Training in progress, step 3750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7ff0a472832711eaff3172c5fae7e57c394992c5717313c4321925b637f52d1
+oid sha256:df9983cfa75636d2ba6946e3991c3dff6bff54761764447b4cee2dbbc8bf3bf7
 size 35668592

metrics.json

@@ -72,3 +72,4 @@
 {"Step":3600,"eval_loss":1.7396867275,"eval_runtime":29.4237,"eval_samples_per_second":3.399,"eval_steps_per_second":0.442,"epoch":2.827965436}
 {"Step":3650,"eval_loss":1.74048388,"eval_runtime":29.3962,"eval_samples_per_second":3.402,"eval_steps_per_second":0.442,"epoch":2.8672427337}
 {"Step":3700,"eval_loss":1.7404457331,"eval_runtime":29.4897,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":2.9065200314}
+{"Step":3750,"eval_loss":1.7380776405,"eval_runtime":29.4462,"eval_samples_per_second":3.396,"eval_steps_per_second":0.441,"epoch":2.9457973291}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.906520031421838,
+  "epoch": 2.9457973291437547,
   "eval_steps": 50,
-  "global_step": 3700,
+  "global_step": 3750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1102,6 +1102,21 @@
       "eval_samples_per_second": 3.402,
       "eval_steps_per_second": 0.442,
       "step": 3650
+    },
+    {
+      "epoch": 2.906520031421838,
+      "grad_norm": 0.2530839145183563,
+      "learning_rate": 1.7311608961303462e-05,
+      "loss": 1.753,
+      "step": 3700
+    },
+    {
+      "epoch": 2.906520031421838,
+      "eval_loss": 1.7404457330703735,
+      "eval_runtime": 29.4897,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.441,
+      "step": 3700
     }
   ],
   "logging_steps": 50,
@@ -1121,7 +1136,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.591575334975488e+16,
+  "total_flos": 4.65347630681088e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null