Training in progress, step 800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0424afb30df829ce224879dc3e6008ca6f265eb79c4d26839dfa7c24d29e45
+oid sha256:0542ca728b0b0c499e1f5d9f35236e5724215b3bfded75c2861297e7a1ffed12
 size 35668592

metrics.json

@@ -13,3 +13,4 @@
 {"Step":650,"eval_loss":0.7570986748,"eval_runtime":56.5753,"eval_samples_per_second":1.768,"eval_steps_per_second":0.23,"epoch":1.2572533849}
 {"Step":700,"eval_loss":0.7555394173,"eval_runtime":56.5444,"eval_samples_per_second":1.769,"eval_steps_per_second":0.23,"epoch":1.3539651838}
 {"Step":750,"eval_loss":0.7549133897,"eval_runtime":56.529,"eval_samples_per_second":1.769,"eval_steps_per_second":0.23,"epoch":1.4506769826}
+{"Step":800,"eval_loss":0.7541146278,"eval_runtime":60.5765,"eval_samples_per_second":1.651,"eval_steps_per_second":0.215,"epoch":1.5473887814}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4506769825918762,
+  "epoch": 1.5473887814313345,
   "eval_steps": 50,
-  "global_step": 750,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,21 @@
       "eval_samples_per_second": 1.769,
       "eval_steps_per_second": 0.23,
       "step": 700
+    },
+    {
+      "epoch": 1.4506769825918762,
+      "grad_norm": 0.037061236798763275,
+      "learning_rate": 0.0002870967741935484,
+      "loss": 0.7471,
+      "step": 750
+    },
+    {
+      "epoch": 1.4506769825918762,
+      "eval_loss": 0.7549133896827698,
+      "eval_runtime": 56.529,
+      "eval_samples_per_second": 1.769,
+      "eval_steps_per_second": 0.23,
+      "step": 750
     }
   ],
   "logging_steps": 50,
@@ -236,7 +251,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.079635354817536e+16,
+  "total_flos": 9.716198010786816e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null