Training in progress, step 150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a204f7ba1263f6a7e60e5f98f50f704c1b55953c604ab0c7cc48edce48deaa24
+oid sha256:c5b9f4dc32699676ed5aa5adc17bcffbf6920fd246efc1c3bbbb6199972d581e
 size 35668592

metrics.json

@@ -1,2 +1,3 @@
 {"Step":50,"eval_loss":1.7071695328,"eval_runtime":27.6118,"eval_samples_per_second":3.622,"eval_steps_per_second":0.471,"epoch":0.08}
 {"Step":100,"eval_loss":1.4855879545,"eval_runtime":27.6396,"eval_samples_per_second":3.618,"eval_steps_per_second":0.47,"epoch":0.16}
+{"Step":150,"eval_loss":1.4662159681,"eval_runtime":27.5933,"eval_samples_per_second":3.624,"eval_steps_per_second":0.471,"epoch":0.24}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16,
+  "epoch": 0.24,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,6 +22,21 @@
       "eval_samples_per_second": 3.622,
       "eval_steps_per_second": 0.471,
       "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.02606302499771118,
+      "learning_rate": 0.0002632978723404255,
+      "loss": 1.6036,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 1.4855879545211792,
+      "eval_runtime": 27.6396,
+      "eval_samples_per_second": 3.618,
+      "eval_steps_per_second": 0.47,
+      "step": 100
     }
   ],
   "logging_steps": 50,
@@ -41,7 +56,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4002786222735360.0,
+  "total_flos": 8026528503644160.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null