Training in progress, step 3550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e85740d5df521aaba95b3f99bf2df807c84588915232157edd1d90942ab64d0
+oid sha256:27176e2442c68859f960660b34ff0250e2e83443a58902e75e705120bb754275
 size 35668592

metrics.json

@@ -68,3 +68,4 @@
 {"Step":3400,"eval_loss":1.7429870367,"eval_runtime":29.4333,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":2.6708562451}
 {"Step":3450,"eval_loss":1.7402327061,"eval_runtime":29.6244,"eval_samples_per_second":3.376,"eval_steps_per_second":0.439,"epoch":2.7101335428}
 {"Step":3500,"eval_loss":1.7408081293,"eval_runtime":29.3534,"eval_samples_per_second":3.407,"eval_steps_per_second":0.443,"epoch":2.7494108405}
+{"Step":3550,"eval_loss":1.7384474277,"eval_runtime":29.4245,"eval_samples_per_second":3.399,"eval_steps_per_second":0.442,"epoch":2.7886881383}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7494108405341713,
+  "epoch": 2.788688138256088,
   "eval_steps": 50,
-  "global_step": 3500,
+  "global_step": 3550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1042,6 +1042,21 @@
       "eval_samples_per_second": 3.376,
       "eval_steps_per_second": 0.439,
       "step": 3450
+    },
+    {
+      "epoch": 2.7494108405341713,
+      "grad_norm": 0.2643437385559082,
+      "learning_rate": 4.640675007273786e-05,
+      "loss": 1.7513,
+      "step": 3500
+    },
+    {
+      "epoch": 2.7494108405341713,
+      "eval_loss": 1.740808129310608,
+      "eval_runtime": 29.3534,
+      "eval_samples_per_second": 3.407,
+      "eval_steps_per_second": 0.443,
+      "step": 3500
     }
   ],
   "logging_steps": 50,
@@ -1061,7 +1076,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.34029965966336e+16,
+  "total_flos": 4.401358806939648e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null