Training in progress, step 3500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abea7f9424ac3af02ad0b09dd1a849679c84990a99d528292dc169390598a368
+oid sha256:8e85740d5df521aaba95b3f99bf2df807c84588915232157edd1d90942ab64d0
 size 35668592

metrics.json

@@ -67,3 +67,4 @@
 {"Step":3350,"eval_loss":1.7433184385,"eval_runtime":29.6962,"eval_samples_per_second":3.367,"eval_steps_per_second":0.438,"epoch":2.6315789474}
 {"Step":3400,"eval_loss":1.7429870367,"eval_runtime":29.4333,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":2.6708562451}
 {"Step":3450,"eval_loss":1.7402327061,"eval_runtime":29.6244,"eval_samples_per_second":3.376,"eval_steps_per_second":0.439,"epoch":2.7101335428}
+{"Step":3500,"eval_loss":1.7408081293,"eval_runtime":29.3534,"eval_samples_per_second":3.407,"eval_steps_per_second":0.443,"epoch":2.7494108405}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7101335428122546,
+  "epoch": 2.7494108405341713,
   "eval_steps": 50,
-  "global_step": 3450,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1027,6 +1027,21 @@
       "eval_samples_per_second": 3.398,
       "eval_steps_per_second": 0.442,
       "step": 3400
+    },
+    {
+      "epoch": 2.7101335428122546,
+      "grad_norm": 0.218011736869812,
+      "learning_rate": 5.368053535059645e-05,
+      "loss": 1.7407,
+      "step": 3450
+    },
+    {
+      "epoch": 2.7101335428122546,
+      "eval_loss": 1.7402327060699463,
+      "eval_runtime": 29.6244,
+      "eval_samples_per_second": 3.376,
+      "eval_steps_per_second": 0.439,
+      "step": 3450
     }
   ],
   "logging_steps": 50,
@@ -1046,7 +1061,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.279455446317056e+16,
+  "total_flos": 4.34029965966336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null