Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd75e79e15a21c061c36831653d5e4f242039ccce5088f3444ac4db972a25ac6
+oid sha256:da4fc4bf8289a80e04830dd9442edc8eb91a99a5e683fa9a132eff0afd906a4f
 size 19552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abde123bec65d70d2a491fb2e2bc2bb56413a0b6d15f803ffdf4b208e304840
+oid sha256:cbf048fe887df4897b8d0de8261f5eaf4cb6dc1d6e891caf100f9d88c0afd5f1
 size 47860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab8ac4d78789b28929bf0bca6c975098bedef6ad81c07465d482ebfc87ce0ee
+oid sha256:719007b97d7d42a16c0d37198ce0dce3d5f047b897028fd22515dbec441991e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67bdc1680e75e7cf9661cc84482edc217f841c56aca5f9a3979c1c72a436f392
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 12.451294898986816,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.38860103626943004,
+  "best_metric": 12.450624465942383,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.5181347150259067,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 30.241,
       "eval_steps_per_second": 15.12,
       "step": 75
+    },
+    {
+      "epoch": 0.39378238341968913,
+      "grad_norm": 0.09004762023687363,
+      "learning_rate": 2.9876321572751144e-05,
+      "loss": 12.4461,
+      "step": 76
+    },
+    {
+      "epoch": 0.39896373056994816,
+      "grad_norm": 0.11161310225725174,
+      "learning_rate": 2.7557479520891104e-05,
+      "loss": 12.4585,
+      "step": 77
+    },
+    {
+      "epoch": 0.40414507772020725,
+      "grad_norm": 0.09739028662443161,
+      "learning_rate": 2.5317852301584643e-05,
+      "loss": 12.4534,
+      "step": 78
+    },
+    {
+      "epoch": 0.40932642487046633,
+      "grad_norm": 0.10811323672533035,
+      "learning_rate": 2.315988891431412e-05,
+      "loss": 12.4641,
+      "step": 79
+    },
+    {
+      "epoch": 0.41450777202072536,
+      "grad_norm": 0.13142776489257812,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 12.4527,
+      "step": 80
+    },
+    {
+      "epoch": 0.41968911917098445,
+      "grad_norm": 0.11857596784830093,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 12.4588,
+      "step": 81
+    },
+    {
+      "epoch": 0.42487046632124353,
+      "grad_norm": 0.10847970843315125,
+      "learning_rate": 1.7199116885197995e-05,
+      "loss": 12.4547,
+      "step": 82
+    },
+    {
+      "epoch": 0.43005181347150256,
+      "grad_norm": 0.0970698669552803,
+      "learning_rate": 1.5390474757906446e-05,
+      "loss": 12.4555,
+      "step": 83
+    },
+    {
+      "epoch": 0.43523316062176165,
+      "grad_norm": 0.10735609382390976,
+      "learning_rate": 1.3674351904242611e-05,
+      "loss": 12.4597,
+      "step": 84
+    },
+    {
+      "epoch": 0.44041450777202074,
+      "grad_norm": 0.12275223433971405,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 12.4475,
+      "step": 85
+    },
+    {
+      "epoch": 0.44559585492227977,
+      "grad_norm": 0.12521672248840332,
+      "learning_rate": 1.0527067017923654e-05,
+      "loss": 12.4532,
+      "step": 86
+    },
+    {
+      "epoch": 0.45077720207253885,
+      "grad_norm": 0.10316548496484756,
+      "learning_rate": 9.09934649508375e-06,
+      "loss": 12.4575,
+      "step": 87
+    },
+    {
+      "epoch": 0.45595854922279794,
+      "grad_norm": 0.12661558389663696,
+      "learning_rate": 7.771024502261526e-06,
+      "loss": 12.4529,
+      "step": 88
+    },
+    {
+      "epoch": 0.46113989637305697,
+      "grad_norm": 0.13413290679454803,
+      "learning_rate": 6.543553540053926e-06,
+      "loss": 12.4472,
+      "step": 89
+    },
+    {
+      "epoch": 0.46632124352331605,
+      "grad_norm": 0.1272674798965454,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 12.4598,
+      "step": 90
+    },
+    {
+      "epoch": 0.47150259067357514,
+      "grad_norm": 0.11629094928503036,
+      "learning_rate": 4.3964218465642355e-06,
+      "loss": 12.4569,
+      "step": 91
+    },
+    {
+      "epoch": 0.47668393782383417,
+      "grad_norm": 0.1196855679154396,
+      "learning_rate": 3.4791089722651436e-06,
+      "loss": 12.4585,
+      "step": 92
+    },
+    {
+      "epoch": 0.48186528497409326,
+      "grad_norm": 0.11991642415523529,
+      "learning_rate": 2.667340275199426e-06,
+      "loss": 12.4523,
+      "step": 93
+    },
+    {
+      "epoch": 0.48704663212435234,
+      "grad_norm": 0.12190738320350647,
+      "learning_rate": 1.9620034125190644e-06,
+      "loss": 12.4582,
+      "step": 94
+    },
+    {
+      "epoch": 0.49222797927461137,
+      "grad_norm": 0.14460605382919312,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 12.4452,
+      "step": 95
+    },
+    {
+      "epoch": 0.49740932642487046,
+      "grad_norm": 0.12674753367900848,
+      "learning_rate": 8.735930673024806e-07,
+      "loss": 12.4645,
+      "step": 96
+    },
+    {
+      "epoch": 0.5025906735751295,
+      "grad_norm": 0.08967099338769913,
+      "learning_rate": 4.917097454988584e-07,
+      "loss": 12.4606,
+      "step": 97
+    },
+    {
+      "epoch": 0.5077720207253886,
+      "grad_norm": 0.09563156962394714,
+      "learning_rate": 2.1863727812254653e-07,
+      "loss": 12.4635,
+      "step": 98
+    },
+    {
+      "epoch": 0.5129533678756477,
+      "grad_norm": 0.10204072296619415,
+      "learning_rate": 5.467426590739511e-08,
+      "loss": 12.4471,
+      "step": 99
+    },
+    {
+      "epoch": 0.5181347150259067,
+      "grad_norm": 0.10895761102437973,
+      "learning_rate": 0.0,
+      "loss": 12.4487,
+      "step": 100
+    },
+    {
+      "epoch": 0.5181347150259067,
+      "eval_loss": 12.450624465942383,
+      "eval_runtime": 2.712,
+      "eval_samples_per_second": 30.237,
+      "eval_steps_per_second": 15.118,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 92484403200.0,
+  "total_flos": 123312537600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null