Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14cfd47c9abbfc122a2202f6a2bdd3613e63b9ed9e514ee20b2a3e6151d46f7a
+oid sha256:c767f93eac094c00b97a165cdace38830a1cc8a806bc69473cae3c9fbe8c77c7
 size 35668592

metrics.json

@@ -10,3 +10,4 @@
 {"Step":500,"eval_loss":1.4477622509,"eval_runtime":27.6496,"eval_samples_per_second":3.617,"eval_steps_per_second":0.47,"epoch":0.8}
 {"Step":550,"eval_loss":1.4466557503,"eval_runtime":27.6503,"eval_samples_per_second":3.617,"eval_steps_per_second":0.47,"epoch":0.88}
 {"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.96,
+  "epoch": 1.04,
   "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": 3.617,
       "eval_steps_per_second": 0.47,
       "step": 550
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.035769980400800705,
+      "learning_rate": 0.00037818612922347364,
+      "loss": 1.4888,
+      "step": 600
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 1.4460580348968506,
+      "eval_runtime": 27.6213,
+      "eval_samples_per_second": 3.62,
+      "eval_steps_per_second": 0.471,
+      "step": 600
     }
   ],
   "logging_steps": 50,
@@ -191,7 +206,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.436487071121408e+16,
+  "total_flos": 4.845166027825152e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null