Training in progress, step 1750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:826e1e57c253eca6a718882f07f5e08f73ee2d2aaf01d05e73e4e05231502dac
+oid sha256:6a02294147bd8a9d203559d524bfd3e2fd1683dd80bcbf72efa928d5af949022
 size 35668592

metrics.json

@@ -32,3 +32,4 @@
 {"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}
+{"Step":1750,"eval_loss":1.8384497166,"eval_runtime":29.4803,"eval_samples_per_second":3.392,"eval_steps_per_second":0.441,"epoch":1.3747054203}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.335428122545169,
+  "epoch": 1.3747054202670856,
   "eval_steps": 50,
-  "global_step": 1700,
+  "global_step": 1750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -502,6 +502,21 @@
       "eval_samples_per_second": 3.394,
       "eval_steps_per_second": 0.441,
       "step": 1650
+    },
+    {
+      "epoch": 1.335428122545169,
+      "grad_norm": 0.21005484461784363,
+      "learning_rate": 0.0003082630200756474,
+      "loss": 1.8661,
+      "step": 1700
+    },
+    {
+      "epoch": 1.335428122545169,
+      "eval_loss": 1.8399604558944702,
+      "eval_runtime": 29.4709,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.441,
+      "step": 1700
     }
   ],
   "logging_steps": 50,
@@ -521,7 +536,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.078764848371712e+16,
+  "total_flos": 2.144677920233472e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null