Training in progress, step 1450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:079525c8ed387cce1ea9e0669805467b05b018b02e24d14699f2e7957dacfe7f
+oid sha256:8e4611d599d8161322f3e6b8d6251a0a636fca8d840e06365ce4111550431816
 size 35668592

metrics.json

@@ -26,3 +26,4 @@
 {"Step":1300,"eval_loss":1.8769853115,"eval_runtime":29.4816,"eval_samples_per_second":3.392,"eval_steps_per_second":0.441,"epoch":1.0212097408}
 {"Step":1350,"eval_loss":1.8668268919,"eval_runtime":29.5392,"eval_samples_per_second":3.385,"eval_steps_per_second":0.44,"epoch":1.0604870385}
 {"Step":1400,"eval_loss":1.8661786318,"eval_runtime":29.4511,"eval_samples_per_second":3.395,"eval_steps_per_second":0.441,"epoch":1.0997643362}
+{"Step":1450,"eval_loss":1.8573988676,"eval_runtime":29.4384,"eval_samples_per_second":3.397,"eval_steps_per_second":0.442,"epoch":1.1390416339}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0997643362136684,
+  "epoch": 1.139041633935585,
   "eval_steps": 50,
-  "global_step": 1400,
+  "global_step": 1450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -412,6 +412,21 @@
       "eval_samples_per_second": 3.385,
       "eval_steps_per_second": 0.44,
       "step": 1350
+    },
+    {
+      "epoch": 1.0997643362136684,
+      "grad_norm": 0.1711549311876297,
+      "learning_rate": 0.00035190573174279896,
+      "loss": 1.8477,
+      "step": 1400
+    },
+    {
+      "epoch": 1.0997643362136684,
+      "eval_loss": 1.8661786317825317,
+      "eval_runtime": 29.4511,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.441,
+      "step": 1400
     }
   ],
   "logging_steps": 50,
@@ -431,7 +446,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.698206414174208e+16,
+  "total_flos": 1.763832907462656e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null