Training in progress, step 2400

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:415b303df99ddef4a29d58e398b0d9ffbf940590ae1978745d7a747f2e77c8e2
+oid sha256:d8be7e6ced38b0ccd0b3ac649f61cec2c7518b1662202cd100359c6489007501
 size 35668592

metrics.json

@@ -45,3 +45,4 @@
 {"Step":2250,"eval_loss":1.7962598801,"eval_runtime":29.3661,"eval_samples_per_second":3.405,"eval_steps_per_second":0.443,"epoch":1.7674783975}
 {"Step":2300,"eval_loss":1.7972977161,"eval_runtime":29.4909,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":1.8067556952}
 {"Step":2350,"eval_loss":1.7902172804,"eval_runtime":29.5667,"eval_samples_per_second":3.382,"eval_steps_per_second":0.44,"epoch":1.8460329929}
+{"Step":2400,"eval_loss":1.7889854908,"eval_runtime":29.5198,"eval_samples_per_second":3.388,"eval_steps_per_second":0.44,"epoch":1.8853102907}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8460329929300863,
+  "epoch": 1.8853102906520032,
   "eval_steps": 50,
-  "global_step": 2350,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -697,6 +697,21 @@
       "eval_samples_per_second": 3.391,
       "eval_steps_per_second": 0.441,
       "step": 2300
+    },
+    {
+      "epoch": 1.8460329929300863,
+      "grad_norm": 0.20243284106254578,
+      "learning_rate": 0.0002137038114634856,
+      "loss": 1.8209,
+      "step": 2350
+    },
+    {
+      "epoch": 1.8460329929300863,
+      "eval_loss": 1.7902172803878784,
+      "eval_runtime": 29.5667,
+      "eval_samples_per_second": 3.382,
+      "eval_steps_per_second": 0.44,
+      "step": 2350
     }
   ],
   "logging_steps": 50,
@@ -716,7 +731,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.896283962226688e+16,
+  "total_flos": 2.957970000132096e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null