Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce16af6efe20a4f464d6bc2e38cd7334edda7f3287d78d421355b2a5ba0b4947
+oid sha256:97b6e4465680aed6fb066b645d7eb90f6b6c972f2f8f81c42d5d5d73e38f1024
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91642a9bd286adb05fb1317402f8f8a959aa0ab54f3ea17938061dee6d7b95d2
+oid sha256:bd2ca174bcc90d77bbd7cb85b2c3c34a9cf3a79df098bf9be6d3075160722118
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a39a41f912d3765e4194e7bf2d118cba79dcbe423e3417f95fa83853160b690
+oid sha256:fdde6ac87a64995609da02d0ac08c227f29316a78167a5224ca4e6df927f97ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10526315789473684,
+  "epoch": 0.14035087719298245,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 26.745,
       "eval_steps_per_second": 13.372,
       "step": 15
+    },
+    {
+      "epoch": 0.11228070175438597,
+      "grad_norm": 6.341962814331055,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 12.5136,
+      "step": 16
+    },
+    {
+      "epoch": 0.11929824561403508,
+      "grad_norm": 6.404966831207275,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.9517,
+      "step": 17
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 6.500393867492676,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 12.8158,
+      "step": 18
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 6.19280481338501,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.0811,
+      "step": 19
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 6.322799205780029,
+      "learning_rate": 0.0,
+      "loss": 12.8055,
+      "step": 20
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "eval_loss": 0.7703096866607666,
+      "eval_runtime": 10.4663,
+      "eval_samples_per_second": 22.931,
+      "eval_steps_per_second": 11.465,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.608389876514816e+16,
+  "total_flos": 2.13773338017792e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null