Training in progress, step 2300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc0fece70ab1538e00171cecdf7ed2a2d9d17c399fdaf69b7d59568e5491a71
+oid sha256:9bc3ce7ffec46ebc27c5cd985eb6e14e8348d3cfa838a7a007617e8dc6429e08
 size 35668592

metrics.json

@@ -43,3 +43,4 @@
 {"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}
 {"Step":2200,"eval_loss":1.7969157696,"eval_runtime":29.4741,"eval_samples_per_second":3.393,"eval_steps_per_second":0.441,"epoch":1.7282010998}
 {"Step":2250,"eval_loss":1.7962598801,"eval_runtime":29.3661,"eval_samples_per_second":3.405,"eval_steps_per_second":0.443,"epoch":1.7674783975}
+{"Step":2300,"eval_loss":1.7972977161,"eval_runtime":29.4909,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":1.8067556952}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.767478397486253,
+  "epoch": 1.8067556952081696,
   "eval_steps": 50,
-  "global_step": 2250,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -667,6 +667,21 @@
       "eval_samples_per_second": 3.393,
       "eval_steps_per_second": 0.441,
       "step": 2200
+    },
+    {
+      "epoch": 1.767478397486253,
+      "grad_norm": 0.2116580605506897,
+      "learning_rate": 0.0002282513820192028,
+      "loss": 1.8467,
+      "step": 2250
+    },
+    {
+      "epoch": 1.767478397486253,
+      "eval_loss": 1.796259880065918,
+      "eval_runtime": 29.3661,
+      "eval_samples_per_second": 3.405,
+      "eval_steps_per_second": 0.443,
+      "step": 2250
     }
   ],
   "logging_steps": 50,
@@ -686,7 +701,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.770619257829376e+16,
+  "total_flos": 2.833899389048832e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null