Training in progress, step 3819

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4126a86cedcc673291758a54cbca8d13b3b7d163ea1261dae62eb96e248768df
+oid sha256:ac9d1260e3eb5e3e89c1771538bf89abfcb0bf3025fd9db1d0c2d3eae71a285b
 size 35668592

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9850746268656714,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 3800,
+  "global_step": 3819,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1132,6 +1132,21 @@
       "eval_samples_per_second": 3.396,
       "eval_steps_per_second": 0.441,
       "step": 3750
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "grad_norm": 0.23328797519207,
+      "learning_rate": 2.764038405586267e-06,
+      "loss": 1.7539,
+      "step": 3800
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "eval_loss": 1.73746657371521,
+      "eval_runtime": 29.4954,
+      "eval_samples_per_second": 3.39,
+      "eval_steps_per_second": 0.441,
+      "step": 3800
     }
   ],
   "logging_steps": 50,
@@ -1151,7 +1166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.720338670196736e+16,
+  "total_flos": 4.78476511570944e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null