Training in progress, step 450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f2c1302eb8dfb962ee436ed86d8053a028b223b513b799301c3f5386b08b0d
+oid sha256:05ebb8e061ac912f602df410a9d77dcf61863b3c8d47ebd333b092a5901e23b7
 size 35668592

metrics.json

@@ -6,3 +6,4 @@
 {"Step":300,"eval_loss":0.7687731385,"eval_runtime":60.6867,"eval_samples_per_second":1.648,"eval_steps_per_second":0.214,"epoch":0.580270793}
 {"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7736943907156673,
+  "epoch": 0.8704061895551257,
   "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": 1.767,
       "eval_steps_per_second": 0.23,
       "step": 350
+    },
+    {
+      "epoch": 0.7736943907156673,
+      "grad_norm": 0.03772694244980812,
+      "learning_rate": 0.0004125448028673835,
+      "loss": 0.7529,
+      "step": 400
+    },
+    {
+      "epoch": 0.7736943907156673,
+      "eval_loss": 0.7637045383453369,
+      "eval_runtime": 56.5561,
+      "eval_samples_per_second": 1.768,
+      "eval_steps_per_second": 0.23,
+      "step": 400
     }
   ],
   "logging_steps": 50,
@@ -131,7 +146,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.537237350801408e+16,
+  "total_flos": 5.189203605086208e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null