Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee238e3ffa359e1fa3d541d5c905c92e688fe115fa8356c9f006a753bb17d3fe
+oid sha256:6f939bd09b4e1ef84fc2a775173b99eed6cca9209aeed0b9233d8de29bc13c86
 size 35668592

metrics.json

@@ -1,3 +1,4 @@
 {"Step":50,"eval_loss":0.9260319471,"eval_runtime":60.9012,"eval_samples_per_second":1.642,"eval_steps_per_second":0.213,"epoch":0.0967117988}
 {"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}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2901353965183752,
+  "epoch": 0.38684719535783363,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,21 @@
       "eval_samples_per_second": 1.769,
       "eval_steps_per_second": 0.23,
       "step": 100
+    },
+    {
+      "epoch": 0.2901353965183752,
+      "grad_norm": 0.02802114002406597,
+      "learning_rate": 0.0004807692307692308,
+      "loss": 0.7996,
+      "step": 150
+    },
+    {
+      "epoch": 0.2901353965183752,
+      "eval_loss": 0.7894760370254517,
+      "eval_runtime": 56.6018,
+      "eval_samples_per_second": 1.767,
+      "eval_steps_per_second": 0.23,
+      "step": 150
     }
   ],
   "logging_steps": 50,
@@ -56,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.308517765742592e+16,
+  "total_flos": 1.956722676252672e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null