Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ebb8e061ac912f602df410a9d77dcf61863b3c8d47ebd333b092a5901e23b7
+oid sha256:3e620996cd153f720211cb2e4aea403a96a43a72bdcfeae457a3f030101aa708
 size 35668592

metrics.json

@@ -7,3 +7,4 @@
 {"Step":350,"eval_loss":0.7662523389,"eval_runtime":56.5991,"eval_samples_per_second":1.767,"eval_steps_per_second":0.23,"epoch":0.6769825919}
 {"Step":400,"eval_loss":0.7637045383,"eval_runtime":56.5561,"eval_samples_per_second":1.768,"eval_steps_per_second":0.23,"epoch":0.7736943907}
 {"Step":450,"eval_loss":0.7616338134,"eval_runtime":56.6718,"eval_samples_per_second":1.765,"eval_steps_per_second":0.229,"epoch":0.8704061896}
+{"Step":500,"eval_loss":0.7601596117,"eval_runtime":56.9725,"eval_samples_per_second":1.755,"eval_steps_per_second":0.228,"epoch":0.9671179884}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8704061895551257,
+  "epoch": 0.9671179883945842,
   "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": 1.768,
       "eval_steps_per_second": 0.23,
       "step": 400
+    },
+    {
+      "epoch": 0.8704061895551257,
+      "grad_norm": 0.04153395816683769,
+      "learning_rate": 0.00039462365591397855,
+      "loss": 0.7562,
+      "step": 450
+    },
+    {
+      "epoch": 0.8704061895551257,
+      "eval_loss": 0.7616338133811951,
+      "eval_runtime": 56.6718,
+      "eval_samples_per_second": 1.765,
+      "eval_steps_per_second": 0.229,
+      "step": 450
     }
   ],
   "logging_steps": 50,
@@ -146,7 +161,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.189203605086208e+16,
+  "total_flos": 5.844805825019904e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null