Training in progress, step 800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c4eff90f98e29b6d31bf4f6a742a1d3c58859c79a62c2c2bdb2a1453ac489e5
+oid sha256:0ab3123cd2501470f99ee711a486049453edf41ab76ce80ab6547479ad7fc8e3
 size 35668592

metrics.json

@@ -13,3 +13,4 @@
 {"Step":650,"eval_loss":1.9631274939,"eval_runtime":29.8472,"eval_samples_per_second":3.35,"eval_steps_per_second":0.436,"epoch":0.5106048704}
 {"Step":700,"eval_loss":1.9546252489,"eval_runtime":29.5017,"eval_samples_per_second":3.39,"eval_steps_per_second":0.441,"epoch":0.5498821681}
 {"Step":750,"eval_loss":1.9469780922,"eval_runtime":29.8753,"eval_samples_per_second":3.347,"eval_steps_per_second":0.435,"epoch":0.5891594658}
+{"Step":800,"eval_loss":1.9397352934,"eval_runtime":29.4107,"eval_samples_per_second":3.4,"eval_steps_per_second":0.442,"epoch":0.6284367636}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.589159465828751,
+  "epoch": 0.6284367635506677,
   "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": 3.39,
       "eval_steps_per_second": 0.441,
       "step": 700
+    },
+    {
+      "epoch": 0.589159465828751,
+      "grad_norm": 0.14641450345516205,
+      "learning_rate": 0.0004464649403549607,
+      "loss": 1.9587,
+      "step": 750
+    },
+    {
+      "epoch": 0.589159465828751,
+      "eval_loss": 1.9469780921936035,
+      "eval_runtime": 29.8753,
+      "eval_samples_per_second": 3.347,
+      "eval_steps_per_second": 0.435,
+      "step": 750
     }
   ],
   "logging_steps": 50,
@@ -236,7 +251,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8759453204889600.0,
+  "total_flos": 9397806976942080.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null