Training in progress, step 350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0064e74028932ad7f7ba5f4b0b4726cba07b854acdb38ca06c6ead7e6b9125d
+oid sha256:31a8d2429cebb283bbde4c281dd25c1ea90c2fb3b23caa9c63898b7d60443418
 size 35668592

metrics.json

@@ -4,3 +4,4 @@
 {"Step":200,"eval_loss":1.4602761269,"eval_runtime":27.615,"eval_samples_per_second":3.621,"eval_steps_per_second":0.471,"epoch":0.32}
 {"Step":250,"eval_loss":1.4578460455,"eval_runtime":27.6799,"eval_samples_per_second":3.613,"eval_steps_per_second":0.47,"epoch":0.4}
 {"Step":300,"eval_loss":1.4557801485,"eval_runtime":27.6578,"eval_samples_per_second":3.616,"eval_steps_per_second":0.47,"epoch":0.48}
+{"Step":350,"eval_loss":1.4533815384,"eval_runtime":27.6598,"eval_samples_per_second":3.615,"eval_steps_per_second":0.47,"epoch":0.56}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.48,
+  "epoch": 0.56,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,21 @@
       "eval_samples_per_second": 3.613,
       "eval_steps_per_second": 0.47,
       "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.040425803512334824,
+      "learning_rate": 0.00046710136336692356,
+      "loss": 1.4813,
+      "step": 300
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 1.4557801485061646,
+      "eval_runtime": 27.6578,
+      "eval_samples_per_second": 3.616,
+      "eval_steps_per_second": 0.47,
+      "step": 300
     }
   ],
   "logging_steps": 50,
@@ -101,7 +116,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.999548261801984e+16,
+  "total_flos": 2.4063644577792e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null