Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a618a7ab1491518429604bb97c497311967854b8a16e0a5f1a890ee408c23c2b
+oid sha256:e416cc4d888cdf12b210413de5a8578762010edc20b842a44d11953f187ca270
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e77aa8b39fc0f2023bec89fec06c6f59cae3efa4d48bf59d1bc35642e898634
+oid sha256:2c95c32c3431613e08d510bda797066196c4a3571a3abdec03a9024fa03d2911
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4064746cde00cef3c678ba04db56228cfb7a609849b1ab5a01cc367c2ec4fb09
+oid sha256:66d8f2e10bd118fdac9d025c1b83156fdd4f01028217426d46dea10b07adc4c1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
+oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003501247319357521,
+  "epoch": 0.004376559149196902,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 23.676,
       "eval_steps_per_second": 2.96,
       "step": 20
+    },
+    {
+      "epoch": 0.003676309685325397,
+      "grad_norm": 6.9651875495910645,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 1.558,
+      "step": 21
+    },
+    {
+      "epoch": 0.004201496783229025,
+      "grad_norm": 4.267176151275635,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 1.1948,
+      "step": 24
+    },
+    {
+      "epoch": 0.004376559149196902,
+      "eval_loss": 1.228528380393982,
+      "eval_runtime": 406.2491,
+      "eval_samples_per_second": 23.683,
+      "eval_steps_per_second": 2.961,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8532591409889280.0,
+  "total_flos": 1.0612410566049792e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null