Training in progress, step 3050

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb3275278fc02dff024f8bbbbe169f36646d84b0bee6929d8281968acd072334
+oid sha256:9ed692ae9066b81d1913846a8c6f7abfb91f6009fa8af2889c897a3849545166
 size 35668592

metrics.json

@@ -58,3 +58,4 @@
 {"Step":2900,"eval_loss":1.7579619884,"eval_runtime":29.3692,"eval_samples_per_second":3.405,"eval_steps_per_second":0.443,"epoch":2.2780832679}
 {"Step":2950,"eval_loss":1.7549589872,"eval_runtime":29.4284,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":2.3173605656}
 {"Step":3000,"eval_loss":1.7528626919,"eval_runtime":29.4272,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":2.3566378633}
+{"Step":3050,"eval_loss":1.7513557673,"eval_runtime":29.577,"eval_samples_per_second":3.381,"eval_steps_per_second":0.44,"epoch":2.395915161}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.356637863315004,
+  "epoch": 2.3959151610369207,
   "eval_steps": 50,
-  "global_step": 3000,
+  "global_step": 3050,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -892,6 +892,21 @@
       "eval_samples_per_second": 3.398,
       "eval_steps_per_second": 0.442,
       "step": 2950
+    },
+    {
+      "epoch": 2.356637863315004,
+      "grad_norm": 0.2826303541660309,
+      "learning_rate": 0.00011914460285132383,
+      "loss": 1.7356,
+      "step": 3000
+    },
+    {
+      "epoch": 2.356637863315004,
+      "eval_loss": 1.7528626918792725,
+      "eval_runtime": 29.4272,
+      "eval_samples_per_second": 3.398,
+      "eval_steps_per_second": 0.442,
+      "step": 3000
     }
   ],
   "logging_steps": 50,
@@ -911,7 +926,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.708716306405376e+16,
+  "total_flos": 3.774020398798848e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null