Training in progress, step 300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b08c248d0bca365a15b41b54b345889e4714bd55a35fc90965bb027407f9a1d7
+oid sha256:c0064e74028932ad7f7ba5f4b0b4726cba07b854acdb38ca06c6ead7e6b9125d
 size 35668592

metrics.json

@@ -3,3 +3,4 @@
 {"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}
+{"Step":300,"eval_loss":1.4703065157,"eval_runtime":149.278,"eval_samples_per_second":3.349,"eval_steps_per_second":0.422,"epoch":0.48}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4,
+  "epoch": 0.48,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,21 @@
       "eval_samples_per_second": 3.353,
       "eval_steps_per_second": 0.422,
       "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.03537657856941223,
+      "learning_rate": 0.00048192056905749855,
+      "loss": 1.5035,
+      "step": 250
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.4729492664337158,
+      "eval_runtime": 149.0332,
+      "eval_samples_per_second": 3.355,
+      "eval_steps_per_second": 0.423,
+      "step": 250
     }
   ],
   "logging_steps": 50,
@@ -86,7 +101,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.595221717180416e+16,
+  "total_flos": 1.999548261801984e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null