Training in progress, step 450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23665d43962ec60940e693cfa26c0650c774a5d7a50c4f6533d64dd93f91953e
+oid sha256:b0ee209e29161e3328d6408dd90144705f7e41e1e55d1f70ddc551c08494f00c
 size 35668592

metrics.json

@@ -6,3 +6,4 @@
 {"Step":300,"eval_loss":1.4557801485,"eval_runtime":27.6578,"eval_samples_per_second":3.616,"eval_steps_per_second":0.47,"epoch":0.48}
 {"Step":350,"eval_loss":1.4533815384,"eval_runtime":27.6598,"eval_samples_per_second":3.615,"eval_steps_per_second":0.47,"epoch":0.56}
 {"Step":400,"eval_loss":1.4522851706,"eval_runtime":27.5987,"eval_samples_per_second":3.623,"eval_steps_per_second":0.471,"epoch":0.64}
+{"Step":450,"eval_loss":1.4484608173,"eval_runtime":27.6359,"eval_samples_per_second":3.618,"eval_steps_per_second":0.47,"epoch":0.72}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.64,
+  "epoch": 0.72,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,21 @@
       "eval_samples_per_second": 3.615,
       "eval_steps_per_second": 0.47,
       "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.03238854929804802,
+      "learning_rate": 0.0004374629519857736,
+      "loss": 1.4765,
+      "step": 400
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.4522851705551147,
+      "eval_runtime": 27.5987,
+      "eval_samples_per_second": 3.623,
+      "eval_steps_per_second": 0.471,
+      "step": 400
     }
   ],
   "logging_steps": 50,
@@ -131,7 +146,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.81330603188224e+16,
+  "total_flos": 3.211130825121792e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null