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:a25e3891d3f1d8c2858caeca0ab3008de6bea93d9edf07f6b98256e732d19767
+oid sha256:3156371f18912efe9870f8d597cf8bf2f37de2339a0d2f009df115d47ceedbc1
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b77cf92f935a71da0afbb805140b29205c9310e39675261d2e1b0a3d82bf06
+oid sha256:530d376e951a9d7026ba0125c54fcd3d684dabfc39e53e82b04a9a031d4d83ef
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19a5387608b3f44ba27260c03bfd18565d894873a92ba1d7da2864d43f572e36
+oid sha256:5c15e094d65a2a04ddf2ebcfc5ab4b15c91e3bbc100ae81a10baa00a1c5a4f71
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f51860b90e5bb277396d1dd182bc1c33f3e2932e797311f860e2584a2205a1f1
+oid sha256:28db7b94298edfbbdbc29b237ba07b0fdc1211300bc39385315854d1fbbaee49
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a937245e3b5cbcd687e1cb8578cfd316893887810f68a852d4b78571836d818
+oid sha256:587da782b6c5f0e8b2fa4d8896a929f45313deb0b7da2c24c2393a205fef0714
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c4c9ec7bc64b05fbe0e5ed9b7055a306b7e172cf8370cbe5995c76966c12d44
+oid sha256:0c43dbd13f8f0564355267a63b86c95dffdc4512d80a63ba57b940fa2854a463
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.2550545930862427,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.15168752370117558,
+  "best_metric": 0.22515492141246796,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.30337504740235116,
   "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": 12.275,
       "eval_steps_per_second": 3.192,
       "step": 25
+    },
+    {
+      "epoch": 0.1577550246492226,
+      "grad_norm": 0.9358745217323303,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 0.2008,
+      "step": 26
+    },
+    {
+      "epoch": 0.16382252559726962,
+      "grad_norm": 0.5705291032791138,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 0.3452,
+      "step": 27
+    },
+    {
+      "epoch": 0.16989002654531665,
+      "grad_norm": 0.5917467474937439,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 0.2588,
+      "step": 28
+    },
+    {
+      "epoch": 0.17595752749336366,
+      "grad_norm": 0.6592450141906738,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 0.2964,
+      "step": 29
+    },
+    {
+      "epoch": 0.1820250284414107,
+      "grad_norm": 0.5917816758155823,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 0.3058,
+      "step": 30
+    },
+    {
+      "epoch": 0.18809252938945772,
+      "grad_norm": 0.5254703164100647,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 0.3066,
+      "step": 31
+    },
+    {
+      "epoch": 0.19416003033750473,
+      "grad_norm": 0.4927206337451935,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 0.3338,
+      "step": 32
+    },
+    {
+      "epoch": 0.20022753128555176,
+      "grad_norm": 0.617469310760498,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 0.3476,
+      "step": 33
+    },
+    {
+      "epoch": 0.2062950322335988,
+      "grad_norm": 0.5512767434120178,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 0.2595,
+      "step": 34
+    },
+    {
+      "epoch": 0.2123625331816458,
+      "grad_norm": 0.6990464925765991,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 0.288,
+      "step": 35
+    },
+    {
+      "epoch": 0.21843003412969283,
+      "grad_norm": 1.4301836490631104,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 0.4128,
+      "step": 36
+    },
+    {
+      "epoch": 0.22449753507773987,
+      "grad_norm": 1.702950119972229,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 0.4041,
+      "step": 37
+    },
+    {
+      "epoch": 0.23056503602578687,
+      "grad_norm": 1.1743119955062866,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 0.2015,
+      "step": 38
+    },
+    {
+      "epoch": 0.2366325369738339,
+      "grad_norm": 0.9276676774024963,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 0.3364,
+      "step": 39
+    },
+    {
+      "epoch": 0.2427000379218809,
+      "grad_norm": 0.53074711561203,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 0.2547,
+      "step": 40
+    },
+    {
+      "epoch": 0.24876753886992795,
+      "grad_norm": 0.4709409773349762,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 0.2583,
+      "step": 41
+    },
+    {
+      "epoch": 0.25483503981797495,
+      "grad_norm": 0.5634525418281555,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 0.3323,
+      "step": 42
+    },
+    {
+      "epoch": 0.260902540766022,
+      "grad_norm": 0.6031685471534729,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 0.2583,
+      "step": 43
+    },
+    {
+      "epoch": 0.266970041714069,
+      "grad_norm": 0.6985509395599365,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 0.3017,
+      "step": 44
+    },
+    {
+      "epoch": 0.27303754266211605,
+      "grad_norm": 0.5389325022697449,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 0.2776,
+      "step": 45
+    },
+    {
+      "epoch": 0.2791050436101631,
+      "grad_norm": 0.4434327185153961,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 0.2907,
+      "step": 46
+    },
+    {
+      "epoch": 0.28517254455821006,
+      "grad_norm": 0.47085919976234436,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 0.2155,
+      "step": 47
+    },
+    {
+      "epoch": 0.2912400455062571,
+      "grad_norm": 0.9153717756271362,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 0.3143,
+      "step": 48
+    },
+    {
+      "epoch": 0.29730754645430413,
+      "grad_norm": 2.431823253631592,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5086,
+      "step": 49
+    },
+    {
+      "epoch": 0.30337504740235116,
+      "grad_norm": 0.8440378904342651,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 0.3082,
+      "step": 50
+    },
+    {
+      "epoch": 0.30337504740235116,
+      "eval_loss": 0.22515492141246796,
+      "eval_runtime": 4.0292,
+      "eval_samples_per_second": 12.409,
+      "eval_steps_per_second": 3.226,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null