Training in progress, step 2150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd5640309c664961bddb645ea9f395168c8ffb25cac09476f629610ef2821c8
+oid sha256:2149203dd37594e32a23d389ed93d6b976d911b7c5472d701ee09fba286e8aa3
 size 35668592

metrics.json

@@ -40,3 +40,4 @@
 {"Step":2000,"eval_loss":1.8210265636,"eval_runtime":29.5979,"eval_samples_per_second":3.379,"eval_steps_per_second":0.439,"epoch":1.5710919089}
 {"Step":2050,"eval_loss":1.8052531481,"eval_runtime":29.6699,"eval_samples_per_second":3.37,"eval_steps_per_second":0.438,"epoch":1.6103692066}
 {"Step":2100,"eval_loss":1.8001557589,"eval_runtime":29.4349,"eval_samples_per_second":3.397,"eval_steps_per_second":0.442,"epoch":1.6496465043}
+{"Step":2150,"eval_loss":1.8008465767,"eval_runtime":29.3948,"eval_samples_per_second":3.402,"eval_steps_per_second":0.442,"epoch":1.688923802}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6496465043205029,
+  "epoch": 1.6889238020424195,
   "eval_steps": 50,
-  "global_step": 2100,
+  "global_step": 2150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -622,6 +622,21 @@
       "eval_samples_per_second": 3.37,
       "eval_steps_per_second": 0.438,
       "step": 2050
+    },
+    {
+      "epoch": 1.6496465043205029,
+      "grad_norm": 0.19593429565429688,
+      "learning_rate": 0.00025007273785277855,
+      "loss": 1.8154,
+      "step": 2100
+    },
+    {
+      "epoch": 1.6496465043205029,
+      "eval_loss": 1.800155758857727,
+      "eval_runtime": 29.4349,
+      "eval_samples_per_second": 3.397,
+      "eval_steps_per_second": 0.442,
+      "step": 2100
     }
   ],
   "logging_steps": 50,
@@ -641,7 +656,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.578486235584512e+16,
+  "total_flos": 2.643342548957184e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null