Training in progress, step 2250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71982cf6e3bd9fa9ad7d1b96ca24acd745ae147272ce6423d668156c5c857ef3
+oid sha256:fbc0fece70ab1538e00171cecdf7ed2a2d9d17c399fdaf69b7d59568e5491a71
 size 35668592

metrics.json

@@ -42,3 +42,4 @@
 {"Step":2100,"eval_loss":1.8001557589,"eval_runtime":29.4349,"eval_samples_per_second":3.397,"eval_steps_per_second":0.442,"epoch":1.6496465043}
 {"Step":2150,"eval_loss":1.8008465767,"eval_runtime":29.3948,"eval_samples_per_second":3.402,"eval_steps_per_second":0.442,"epoch":1.688923802}
 {"Step":2200,"eval_loss":1.7969157696,"eval_runtime":29.4741,"eval_samples_per_second":3.393,"eval_steps_per_second":0.441,"epoch":1.7282010998}
+{"Step":2250,"eval_loss":1.7962598801,"eval_runtime":29.3661,"eval_samples_per_second":3.405,"eval_steps_per_second":0.443,"epoch":1.7674783975}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7282010997643362,
+  "epoch": 1.767478397486253,
   "eval_steps": 50,
-  "global_step": 2200,
+  "global_step": 2250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -652,6 +652,21 @@
       "eval_samples_per_second": 3.402,
       "eval_steps_per_second": 0.442,
       "step": 2150
+    },
+    {
+      "epoch": 1.7282010997643362,
+      "grad_norm": 0.20354895293712616,
+      "learning_rate": 0.0002355251672970614,
+      "loss": 1.8297,
+      "step": 2200
+    },
+    {
+      "epoch": 1.7282010997643362,
+      "eval_loss": 1.7969157695770264,
+      "eval_runtime": 29.4741,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.441,
+      "step": 2200
     }
   ],
   "logging_steps": 50,
@@ -671,7 +686,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.706730147141632e+16,
+  "total_flos": 2.770619257829376e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null