Training in progress, step 1700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8335629fc723a1359d824244a9ea22d0ba4f283c1a833c7a9ff4101ff6d09ecd
+oid sha256:826e1e57c253eca6a718882f07f5e08f73ee2d2aaf01d05e73e4e05231502dac
 size 35668592

metrics.json

@@ -31,3 +31,4 @@
 {"Step":1550,"eval_loss":1.8602547646,"eval_runtime":29.5084,"eval_samples_per_second":3.389,"eval_steps_per_second":0.441,"epoch":1.2175962294}
 {"Step":1600,"eval_loss":1.8516952991,"eval_runtime":29.539,"eval_samples_per_second":3.385,"eval_steps_per_second":0.44,"epoch":1.2568735271}
 {"Step":1650,"eval_loss":1.8447459936,"eval_runtime":29.4621,"eval_samples_per_second":3.394,"eval_steps_per_second":0.441,"epoch":1.2961508248}
+{"Step":1700,"eval_loss":1.8399604559,"eval_runtime":29.4709,"eval_samples_per_second":3.393,"eval_steps_per_second":0.441,"epoch":1.3354281225}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2961508248232523,
+  "epoch": 1.335428122545169,
   "eval_steps": 50,
-  "global_step": 1650,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -487,6 +487,21 @@
       "eval_samples_per_second": 3.385,
       "eval_steps_per_second": 0.44,
       "step": 1600
+    },
+    {
+      "epoch": 1.2961508248232523,
+      "grad_norm": 0.23483967781066895,
+      "learning_rate": 0.000315536805353506,
+      "loss": 1.8204,
+      "step": 1650
+    },
+    {
+      "epoch": 1.2961508248232523,
+      "eval_loss": 1.8447459936141968,
+      "eval_runtime": 29.4621,
+      "eval_samples_per_second": 3.394,
+      "eval_steps_per_second": 0.441,
+      "step": 1650
     }
   ],
   "logging_steps": 50,
@@ -506,7 +521,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.017078810466304e+16,
+  "total_flos": 2.078764848371712e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null