Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:534a56f1bf6242ac01256fc251a65ba40fadd6dbde0ad139e92e273947832828
+oid sha256:b55460d6ad24c3b818125af12fa11cdaaf0ecf7a81a4454530e25229283dcac8
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76876b339ecf59507472e1a10a856c25237d43ea6e48ae776212f06d9005ab59
+oid sha256:e10ca02b7e83f6508c535ce5b5efbcda00118745f4262b5b374fa03dbdeee3d7
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6b28ddceffcfbb0eba88c1253d9911a71087a0094e0bfdf46af8eb09c71e1e
+oid sha256:853bed1ad0054fcc4b7b593768f530b0d09e04ae380bdf347d707c7c2039d4d2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d309aaef3b1e5898ac57d64657b760ac77a2c95a5d95f8529614ca1aed1aaaa
+oid sha256:61383d7ceb3182657c317ebd27fc828810f33b43538858ee366085005e7cdc0b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c53f4da5420488101ec3275bdfc923e394ed7e19e556423cd25a0dedcbfc47
+oid sha256:84e897519067204c35d38d53d3e50876a46945aaf384075e684a9ceaacfcb95b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17433ce56533032b14ee12a4eaa80b1ba94e3f84b10da2de1e7b768ebdb2efb1
+oid sha256:aedde11412e361c62c36439ada43621f054338e48e85b641939d780d00e98cd1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.12278789281845093,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0355769016965735,
+  "best_metric": 0.08122972398996353,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.05336535254486025,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 14.25,
       "eval_steps_per_second": 3.705,
       "step": 50
+    },
+    {
+      "epoch": 0.03628843973050497,
+      "grad_norm": 1.0250176191329956,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.2113,
+      "step": 51
+    },
+    {
+      "epoch": 0.03699997776443644,
+      "grad_norm": 0.8808900713920593,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 0.1611,
+      "step": 52
+    },
+    {
+      "epoch": 0.03771151579836791,
+      "grad_norm": 0.8555270433425903,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 0.127,
+      "step": 53
+    },
+    {
+      "epoch": 0.03842305383229938,
+      "grad_norm": 0.9593107104301453,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1143,
+      "step": 54
+    },
+    {
+      "epoch": 0.03913459186623085,
+      "grad_norm": 0.8327104449272156,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 0.0989,
+      "step": 55
+    },
+    {
+      "epoch": 0.03984612990016232,
+      "grad_norm": 0.6464086174964905,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 0.0817,
+      "step": 56
+    },
+    {
+      "epoch": 0.04055766793409379,
+      "grad_norm": 0.49059954285621643,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0748,
+      "step": 57
+    },
+    {
+      "epoch": 0.04126920596802526,
+      "grad_norm": 0.3070560097694397,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 0.0581,
+      "step": 58
+    },
+    {
+      "epoch": 0.04198074400195673,
+      "grad_norm": 0.3088557720184326,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 0.051,
+      "step": 59
+    },
+    {
+      "epoch": 0.0426922820358882,
+      "grad_norm": 0.3666839301586151,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0588,
+      "step": 60
+    },
+    {
+      "epoch": 0.04340382006981967,
+      "grad_norm": 0.4506279230117798,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 0.0734,
+      "step": 61
+    },
+    {
+      "epoch": 0.04411535810375114,
+      "grad_norm": 0.6894549131393433,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 0.0656,
+      "step": 62
+    },
+    {
+      "epoch": 0.044826896137682606,
+      "grad_norm": 2.1693735122680664,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.1742,
+      "step": 63
+    },
+    {
+      "epoch": 0.04553843417161408,
+      "grad_norm": 0.7992150783538818,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 0.1506,
+      "step": 64
+    },
+    {
+      "epoch": 0.046249972205545546,
+      "grad_norm": 0.5185897350311279,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 0.113,
+      "step": 65
+    },
+    {
+      "epoch": 0.04696151023947702,
+      "grad_norm": 0.43015819787979126,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0864,
+      "step": 66
+    },
+    {
+      "epoch": 0.04767304827340849,
+      "grad_norm": 0.38855844736099243,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 0.0895,
+      "step": 67
+    },
+    {
+      "epoch": 0.04838458630733996,
+      "grad_norm": 0.2907514274120331,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 0.0589,
+      "step": 68
+    },
+    {
+      "epoch": 0.04909612434127143,
+      "grad_norm": 0.34849977493286133,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0473,
+      "step": 69
+    },
+    {
+      "epoch": 0.0498076623752029,
+      "grad_norm": 0.2817358672618866,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 0.0527,
+      "step": 70
+    },
+    {
+      "epoch": 0.05051920040913437,
+      "grad_norm": 0.3551785349845886,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 0.0596,
+      "step": 71
+    },
+    {
+      "epoch": 0.05123073844306584,
+      "grad_norm": 0.3679645359516144,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0543,
+      "step": 72
+    },
+    {
+      "epoch": 0.05194227647699731,
+      "grad_norm": 0.4032980799674988,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 0.0499,
+      "step": 73
+    },
+    {
+      "epoch": 0.05265381451092878,
+      "grad_norm": 0.48960503935813904,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 0.0701,
+      "step": 74
+    },
+    {
+      "epoch": 0.05336535254486025,
+      "grad_norm": 0.8739669322967529,
+      "learning_rate": 1e-05,
+      "loss": 0.0798,
+      "step": 75
+    },
+    {
+      "epoch": 0.05336535254486025,
+      "eval_loss": 0.08122972398996353,
+      "eval_runtime": 3.517,
+      "eval_samples_per_second": 14.217,
+      "eval_steps_per_second": 3.696,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.968083617316864e+17,
+  "total_flos": 8.952125425975296e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null