Training in progress, step 47, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f1ca19195dda06fa0c0010f835875682f35d65c4b4814cf99769d465a8fcf6
+oid sha256:480387c563620a21b481b6b338550bf5c78a02c129bae75468dabcf96a1e12d5
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31fd7c1e36024e266b482763c72e1e450b1169939e191dc217646e0d328cd808
+oid sha256:2da25ffbf60ad0fc90ed6464743c8e1bd5172c8901e4e971505f30616959206a
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ac6a610b7350c409f478f4d40373ee235e3a55778f16948b61c3f53ee83e77
+oid sha256:e97692b4dde479106744c0fb4517691f87e4aa515a0acb9e0d4186b895e8ec25
 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": 10.36490249633789,
   "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": 758.896,
       "eval_steps_per_second": 94.862,
       "step": 25
+    },
+    {
+      "epoch": 1.6910569105691056,
+      "grad_norm": 0.16444501280784607,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.0758,
+      "step": 26
+    },
+    {
+      "epoch": 1.7560975609756098,
+      "grad_norm": 0.1527736634016037,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 9.9086,
+      "step": 27
+    },
+    {
+      "epoch": 1.821138211382114,
+      "grad_norm": 0.1393318772315979,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 11.2915,
+      "step": 28
+    },
+    {
+      "epoch": 1.886178861788618,
+      "grad_norm": 0.2215719223022461,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 9.5102,
+      "step": 29
+    },
+    {
+      "epoch": 1.951219512195122,
+      "grad_norm": 0.2005256563425064,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 11.0727,
+      "step": 30
+    },
+    {
+      "epoch": 2.016260162601626,
+      "grad_norm": 0.221042200922966,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 17.1926,
+      "step": 31
+    },
+    {
+      "epoch": 2.08130081300813,
+      "grad_norm": 0.14217452704906464,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.4657,
+      "step": 32
+    },
+    {
+      "epoch": 2.1463414634146343,
+      "grad_norm": 0.1489098221063614,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 9.044,
+      "step": 33
+    },
+    {
+      "epoch": 2.2113821138211383,
+      "grad_norm": 0.14052225649356842,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 8.38,
+      "step": 34
+    },
+    {
+      "epoch": 2.2764227642276422,
+      "grad_norm": 0.2919885218143463,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 13.4178,
+      "step": 35
+    },
+    {
+      "epoch": 2.341463414634146,
+      "grad_norm": 0.14278586208820343,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 11.0784,
+      "step": 36
+    },
+    {
+      "epoch": 2.40650406504065,
+      "grad_norm": 0.15102294087409973,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 8.6945,
+      "step": 37
+    },
+    {
+      "epoch": 2.4715447154471546,
+      "grad_norm": 0.1303826868534088,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 7.9293,
+      "step": 38
+    },
+    {
+      "epoch": 2.5365853658536586,
+      "grad_norm": 0.2822273075580597,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 13.5914,
+      "step": 39
+    },
+    {
+      "epoch": 2.6016260162601625,
+      "grad_norm": 0.15251681208610535,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 11.455,
+      "step": 40
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.16769857704639435,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 8.5039,
+      "step": 41
+    },
+    {
+      "epoch": 2.7317073170731705,
+      "grad_norm": 0.12688644230365753,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 7.7516,
+      "step": 42
+    },
+    {
+      "epoch": 2.796747967479675,
+      "grad_norm": 0.22355830669403076,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 13.4321,
+      "step": 43
+    },
+    {
+      "epoch": 2.861788617886179,
+      "grad_norm": 0.14232714474201202,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.0322,
+      "step": 44
+    },
+    {
+      "epoch": 2.926829268292683,
+      "grad_norm": 0.20755743980407715,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.6157,
+      "step": 45
+    },
+    {
+      "epoch": 2.991869918699187,
+      "grad_norm": 0.2799222767353058,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 15.4765,
+      "step": 46
+    },
+    {
+      "epoch": 3.0569105691056913,
+      "grad_norm": 0.22992239892482758,
+      "learning_rate": 0.0,
+      "loss": 11.6473,
+      "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