Training in progress, step 1100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29fabdd7a48613dbbbd18d98542a8c73ac5f6d3931a7ddb3c9edadb5be9aa7af
+oid sha256:924c4d4d6522023e206826f8846fe40e8c770ac9967ac2ad0f4fd77ed07ae880
 size 35668592

metrics.json

@@ -19,3 +19,4 @@
 {"Step":950,"eval_loss":1.9149932861,"eval_runtime":29.4076,"eval_samples_per_second":3.4,"eval_steps_per_second":0.442,"epoch":0.7462686567}
 {"Step":1000,"eval_loss":1.9071648121,"eval_runtime":29.4527,"eval_samples_per_second":3.395,"eval_steps_per_second":0.441,"epoch":0.7855459544}
 {"Step":1050,"eval_loss":1.8993133307,"eval_runtime":29.5512,"eval_samples_per_second":3.384,"eval_steps_per_second":0.44,"epoch":0.8248232522}
+{"Step":1100,"eval_loss":1.9054021835,"eval_runtime":29.3876,"eval_samples_per_second":3.403,"eval_steps_per_second":0.442,"epoch":0.8641005499}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8248232521602514,
+  "epoch": 0.8641005498821681,
   "eval_steps": 50,
-  "global_step": 1050,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,6 +307,21 @@
       "eval_samples_per_second": 3.395,
       "eval_steps_per_second": 0.441,
       "step": 1000
+    },
+    {
+      "epoch": 0.8248232521602514,
+      "grad_norm": 0.1651030331850052,
+      "learning_rate": 0.00040282222868780914,
+      "loss": 1.9325,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8248232521602514,
+      "eval_loss": 1.8993133306503296,
+      "eval_runtime": 29.5512,
+      "eval_samples_per_second": 3.384,
+      "eval_steps_per_second": 0.44,
+      "step": 1050
     }
   ],
   "logging_steps": 50,
@@ -326,7 +341,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.253172278771712e+16,
+  "total_flos": 1.316362854187008e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null