Training in progress, step 400

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a8d2429cebb283bbde4c281dd25c1ea90c2fb3b23caa9c63898b7d60443418
+oid sha256:23665d43962ec60940e693cfa26c0650c774a5d7a50c4f6533d64dd93f91953e
 size 35668592

metrics.json

@@ -5,3 +5,4 @@
 {"Step":250,"eval_loss":1.4578460455,"eval_runtime":27.6799,"eval_samples_per_second":3.613,"eval_steps_per_second":0.47,"epoch":0.4}
 {"Step":300,"eval_loss":1.4557801485,"eval_runtime":27.6578,"eval_samples_per_second":3.616,"eval_steps_per_second":0.47,"epoch":0.48}
 {"Step":350,"eval_loss":1.4533815384,"eval_runtime":27.6598,"eval_samples_per_second":3.615,"eval_steps_per_second":0.47,"epoch":0.56}
+{"Step":400,"eval_loss":1.4522851706,"eval_runtime":27.5987,"eval_samples_per_second":3.623,"eval_steps_per_second":0.471,"epoch":0.64}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.56,
+  "epoch": 0.64,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -97,6 +97,21 @@
       "eval_samples_per_second": 3.616,
       "eval_steps_per_second": 0.47,
       "step": 300
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.03970955312252045,
+      "learning_rate": 0.00045228215767634857,
+      "loss": 1.4878,
+      "step": 350
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 1.4533815383911133,
+      "eval_runtime": 27.6598,
+      "eval_samples_per_second": 3.615,
+      "eval_steps_per_second": 0.47,
+      "step": 350
     }
   ],
   "logging_steps": 50,
@@ -116,7 +131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4063644577792e+16,
+  "total_flos": 2.81330603188224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null