Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96ccc5b9ac087dba0f10fdc4d5342763320b3d393d47476a061e07710ee9b638
+oid sha256:833eb01138783f900186e10d4e4abdce2331f847c08833bd0fa504402085a60b
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7e67d1ef70988eb681b3fa8d5f97f7cf8dd017881f8271c13d1e14c3a983051
+oid sha256:be261bb291f9b4a5d55868833557a7b0f1e34d282ee624617485ad6c262a8639
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0432b165814871079f9ee89b9acfe77d274309a01b9cb7e1f0b9e05d72efa489
+oid sha256:d57cb21cc7fa77e1d0615ec039ca096efa9b134639fd673e38d6b4c2602fef16
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7736f824b0a772b3806e37af9e860068207311e879196bc19f8a76d97eaf6bce
+oid sha256:61c2b4927e3039b26d377375be782c03ce853d193f96b5868ccf559441e84af9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.09471629559993744,
-  "best_model_checkpoint": "miner_id_besimray/checkpoint-100",
-  "epoch": 1.2861736334405145,
+  "best_metric": 0.07654841244220734,
+  "best_model_checkpoint": "miner_id_besimray/checkpoint-120",
+  "epoch": 1.5434083601286175,
   "eval_steps": 20,
-  "global_step": 100,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -755,6 +755,154 @@
       "eval_samples_per_second": 23.861,
       "eval_steps_per_second": 2.473,
       "step": 100
+    },
+    {
+      "epoch": 1.2990353697749195,
+      "grad_norm": 0.821508526802063,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0432,
+      "step": 101
+    },
+    {
+      "epoch": 1.3118971061093248,
+      "grad_norm": 2.061079740524292,
+      "learning_rate": 5.261313375270014e-05,
+      "loss": 0.0979,
+      "step": 102
+    },
+    {
+      "epoch": 1.32475884244373,
+      "grad_norm": 1.4887949228286743,
+      "learning_rate": 5.0649178193565314e-05,
+      "loss": 0.0788,
+      "step": 103
+    },
+    {
+      "epoch": 1.337620578778135,
+      "grad_norm": 0.8588582873344421,
+      "learning_rate": 4.87100722594094e-05,
+      "loss": 0.0554,
+      "step": 104
+    },
+    {
+      "epoch": 1.3504823151125402,
+      "grad_norm": 0.8016582131385803,
+      "learning_rate": 4.6796792348466356e-05,
+      "loss": 0.065,
+      "step": 105
+    },
+    {
+      "epoch": 1.3633440514469453,
+      "grad_norm": 1.197761058807373,
+      "learning_rate": 4.491030185478976e-05,
+      "loss": 0.1194,
+      "step": 106
+    },
+    {
+      "epoch": 1.3762057877813505,
+      "grad_norm": 0.5511653423309326,
+      "learning_rate": 4.305155068315481e-05,
+      "loss": 0.032,
+      "step": 107
+    },
+    {
+      "epoch": 1.3890675241157555,
+      "grad_norm": 1.1377793550491333,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0882,
+      "step": 108
+    },
+    {
+      "epoch": 1.4019292604501608,
+      "grad_norm": 0.49581602215766907,
+      "learning_rate": 3.942099561591802e-05,
+      "loss": 0.0292,
+      "step": 109
+    },
+    {
+      "epoch": 1.414790996784566,
+      "grad_norm": 1.2391666173934937,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 0.0838,
+      "step": 110
+    },
+    {
+      "epoch": 1.427652733118971,
+      "grad_norm": 0.8613415360450745,
+      "learning_rate": 3.591243860149759e-05,
+      "loss": 0.059,
+      "step": 111
+    },
+    {
+      "epoch": 1.4405144694533762,
+      "grad_norm": 1.378289818763733,
+      "learning_rate": 3.4206127406028745e-05,
+      "loss": 0.0894,
+      "step": 112
+    },
+    {
+      "epoch": 1.4533762057877815,
+      "grad_norm": 1.2210605144500732,
+      "learning_rate": 3.253294540679257e-05,
+      "loss": 0.1327,
+      "step": 113
+    },
+    {
+      "epoch": 1.4662379421221865,
+      "grad_norm": 1.610064148902893,
+      "learning_rate": 3.089373510131354e-05,
+      "loss": 0.1172,
+      "step": 114
+    },
+    {
+      "epoch": 1.4790996784565915,
+      "grad_norm": 0.9988131523132324,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0927,
+      "step": 115
+    },
+    {
+      "epoch": 1.4919614147909968,
+      "grad_norm": 0.8481462597846985,
+      "learning_rate": 2.7720513617260856e-05,
+      "loss": 0.0406,
+      "step": 116
+    },
+    {
+      "epoch": 1.504823151125402,
+      "grad_norm": 0.4117134213447571,
+      "learning_rate": 2.6188100251265945e-05,
+      "loss": 0.0235,
+      "step": 117
+    },
+    {
+      "epoch": 1.517684887459807,
+      "grad_norm": 1.1421048641204834,
+      "learning_rate": 2.4692853399638917e-05,
+      "loss": 0.0818,
+      "step": 118
+    },
+    {
+      "epoch": 1.5305466237942122,
+      "grad_norm": 0.8076781630516052,
+      "learning_rate": 2.323552596419889e-05,
+      "loss": 0.053,
+      "step": 119
+    },
+    {
+      "epoch": 1.5434083601286175,
+      "grad_norm": 1.6947088241577148,
+      "learning_rate": 2.181685175319702e-05,
+      "loss": 0.1237,
+      "step": 120
+    },
+    {
+      "epoch": 1.5434083601286175,
+      "eval_loss": 0.07654841244220734,
+      "eval_runtime": 6.4533,
+      "eval_samples_per_second": 25.413,
+      "eval_steps_per_second": 2.634,
+      "step": 120
     }
   ],
   "logging_steps": 1,
@@ -783,7 +931,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.394546334728192e+16,
+  "total_flos": 2.858372738187264e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null