Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754bd3b1c25cd89aed05f39473149f0c8170d74fdaadf44d59ca7b324caa521f
+oid sha256:a559ce7c883fef8da7cd435798f9c7069febf902f05e3c31dd418db0386fbaef
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53321bdc050953e7071a088fc5ab3637193860e8dead123b6ff04e05d087c444
+oid sha256:0c26d2fa6e47921dc1f8eb0ae74f7c0c2552221755c67414f671e13a0bba2e4d
 size 341314196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e78e12062bb532132413dc2881e7c25fbf89a4bcec49c2431ba3c3d4d63903aa
+oid sha256:94f67d8950e212ff8690dcf3c5fcba9e6f9007b37c74cae50ce1ed6f89e9426d
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c71f240e208ecbc77d6d7672d3b394f104d15003a4ced2dd2665120af5cacb
+oid sha256:1ff205c15af7ea8a8ba932c7ad281ac2fc87bb9fab7c87bf0a43c1954f83be02
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e88e972059e9582e885e0b2f5f98389fa337f6b23b4708f209b0f54ee30ae28
+oid sha256:a28285f7ff3b313c4272837b3e5144f0b099a09ae7c835c10a4c617d92f10fab
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de76065134be6d693b35d12bc16f37441d2efe2333170ab9ee2327bc217834a2
+oid sha256:73f98cb18f823936b20e83285df50b2380f275dd327c0bf367b3de4ac63b1ff1
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41b5ac05bc352d6d3b4f91d4b96b3f08f55970044eed9262ccd24280d45f55a9
+oid sha256:89425a5370411926926f00a7f319e3a6fa66a470b1a4824c59f71274bad0559f
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56267cc3326b2a94e7b7d8cfb95af18e46c39067dae125f3b4b5972b9987d302
+oid sha256:6a0f6f1afefb5748ab7541c09d78f81d06551738648d3eb1c04db4146f0f4557
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1c4120bdbd775ade772afbcb11dfb22404753e61fb5f8b02eb9ad6bad0b5df
+oid sha256:8129f0cd3b0552c45acb3a5633c1cf289db547a9c2b8873854f2eb6c45c27b8b
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd0069d979e4bd5640fd8a33278712a48cd6e15794fb123631ee40e550d0d78d
+oid sha256:6a6e430b04579656febc8cbf696420470fffb1d38416de40aa430c4b8b861e38
 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": 2.116605520248413,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.4608294930875576,
+  "best_metric": 2.094890832901001,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.9216589861751152,
   "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": 114.671,
       "eval_steps_per_second": 3.613,
       "step": 50
+    },
+    {
+      "epoch": 0.4700460829493088,
+      "grad_norm": 0.2561372220516205,
+      "learning_rate": 7.920526315789474e-05,
+      "loss": 1.9023,
+      "step": 51
+    },
+    {
+      "epoch": 0.4792626728110599,
+      "grad_norm": 0.34022021293640137,
+      "learning_rate": 7.867368421052631e-05,
+      "loss": 2.0268,
+      "step": 52
+    },
+    {
+      "epoch": 0.48847926267281105,
+      "grad_norm": 0.36793768405914307,
+      "learning_rate": 7.814210526315789e-05,
+      "loss": 2.05,
+      "step": 53
+    },
+    {
+      "epoch": 0.4976958525345622,
+      "grad_norm": 0.3726247251033783,
+      "learning_rate": 7.761052631578946e-05,
+      "loss": 2.1283,
+      "step": 54
+    },
+    {
+      "epoch": 0.5069124423963134,
+      "grad_norm": 0.3833205997943878,
+      "learning_rate": 7.707894736842105e-05,
+      "loss": 2.1589,
+      "step": 55
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 0.5375770926475525,
+      "learning_rate": 7.654736842105264e-05,
+      "loss": 2.2673,
+      "step": 56
+    },
+    {
+      "epoch": 0.5253456221198156,
+      "grad_norm": 0.2441074550151825,
+      "learning_rate": 7.601578947368422e-05,
+      "loss": 1.9027,
+      "step": 57
+    },
+    {
+      "epoch": 0.5345622119815668,
+      "grad_norm": 0.2560899257659912,
+      "learning_rate": 7.548421052631579e-05,
+      "loss": 2.0017,
+      "step": 58
+    },
+    {
+      "epoch": 0.543778801843318,
+      "grad_norm": 0.29515939950942993,
+      "learning_rate": 7.495263157894737e-05,
