Training in progress, step 3350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c51a3cf3b944249bba0321177b9c99098891a877403a8366d5e05fd39fa08e14
+oid sha256:195761a378cb161498a3c07628d86627933f268f85b7d74be6f5f7680c6e2688
 size 35668592

metrics.json

@@ -64,3 +64,4 @@
 {"Step":3200,"eval_loss":1.7496337891,"eval_runtime":29.4486,"eval_samples_per_second":3.396,"eval_steps_per_second":0.441,"epoch":2.5137470542}
 {"Step":3250,"eval_loss":1.7441329956,"eval_runtime":29.3681,"eval_samples_per_second":3.405,"eval_steps_per_second":0.443,"epoch":2.5530243519}
 {"Step":3300,"eval_loss":1.7436232567,"eval_runtime":29.5214,"eval_samples_per_second":3.387,"eval_steps_per_second":0.44,"epoch":2.5923016496}
+{"Step":3350,"eval_loss":1.7433184385,"eval_runtime":29.6962,"eval_samples_per_second":3.367,"eval_steps_per_second":0.438,"epoch":2.6315789474}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5923016496465046,
+  "epoch": 2.6315789473684212,
   "eval_steps": 50,
-  "global_step": 3300,
+  "global_step": 3350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -982,6 +982,21 @@
       "eval_samples_per_second": 3.405,
       "eval_steps_per_second": 0.443,
       "step": 3250
+    },
+    {
+      "epoch": 2.5923016496465046,
+      "grad_norm": 0.2186252772808075,
+      "learning_rate": 7.550189118417226e-05,
+      "loss": 1.7517,
+      "step": 3300
+    },
+    {
+      "epoch": 2.5923016496465046,
+      "eval_loss": 1.7436232566833496,
+      "eval_runtime": 29.5214,
+      "eval_samples_per_second": 3.387,
+      "eval_steps_per_second": 0.44,
+      "step": 3300
     }
   ],
   "logging_steps": 50,
@@ -1001,7 +1016,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.087089578981376e+16,
+  "total_flos": 4.15276980575232e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null