Training in progress, step 350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52e5b21efcff07a93f2b659f7c57e6cacbb0c9bfdf26d9b4fabe959421c4d76f
+oid sha256:26ead50c513c37732efea9076d192b04a31af3830534624ffcda5bac2a4f7997
 size 35668592

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.544,
+  "epoch": 0.56,
   "eval_steps": 20,
-  "global_step": 340,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,21 @@
       "eval_samples_per_second": 3.332,
       "eval_steps_per_second": 0.416,
       "step": 320
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.041331056505441666,
+      "learning_rate": 0.00045524599881446355,
+      "loss": 1.4742,
+      "step": 340
+    },
+    {
+      "epoch": 0.544,
+      "eval_loss": 1.4830516576766968,
+      "eval_runtime": 1501.5622,
+      "eval_samples_per_second": 3.33,
+      "eval_steps_per_second": 0.416,
+      "step": 340
     }
   ],
   "logging_steps": 20,
@@ -266,7 +281,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.650851803136e+16,
+  "total_flos": 2.729553443831808e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null