Training in progress, step 258, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e00f795373d48fe700f3ac538f1e6d917f657c2991866baedbe4e97016442d
+oid sha256:7642ab38cc4d0ac27666134eef25f6c939e09eff7de2f2a5046f957d09102f5a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27e19611464de0f4881682ee88217089320bf712b39dad09f36dceb911be8b94
-size 43122580
+oid sha256:c34e65ccc0893f3f3201d4a3301526f6e4e030e855c54408dc5be073adb6686d
+size 43123028

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de20a5cd3c88682fc5b2bee85dd4db1a9c7684b18bea5f60553dccb8e074f2c
+oid sha256:3b536e9b95d89439a3272f61cd2b9c84ddc6a9f0549c2b6fbdf7508ca48a0bca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ac80c0099741497605b86b89633b368aa3c621dc73b66fb8d88b5b18259b2d6
+oid sha256:de60b07a925742ae141dd83d6368ce8ec8048f752fbd50a4e436245ca25d81ac
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.44831588864326477,
-  "best_model_checkpoint": "miner_id_24/checkpoint-215",
-  "epoch": 0.6643491695635381,
+  "best_metric": 0.44344472885131836,
+  "best_model_checkpoint": "miner_id_24/checkpoint-258",
+  "epoch": 0.7972190034762456,
   "eval_steps": 43,
-  "global_step": 215,
+  "global_step": 258,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -90,6 +90,21 @@
       "eval_samples_per_second": 21.424,
       "eval_steps_per_second": 1.35,
       "step": 215
+    },
+    {
+      "epoch": 0.7972190034762456,
+      "grad_norm": 3.9321422576904297,
+      "learning_rate": 0.00039997623742088825,
+      "loss": 3.5561,
+      "step": 258
+    },
+    {
+      "epoch": 0.7972190034762456,
+      "eval_loss": 0.44344472885131836,
+      "eval_runtime": 70.4613,
+      "eval_samples_per_second": 21.615,
+      "eval_steps_per_second": 1.362,
+      "step": 258
     }
   ],
   "logging_steps": 43,
@@ -118,7 +133,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1290711730537103e+18,
+  "total_flos": 1.3502583541145272e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null