Training in progress, step 1950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d5a58ad04391fce2b4f026ecb29945e866c96d04ed28a127d17992cf9f382f7
+oid sha256:bff49702dde3a23c57f475cc3f83133a68c1131ab1e6768ab3ff714249d83bf4
 size 35668592

metrics.json

@@ -36,3 +36,4 @@
 {"Step":1800,"eval_loss":1.8313938379,"eval_runtime":29.4965,"eval_samples_per_second":3.39,"eval_steps_per_second":0.441,"epoch":1.413982718}
 {"Step":1850,"eval_loss":1.8278540373,"eval_runtime":29.4535,"eval_samples_per_second":3.395,"eval_steps_per_second":0.441,"epoch":1.4532600157}
 {"Step":1900,"eval_loss":1.8285325766,"eval_runtime":29.5818,"eval_samples_per_second":3.38,"eval_steps_per_second":0.439,"epoch":1.4925373134}
+{"Step":1950,"eval_loss":1.8242964745,"eval_runtime":29.4834,"eval_samples_per_second":3.392,"eval_steps_per_second":0.441,"epoch":1.5318146112}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4925373134328357,
+  "epoch": 1.5318146111547526,
   "eval_steps": 50,
-  "global_step": 1900,
+  "global_step": 1950,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -562,6 +562,21 @@
       "eval_samples_per_second": 3.395,
       "eval_steps_per_second": 0.441,
       "step": 1850
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "grad_norm": 0.2101767212152481,
+      "learning_rate": 0.00027916787896421297,
+      "loss": 1.8249,
+      "step": 1900
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "eval_loss": 1.8285325765609741,
+      "eval_runtime": 29.5818,
+      "eval_samples_per_second": 3.38,
+      "eval_steps_per_second": 0.439,
+      "step": 1900
     }
   ],
   "logging_steps": 50,
@@ -581,7 +596,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.327246382594048e+16,
+  "total_flos": 2.390168290596864e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null