Training in progress, step 47, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab678ec3b9177873ef6000c68381a8927feec8290e8e6f3815749fc04cac39d2
+oid sha256:9b3ea7aff34a6aeff7c095dadcd3f4306b8c3a5734094df7552010ede104800c
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5698490167455520fb24a32e13524bc66188dd2d30baf34b15eaaf450dd4ca3
+oid sha256:ce12d67d5673915dad82705708d89d00e3dcfe9bd366d048ee5bdac041381515
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:712ceb84ef60c2c784fa7af39d127e750bb14a8ea30edaef3e0d48c5a09615ab
+oid sha256:73a34da48d7eb442169be35dcdbc580bcd4a80aca4e5469d4b9a0878db76a1e1
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:278148bb638b04b3a1fd4cd803db0fd777e1e40632e0edf8edeb4ac0cdcc0732
+oid sha256:5edd7eeb3f612dfd6a07be45d4794dd10fa6463b830f0d492b61b03851786e45
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:205509a1ebbc7f62d8c673f5ba8a87d99566e48fe8494c4a889a5efd6437cf89
+oid sha256:d27a88ad06c5048a02e9ea8e9a810d6a2f20c6dccb35bd4f1b9d46ce1321aef1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b78afa2cfb0ab80d1cd351b75c7749bcd20f767e01079d6cd03b2abf6d084c9a
+oid sha256:ec32301b7d4ff0f980feff9d429bddca95c42f382219a5574bc6778cd50d65e3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:698599bc6a23f90bcfa6fe6477fe271a75dd69b61906d06e949f339ef005f13a
+oid sha256:35151b95c3cc502d9e4fc6d9dc99d112a424ad3624e33428ecbe517e837a6fc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.363144874572754,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.6260162601626016,
+  "epoch": 3.0569105691056913,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 47,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,160 @@
       "eval_samples_per_second": 755.6,
       "eval_steps_per_second": 94.45,
       "step": 25
+    },
+    {
+      "epoch": 1.6910569105691056,
+      "grad_norm": 0.20653556287288666,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.0741,
+      "step": 26
+    },
+    {
+      "epoch": 1.7560975609756098,
+      "grad_norm": 0.2042083591222763,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 9.9069,
+      "step": 27
+    },
+    {
+      "epoch": 1.821138211382114,
+      "grad_norm": 0.17668259143829346,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 11.2898,
+      "step": 28
+    },
+    {
+      "epoch": 1.886178861788618,
+      "grad_norm": 0.30113402009010315,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 9.5075,
+      "step": 29
+    },
+    {
+      "epoch": 1.951219512195122,
+      "grad_norm": 0.2606578469276428,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 11.0706,
+      "step": 30
+    },
+    {
+      "epoch": 2.016260162601626,
+      "grad_norm": 0.29925504326820374,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 17.1891,
+      "step": 31
+    },
+    {
+      "epoch": 2.08130081300813,
+      "grad_norm": 0.18933387100696564,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.4637,
+      "step": 32
+    },
+    {
+      "epoch": 2.1463414634146343,
+      "grad_norm": 0.20285484194755554,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 9.0417,
+      "step": 33
+    },
+    {
+      "epoch": 2.2113821138211383,
+      "grad_norm": 0.18055562674999237,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 8.3783,
+      "step": 34
+    },
+    {
+      "epoch": 2.2764227642276422,
+      "grad_norm": 0.3930016756057739,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 13.4143,
+      "step": 35
+    },
+    {
+      "epoch": 2.341463414634146,
+      "grad_norm": 0.18804241716861725,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 11.0764,
+      "step": 36
+    },
+    {
+      "epoch": 2.40650406504065,
+      "grad_norm": 0.20714622735977173,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 8.692,
+      "step": 37
+    },
+    {
+      "epoch": 2.4715447154471546,
+      "grad_norm": 0.16578172147274017,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 7.9278,
+      "step": 38
+    },
+    {
+      "epoch": 2.5365853658536586,
+      "grad_norm": 0.38254594802856445,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 13.5877,
+      "step": 39
+    },
+    {
+      "epoch": 2.6016260162601625,
+      "grad_norm": 0.19641678035259247,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 11.453,
+      "step": 40
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.2300872653722763,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 8.5011,
+      "step": 41
+    },
+    {
+      "epoch": 2.7317073170731705,
+      "grad_norm": 0.1619451344013214,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 7.7501,
+      "step": 42
+    },
+    {
+      "epoch": 2.796747967479675,
+      "grad_norm": 0.3057861328125,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 13.4289,
+      "step": 43
+    },
+    {
+      "epoch": 2.861788617886179,
+      "grad_norm": 0.19348877668380737,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.0297,
+      "step": 44
+    },
+    {
+      "epoch": 2.926829268292683,
+      "grad_norm": 0.27544501423835754,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.6125,
+      "step": 45
+    },
+    {
+      "epoch": 2.991869918699187,
+      "grad_norm": 0.38650020956993103,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 15.4729,
+      "step": 46
+    },
+    {
+      "epoch": 3.0569105691056913,
+      "grad_norm": 0.31395643949508667,
+      "learning_rate": 0.0,
+      "loss": 11.6441,
+      "step": 47
     }
   ],
   "logging_steps": 1,
@@ -221,12 +375,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 25179695087616.0,
+  "total_flos": 47285435891712.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null