Training in progress, step 1900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a7ff2f497205b297d83618f87778f1833f94c73aacdd604b6986e6cf2b1406
+oid sha256:e4ba6555d1283eae2b128a4103aef1a8018e6c4c4289b166698c46e61ced236b
 size 35668592

metrics.json

@@ -35,3 +35,4 @@
 {"Step":1750,"eval_loss":1.9372723103,"eval_runtime":27.2797,"eval_samples_per_second":3.666,"eval_steps_per_second":0.477,"epoch":2.751572327}
 {"Step":1800,"eval_loss":1.9364655018,"eval_runtime":27.2904,"eval_samples_per_second":3.664,"eval_steps_per_second":0.476,"epoch":2.8301886792}
 {"Step":1850,"eval_loss":1.9341883659,"eval_runtime":27.2939,"eval_samples_per_second":3.664,"eval_steps_per_second":0.476,"epoch":2.9088050314}
+{"Step":1900,"eval_loss":1.9331157207,"eval_runtime":27.3592,"eval_samples_per_second":3.655,"eval_steps_per_second":0.475,"epoch":2.9874213836}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.908805031446541,
+  "epoch": 2.9874213836477987,
   "eval_steps": 50,
-  "global_step": 1850,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -547,6 +547,21 @@
       "eval_samples_per_second": 3.664,
       "eval_steps_per_second": 0.476,
       "step": 1800
+    },
+    {
+      "epoch": 2.908805031446541,
+      "grad_norm": 0.22059138119220734,
+      "learning_rate": 1.68899242865463e-05,
+      "loss": 1.8207,
+      "step": 1850
+    },
+    {
+      "epoch": 2.908805031446541,
+      "eval_loss": 1.9341883659362793,
+      "eval_runtime": 27.2939,
+      "eval_samples_per_second": 3.664,
+      "eval_steps_per_second": 0.476,
+      "step": 1850
     }
   ],
   "logging_steps": 50,
@@ -566,7 +581,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.249892556750848e+16,
+  "total_flos": 2.314372735746048e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null