Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20e5dde333ed120063aeedbe3bb3fe678dcd00c642436caca387051d76c52325
+oid sha256:adbbb5e99da43e9e72084f68db69aa1ee0ec888d7c67d7974a2aff817b8e79af
 size 35668592

metrics.json

@@ -8,3 +8,4 @@
 {"Step":400,"eval_loss":1.4522851706,"eval_runtime":27.5987,"eval_samples_per_second":3.623,"eval_steps_per_second":0.471,"epoch":0.64}
 {"Step":450,"eval_loss":1.4484608173,"eval_runtime":27.6359,"eval_samples_per_second":3.618,"eval_steps_per_second":0.47,"epoch":0.72}
 {"Step":500,"eval_loss":1.4477622509,"eval_runtime":27.6496,"eval_samples_per_second":3.617,"eval_steps_per_second":0.47,"epoch":0.8}
+{"Step":550,"eval_loss":1.4466557503,"eval_runtime":27.6503,"eval_samples_per_second":3.617,"eval_steps_per_second":0.47,"epoch":0.88}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
+  "epoch": 0.88,
   "eval_steps": 50,
-  "global_step": 500,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -142,6 +142,21 @@
       "eval_samples_per_second": 3.618,
       "eval_steps_per_second": 0.47,
       "step": 450
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.035757772624492645,
+      "learning_rate": 0.0004078245406046236,
+      "loss": 1.4925,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.4477622509002686,
+      "eval_runtime": 27.6496,
+      "eval_samples_per_second": 3.617,
+      "eval_steps_per_second": 0.47,
+      "step": 500
     }
   ],
   "logging_steps": 50,
@@ -161,7 +176,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.610746734444544e+16,
+  "total_flos": 4.020088404099072e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null