Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a19be5027deb8276e646f2227e024994b7d7cf2a58fbe3961da752be7e509165
+oid sha256:4754a891d4ff82e43793e784b5555d927c5886600c77787f607532e2db801673
 size 35668592

metrics.json

@@ -7,3 +7,4 @@
 {"Step":350,"eval_loss":2.0286335945,"eval_runtime":29.3134,"eval_samples_per_second":3.411,"eval_steps_per_second":0.443,"epoch":0.2749410841}
 {"Step":400,"eval_loss":2.0177054405,"eval_runtime":29.516,"eval_samples_per_second":3.388,"eval_steps_per_second":0.44,"epoch":0.3142183818}
 {"Step":450,"eval_loss":2.001973629,"eval_runtime":29.578,"eval_samples_per_second":3.381,"eval_steps_per_second":0.44,"epoch":0.3534956795}
+{"Step":500,"eval_loss":1.9914397001,"eval_runtime":29.3577,"eval_samples_per_second":3.406,"eval_steps_per_second":0.443,"epoch":0.3927729772}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3534956794972506,
+  "epoch": 0.3927729772191673,
   "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": 3.388,
       "eval_steps_per_second": 0.44,
       "step": 400
+    },
+    {
+      "epoch": 0.3534956794972506,
+      "grad_norm": 0.18964040279388428,
+      "learning_rate": 0.0004901076520221123,
+      "loss": 1.9971,
+      "step": 450
+    },
+    {
+      "epoch": 0.3534956794972506,
+      "eval_loss": 2.0019736289978027,
+      "eval_runtime": 29.578,
+      "eval_samples_per_second": 3.381,
+      "eval_steps_per_second": 0.44,
+      "step": 450
     }
   ],
   "logging_steps": 50,
@@ -146,7 +161,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5027662845542400.0,
+  "total_flos": 5639866322780160.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null