Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:942705692987fb60072027d9a7e9abbcc6f370ee01585453b3422eb7a6cd97e0
+oid sha256:f22f494363f5c78be0a91a439b8cf5eced631cfbcd7ea5aeeb81d13f9bd97f92
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:403022c6bc827359951f42ea674ee8e85de001a2cbd85b93b03b980a02deb379
+oid sha256:f611024d2671c7eab5ca8035be37120c59713b491d82d2d05ac257b8042fce50
 size 341314196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa226251fb6d50e8871e4fc6eed64ca88c7efc0734dfcf74c6ba40d94dd558b
+oid sha256:becef6bf5a147600328cdbd634e390437e4c717589513d6c9c390e8b5dae63e8
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66889aadb1bf1079e2720881d32fd0156a7bb5507961c3a31e86992d60eb6c59
+oid sha256:d24ced83665119765999131ce9b8a1fc1891a3f4ab05d5f9e4379f8dd5a57618
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea8f1b9c887caad20e3c43676d54a043a13cc6782a958f4e5a26095d5997193e
+oid sha256:dccca4f46373bb3ba57dbd75e7849e9c4c8da06fa0683aa23843806041b94a57
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a1edde357b14642587f5835640e8b76743e2590c06f9dc0f7617422e2bb951a
+oid sha256:b317bba3757b4356e895d62dc56fd854ddf084f6b334ce39cfabe913ac4cd520
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e498ff44401418a43b3e145e3e50d0c7906d43ed2787c6c39ae6d009e5322ec8
+oid sha256:5bf00b93e7bc95e091a0d1a8be34054411735ec87877c71f631c693881e16190
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a8cf7807336a89f02f64d1818f4496108462f773c00109cd93ec6ca23545fa
+oid sha256:63e81b68c9b74f64c66af4ec893bfa9c8d36c346904c542c8739be0b5f606e50
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d516aeba334708b47a0f32020281379628ac142ef6c1a3ffca015bebf18c783b
+oid sha256:16c3cc8f43ba77d2507e05e7399a518fef5e838ee8ef76ce6840fef01723a792
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe578290be6ae6decf4a9c7e7162802bdd6a6bea1d517b4ad06fbc5d9daa29a
+oid sha256:f91f078c1abf7eb3ddea70d00a60f4afe9e150309ded192168a1ea240d1abd52
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b7e7d044a338e6b420016be2e48e692869df520a6f768a0f5ba8de63e9bb378
+oid sha256:f6b2f615f21faa4fde4442b48613d92f84c55cd5ef4fb4d04d8e3f819305ce14
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.522826075553894,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.5763688760806917,
+  "best_metric": 0.3946053087711334,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 1.1556195965417868,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,364 @@
       "eval_samples_per_second": 68.963,
       "eval_steps_per_second": 2.188,
       "step": 50
+    },
+    {
+      "epoch": 0.5878962536023055,
+      "grad_norm": 3.06416392326355,
+      "learning_rate": 7.920526315789474e-05,
+      "loss": 1.8642,
+      "step": 51
+    },
+    {
+      "epoch": 0.5994236311239193,
+      "grad_norm": 1.5283445119857788,
+      "learning_rate": 7.867368421052631e-05,
+      "loss": 1.8985,
+      "step": 52
+    },
+    {
+      "epoch": 0.6109510086455331,
+      "grad_norm": 1.7631272077560425,
+      "learning_rate": 7.814210526315789e-05,
+      "loss": 1.7763,
+      "step": 53
+    },
+    {
+      "epoch": 0.622478386167147,
+      "grad_norm": 1.3397003412246704,
+      "learning_rate": 7.761052631578946e-05,
+      "loss": 1.9477,
+      "step": 54
+    },
+    {
+      "epoch": 0.6340057636887608,
+      "grad_norm": 1.6053922176361084,
+      "learning_rate": 7.707894736842105e-05,
+      "loss": 2.18,
+      "step": 55
+    },
+    {
+      "epoch": 0.6455331412103746,
+      "grad_norm": 2.7249755859375,
+      "learning_rate": 7.654736842105264e-05,
+      "loss": 2.3534,
+      "step": 56
+    },
+    {
+      "epoch": 0.6570605187319885,
+      "grad_norm": 2.97141432762146,
+      "learning_rate": 7.601578947368422e-05,
+      "loss": 2.4034,
+      "step": 57
+    },
+    {
+      "epoch": 0.6685878962536023,
+      "grad_norm": 1.9900548458099365,
+      "learning_rate": 7.548421052631579e-05,
+      "loss": 1.8997,
