Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0ee209e29161e3328d6408dd90144705f7e41e1e55d1f70ddc551c08494f00c
+oid sha256:20e5dde333ed120063aeedbe3bb3fe678dcd00c642436caca387051d76c52325
 size 35668592

metrics.json

@@ -7,3 +7,4 @@
 {"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}
+{"Step":500,"eval_loss":1.4477622509,"eval_runtime":27.6496,"eval_samples_per_second":3.617,"eval_steps_per_second":0.47,"epoch":0.8}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.72,
+  "epoch": 0.8,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,21 @@
       "eval_samples_per_second": 3.623,
       "eval_steps_per_second": 0.471,
       "step": 400
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.04000236839056015,
+      "learning_rate": 0.0004226437462951986,
+      "loss": 1.4803,
+      "step": 450
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 1.4484608173370361,
+      "eval_runtime": 27.6359,
+      "eval_samples_per_second": 3.618,
+      "eval_steps_per_second": 0.47,
+      "step": 450
     }
   ],
   "logging_steps": 50,
@@ -146,7 +161,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.211130825121792e+16,
+  "total_flos": 3.610746734444544e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null