Training in progress, step 1900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d73344f83d307300356133d1445d496171ccb8aa36d3fa339f268eeee7dfc22
+oid sha256:2d5a58ad04391fce2b4f026ecb29945e866c96d04ed28a127d17992cf9f382f7
 size 35668592

metrics.json

@@ -35,3 +35,4 @@
 {"Step":1750,"eval_loss":1.8384497166,"eval_runtime":29.4803,"eval_samples_per_second":3.392,"eval_steps_per_second":0.441,"epoch":1.3747054203}
 {"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.453260015710919,
+  "epoch": 1.4925373134328357,
   "eval_steps": 50,
-  "global_step": 1850,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -547,6 +547,21 @@
       "eval_samples_per_second": 3.39,
       "eval_steps_per_second": 0.441,
       "step": 1800
+    },
+    {
+      "epoch": 1.453260015710919,
+      "grad_norm": 0.2181958109140396,
+      "learning_rate": 0.0002864416642420716,
+      "loss": 1.8431,
+      "step": 1850
+    },
+    {
+      "epoch": 1.453260015710919,
+      "eval_loss": 1.827854037284851,
+      "eval_runtime": 29.4535,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.441,
+      "step": 1850
     }
   ],
   "logging_steps": 50,
@@ -566,7 +581,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.267064882198528e+16,
+  "total_flos": 2.327246382594048e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null