Training in progress, step 125

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:991de16316201409d6ee8026268d6e6f98363867bb77e38a127dc24aad73c65c
+oid sha256:79a7f9067104ba188f808a51c9fa02a0efe307c1fa192f76821eb446bfdce94c
 size 35668592

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.96,
+  "epoch": 1.0,
   "eval_steps": 20,
-  "global_step": 120,
+  "global_step": 125,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,21 @@
       "eval_samples_per_second": 3.375,
       "eval_steps_per_second": 0.422,
       "step": 100
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.07054605334997177,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 1.6203,
+      "step": 120
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 1.5859812498092651,
+      "eval_runtime": 295.6456,
+      "eval_samples_per_second": 3.382,
+      "eval_steps_per_second": 0.423,
+      "step": 120
     }
   ],
   "logging_steps": 20,
@@ -101,7 +116,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8703928606310400.0,
+  "total_flos": 9518169977733120.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null