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:ded30752c82015cdc81c5cd344f66ff786790fa455dbfd06c1304c2bb0ad3c4b
+oid sha256:c4b694e97f12ba0d9b80936d6bca813b6ce7af19d72d9a807f8b927879c1e5ce
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddf474575d250c98f0bbeb23f7ae703bcb03a5d658c648939bc68929972c1e31
+oid sha256:ac9f2e903bbf84f3f99839f1d4f0bfde2eed106e8182b31e802c69d07bca5e69
 size 82461044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcc24c73277f3c96f28b7c301c952e3126c4ad16110cf35bdcfaeb3044f08301
+oid sha256:97ba33e881ebfe096fa15ecb254e8f1a02b8bcbe89cb30588c4574966da54992
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a53e373878af8696de39d4b7adb8634138f0e346e89bffc05bcb76c7b6de169
+oid sha256:30565d7b1986ad1c3966f0f9b850f0ae7d4cfe76be60a78deb1442c25c9c950e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.5573015213012695,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.09102286949596086,
+  "best_metric": 2.5509848594665527,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.10240072818295597,
   "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": 10.026,
       "eval_steps_per_second": 2.508,
       "step": 400
+    },
+    {
+      "epoch": 0.09329844123335988,
+      "grad_norm": 0.5412922501564026,
+      "learning_rate": 1.9862232585005475e-05,
+      "loss": 2.5775,
+      "step": 410
+    },
+    {
+      "epoch": 0.0955740129707589,
+      "grad_norm": 0.5537426471710205,
+      "learning_rate": 1.58029979997317e-05,
+      "loss": 2.5315,
+      "step": 420
+    },
+    {
+      "epoch": 0.09784958470815792,
+      "grad_norm": 0.532833993434906,
+      "learning_rate": 1.2173450342671593e-05,
+      "loss": 2.4957,
+      "step": 430
+    },
+    {
+      "epoch": 0.10012515644555695,
+      "grad_norm": 0.5533403158187866,
+      "learning_rate": 8.991272405169498e-06,
+      "loss": 2.512,
+      "step": 440
+    },
+    {
+      "epoch": 0.10240072818295597,
+      "grad_norm": 1.024665117263794,
+      "learning_rate": 6.271967438265535e-06,
+      "loss": 2.4862,
+      "step": 450
+    },
+    {
+      "epoch": 0.10240072818295597,
+      "eval_loss": 2.5509848594665527,
+      "eval_runtime": 184.5083,
+      "eval_samples_per_second": 10.032,
+      "eval_steps_per_second": 2.509,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3159403401877914e+17,
+  "total_flos": 1.4819620298529178e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null