Training in progress, step 1400

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b49296fb20e1f4737ca4b3be6762448d99c7c4402dfb07a306f7a6007855f7
+oid sha256:079525c8ed387cce1ea9e0669805467b05b018b02e24d14699f2e7957dacfe7f
 size 35668592

metrics.json

@@ -25,3 +25,4 @@
 {"Step":1250,"eval_loss":1.8784922361,"eval_runtime":29.4313,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":0.981932443}
 {"Step":1300,"eval_loss":1.8769853115,"eval_runtime":29.4816,"eval_samples_per_second":3.392,"eval_steps_per_second":0.441,"epoch":1.0212097408}
 {"Step":1350,"eval_loss":1.8668268919,"eval_runtime":29.5392,"eval_samples_per_second":3.385,"eval_steps_per_second":0.44,"epoch":1.0604870385}
+{"Step":1400,"eval_loss":1.8661786318,"eval_runtime":29.4511,"eval_samples_per_second":3.395,"eval_steps_per_second":0.441,"epoch":1.0997643362}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0604870384917517,
+  "epoch": 1.0997643362136684,
   "eval_steps": 50,
-  "global_step": 1350,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -397,6 +397,21 @@
       "eval_samples_per_second": 3.392,
       "eval_steps_per_second": 0.441,
       "step": 1300
+    },
+    {
+      "epoch": 1.0604870384917517,
+      "grad_norm": 0.18526038527488708,
+      "learning_rate": 0.00035917951702065757,
+      "loss": 1.8603,
+      "step": 1350
+    },
+    {
+      "epoch": 1.0604870384917517,
+      "eval_loss": 1.8668268918991089,
+      "eval_runtime": 29.5392,
+      "eval_samples_per_second": 3.385,
+      "eval_steps_per_second": 0.44,
+      "step": 1350
     }
   ],
   "logging_steps": 50,
@@ -416,7 +431,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.635230772688896e+16,
+  "total_flos": 1.698206414174208e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null