Training in progress, step 1350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3825e4093c89d9d66e541882f346bffb1d07ab9fbc09f689e0cb4443218b03
+oid sha256:a2b49296fb20e1f4737ca4b3be6762448d99c7c4402dfb07a306f7a6007855f7
 size 35668592

metrics.json

@@ -24,3 +24,4 @@
 {"Step":1200,"eval_loss":1.8822929859,"eval_runtime":29.4891,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":0.9426551453}
 {"Step":1250,"eval_loss":1.8784922361,"eval_runtime":29.4313,"eval_samples_per_second":3.398,"eval_steps_per_second":0.442,"epoch":0.981932443}
 {"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.021209740769835,
+  "epoch": 1.0604870384917517,
   "eval_steps": 50,
-  "global_step": 1300,
+  "global_step": 1350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -382,6 +382,21 @@
       "eval_samples_per_second": 3.398,
       "eval_steps_per_second": 0.442,
       "step": 1250
+    },
+    {
+      "epoch": 1.021209740769835,
+      "grad_norm": 0.17562049627304077,
+      "learning_rate": 0.00036645330229851617,
+      "loss": 1.9034,
+      "step": 1300
+    },
+    {
+      "epoch": 1.021209740769835,
+      "eval_loss": 1.8769853115081787,
+      "eval_runtime": 29.4816,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 0.441,
+      "step": 1300
     }
   ],
   "logging_steps": 50,
@@ -401,7 +416,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.571417784434688e+16,
+  "total_flos": 1.635230772688896e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null