Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e620996cd153f720211cb2e4aea403a96a43a72bdcfeae457a3f030101aa708
+oid sha256:84ca4328b493b135f4faafc09a027ff06e038fa4977c582a54a1a8400a2cb4ef
 size 35668592

metrics.json

@@ -8,3 +8,4 @@
 {"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}
+{"Step":550,"eval_loss":0.7588610053,"eval_runtime":60.6429,"eval_samples_per_second":1.649,"eval_steps_per_second":0.214,"epoch":1.0638297872}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9671179883945842,
+  "epoch": 1.0638297872340425,
   "eval_steps": 50,
-  "global_step": 500,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -142,6 +142,21 @@
       "eval_samples_per_second": 1.765,
       "eval_steps_per_second": 0.229,
       "step": 450
+    },
+    {
+      "epoch": 0.9671179883945842,
+      "grad_norm": 0.03528429567813873,
+      "learning_rate": 0.00037670250896057353,
+      "loss": 0.7507,
+      "step": 500
+    },
+    {
+      "epoch": 0.9671179883945842,
+      "eval_loss": 0.7601596117019653,
+      "eval_runtime": 56.9725,
+      "eval_samples_per_second": 1.755,
+      "eval_steps_per_second": 0.228,
+      "step": 500
     }
   ],
   "logging_steps": 50,
@@ -161,7 +176,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.844805825019904e+16,
+  "total_flos": 6.507715798573056e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null