Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64022d3bfa04f227eb08e743f21dfd8b32bd51c334f80ace0fdb3b576081c74a
+oid sha256:45b0050213bb85c5407866035534d4eb9c1fe57a5ae0e7b73f6b7494e0d81ecf
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be1c12537e6678c1f1b260871392f0d65d7046c2b655f10b29b86b9a2211c137
+oid sha256:394a77afe54ee63806cffea0fbc63fe915bd813b39c218b4b3692dc988973220
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381f3392b1f06c4ce374ec023dc8818e83c8cef672afd1e54b3a1c5f749f4e59
+oid sha256:fe1621d6c271412bae68a0eb84d7a35437841f80402d3f1f868ba44c05bcc41f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed6a695e818cc0a7cd1918163e2e483efd1a2ac2bc9fbb2f71b6352c2af0b21
+oid sha256:47c572929b37d598d5524c3fc24b1d8a1cfe3d048c7612de921d6f8374edff9d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acb8857e218b04440dd6e7bfeaf10914ca4e9149d7da175d7f36fc65692fc3d9
+oid sha256:bd7d5ec911b47675100a38d7fd767fb6f2f843b97212c7bca6afbc61725eb1e0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e8df6fcd30f263caa62863c6cf85978a20c44ed73d33bff8e0971512b202452
+oid sha256:e098fb865602bc5d9c49ef08e0b579674b199b3ade815eb1d6a7d5b3e441fa01
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0478220dc1c61b501af7edfe8fa4a46b7ebe1a2bbd0ae4d7514712a0c8b72900
+oid sha256:3192059420211edc26748a07e2699e00ee3be65f92a2cf84ef56d22611d9eb5c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.07570720463991165,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4993757802746567,
+  "best_metric": 0.05686701834201813,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.9987515605493134,
   "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": 98.895,
       "eval_steps_per_second": 6.309,
       "step": 25
+    },
+    {
+      "epoch": 0.519350811485643,
+      "grad_norm": 1.0404666662216187,
+      "learning_rate": 8.842005554284296e-05,
+      "loss": 0.1171,
+      "step": 26
+    },
+    {
+      "epoch": 0.5393258426966292,
+      "grad_norm": 0.6350396871566772,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 0.0752,
+      "step": 27
+    },
+    {
+      "epoch": 0.5593008739076155,
+      "grad_norm": 0.5021554827690125,
+      "learning_rate": 8.622126023955446e-05,
+      "loss": 0.0646,
+      "step": 28
+    },
+    {
+      "epoch": 0.5792759051186017,
+      "grad_norm": 0.7377936244010925,
+      "learning_rate": 8.506183921362443e-05,
+      "loss": 0.0745,
+      "step": 29
+    },
+    {
+      "epoch": 0.599250936329588,
+      "grad_norm": 0.5337192416191101,
+      "learning_rate": 8.386407858128706e-05,
+      "loss": 0.0594,
+      "step": 30
+    },
+    {
+      "epoch": 0.6192259675405742,
+      "grad_norm": 0.5033006072044373,
+      "learning_rate": 8.262928807620843e-05,
+      "loss": 0.0501,
+      "step": 31
+    },
+    {
+      "epoch": 0.6392009987515606,
+      "grad_norm": 0.4639797806739807,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 0.0591,
+      "step": 32
+    },
+    {
+      "epoch": 0.6591760299625468,
+      "grad_norm": 0.47012022137641907,
+      "learning_rate": 8.005405736415126e-05,
+      "loss": 0.0583,
+      "step": 33
+    },
+    {
+      "epoch": 0.6791510611735331,
+      "grad_norm": 0.40740257501602173,
+      "learning_rate": 7.871643313414718e-05,
+      "loss": 0.0393,
+      "step": 34
+    },
+    {
+      "epoch": 0.6991260923845194,
+      "grad_norm": 0.4334827959537506,
+      "learning_rate": 7.734740790612136e-05,
+      "loss": 0.0694,
+      "step": 35
+    },
+    {
+      "epoch": 0.7191011235955056,
+      "grad_norm": 0.34927257895469666,
+      "learning_rate": 7.594847868906076e-05,
+      "loss": 0.0407,
+      "step": 36
+    },
+    {
+      "epoch": 0.7390761548064919,
+      "grad_norm": 0.3759843707084656,
+      "learning_rate": 7.452117519152542e-05,
+      "loss": 0.0333,
+      "step": 37
+    },
+    {
+      "epoch": 0.7590511860174781,
+      "grad_norm": 0.3167741596698761,
+      "learning_rate": 7.30670581489344e-05,
+      "loss": 0.0618,
+      "step": 38
+    },
+    {
+      "epoch": 0.7790262172284644,
+      "grad_norm": 1.1636722087860107,
+      "learning_rate": 7.158771761692464e-05,
+      "loss": 0.1346,
+      "step": 39
+    },
+    {
+      "epoch": 0.7990012484394506,
+      "grad_norm": 0.699979305267334,
+      "learning_rate": 7.008477123264848e-05,
+      "loss": 0.0876,
+      "step": 40
+    },
+    {
+      "epoch": 0.818976279650437,
+      "grad_norm": 0.5671290755271912,
+      "learning_rate": 6.855986244591104e-05,
+      "loss": 0.0756,
+      "step": 41
+    },
+    {
+      "epoch": 0.8389513108614233,
+      "grad_norm": 0.3836475908756256,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 0.0673,
+      "step": 42
+    },
+    {
+      "epoch": 0.8589263420724095,
+      "grad_norm": 0.3973909020423889,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0461,
+      "step": 43
+    },
+    {
+      "epoch": 0.8789013732833958,
+      "grad_norm": 0.41587159037590027,
+      "learning_rate": 6.387014543809223e-05,
+      "loss": 0.0576,
+      "step": 44
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.47783681750297546,
+      "learning_rate": 6.227427435703997e-05,
+      "loss": 0.0507,
+      "step": 45
+    },
+    {
+      "epoch": 0.9188514357053683,
+      "grad_norm": 0.5148672461509705,
+      "learning_rate": 6.066498153718735e-05,
+      "loss": 0.0676,
+      "step": 46
+    },
+    {
+      "epoch": 0.9388264669163545,
+      "grad_norm": 0.5991238355636597,
+      "learning_rate": 5.90440267166055e-05,
+      "loss": 0.0565,
+      "step": 47
+    },
+    {
+      "epoch": 0.9588014981273408,
+      "grad_norm": 0.5729100704193115,
+      "learning_rate": 5.74131823855921e-05,
+      "loss": 0.0693,
+      "step": 48
+    },
+    {
+      "epoch": 0.978776529338327,
+      "grad_norm": 0.46636906266212463,
+      "learning_rate": 5.577423184847932e-05,
+      "loss": 0.0614,
+      "step": 49
+    },
+    {
+      "epoch": 0.9987515605493134,
+      "grad_norm": 0.3745470643043518,
+      "learning_rate": 5.4128967273616625e-05,
+      "loss": 0.0263,
+      "step": 50
+    },
+    {
+      "epoch": 0.9987515605493134,
+      "eval_loss": 0.05686701834201813,
+      "eval_runtime": 6.7983,
+      "eval_samples_per_second": 99.142,
+      "eval_steps_per_second": 6.325,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.059536353886208e+17,
+  "total_flos": 2.119072707772416e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null