Training in progress, step 3100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ed692ae9066b81d1913846a8c6f7abfb91f6009fa8af2889c897a3849545166
+oid sha256:487d48efb52d69cb5eca5d0442f4f8d423e30d7bb977365b8313665dc2c93ede
 size 35668592

metrics.json

@@ -59,3 +59,4 @@
 {"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}
+{"Step":3100,"eval_loss":1.7509515285,"eval_runtime":29.3774,"eval_samples_per_second":3.404,"eval_steps_per_second":0.443,"epoch":2.4351924588}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3959151610369207,
+  "epoch": 2.4359780047132755,
   "eval_steps": 50,
-  "global_step": 3050,
+  "global_step": 3101,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -907,6 +907,36 @@
       "eval_samples_per_second": 3.398,
       "eval_steps_per_second": 0.442,
       "step": 3000
+    },
+    {
+      "epoch": 2.3959151610369207,
+      "grad_norm": 0.20650461316108704,
+      "learning_rate": 0.00011187081757346524,
+      "loss": 1.7575,
+      "step": 3050
+    },
+    {
+      "epoch": 2.3959151610369207,
+      "eval_loss": 1.751355767250061,
+      "eval_runtime": 29.577,
+      "eval_samples_per_second": 3.381,
+      "eval_steps_per_second": 0.44,
+      "step": 3050
+    },
+    {
+      "epoch": 2.4351924587588374,
+      "grad_norm": 0.22746974229812622,
+      "learning_rate": 0.00010459703229560663,
+      "loss": 1.7547,
+      "step": 3100
+    },
+    {
+      "epoch": 2.4351924587588374,
+      "eval_loss": 1.7509515285491943,
+      "eval_runtime": 29.3774,
+      "eval_samples_per_second": 3.404,
+      "eval_steps_per_second": 0.443,
+      "step": 3100
     }
   ],
   "logging_steps": 50,
@@ -926,7 +956,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.774020398798848e+16,
+  "total_flos": 3.89905821256704e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null