Training in progress, step 2500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:023334ef8434b77f1aa53a40a6350555905065ef546006a46192288e80c0294c
+oid sha256:12aea5d4279830298c7208e492f2aaaaa230cfb000f8410d46d3aaf09d5db0e3
 size 35668592

metrics.json

@@ -47,3 +47,4 @@
 {"Step":2350,"eval_loss":1.7902172804,"eval_runtime":29.5667,"eval_samples_per_second":3.382,"eval_steps_per_second":0.44,"epoch":1.8460329929}
 {"Step":2400,"eval_loss":1.7889854908,"eval_runtime":29.5198,"eval_samples_per_second":3.388,"eval_steps_per_second":0.44,"epoch":1.8853102907}
 {"Step":2450,"eval_loss":1.7838914394,"eval_runtime":29.4874,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":1.9245875884}
+{"Step":2500,"eval_loss":1.7779937983,"eval_runtime":29.5562,"eval_samples_per_second":3.383,"eval_steps_per_second":0.44,"epoch":1.9638648861}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9245875883739199,
+  "epoch": 1.9638648860958368,
   "eval_steps": 50,
-  "global_step": 2450,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -727,6 +727,21 @@
       "eval_samples_per_second": 3.388,
       "eval_steps_per_second": 0.44,
       "step": 2400
+    },
+    {
+      "epoch": 1.9245875883739199,
+      "grad_norm": 0.1968667209148407,
+      "learning_rate": 0.0001991562409077684,
+      "loss": 1.8153,
+      "step": 2450
+    },
+    {
+      "epoch": 1.9245875883739199,
+      "eval_loss": 1.7838914394378662,
+      "eval_runtime": 29.4874,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.441,
+      "step": 2450
     }
   ],
   "logging_steps": 50,
@@ -746,7 +761,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.023417381812224e+16,
+  "total_flos": 3.08714529205248e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null