,
+  "total_flos": 1.944945942331392e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null