Training in progress, step 1350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6335cf58c6cc23ddd2e1d6c638529bff79aa05b9a843045ec46dc902615a1676
+oid sha256:0b39bbdc81457db12e6b2719ed3095cfb39905cf0d0021aa356976e78a3c10fe
 size 35668592

metrics.json

@@ -24,3 +24,4 @@
 {"Step":1200,"eval_loss":0.7510370612,"eval_runtime":56.6798,"eval_samples_per_second":1.764,"eval_steps_per_second":0.229,"epoch":2.3210831721}
 {"Step":1250,"eval_loss":0.7501779795,"eval_runtime":56.6502,"eval_samples_per_second":1.765,"eval_steps_per_second":0.229,"epoch":2.417794971}
 {"Step":1300,"eval_loss":0.7498863339,"eval_runtime":60.6054,"eval_samples_per_second":1.65,"eval_steps_per_second":0.215,"epoch":2.5145067698}
+{"Step":1350,"eval_loss":0.7502144575,"eval_runtime":57.5261,"eval_samples_per_second":1.738,"eval_steps_per_second":0.226,"epoch":2.6112185687}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.514506769825919,
+  "epoch": 2.611218568665377,
   "eval_steps": 50,
-  "global_step": 1300,
+  "global_step": 1350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -382,6 +382,21 @@
       "eval_samples_per_second": 1.765,
       "eval_steps_per_second": 0.229,
       "step": 1250
+    },
+    {
+      "epoch": 2.514506769825919,
+      "grad_norm": 0.04406700283288956,
+      "learning_rate": 8.996415770609319e-05,
+      "loss": 0.7285,
+      "step": 1300
+    },
+    {
+      "epoch": 2.514506769825919,
+      "eval_loss": 0.7498863339424133,
+      "eval_runtime": 60.6054,
+      "eval_samples_per_second": 1.65,
+      "eval_steps_per_second": 0.215,
+      "step": 1300
     }
   ],
   "logging_steps": 50,
@@ -401,7 +416,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6217629230802944e+17,
+  "total_flos": 1.6870311931521024e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null