Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b00ef0475cb155d1d87c69f70a1dc562884509b7d69fa25f17cc5ac1d1fca2b1
+oid sha256:f8098a0e4655aab316808147890f9f04a3067b110bc03393fe4608baf3eab544
 size 35668592

metrics.json

@@ -10,3 +10,4 @@
 {"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}
+{"Step":650,"eval_loss":1.9631274939,"eval_runtime":29.8472,"eval_samples_per_second":3.35,"eval_steps_per_second":0.436,"epoch":0.5106048704}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4713275726630008,
+  "epoch": 0.5106048703849175,
   "eval_steps": 50,
-  "global_step": 600,
+  "global_step": 650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -172,6 +172,21 @@
       "eval_samples_per_second": 3.38,
       "eval_steps_per_second": 0.439,
       "step": 550
+    },
+    {
+      "epoch": 0.4713275726630008,
+      "grad_norm": 0.17965032160282135,
+      "learning_rate": 0.00046828629618853653,
+      "loss": 1.9562,
+      "step": 600
+    },
+    {
+      "epoch": 0.4713275726630008,
+      "eval_loss": 1.9679882526397705,
+      "eval_runtime": 29.7136,
+      "eval_samples_per_second": 3.365,
+      "eval_steps_per_second": 0.438,
+      "step": 600
     }
   ],
   "logging_steps": 50,
@@ -191,7 +206,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6865885281730560.0,
+  "total_flos": 7497791035883520.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null