Training in progress, step 1150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:924c4d4d6522023e206826f8846fe40e8c770ac9967ac2ad0f4fd77ed07ae880
+oid sha256:31bdb9899bcd39de8ac7c8798b488848ac89ad7e6d2485f73f56eab68c7e6e24
 size 35668592

metrics.json

@@ -20,3 +20,4 @@
 {"Step":1000,"eval_loss":1.9071648121,"eval_runtime":29.4527,"eval_samples_per_second":3.395,"eval_steps_per_second":0.441,"epoch":0.7855459544}
 {"Step":1050,"eval_loss":1.8993133307,"eval_runtime":29.5512,"eval_samples_per_second":3.384,"eval_steps_per_second":0.44,"epoch":0.8248232522}
 {"Step":1100,"eval_loss":1.9054021835,"eval_runtime":29.3876,"eval_samples_per_second":3.403,"eval_steps_per_second":0.442,"epoch":0.8641005499}
+{"Step":1150,"eval_loss":1.8948385715,"eval_runtime":29.428,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":0.9033778476}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8641005498821681,
+  "epoch": 0.9033778476040848,
   "eval_steps": 50,
-  "global_step": 1100,
+  "global_step": 1150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -322,6 +322,21 @@
       "eval_samples_per_second": 3.384,
       "eval_steps_per_second": 0.44,
       "step": 1050
+    },
+    {
+      "epoch": 0.8641005498821681,
+      "grad_norm": 0.16182482242584229,
+      "learning_rate": 0.00039554844340995054,
+      "loss": 1.9183,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8641005498821681,
+      "eval_loss": 1.9054021835327148,
+      "eval_runtime": 29.3876,
+      "eval_samples_per_second": 3.403,
+      "eval_steps_per_second": 0.442,
+      "step": 1100
     }
   ],
   "logging_steps": 50,
@@ -341,7 +356,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.316362854187008e+16,
+  "total_flos": 1.378693693882368e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null