Training in progress, step 330

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164cd75ce7d75783388fda00bd1983d8add8c0d60e1682807773d77977bbb275
+oid sha256:673aa39bdc5c2f0ebc47b58e552386c125809c5f0bc1ce481fb92273af7b8e68
 size 35668592

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.512,
+  "epoch": 0.528,
   "eval_steps": 20,
-  "global_step": 320,
+  "global_step": 330,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -232,6 +232,21 @@
       "eval_samples_per_second": 3.396,
       "eval_steps_per_second": 0.425,
       "step": 300
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.03938526660203934,
+      "learning_rate": 0.00046117368109069355,
+      "loss": 1.4996,
+      "step": 320
+    },
+    {
+      "epoch": 0.512,
+      "eval_loss": 1.4825308322906494,
+      "eval_runtime": 1500.8065,
+      "eval_samples_per_second": 3.332,
+      "eval_steps_per_second": 0.416,
+      "step": 320
     }
   ],
   "logging_steps": 20,
@@ -251,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.490887225745408e+16,
+  "total_flos": 2.572185984761856e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null