Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d38707f769ac94fc3404bca203ff44d59f44f98e11b3b8ccfd58bd09b279b842
+oid sha256:c5b7485765e1ee6b331dadfceabb8900e2cfb6bb74d0e49d00f6c59f80d858f4
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a882b9ac3d39829554926fc6f3021f0c41f1eec6f3b08786795b0b52e7bbbc
+oid sha256:73a36b4ea2995908c677da996d16476fa28e54b37e4bdca35739c28d15e5f8c8
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:076b1211decf60a02d31eacee2d0525ceb841eb65ba02be607811defe4cc74bf
+oid sha256:e2787a2e085d67a013cad80a12cd9d77bc6b7ecf6ce0cbefba10f292935ac76b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58e0de857b6a45654b387bce8e8a80846023ef7c2a9e8c94f0c5b7891589e3df
+oid sha256:f5b35706de91e344e49891f8743c2ab607c7e0d80bbc534bb6605c5cbeb51b2a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:236cfd5d1022f64d194340fd1055c20b9ee0cffb50bb9e8c5fb32179168fc1b6
+oid sha256:5a34d7ba1a3a4bae543150986b96532d1cc050d95703a880d5f44782cde5afe3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446fa135a6d29e0c4318537c04446285b6fc2d09f4ea47b719b1bb9df61fb6bd
+oid sha256:23c26b8e21566ad272fdc7797a4b4d8e851a70f89efcfadbd318f42d197dacbc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.00033007311867550015,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.031773770752244024,
+  "best_metric": 0.00027677693287841976,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06354754150448805,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 24.008,
       "eval_steps_per_second": 6.242,
       "step": 25
+    },
+    {
+      "epoch": 0.033044721582333784,
+      "grad_norm": 0.058413226157426834,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0024,
+      "step": 26
+    },
+    {
+      "epoch": 0.034315672412423545,
+      "grad_norm": 0.09031689167022705,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0034,
+      "step": 27
+    },
+    {
+      "epoch": 0.035586623242513306,
+      "grad_norm": 0.03944770619273186,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0011,
+      "step": 28
+    },
+    {
+      "epoch": 0.036857574072603067,
+      "grad_norm": 0.04432542622089386,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0015,
+      "step": 29
+    },
+    {
+      "epoch": 0.03812852490269283,
+      "grad_norm": 0.0764271542429924,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0012,
+      "step": 30
+    },
+    {
+      "epoch": 0.03939947573278259,
+      "grad_norm": 0.09056982398033142,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0037,
+      "step": 31
+    },
+    {
+      "epoch": 0.04067042656287235,
+      "grad_norm": 0.05006411299109459,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.001,
+      "step": 32
+    },
+    {
+      "epoch": 0.04194137739296211,
+      "grad_norm": 0.019817272201180458,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0002,
+      "step": 33
+    },
+    {
+      "epoch": 0.04321232822305187,
+      "grad_norm": 0.09425932168960571,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0011,
+      "step": 34
+    },
+    {
+      "epoch": 0.04448327905314163,
+      "grad_norm": 0.235464408993721,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0009,
+      "step": 35
+    },
+    {
+      "epoch": 0.04575422988323139,
+      "grad_norm": 0.08573014289140701,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0026,
+      "step": 36
+    },
+    {
+      "epoch": 0.04702518071332115,
+      "grad_norm": 0.010113895870745182,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0003,
+      "step": 37
+    },
+    {
+      "epoch": 0.04829613154341091,
+      "grad_norm": 0.1582615077495575,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0045,
+      "step": 38
+    },
+    {
+      "epoch": 0.04956708237350067,
+      "grad_norm": 0.031762491911649704,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0013,
+      "step": 39
+    },
+    {
+      "epoch": 0.050838033203590434,
+      "grad_norm": 0.02582133747637272,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0008,
+      "step": 40
+    },
+    {
+      "epoch": 0.052108984033680195,
+      "grad_norm": 0.022741837427020073,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0002,
+      "step": 41
+    },
+    {
+      "epoch": 0.053379934863769955,
+      "grad_norm": 0.07146788388490677,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0014,
+      "step": 42
+    },
+    {
+      "epoch": 0.054650885693859716,
+      "grad_norm": 0.06038248538970947,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0007,
+      "step": 43
+    },
+    {
+      "epoch": 0.05592183652394948,
+      "grad_norm": 0.03409354016184807,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0005,
+      "step": 44
+    },
+    {
+      "epoch": 0.05719278735403924,
+      "grad_norm": 0.01463512983173132,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0005,
+      "step": 45
+    },
+    {
+      "epoch": 0.058463738184129005,
+      "grad_norm": 0.01581159234046936,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0004,
+      "step": 46
+    },
+    {
+      "epoch": 0.059734689014218766,
+      "grad_norm": 0.1253223568201065,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0037,
+      "step": 47
+    },
+    {
+      "epoch": 0.061005639844308526,
+      "grad_norm": 0.2984582483768463,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0123,
+      "step": 48
+    },
+    {
+      "epoch": 0.06227659067439829,
+      "grad_norm": 0.009870694950222969,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0003,
+      "step": 49
+    },
+    {
+      "epoch": 0.06354754150448805,
+      "grad_norm": 0.19125765562057495,
+      "learning_rate": 1e-05,
+      "loss": 0.0042,
+      "step": 50
+    },
+    {
+      "epoch": 0.06354754150448805,
+      "eval_loss": 0.00027677693287841976,
+      "eval_runtime": 2.0959,
+      "eval_samples_per_second": 23.856,
+      "eval_steps_per_second": 6.203,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null