Training in progress, step 850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab3123cd2501470f99ee711a486049453edf41ab76ce80ab6547479ad7fc8e3
+oid sha256:a6c7263a7954b3c88441c967ecceb812be5104a076841369ba94e3b504f8c774
 size 35668592

metrics.json

@@ -14,3 +14,4 @@
 {"Step":700,"eval_loss":1.9546252489,"eval_runtime":29.5017,"eval_samples_per_second":3.39,"eval_steps_per_second":0.441,"epoch":0.5498821681}
 {"Step":750,"eval_loss":1.9469780922,"eval_runtime":29.8753,"eval_samples_per_second":3.347,"eval_steps_per_second":0.435,"epoch":0.5891594658}
 {"Step":800,"eval_loss":1.9397352934,"eval_runtime":29.4107,"eval_samples_per_second":3.4,"eval_steps_per_second":0.442,"epoch":0.6284367636}
+{"Step":850,"eval_loss":1.9425079823,"eval_runtime":29.4898,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":0.6677140613}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6284367635506677,
+  "epoch": 0.6677140612725845,
   "eval_steps": 50,
-  "global_step": 800,
+  "global_step": 850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -232,6 +232,21 @@
       "eval_samples_per_second": 3.347,
       "eval_steps_per_second": 0.435,
       "step": 750
+    },
+    {
+      "epoch": 0.6284367635506677,
+      "grad_norm": 0.19608749449253082,
+      "learning_rate": 0.0004391911550771021,
+      "loss": 1.9408,
+      "step": 800
+    },
+    {
+      "epoch": 0.6284367635506677,
+      "eval_loss": 1.9397352933883667,
+      "eval_runtime": 29.4107,
+      "eval_samples_per_second": 3.4,
+      "eval_steps_per_second": 0.442,
+      "step": 800
     }
   ],
   "logging_steps": 50,
@@ -251,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9397806976942080.0,
+  "total_flos": 1.002595138732032e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null