Training in progress, step 3700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f83d7257a93219ca2b309fb58a35c66a8a2c90530e02df63273cc4a0e1390e4
+oid sha256:a7ff0a472832711eaff3172c5fae7e57c394992c5717313c4321925b637f52d1
 size 35668592

metrics.json

@@ -71,3 +71,4 @@
 {"Step":3550,"eval_loss":1.7384474277,"eval_runtime":29.4245,"eval_samples_per_second":3.399,"eval_steps_per_second":0.442,"epoch":2.7886881383}
 {"Step":3600,"eval_loss":1.7396867275,"eval_runtime":29.4237,"eval_samples_per_second":3.399,"eval_steps_per_second":0.442,"epoch":2.827965436}
 {"Step":3650,"eval_loss":1.74048388,"eval_runtime":29.3962,"eval_samples_per_second":3.402,"eval_steps_per_second":0.442,"epoch":2.8672427337}
+{"Step":3700,"eval_loss":1.7404457331,"eval_runtime":29.4897,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":2.9065200314}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8672427336999213,
+  "epoch": 2.906520031421838,
   "eval_steps": 50,
-  "global_step": 3650,
+  "global_step": 3700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1087,6 +1087,21 @@
       "eval_samples_per_second": 3.399,
       "eval_steps_per_second": 0.442,
       "step": 3600
+    },
+    {
+      "epoch": 2.8672427336999213,
+      "grad_norm": 0.2239353060722351,
+      "learning_rate": 2.458539423916206e-05,
+      "loss": 1.7557,
+      "step": 3650
+    },
+    {
+      "epoch": 2.8672427336999213,
+      "eval_loss": 1.7404838800430298,
+      "eval_runtime": 29.3962,
+      "eval_samples_per_second": 3.402,
+      "eval_steps_per_second": 0.442,
+      "step": 3650
     }
   ],
   "logging_steps": 50,
@@ -1106,7 +1121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.527668313126912e+16,
+  "total_flos": 4.591575334975488e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null