Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f260a8859bd7b12f563e4671818d7103f51af6030a50d5e3520c496388f6baa
+oid sha256:b08c248d0bca365a15b41b54b345889e4714bd55a35fc90965bb027407f9a1d7
 size 35668592

metrics.json

@@ -2,3 +2,4 @@
 {"Step":100,"eval_loss":1.5024453402,"eval_runtime":149.3514,"eval_samples_per_second":3.348,"eval_steps_per_second":0.422,"epoch":0.16}
 {"Step":150,"eval_loss":1.4826966524,"eval_runtime":149.1669,"eval_samples_per_second":3.352,"eval_steps_per_second":0.422,"epoch":0.24}
 {"Step":200,"eval_loss":1.4759048223,"eval_runtime":149.1268,"eval_samples_per_second":3.353,"eval_steps_per_second":0.422,"epoch":0.32}
+{"Step":250,"eval_loss":1.4729492664,"eval_runtime":149.0332,"eval_samples_per_second":3.355,"eval_steps_per_second":0.423,"epoch":0.4}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32,
+  "epoch": 0.4,
   "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": 3.352,
       "eval_steps_per_second": 0.422,
       "step": 150
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.04070857912302017,
+      "learning_rate": 0.0004967397747480735,
+      "loss": 1.4822,
+      "step": 200
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 1.4759048223495483,
+      "eval_runtime": 149.1268,
+      "eval_samples_per_second": 3.353,
+      "eval_steps_per_second": 0.422,
+      "step": 200
     }
   ],
   "logging_steps": 50,
@@ -71,7 +86,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.205403212832768e+16,
+  "total_flos": 1.595221717180416e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null