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:eb73775f7bc729481aee94659de66fdb84c38dab5f5f0b457ba9ff47ddea7463
+oid sha256:c6f4146fbbfb52b8f96c566775a4645c66521d1dee86583e76129376a7e4ccbe
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f05fb84fea011de6904909e24734de177cf476a6488abd299110904545a816a
+oid sha256:8045eeec8dd00c26eefde1db6f4be582b57a4f9ac4453a201de241a3bdf2fc5c
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd1857f774f2ddd57d3373059fd5ee1a8a92f027318c13b282e3409fadd96f2
+oid sha256:1f05977fbd8be67895f5c29ba8404504f004f539b203fd8b81b83e6c979fdbf8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0b8f51409e351976a434bee1b1d486e93864c0d6a111f6ac551f93fa26cf18b
+oid sha256:081c54c9c01ce1ea54955a3a5abd58d677667e3864cfd2a12481ed1a90f7f944
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6a7bb6e664f812332b359e3d1c04ad3bbf92e5fe65534fd07e1f897b3acda20
+oid sha256:fabdf0974dd98454821e402f14f532a39394fe70fe2c259efbcb85a054eb358b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98fd3e99ebe6bcb40bd97f7512652ec6c97c01ffaa7e76e8bc12ee2ed94aa8d3
+oid sha256:e2ead22fa6945d10eafb4b72edf5c6ea6b589a3cc11a5254282ef81982aed17c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.938733100891113,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.21668472372697725,
+  "best_metric": 11.933380126953125,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4333694474539545,
   "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": 191.665,
       "eval_steps_per_second": 49.833,
       "step": 25
+    },
+    {
+      "epoch": 0.22535211267605634,
+      "grad_norm": 0.024506624788045883,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 11.932,
+      "step": 26
+    },
+    {
+      "epoch": 0.23401950162513543,
+      "grad_norm": 0.03506021574139595,
+      "learning_rate": 7.75e-05,
+      "loss": 11.933,
+      "step": 27
+    },
+    {
+      "epoch": 0.24268689057421453,
+      "grad_norm": 0.04695020988583565,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 11.9338,
+      "step": 28
+    },
+    {
+      "epoch": 0.2513542795232936,
+      "grad_norm": 0.05981919541954994,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 11.9342,
+      "step": 29
+    },
+    {
+      "epoch": 0.2600216684723727,
+      "grad_norm": 0.061907246708869934,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 11.9334,
+      "step": 30
+    },
+    {
+      "epoch": 0.26868905742145177,
+      "grad_norm": 0.07472109794616699,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 11.9334,
+      "step": 31
+    },
+    {
+      "epoch": 0.27735644637053086,
+      "grad_norm": 0.09128537774085999,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 11.9335,
+      "step": 32
+    },
+    {
+      "epoch": 0.28602383531960995,
+      "grad_norm": 0.10218062251806259,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 11.9348,
+      "step": 33
+    },
+    {
+      "epoch": 0.29469122426868904,
+      "grad_norm": 0.11169303208589554,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 11.9348,
+      "step": 34
+    },
+    {
+      "epoch": 0.30335861321776814,
+      "grad_norm": 0.14492186903953552,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 11.9349,
+      "step": 35
+    },
+    {
+      "epoch": 0.3120260021668472,
+      "grad_norm": 0.18491142988204956,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 11.9366,
+      "step": 36
+    },
+    {
+      "epoch": 0.3206933911159263,
+      "grad_norm": 0.245423823595047,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 11.9378,
+      "step": 37
+    },
+    {
+      "epoch": 0.3293607800650054,
+      "grad_norm": 0.05013355612754822,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 11.9315,
+      "step": 38
+    },
+    {
+      "epoch": 0.3380281690140845,
+      "grad_norm": 0.047407366335392,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9323,
+      "step": 39
+    },
+    {
+      "epoch": 0.3466955579631636,
+      "grad_norm": 0.055343057960271835,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 11.9334,
+      "step": 40
+    },
+    {
+      "epoch": 0.3553629469122427,
+      "grad_norm": 0.07278693467378616,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 11.9319,
+      "step": 41
+    },
+    {
+      "epoch": 0.3640303358613218,
+      "grad_norm": 0.08519124239683151,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9313,
+      "step": 42
+    },
+    {
+      "epoch": 0.37269772481040087,
+      "grad_norm": 0.09722817689180374,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 11.9318,
+      "step": 43
+    },
+    {
+      "epoch": 0.38136511375947996,
+      "grad_norm": 0.0941312164068222,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 11.9312,
+      "step": 44
+    },
+    {
+      "epoch": 0.39003250270855905,
+      "grad_norm": 0.12124495208263397,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.931,
+      "step": 45
+    },
+    {
+      "epoch": 0.39869989165763814,
+      "grad_norm": 0.12268517166376114,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 11.9317,
+      "step": 46
+    },
+    {
+      "epoch": 0.40736728060671723,
+      "grad_norm": 0.16867737472057343,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 11.9314,
+      "step": 47
+    },
+    {
+      "epoch": 0.4160346695557963,
+      "grad_norm": 0.18943016231060028,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.933,
+      "step": 48
+    },
+    {
+      "epoch": 0.4247020585048754,
+      "grad_norm": 0.24677303433418274,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 11.9336,
+      "step": 49
+    },
+    {
+      "epoch": 0.4333694474539545,
+      "grad_norm": 0.34038564562797546,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 11.9339,
+      "step": 50
+    },
+    {
+      "epoch": 0.4333694474539545,
+      "eval_loss": 11.933380126953125,
+      "eval_runtime": 0.2591,
+      "eval_samples_per_second": 192.978,
+      "eval_steps_per_second": 50.174,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 522713137152.0,
+  "total_flos": 1045263384576.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null