Training in progress, step 110

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ad3f448319f6634235c977e9c7622be7970146c251a3a932df2d2e2349bf78
+oid sha256:971eb4dce686ad648c7705b6c521505ecb2d5dbc4b7bfd367dfe9618630ae0d6
 size 35668592

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
+  "epoch": 0.88,
   "eval_steps": 20,
-  "global_step": 100,
+  "global_step": 110,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,21 @@
       "eval_samples_per_second": 3.388,
       "eval_steps_per_second": 0.424,
       "step": 80
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.06708831340074539,
+      "learning_rate": 2.3214285714285715e-05,
+      "loss": 1.6024,
+      "step": 100
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.5983840227127075,
+      "eval_runtime": 296.3017,
+      "eval_samples_per_second": 3.375,
+      "eval_steps_per_second": 0.422,
+      "step": 100
     }
   ],
   "logging_steps": 20,
@@ -86,7 +101,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7122910439669760.0,
+  "total_flos": 7927479784243200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null