Training in progress, step 300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4175c4e77170edcb5b4d1badf91a95b80b5a7b504b6c4819bb82e2c3d6f7163
+oid sha256:2161fd6cea778e72ee4a1f309af0fcaaf9a9e81b4f5c1b39f0d379d23ec50d10
 size 35668592

metrics.json

@@ -3,3 +3,4 @@
 {"Step":150,"eval_loss":0.789476037,"eval_runtime":56.6018,"eval_samples_per_second":1.767,"eval_steps_per_second":0.23,"epoch":0.2901353965}
 {"Step":200,"eval_loss":0.7783958316,"eval_runtime":56.5799,"eval_samples_per_second":1.767,"eval_steps_per_second":0.23,"epoch":0.3868471954}
 {"Step":250,"eval_loss":0.7721498013,"eval_runtime":57.9466,"eval_samples_per_second":1.726,"eval_steps_per_second":0.224,"epoch":0.4835589942}
+{"Step":300,"eval_loss":0.7687731385,"eval_runtime":60.6867,"eval_samples_per_second":1.648,"eval_steps_per_second":0.214,"epoch":0.580270793}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4835589941972921,
+  "epoch": 0.5802707930367504,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,21 @@
       "eval_samples_per_second": 1.767,
       "eval_steps_per_second": 0.23,
       "step": 200
+    },
+    {
+      "epoch": 0.4835589941972921,
+      "grad_norm": 0.03580320626497269,
+      "learning_rate": 0.00046630824372759856,
+      "loss": 0.7671,
+      "step": 250
+    },
+    {
+      "epoch": 0.4835589941972921,
+      "eval_loss": 0.7721498012542725,
+      "eval_runtime": 57.9466,
+      "eval_samples_per_second": 1.726,
+      "eval_steps_per_second": 0.224,
+      "step": 250
     }
   ],
   "logging_steps": 50,
@@ -86,7 +101,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.599196015296512e+16,
+  "total_flos": 3.250714490560512e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null