Training in progress, step 750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d802db11b0159c88a394933a1d20e5319f8ee8804fafa8042da038283f60ed
+oid sha256:3c4eff90f98e29b6d31bf4f6a742a1d3c58859c79a62c2c2bdb2a1453ac489e5
 size 35668592

metrics.json

@@ -12,3 +12,4 @@
 {"Step":600,"eval_loss":1.9679882526,"eval_runtime":29.7136,"eval_samples_per_second":3.365,"eval_steps_per_second":0.438,"epoch":0.4713275727}
 {"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5498821681068342,
+  "epoch": 0.589159465828751,
   "eval_steps": 50,
-  "global_step": 700,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -202,6 +202,21 @@
       "eval_samples_per_second": 3.35,
       "eval_steps_per_second": 0.436,
       "step": 650
+    },
+    {
+      "epoch": 0.5498821681068342,
+      "grad_norm": 0.1479049026966095,
+      "learning_rate": 0.0004537387256328193,
+      "loss": 1.9423,
+      "step": 700
+    },
+    {
+      "epoch": 0.5498821681068342,
+      "eval_loss": 1.9546252489089966,
+      "eval_runtime": 29.5017,
+      "eval_samples_per_second": 3.39,
+      "eval_steps_per_second": 0.441,
+      "step": 700
     }
   ],
   "logging_steps": 50,
@@ -221,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8111069182771200.0,
+  "total_flos": 8759453204889600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null