Training in progress, step 2550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12aea5d4279830298c7208e492f2aaaaa230cfb000f8410d46d3aaf09d5db0e3
+oid sha256:07e0060b7e757a9841743d6b207328f24c38b0b941a516caa96bc09354b573c7
 size 35668592

metrics.json

@@ -48,3 +48,4 @@
 {"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}
+{"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9638648860958368,
+  "epoch": 2.0031421838177534,
   "eval_steps": 50,
-  "global_step": 2500,
+  "global_step": 2550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -742,6 +742,21 @@
       "eval_samples_per_second": 3.391,
       "eval_steps_per_second": 0.441,
       "step": 2450
+    },
+    {
+      "epoch": 1.9638648860958368,
+      "grad_norm": 0.2244279533624649,
+      "learning_rate": 0.0001918824556299098,
+      "loss": 1.7845,
+      "step": 2500
+    },
+    {
+      "epoch": 1.9638648860958368,
+      "eval_loss": 1.7779937982559204,
+      "eval_runtime": 29.5562,
+      "eval_samples_per_second": 3.383,
+      "eval_steps_per_second": 0.44,
+      "step": 2500
     }
   ],
   "logging_steps": 50,
@@ -761,7 +776,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.08714529205248e+16,
+  "total_flos": 3.1482223504896e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null