Training in progress, step 2700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15aef3d44cc29c204e8ca0fb979a8d9bbdf4e68623bbe2b0a744edf8777264dd
+oid sha256:24985e82bf76520307e5bc7c5d88100c0a4c123052eefa641905271c0098c921
 size 35668592

metrics.json

@@ -51,3 +51,4 @@
 {"Step":2550,"eval_loss":1.7793732882,"eval_runtime":29.5808,"eval_samples_per_second":3.381,"eval_steps_per_second":0.439,"epoch":2.0031421838}
 {"Step":2600,"eval_loss":1.7732738256,"eval_runtime":29.4165,"eval_samples_per_second":3.399,"eval_steps_per_second":0.442,"epoch":2.0424194815}
 {"Step":2650,"eval_loss":1.7721085548,"eval_runtime":29.5171,"eval_samples_per_second":3.388,"eval_steps_per_second":0.44,"epoch":2.0816967793}
+{"Step":2700,"eval_loss":1.7694271803,"eval_runtime":29.9036,"eval_samples_per_second":3.344,"eval_steps_per_second":0.435,"epoch":2.120974077}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.081696779261587,
+  "epoch": 2.1209740769835035,
   "eval_steps": 50,
-  "global_step": 2650,
+  "global_step": 2700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -787,6 +787,21 @@
       "eval_samples_per_second": 3.399,
       "eval_steps_per_second": 0.442,
       "step": 2600
+    },
+    {
+      "epoch": 2.081696779261587,
+      "grad_norm": 0.21199199557304382,
+      "learning_rate": 0.00017006109979633404,
+      "loss": 1.7558,
+      "step": 2650
+    },
+    {
+      "epoch": 2.081696779261587,
+      "eval_loss": 1.772108554840088,
+      "eval_runtime": 29.5171,
+      "eval_samples_per_second": 3.388,
+      "eval_steps_per_second": 0.44,
+      "step": 2650
     }
   ],
   "logging_steps": 50,
@@ -806,7 +821,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.269355531196416e+16,
+  "total_flos": 3.3322595280384e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null