+      "step": 58
+    },
+    {
+      "epoch": 0.6801152737752162,
+      "grad_norm": 1.2884211540222168,
+      "learning_rate": 7.495263157894737e-05,
+      "loss": 1.7887,
+      "step": 59
+    },
+    {
+      "epoch": 0.69164265129683,
+      "grad_norm": 1.2060939073562622,
+      "learning_rate": 7.442105263157894e-05,
+      "loss": 1.7919,
+      "step": 60
+    },
+    {
+      "epoch": 0.7031700288184438,
+      "grad_norm": 1.6086294651031494,
+      "learning_rate": 7.388947368421053e-05,
+      "loss": 1.947,
+      "step": 61
+    },
+    {
+      "epoch": 0.7146974063400576,
+      "grad_norm": 2.0594823360443115,
+      "learning_rate": 7.335789473684211e-05,
+      "loss": 2.2118,
+      "step": 62
+    },
+    {
+      "epoch": 0.7262247838616714,
+      "grad_norm": 3.474539041519165,
+      "learning_rate": 7.282631578947368e-05,
+      "loss": 2.4448,
+      "step": 63
+    },
+    {
+      "epoch": 0.7377521613832853,
+      "grad_norm": 2.4555892944335938,
+      "learning_rate": 7.229473684210527e-05,
+      "loss": 1.6301,
+      "step": 64
+    },
+    {
+      "epoch": 0.7492795389048992,
+      "grad_norm": 1.3167078495025635,
+      "learning_rate": 7.176315789473685e-05,
+      "loss": 1.8001,
+      "step": 65
+    },
+    {
+      "epoch": 0.760806916426513,
+      "grad_norm": 1.3120259046554565,
+      "learning_rate": 7.123157894736842e-05,
+      "loss": 1.6406,
+      "step": 66
+    },
+    {
+      "epoch": 0.7723342939481268,
+      "grad_norm": 1.2128572463989258,
+      "learning_rate": 7.07e-05,
+      "loss": 1.9768,
+      "step": 67
+    },
+    {
+      "epoch": 0.7838616714697406,
+      "grad_norm": 1.7433110475540161,
+      "learning_rate": 7.016842105263159e-05,
+      "loss": 2.0889,
+      "step": 68
+    },
+    {
+      "epoch": 0.7953890489913544,
+      "grad_norm": 2.9662296772003174,
+      "learning_rate": 6.963684210526316e-05,
+      "loss": 2.4274,
+      "step": 69
+    },
+    {
+      "epoch": 0.8069164265129684,
+      "grad_norm": 1.7265340089797974,
+      "learning_rate": 6.910526315789474e-05,
+      "loss": 1.6667,
+      "step": 70
+    },
+    {
+      "epoch": 0.8184438040345822,
+      "grad_norm": 1.2966630458831787,
+      "learning_rate": 6.857368421052631e-05,
+      "loss": 1.5911,
+      "step": 71
+    },
+    {
+      "epoch": 0.829971181556196,
+      "grad_norm": 1.1538748741149902,
+      "learning_rate": 6.80421052631579e-05,
+      "loss": 1.623,
+      "step": 72
+    },
+    {
+      "epoch": 0.8414985590778098,
+      "grad_norm": 1.2530492544174194,
+      "learning_rate": 6.751052631578948e-05,
+      "loss": 1.6128,
+      "step": 73
+    },
+    {
+      "epoch": 0.8530259365994236,
+      "grad_norm": 1.6641517877578735,
+      "learning_rate": 6.697894736842105e-05,
+      "loss": 2.1622,
+      "step": 74
+    },
+    {
+      "epoch": 0.8645533141210374,
+      "grad_norm": 2.932410955429077,
+      "learning_rate": 6.644736842105264e-05,
+      "loss": 2.34,
+      "step": 75
+    },
+    {
+      "epoch": 0.8760806916426513,
+      "grad_norm": 1.564931869506836,
+      "learning_rate": 6.591578947368422e-05,
+      "loss": 1.5343,
+      "step": 76
+    },
+    {
+      "epoch": 0.8876080691642652,
+      "grad_norm": 1.22451913356781,
+      "learning_rate": 6.538421052631579e-05,
+      "loss": 1.5855,
+      "step": 77
+    },
+    {
+      "epoch": 0.899135446685879,
+      "grad_norm": 1.0155211687088013,
+      "learning_rate": 6.485263157894737e-05,
+      "loss": 1.4917,
+      "step": 78
+    },
+    {
+      "epoch": 0.9106628242074928,
+      "grad_norm": 1.1343241930007935,
+      "learning_rate": 6.432105263157894e-05,
+      "loss": 1.4143,
+      "step": 79
+    },
+    {
+      "epoch": 0.9221902017291066,
+      "grad_norm": 1.3770869970321655,
+      "learning_rate": 6.378947368421053e-05,
+      "loss": 1.9376,
+      "step": 80
+    },
+    {
+      "epoch": 0.9337175792507204,
