Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:435cb9ffb6dba1b1bca47db7df00e5b4a0c86489433192deba7487d14b10440a
+oid sha256:fe1e6c0f60e9a7d2d9d72908d2cc8be5a3e81aafa607a805cc7a360c1471788a
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35d4a927b1f10c2eb0bcb89348b1ada8098e08a742dbca066edb1b809f494dc0
+oid sha256:0745e23c080bc6a723eeee1423950444b009e3ebd8c2be835c4217ccd8e0c491
 size 418094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c44b074319deaa330dbf9fbcc287dd8e1e161bc5b931e9fb7621646bc763b5e0
+oid sha256:529521ef0526c656a6cd0091a68822c3c32809b75d530758bac154189a052a86
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18572f0adae215b3259455cf96083d95e78dc1ab7af393890cd3753bf61cc9f4
+oid sha256:ac6ee4c7143f9893927b533c972fc3aa0da9526c7e014b3849d291e400a8521c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.793699741363525,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.09410657569697682,
+  "best_metric": 6.792733192443848,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.10586989765909893,
   "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": 554.821,
       "eval_steps_per_second": 138.86,
       "step": 400
+    },
+    {
+      "epoch": 0.09645924008940125,
+      "grad_norm": 0.6257851719856262,
+      "learning_rate": 2.0435181601880635e-05,
+      "loss": 6.8415,
+      "step": 410
+    },
+    {
+      "epoch": 0.09881190448182567,
+      "grad_norm": 0.5798721313476562,
+      "learning_rate": 1.625885371126242e-05,
+      "loss": 6.825,
+      "step": 420
+    },
+    {
+      "epoch": 0.10116456887425009,
+      "grad_norm": 0.5897112488746643,
+      "learning_rate": 1.2524607564094813e-05,
+      "loss": 6.797,
+      "step": 430
+    },
+    {
+      "epoch": 0.1035172332666745,
+      "grad_norm": 0.7111787796020508,
+      "learning_rate": 9.250636032241695e-06,
+      "loss": 6.772,
+      "step": 440
+    },
+    {
+      "epoch": 0.10586989765909893,
+      "grad_norm": 1.2426642179489136,
+      "learning_rate": 6.45288957590781e-06,
+      "loss": 6.7647,
+      "step": 450
+    },
+    {
+      "epoch": 0.10586989765909893,
+      "eval_loss": 6.792733192443848,
+      "eval_runtime": 3.2252,
+      "eval_samples_per_second": 555.008,
+      "eval_steps_per_second": 138.907,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 961128038400.0,
+  "total_flos": 1081269043200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null