Training in progress, step 1250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a506900ef7b68c44ed7c9b2fc4220f560bce93148c6c6063f3c4d3e209b7ec81
+oid sha256:25b9555b512ee0f3ff5928956f20f7f34bbb2aa124b7d66480399f453c7567e1
 size 35668592

metrics.json

@@ -22,3 +22,4 @@
 {"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}
 {"Step":1200,"eval_loss":1.8822929859,"eval_runtime":29.4891,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":0.9426551453}
+{"Step":1250,"eval_loss":1.8784922361,"eval_runtime":29.4313,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":0.981932443}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9426551453260016,
+  "epoch": 0.9819324430479183,
   "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": 3.398,
       "eval_steps_per_second": 0.442,
       "step": 1150
+    },
+    {
+      "epoch": 0.9426551453260016,
+      "grad_norm": 0.14458701014518738,
+      "learning_rate": 0.0003810008728542333,
+      "loss": 1.9261,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9426551453260016,
+      "eval_loss": 1.8822929859161377,
+      "eval_runtime": 29.4891,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.441,
+      "step": 1200
     }
   ],
   "logging_steps": 50,
@@ -371,7 +386,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.443890319310848e+16,
+  "total_flos": 1.507062983565312e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null