+      "grad_norm": 2.184307813644409,
+      "learning_rate": 6.32578947368421e-05,
+      "loss": 2.1743,
+      "step": 81
+    },
+    {
+      "epoch": 0.9452449567723343,
+      "grad_norm": 2.2855091094970703,
+      "learning_rate": 6.27263157894737e-05,
+      "loss": 2.0407,
+      "step": 82
+    },
+    {
+      "epoch": 0.9567723342939481,
+      "grad_norm": 1.2995476722717285,
+      "learning_rate": 6.219473684210527e-05,
+      "loss": 1.5107,
+      "step": 83
+    },
+    {
+      "epoch": 0.968299711815562,
+      "grad_norm": 1.1009643077850342,
+      "learning_rate": 6.166315789473685e-05,
+      "loss": 1.4408,
+      "step": 84
+    },
+    {
+      "epoch": 0.9798270893371758,
+      "grad_norm": 1.1911717653274536,
+      "learning_rate": 6.113157894736842e-05,
+      "loss": 1.7328,
+      "step": 85
+    },
+    {
+      "epoch": 0.9913544668587896,
+      "grad_norm": 1.749642014503479,
+      "learning_rate": 6.0599999999999996e-05,
+      "loss": 1.8929,
+      "step": 86
+    },
+    {
+      "epoch": 1.005763688760807,
+      "grad_norm": 2.45554256439209,
+      "learning_rate": 6.006842105263158e-05,
+      "loss": 1.955,
+      "step": 87
+    },
+    {
+      "epoch": 1.0172910662824208,
+      "grad_norm": 1.4383282661437988,
+      "learning_rate": 5.953684210526315e-05,
+      "loss": 1.2303,
+      "step": 88
+    },
+    {
+      "epoch": 1.0288184438040346,
+      "grad_norm": 1.0873348712921143,
+      "learning_rate": 5.900526315789474e-05,
+      "loss": 1.2904,
+      "step": 89
+    },
+    {
+      "epoch": 1.0403458213256485,
+      "grad_norm": 1.093670129776001,
+      "learning_rate": 5.847368421052632e-05,
+      "loss": 1.342,
+      "step": 90
+    },
+    {
+      "epoch": 1.0518731988472623,
+      "grad_norm": 1.1975847482681274,
+      "learning_rate": 5.79421052631579e-05,
+      "loss": 1.5195,
+      "step": 91
+    },
+    {
+      "epoch": 1.063400576368876,
+      "grad_norm": 1.6481062173843384,
+      "learning_rate": 5.7410526315789475e-05,
+      "loss": 1.7187,
+      "step": 92
+    },
+    {
+      "epoch": 1.07492795389049,
+      "grad_norm": 2.8624935150146484,
+      "learning_rate": 5.687894736842105e-05,
+      "loss": 1.8387,
+      "step": 93
+    },
+    {
+      "epoch": 1.0864553314121037,
+      "grad_norm": 1.3205828666687012,
+      "learning_rate": 5.6347368421052625e-05,
+      "loss": 1.3021,
+      "step": 94
+    },
+    {
+      "epoch": 1.0979827089337175,
+      "grad_norm": 1.1411229372024536,
+      "learning_rate": 5.5815789473684214e-05,
+      "loss": 1.3437,
+      "step": 95
+    },
+    {
+      "epoch": 1.1095100864553313,
+      "grad_norm": 1.0338324308395386,
+      "learning_rate": 5.5284210526315796e-05,
+      "loss": 1.3011,
+      "step": 96
+    },
+    {
+      "epoch": 1.1210374639769451,
+      "grad_norm": 1.0531305074691772,
+      "learning_rate": 5.475263157894737e-05,
+      "loss": 1.3966,
+      "step": 97
+    },
+    {
+      "epoch": 1.1325648414985592,
+      "grad_norm": 1.6607333421707153,
+      "learning_rate": 5.422105263157895e-05,
+      "loss": 1.7677,
+      "step": 98
+    },
+    {
+      "epoch": 1.144092219020173,
+      "grad_norm": 2.978102684020996,
+      "learning_rate": 5.368947368421053e-05,
+      "loss": 2.0096,
+      "step": 99
+    },
+    {
+      "epoch": 1.1556195965417868,
+      "grad_norm": 1.1680306196212769,
+      "learning_rate": 5.3157894736842104e-05,
+      "loss": 1.2335,
+      "step": 100
+    },
+    {
+      "epoch": 1.1556195965417868,
+      "eval_loss": 0.3946053087711334,
+      "eval_runtime": 17.2978,
+      "eval_samples_per_second": 67.407,
+      "eval_steps_per_second": 2.139,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -401,7 +759,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.843577643761664e+17,
+  "total_flos": 1.7708620277790802e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null