Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f2ffa6272351a71666d1acc3a59b1e6f821a07577b8c86329ce30c8eb5736e4
+oid sha256:0a959d3e2c734772605e5230b07eb049bc75a9d337c43e4c12b920095a80d02b
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09667ced072b45b31ab0b8bd8200396aa0107a1a72453557aee7ab34829a5780
+oid sha256:a27ee3419a245578a2277005c188d6d5258bb8341f12348499f11e663fad5476
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef526cec68f8d11289caecca419578ea999fdaac0825cd8802ad893129bd8eb
+oid sha256:24795ebfcca9e4abb0f4bd3458750424e888df4066034ea7fa5c8e1351dd64a8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f83d259563f490ff1ff7e4916ac178dc618734e66d8ea8288665df23ceab41
+oid sha256:5fa0f7e2faaa98aa485e5dc42922e1b1819381507fa6961c3be50a0b49af04c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.07403463125228882,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.17905102954341987,
+  "best_metric": 0.06836262345314026,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.20143240823634737,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 16.532,
       "eval_steps_per_second": 4.146,
       "step": 400
+    },
+    {
+      "epoch": 0.18352730528200537,
+      "grad_norm": 0.6138676404953003,
+      "learning_rate": 2.024419859625558e-05,
+      "loss": 0.1626,
+      "step": 410
+    },
+    {
+      "epoch": 0.18800358102059087,
+      "grad_norm": 0.581366240978241,
+      "learning_rate": 1.610690180741885e-05,
+      "loss": 0.1102,
+      "step": 420
+    },
+    {
+      "epoch": 0.19247985675917637,
+      "grad_norm": 0.7073346376419067,
+      "learning_rate": 1.240755515695374e-05,
+      "loss": 0.1405,
+      "step": 430
+    },
+    {
+      "epoch": 0.19695613249776187,
+      "grad_norm": 0.80199134349823,
+      "learning_rate": 9.164181489884296e-06,
+      "loss": 0.1096,
+      "step": 440
+    },
+    {
+      "epoch": 0.20143240823634737,
+      "grad_norm": 1.6628501415252686,
+      "learning_rate": 6.392582196693718e-06,
+      "loss": 0.1787,
+      "step": 450
+    },
+    {
+      "epoch": 0.20143240823634737,
+      "eval_loss": 0.06836262345314026,
+      "eval_runtime": 56.6998,
+      "eval_samples_per_second": 16.596,
+      "eval_steps_per_second": 4.162,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.22654807898194e+16,
+  "total_flos": 8.129866588854682e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null