Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f939bd09b4e1ef84fc2a775173b99eed6cca9209aeed0b9233d8de29bc13c86
+oid sha256:f4175c4e77170edcb5b4d1badf91a95b80b5a7b504b6c4819bb82e2c3d6f7163
 size 35668592

metrics.json

@@ -2,3 +2,4 @@
 {"Step":100,"eval_loss":0.8202204108,"eval_runtime":56.5241,"eval_samples_per_second":1.769,"eval_steps_per_second":0.23,"epoch":0.1934235977}
 {"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.38684719535783363,
+  "epoch": 0.4835589941972921,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,21 @@
       "eval_samples_per_second": 1.767,
       "eval_steps_per_second": 0.23,
       "step": 150
+    },
+    {
+      "epoch": 0.38684719535783363,
+      "grad_norm": 0.03189089894294739,
+      "learning_rate": 0.0004842293906810036,
+      "loss": 0.7802,
+      "step": 200
+    },
+    {
+      "epoch": 0.38684719535783363,
+      "eval_loss": 0.7783958315849304,
+      "eval_runtime": 56.5799,
+      "eval_samples_per_second": 1.767,
+      "eval_steps_per_second": 0.23,
+      "step": 200
     }
   ],
   "logging_steps": 50,
@@ -71,7 +86,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.956722676252672e+16,
+  "total_flos": 2.599196015296512e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null