+      "loss": 2.1535,
+      "step": 59
+    },
+    {
+      "epoch": 0.5529953917050692,
+      "grad_norm": 0.33528003096580505,
+      "learning_rate": 7.442105263157894e-05,
+      "loss": 2.1311,
+      "step": 60
+    },
+    {
+      "epoch": 0.5622119815668203,
+      "grad_norm": 0.36277294158935547,
+      "learning_rate": 7.388947368421053e-05,
+      "loss": 2.1752,
+      "step": 61
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.45456284284591675,
+      "learning_rate": 7.335789473684211e-05,
+      "loss": 2.2492,
+      "step": 62
+    },
+    {
+      "epoch": 0.5806451612903226,
+      "grad_norm": 0.2679094970226288,
+      "learning_rate": 7.282631578947368e-05,
+      "loss": 1.8828,
+      "step": 63
+    },
+    {
+      "epoch": 0.5898617511520737,
+      "grad_norm": 0.2793255150318146,
+      "learning_rate": 7.229473684210527e-05,
+      "loss": 2.0206,
+      "step": 64
+    },
+    {
+      "epoch": 0.5990783410138248,
+      "grad_norm": 0.3043336868286133,
+      "learning_rate": 7.176315789473685e-05,
+      "loss": 2.0663,
+      "step": 65
+    },
+    {
+      "epoch": 0.6082949308755761,
+      "grad_norm": 0.33438342809677124,
+      "learning_rate": 7.123157894736842e-05,
+      "loss": 2.0858,
+      "step": 66
+    },
+    {
+      "epoch": 0.6175115207373272,
+      "grad_norm": 0.34761834144592285,
+      "learning_rate": 7.07e-05,
+      "loss": 2.1531,
+      "step": 67
+    },
+    {
+      "epoch": 0.6267281105990783,
+      "grad_norm": 0.42960384488105774,
+      "learning_rate": 7.016842105263159e-05,
+      "loss": 2.2121,
+      "step": 68
+    },
+    {
+      "epoch": 0.6359447004608295,
+      "grad_norm": 0.3402632772922516,
+      "learning_rate": 6.963684210526316e-05,
+      "loss": 1.9788,
+      "step": 69
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.24986091256141663,
+      "learning_rate": 6.910526315789474e-05,
+      "loss": 1.9569,
+      "step": 70
+    },
+    {
+      "epoch": 0.6543778801843319,
+      "grad_norm": 0.2692315876483917,
+      "learning_rate": 6.857368421052631e-05,
+      "loss": 2.0614,
+      "step": 71
+    },
+    {
+      "epoch": 0.663594470046083,
+      "grad_norm": 0.30594998598098755,
+      "learning_rate": 6.80421052631579e-05,
+      "loss": 2.1189,
+      "step": 72
+    },
+    {
+      "epoch": 0.6728110599078341,
+      "grad_norm": 0.3443293273448944,
+      "learning_rate": 6.751052631578948e-05,
+      "loss": 2.1243,
+      "step": 73
+    },
+    {
+      "epoch": 0.6820276497695853,
+      "grad_norm": 0.4179190993309021,
+      "learning_rate": 6.697894736842105e-05,
+      "loss": 2.142,
+      "step": 74
+    },
+    {
+      "epoch": 0.6912442396313364,
+      "grad_norm": 0.5722486972808838,
+      "learning_rate": 6.644736842105264e-05,
+      "loss": 2.2698,
+      "step": 75
+    },
+    {
+      "epoch": 0.7004608294930875,
+      "grad_norm": 0.303549587726593,
+      "learning_rate": 6.591578947368422e-05,
+      "loss": 1.9124,
+      "step": 76
+    },
+    {
+      "epoch": 0.7096774193548387,
+      "grad_norm": 0.35244593024253845,
+      "learning_rate": 6.538421052631579e-05,
+      "loss": 2.065,
+      "step": 77
+    },
+    {
+      "epoch": 0.7188940092165899,
+      "grad_norm": 0.3539853096008301,
+      "learning_rate": 6.485263157894737e-05,
+      "loss": 2.1142,
+      "step": 78
+    },
+    {
+      "epoch": 0.728110599078341,
+      "grad_norm": 0.3328129053115845,
+      "learning_rate": 6.432105263157894e-05,
+      "loss": 2.0702,
+      "step": 79
+    },
+    {
+      "epoch": 0.7373271889400922,
+      "grad_norm": 0.38564491271972656,
+      "learning_rate": 6.378947368421053e-05,
+      "loss": 2.1442,
+      "step": 80
+    },
+    {
+      "epoch": 0.7465437788018433,
+      "grad_norm": 0.5515257716178894,
