Training in progress, step 1250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001db2cc0f28eef9e586f657554b5c65108455c804890b96f6eac5c4428c92cd
+oid sha256:e8ebe2118199830aa8d71391608f11945dfea373477645282fc897b0b7593d37
 size 35668592

metrics.json

@@ -22,3 +22,4 @@
 {"Step":1100,"eval_loss":0.7509506345,"eval_runtime":56.8661,"eval_samples_per_second":1.759,"eval_steps_per_second":0.229,"epoch":2.1276595745}
 {"Step":1150,"eval_loss":0.7505396008,"eval_runtime":56.5726,"eval_samples_per_second":1.768,"eval_steps_per_second":0.23,"epoch":2.2243713733}
 {"Step":1200,"eval_loss":0.7510370612,"eval_runtime":56.6798,"eval_samples_per_second":1.764,"eval_steps_per_second":0.229,"epoch":2.3210831721}
+{"Step":1250,"eval_loss":0.7501779795,"eval_runtime":56.6502,"eval_samples_per_second":1.765,"eval_steps_per_second":0.229,"epoch":2.417794971}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3210831721470018,
+  "epoch": 2.4177949709864603,
   "eval_steps": 50,
-  "global_step": 1200,
+  "global_step": 1250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -352,6 +352,21 @@
       "eval_samples_per_second": 1.768,
       "eval_steps_per_second": 0.23,
       "step": 1150
+    },
+    {
+      "epoch": 2.3210831721470018,
+      "grad_norm": 0.043631162494421005,
+      "learning_rate": 0.00012580645161290322,
+      "loss": 0.7242,
+      "step": 1200
+    },
+    {
+      "epoch": 2.3210831721470018,
+      "eval_loss": 0.751037061214447,
+      "eval_runtime": 56.6798,
+      "eval_samples_per_second": 1.764,
+      "eval_steps_per_second": 0.229,
+      "step": 1200
     }
   ],
   "logging_steps": 50,
@@ -371,7 +386,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4913266854373376e+17,
+  "total_flos": 1.55590895804928e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null