Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fad674a631a87bf2db765e3627b2e6d6df8c1b7797bbcfdede9afd5e39ffe54
+oid sha256:d902103cfef4916f3e11ad299a0329676c77a975702d7da8b9d803f263e4dec7
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02156ba6b484c1b9d068c01ea5776c25242d91abe6805c2a76fe970879ebf8dc
+oid sha256:7257ea718196d19ae1f90ff0877f2f2c279566d7c866f6b2ba2e2a4ac76525d0
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73541e35f8e1b5c7ccdae9c3bae6231436cbe77551e8b7c50a3e8570b2cc594f
+oid sha256:48dc6a3d1260b380af9fb983548719bea835016acecf353498ef64e391511f8d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4875050941850c29e209a22482a2d40d85bf3c892c93b470a6026746b923768
+oid sha256:670d1f42a5208754299a143442aabd9ef26bab47ca439decac785493fcbeb1af
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e77af726f7190a11984e3f56f02da699fc3c1ed55ce4a5bc826df29915654335
+oid sha256:ede8d00b932613c6ec594b88a7b6daf8017872cc430afa99e7bc9c89b091dc32
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3135adaf31d967e62694ac1f67644ebc208d5a3e90139f7bb7e63ac1119f6d34
+oid sha256:cae2ad1de449754f6a00457fe66f0396cb86437a717906a1f641c83dcfb76f3e
 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": 10.371356010437012,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.031409501374165684,
+  "best_metric": 10.367506980895996,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06281900274833137,
   "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": 427.697,
       "eval_steps_per_second": 111.201,
       "step": 25
+    },
+    {
+      "epoch": 0.032665881429132314,
+      "grad_norm": 0.09042679518461227,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3756,
+      "step": 26
+    },
+    {
+      "epoch": 0.03392226148409894,
+      "grad_norm": 0.08610530197620392,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.373,
+      "step": 27
+    },
+    {
+      "epoch": 0.03517864153906557,
+      "grad_norm": 0.08801662921905518,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3724,
+      "step": 28
+    },
+    {
+      "epoch": 0.036435021594032196,
+      "grad_norm": 0.09608513861894608,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3699,
+      "step": 29
+    },
+    {
+      "epoch": 0.03769140164899882,
+      "grad_norm": 0.09346794337034225,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3698,
+      "step": 30
+    },
+    {
+      "epoch": 0.03894778170396545,
+      "grad_norm": 0.1273888796567917,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3702,
+      "step": 31
+    },
+    {
+      "epoch": 0.04020416175893208,
+      "grad_norm": 0.11089735478162766,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3707,
+      "step": 32
+    },
+    {
+      "epoch": 0.0414605418138987,
+      "grad_norm": 0.13149495422840118,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3703,
+      "step": 33
+    },
+    {
+      "epoch": 0.04271692186886533,
+      "grad_norm": 0.1491594761610031,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3697,
+      "step": 34
+    },
+    {
+      "epoch": 0.04397330192383196,
+      "grad_norm": 0.17393919825553894,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3708,
+      "step": 35
+    },
+    {
+      "epoch": 0.045229681978798585,
+      "grad_norm": 0.18291912972927094,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3714,
+      "step": 36
+    },
+    {
+      "epoch": 0.046486062033765214,
+      "grad_norm": 0.18662983179092407,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3698,
+      "step": 37
+    },
+    {
+      "epoch": 0.047742442088731844,
+      "grad_norm": 0.11758657544851303,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3715,
+      "step": 38
+    },
+    {
+      "epoch": 0.04899882214369847,
+      "grad_norm": 0.08886243402957916,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3718,
+      "step": 39
+    },
+    {
+      "epoch": 0.0502552021986651,
+      "grad_norm": 0.09938018769025803,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3703,
+      "step": 40
+    },
+    {
+      "epoch": 0.05151158225363173,
+      "grad_norm": 0.12390407174825668,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3713,
+      "step": 41
+    },
+    {
+      "epoch": 0.05276796230859835,
+      "grad_norm": 0.09068513661623001,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3667,
+      "step": 42
+    },
+    {
+      "epoch": 0.05402434236356498,
+      "grad_norm": 0.1155741810798645,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3689,
+      "step": 43
+    },
+    {
+      "epoch": 0.0552807224185316,
+      "grad_norm": 0.11526913195848465,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3725,
+      "step": 44
+    },
+    {
+      "epoch": 0.05653710247349823,
+      "grad_norm": 0.12869693338871002,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3692,
+      "step": 45
+    },
+    {
+      "epoch": 0.05779348252846486,
+      "grad_norm": 0.14980974793434143,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3697,
+      "step": 46
+    },
+    {
+      "epoch": 0.059049862583431485,
+      "grad_norm": 0.155381977558136,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3677,
+      "step": 47
+    },
+    {
+      "epoch": 0.060306242638398115,
+      "grad_norm": 0.21512186527252197,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3681,
+      "step": 48
+    },
+    {
+      "epoch": 0.061562622693364745,
+      "grad_norm": 0.23681750893592834,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.37,
+      "step": 49
+    },
+    {
+      "epoch": 0.06281900274833137,
+      "grad_norm": 0.24694152176380157,
+      "learning_rate": 1e-05,
+      "loss": 10.362,
+      "step": 50
+    },
+    {
+      "epoch": 0.06281900274833137,
+      "eval_loss": 10.367506980895996,
+      "eval_runtime": 0.1,
+      "eval_samples_per_second": 500.099,
+      "eval_steps_per_second": 130.026,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null