Training in progress, step 2800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13d1f7d583dfc0f47ccb619dbbe99b944e5ee767d070c60d516fdd9cbbd41a76
+oid sha256:94482331b174360b99ce16965891f55631c83e4295d8d5443d4933b23e963041
 size 35668592

metrics.json

@@ -53,3 +53,4 @@
 {"Step":2650,"eval_loss":1.7721085548,"eval_runtime":29.5171,"eval_samples_per_second":3.388,"eval_steps_per_second":0.44,"epoch":2.0816967793}
 {"Step":2700,"eval_loss":1.7694271803,"eval_runtime":29.9036,"eval_samples_per_second":3.344,"eval_steps_per_second":0.435,"epoch":2.120974077}
 {"Step":2750,"eval_loss":1.7644474506,"eval_runtime":29.5003,"eval_samples_per_second":3.39,"eval_steps_per_second":0.441,"epoch":2.1602513747}
+{"Step":2800,"eval_loss":1.76300776,"eval_runtime":29.3837,"eval_samples_per_second":3.403,"eval_steps_per_second":0.442,"epoch":2.1995286724}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.16025137470542,
+  "epoch": 2.199528672427337,
   "eval_steps": 50,
-  "global_step": 2750,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -817,6 +817,21 @@
       "eval_samples_per_second": 3.344,
       "eval_steps_per_second": 0.435,
       "step": 2700
+    },
+    {
+      "epoch": 2.16025137470542,
+      "grad_norm": 0.2310086041688919,
+      "learning_rate": 0.00015551352924061683,
+      "loss": 1.7735,
+      "step": 2750
+    },
+    {
+      "epoch": 2.16025137470542,
+      "eval_loss": 1.7644474506378174,
+      "eval_runtime": 29.5003,
+      "eval_samples_per_second": 3.39,
+      "eval_steps_per_second": 0.441,
+      "step": 2750
     }
   ],
   "logging_steps": 50,
@@ -836,7 +851,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.39324703067136e+16,
+  "total_flos": 3.456043560548352e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null