Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adbbb5e99da43e9e72084f68db69aa1ee0ec888d7c67d7974a2aff817b8e79af
+oid sha256:14cfd47c9abbfc122a2202f6a2bdd3613e63b9ed9e514ee20b2a3e6151d46f7a
 size 35668592

metrics.json

@@ -9,3 +9,4 @@
 {"Step":450,"eval_loss":1.4484608173,"eval_runtime":27.6359,"eval_samples_per_second":3.618,"eval_steps_per_second":0.47,"epoch":0.72}
 {"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.88,
+  "epoch": 0.96,
   "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": 3.617,
       "eval_steps_per_second": 0.47,
       "step": 500
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.039886392652988434,
+      "learning_rate": 0.0003930053349140486,
+      "loss": 1.49,
+      "step": 550
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 1.4466557502746582,
+      "eval_runtime": 27.6503,
+      "eval_samples_per_second": 3.617,
+      "eval_steps_per_second": 0.47,
+      "step": 550
     }
   ],
   "logging_steps": 50,
@@ -176,7 +191,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.020088404099072e+16,
+  "total_flos": 4.436487071121408e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null