Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b376ad1f20e0a96dc6d12291a3fceb54fcaf654a80ae376f5b4307170c059e
+oid sha256:05fdcf96d38b25efdb98cb376e0d38cc31e85e2c75cfa2873bcfea94efcb68f1
 size 102812592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b54654c28522bbd52905a8893cdc09b061b1ff02c48cc79ab69f1d0c8fbb6c05
+oid sha256:4e86c879304528c70c485ada0dcfdc5193fb0d97acda42b81cfa821222cc8962
 size 205850474

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd778f01e70aadc89439ba0d91a94104c295c30c9876d3c62bb03d5aa427f028
+oid sha256:25d3c1eada86d9e3106027ca8f20fd1d88b256409ba07bc544f7721169315322
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004067314047485892,
+  "epoch": 0.006100971071228837,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 17.898,
       "eval_steps_per_second": 8.954,
       "step": 20
+    },
+    {
+      "epoch": 0.004270679749860186,
+      "grad_norm": 1.37641441822052,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.5019,
+      "step": 21
+    },
+    {
+      "epoch": 0.0048807768569830694,
+      "grad_norm": 1.7818759679794312,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.4352,
+      "step": 24
+    },
+    {
+      "epoch": 0.005084142559357364,
+      "eval_loss": 1.4820669889450073,
+      "eval_runtime": 115.7161,
+      "eval_samples_per_second": 17.897,
+      "eval_steps_per_second": 8.953,
+      "step": 25
+    },
+    {
+      "epoch": 0.005490873964105953,
+      "grad_norm": 1.5027129650115967,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.3072,
+      "step": 27
+    },
+    {
+      "epoch": 0.006100971071228837,
+      "grad_norm": 1.505488634109497,
+      "learning_rate": 0.0,
+      "loss": 1.2843,
+      "step": 30
+    },
+    {
+      "epoch": 0.006100971071228837,
+      "eval_loss": 1.4783607721328735,
+      "eval_runtime": 115.7322,
+      "eval_samples_per_second": 17.895,
+      "eval_steps_per_second": 8.952,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3055955465994240.0,
+  "total_flos": 4583933198991360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null