Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8035f9fa9dd6c0bc4c45f52e521e22b86b166323c7b65c08dae62f991969fe91
+oid sha256:2626fe35e6f83de99f058fbe7858cfb48ff4077837213d14a418ba4721bfb4ae
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9540dbc5ce3a1982e347d4515a812d4aff17509d9697d169e86400d7e8ed1728
+oid sha256:c94f83497f051a6aefa1401f944ba5ae9c11134faca09b09cb64d72d9ff8c979
 size 74090938

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aade009e3ca8120543da9c7073fdeeb8ddb7dd337ceb29df767706c304138238
+oid sha256:6cb21cbb22e6af7a5398ea007cced10baef621a5b7ab52ee9cbe09f3a9941c3d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3567347526550293,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004545454545454545,
+  "best_metric": 1.2963515520095825,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00909090909090909,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 11.7,
       "eval_steps_per_second": 5.856,
       "step": 10
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 0.29608702659606934,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 1.3418,
+      "step": 11
+    },
+    {
+      "epoch": 0.005454545454545455,
+      "grad_norm": 0.27602267265319824,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 1.069,
+      "step": 12
+    },
+    {
+      "epoch": 0.005909090909090909,
+      "grad_norm": 0.30428454279899597,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.4957,
+      "step": 13
+    },
+    {
+      "epoch": 0.006363636363636364,
+      "grad_norm": 0.32315993309020996,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.0698,
+      "step": 14
+    },
+    {
+      "epoch": 0.006818181818181818,
+      "grad_norm": 0.2515247166156769,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.2932,
+      "step": 15
+    },
+    {
+      "epoch": 0.006818181818181818,
+      "eval_loss": 1.3137667179107666,
+      "eval_runtime": 85.1577,
+      "eval_samples_per_second": 10.886,
+      "eval_steps_per_second": 5.449,
+      "step": 15
+    },
+    {
+      "epoch": 0.007272727272727273,
+      "grad_norm": 0.28928083181381226,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.1773,
+      "step": 16
+    },
+    {
+      "epoch": 0.007727272727272728,
+      "grad_norm": 0.4229072034358978,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.5595,
+      "step": 17
+    },
+    {
+      "epoch": 0.008181818181818182,
+      "grad_norm": 0.24980007112026215,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.0698,
+      "step": 18
+    },
+    {
+      "epoch": 0.008636363636363636,
+      "grad_norm": 0.38862258195877075,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3397,
+      "step": 19
+    },
+    {
+      "epoch": 0.00909090909090909,
+      "grad_norm": 0.2815423011779785,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.004,
+      "step": 20
+    },
+    {
+      "epoch": 0.00909090909090909,
+      "eval_loss": 1.2963515520095825,
+      "eval_runtime": 76.7123,
+      "eval_samples_per_second": 12.084,
+      "eval_steps_per_second": 6.049,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 543199583010816.0,
+  "total_flos": 1045861883707392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null