Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b971694d3b36e1f367d70340d7540925478b639b5aefdc5fb58efe82e3529a7b
+oid sha256:69cf6ad416ebd5240085fafc1a17ba4e8e8be0b1bc9626b3c2dc5b27526f0418
 size 35668592

metrics.json

@@ -2,3 +2,4 @@
 {"Step":100,"eval_loss":2.5934023857,"eval_runtime":29.4336,"eval_samples_per_second":3.397,"eval_steps_per_second":0.442,"epoch":0.0785545954}
 {"Step":150,"eval_loss":2.2559566498,"eval_runtime":29.4433,"eval_samples_per_second":3.396,"eval_steps_per_second":0.442,"epoch":0.1178318932}
 {"Step":200,"eval_loss":2.1369433403,"eval_runtime":29.6429,"eval_samples_per_second":3.373,"eval_steps_per_second":0.439,"epoch":0.1571091909}
+{"Step":250,"eval_loss":2.0804655552,"eval_runtime":29.5575,"eval_samples_per_second":3.383,"eval_steps_per_second":0.44,"epoch":0.1963864886}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15710919088766692,
+  "epoch": 0.19638648860958366,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,21 @@
       "eval_samples_per_second": 3.396,
       "eval_steps_per_second": 0.442,
       "step": 150
+    },
+    {
+      "epoch": 0.15710919088766692,
+      "grad_norm": 0.18111871182918549,
+      "learning_rate": 0.0002617801047120419,
+      "loss": 2.1397,
+      "step": 200
+    },
+    {
+      "epoch": 0.15710919088766692,
+      "eval_loss": 2.1369433403015137,
+      "eval_runtime": 29.6429,
+      "eval_samples_per_second": 3.373,
+      "eval_steps_per_second": 0.439,
+      "step": 200
     }
   ],
   "logging_steps": 50,
@@ -71,7 +86,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1866163847086080.0,
+  "total_flos": 2505234065571840.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null