Training in progress, step 2650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cfdcec4d41fe4ac86ec9ec7b6c3070b8a088d9a232f715ffbe3e94cea7d4adb
+oid sha256:15aef3d44cc29c204e8ca0fb979a8d9bbdf4e68623bbe2b0a744edf8777264dd
 size 35668592

metrics.json

@@ -50,3 +50,4 @@
 {"Step":2500,"eval_loss":1.7779937983,"eval_runtime":29.5562,"eval_samples_per_second":3.383,"eval_steps_per_second":0.44,"epoch":1.9638648861}
 {"Step":2550,"eval_loss":1.7793732882,"eval_runtime":29.5808,"eval_samples_per_second":3.381,"eval_steps_per_second":0.439,"epoch":2.0031421838}
 {"Step":2600,"eval_loss":1.7732738256,"eval_runtime":29.4165,"eval_samples_per_second":3.399,"eval_steps_per_second":0.442,"epoch":2.0424194815}
+{"Step":2650,"eval_loss":1.7721085548,"eval_runtime":29.5171,"eval_samples_per_second":3.388,"eval_steps_per_second":0.44,"epoch":2.0816967793}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.04241948153967,
+  "epoch": 2.081696779261587,
   "eval_steps": 50,
-  "global_step": 2600,
+  "global_step": 2650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -772,6 +772,21 @@
       "eval_samples_per_second": 3.381,
       "eval_steps_per_second": 0.439,
       "step": 2550
+    },
+    {
+      "epoch": 2.04241948153967,
+      "grad_norm": 0.2194184958934784,
+      "learning_rate": 0.0001773348850741926,
+      "loss": 1.7922,
+      "step": 2600
+    },
+    {
+      "epoch": 2.04241948153967,
+      "eval_loss": 1.7732738256454468,
+      "eval_runtime": 29.4165,
+      "eval_samples_per_second": 3.399,
+      "eval_steps_per_second": 0.442,
+      "step": 2600
     }
   ],
   "logging_steps": 50,
@@ -791,7 +806,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.208869541066752e+16,
+  "total_flos": 3.269355531196416e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null