Training in progress, step 750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f916fa238951c9e367e3db7fcbd24796cb3eb724be036ba458920b60714ae378
+oid sha256:7f8077a38d421c12a635b0c9b66d9262814e0f3d786f8385dd35f4f347ce9240
 size 35668592

metrics.json

@@ -12,3 +12,4 @@
 {"Step":600,"eval_loss":1.4460580349,"eval_runtime":27.6213,"eval_samples_per_second":3.62,"eval_steps_per_second":0.471,"epoch":0.96}
 {"Step":650,"eval_loss":1.4470006227,"eval_runtime":27.6084,"eval_samples_per_second":3.622,"eval_steps_per_second":0.471,"epoch":1.04}
 {"Step":700,"eval_loss":1.4475681782,"eval_runtime":27.6032,"eval_samples_per_second":3.623,"eval_steps_per_second":0.471,"epoch":1.12}
+{"Step":750,"eval_loss":1.44754529,"eval_runtime":27.6035,"eval_samples_per_second":3.623,"eval_steps_per_second":0.471,"epoch":1.2}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.12,
+  "epoch": 1.2,
   "eval_steps": 50,
-  "global_step": 700,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -202,6 +202,21 @@
       "eval_samples_per_second": 3.622,
       "eval_steps_per_second": 0.471,
       "step": 650
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.04102110490202904,
+      "learning_rate": 0.00034854771784232366,
+      "loss": 1.4677,
+      "step": 700
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 1.4475681781768799,
+      "eval_runtime": 27.6032,
+      "eval_samples_per_second": 3.623,
+      "eval_steps_per_second": 0.471,
+      "step": 700
     }
   ],
   "logging_steps": 50,
@@ -221,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.235862179053568e+16,
+  "total_flos": 5.641442504933376e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null