+      "learning_rate": 6.32578947368421e-05,
+      "loss": 2.2783,
+      "step": 81
+    },
+    {
+      "epoch": 0.7557603686635944,
+      "grad_norm": 0.24224898219108582,
+      "learning_rate": 6.27263157894737e-05,
+      "loss": 1.908,
+      "step": 82
+    },
+    {
+      "epoch": 0.7649769585253456,
+      "grad_norm": 0.24595709145069122,
+      "learning_rate": 6.219473684210527e-05,
+      "loss": 2.004,
+      "step": 83
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.2858838140964508,
+      "learning_rate": 6.166315789473685e-05,
+      "loss": 2.0666,
+      "step": 84
+    },
+    {
+      "epoch": 0.783410138248848,
+      "grad_norm": 0.3219738006591797,
+      "learning_rate": 6.113157894736842e-05,
+      "loss": 2.1556,
+      "step": 85
+    },
+    {
+      "epoch": 0.7926267281105991,
+      "grad_norm": 0.3724604547023773,
+      "learning_rate": 6.0599999999999996e-05,
+      "loss": 2.1175,
+      "step": 86
+    },
+    {
+      "epoch": 0.8018433179723502,
+      "grad_norm": 0.4245091378688812,
+      "learning_rate": 6.006842105263158e-05,
+      "loss": 2.1737,
+      "step": 87
+    },
+    {
+      "epoch": 0.8110599078341014,
+      "grad_norm": 0.27818793058395386,
+      "learning_rate": 5.953684210526315e-05,
+      "loss": 1.9384,
+      "step": 88
+    },
+    {
+      "epoch": 0.8202764976958525,
+      "grad_norm": 0.265677809715271,
+      "learning_rate": 5.900526315789474e-05,
+      "loss": 1.9712,
+      "step": 89
+    },
+    {
+      "epoch": 0.8294930875576036,
+      "grad_norm": 0.28756722807884216,
+      "learning_rate": 5.847368421052632e-05,
+      "loss": 2.0308,
+      "step": 90
+    },
+    {
+      "epoch": 0.8387096774193549,
+      "grad_norm": 0.3114590048789978,
+      "learning_rate": 5.79421052631579e-05,
+      "loss": 2.106,
+      "step": 91
+    },
+    {
+      "epoch": 0.847926267281106,
+      "grad_norm": 0.36105430126190186,
+      "learning_rate": 5.7410526315789475e-05,
+      "loss": 2.08,
+      "step": 92
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.47732144594192505,
+      "learning_rate": 5.687894736842105e-05,
+      "loss": 2.1652,
+      "step": 93
+    },
+    {
+      "epoch": 0.8663594470046083,
+      "grad_norm": 0.3170245885848999,
+      "learning_rate": 5.6347368421052625e-05,
+      "loss": 1.8834,
+      "step": 94
+    },
+    {
+      "epoch": 0.8755760368663594,
+      "grad_norm": 0.2604347765445709,
+      "learning_rate": 5.5815789473684214e-05,
+      "loss": 1.9625,
+      "step": 95
+    },
+    {
+      "epoch": 0.8847926267281107,
+      "grad_norm": 0.3109751045703888,
+      "learning_rate": 5.5284210526315796e-05,
+      "loss": 2.0527,
+      "step": 96
+    },
+    {
+      "epoch": 0.8940092165898618,
+      "grad_norm": 0.3108777403831482,
+      "learning_rate": 5.475263157894737e-05,
+      "loss": 2.0632,
+      "step": 97
+    },
+    {
+      "epoch": 0.9032258064516129,
+      "grad_norm": 0.32949569821357727,
+      "learning_rate": 5.422105263157895e-05,
+      "loss": 2.1305,
+      "step": 98
+    },
+    {
+      "epoch": 0.9124423963133641,
+      "grad_norm": 0.3967636227607727,
+      "learning_rate": 5.368947368421053e-05,
+      "loss": 2.1667,
+      "step": 99
+    },
+    {
+      "epoch": 0.9216589861751152,
+      "grad_norm": 0.5703552961349487,
+      "learning_rate": 5.3157894736842104e-05,
+      "loss": 2.2293,
+      "step": 100
+    },
+    {
+      "epoch": 0.9216589861751152,
+      "eval_loss": 2.094890832901001,
+      "eval_runtime": 12.638,
+      "eval_samples_per_second": 115.525,
+      "eval_steps_per_second": 3.64,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -401,7 +759,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.034054314983424e+17,
+  "total_flos": 1.2068108629966848e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null