Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf2833c02447b29e736d88473f6e0ed1f4bd690f239c0a109e9885f5cf5e3652
+oid sha256:b00ef0475cb155d1d87c69f70a1dc562884509b7d69fa25f17cc5ac1d1fca2b1
 size 35668592

metrics.json

@@ -9,3 +9,4 @@
 {"Step":450,"eval_loss":2.001973629,"eval_runtime":29.578,"eval_samples_per_second":3.381,"eval_steps_per_second":0.44,"epoch":0.3534956795}
 {"Step":500,"eval_loss":1.9914397001,"eval_runtime":29.3577,"eval_samples_per_second":3.406,"eval_steps_per_second":0.443,"epoch":0.3927729772}
 {"Step":550,"eval_loss":1.9789185524,"eval_runtime":29.5883,"eval_samples_per_second":3.38,"eval_steps_per_second":0.439,"epoch":0.4320502749}
+{"Step":600,"eval_loss":1.9679882526,"eval_runtime":29.7136,"eval_samples_per_second":3.365,"eval_steps_per_second":0.438,"epoch":0.4713275727}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.43205027494108406,
+  "epoch": 0.4713275726630008,
   "eval_steps": 50,
-  "global_step": 550,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,6 +157,21 @@
       "eval_samples_per_second": 3.406,
       "eval_steps_per_second": 0.443,
       "step": 500
+    },
+    {
+      "epoch": 0.43205027494108406,
+      "grad_norm": 0.1806900054216385,
+      "learning_rate": 0.00047556008146639513,
+      "loss": 1.9677,
+      "step": 550
+    },
+    {
+      "epoch": 0.43205027494108406,
+      "eval_loss": 1.9789185523986816,
+      "eval_runtime": 29.5883,
+      "eval_samples_per_second": 3.38,
+      "eval_steps_per_second": 0.439,
+      "step": 550
     }
   ],
   "logging_steps": 50,
@@ -176,7 +191,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6245084447293440.0,
+  "total_flos": 6865885281730560.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null