Training in progress, step 1150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0249ddb36a9d4dc7a7221c0517131da5d934fe1fa4a4a18f655e370827ae3e59
+oid sha256:7479b5aff4fb6157ffd37e56061e1b2c5f90d14f4601420aadd7008a772e6a3b
 size 35668592

metrics.json

@@ -20,3 +20,4 @@
 {"Step":1000,"eval_loss":0.751624763,"eval_runtime":56.5619,"eval_samples_per_second":1.768,"eval_steps_per_second":0.23,"epoch":1.9342359768}
 {"Step":1050,"eval_loss":0.7514955997,"eval_runtime":60.5727,"eval_samples_per_second":1.651,"eval_steps_per_second":0.215,"epoch":2.0309477756}
 {"Step":1100,"eval_loss":0.7509506345,"eval_runtime":56.8661,"eval_samples_per_second":1.759,"eval_steps_per_second":0.229,"epoch":2.1276595745}
+{"Step":1150,"eval_loss":0.7505396008,"eval_runtime":56.5726,"eval_samples_per_second":1.768,"eval_steps_per_second":0.23,"epoch":2.2243713733}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.127659574468085,
+  "epoch": 2.2243713733075436,
   "eval_steps": 50,
-  "global_step": 1100,
+  "global_step": 1150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -322,6 +322,21 @@
       "eval_samples_per_second": 1.651,
       "eval_steps_per_second": 0.215,
       "step": 1050
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 0.04245985299348831,
+      "learning_rate": 0.00016164874551971326,
+      "loss": 0.7264,
+      "step": 1100
+    },
+    {
+      "epoch": 2.127659574468085,
+      "eval_loss": 0.7509506344795227,
+      "eval_runtime": 56.8661,
+      "eval_samples_per_second": 1.759,
+      "eval_steps_per_second": 0.229,
+      "step": 1100
     }
   ],
   "logging_steps": 50,
@@ -341,7 +356,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3621119889631232e+17,
+  "total_flos": 1.426061997597696e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null