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:c3cca8fd2b2314de6cc2be4ddf535ba79f8f9c4179a9c2b12067671fbb52f390
+oid sha256:359e4efeb6cde7adbac73f1f199b45366f9aa403d2ed7f5214ed473719deb84b
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcec806d338759ee516d0232de3be9dd9d40257d6c19274ff0111fb442a85d48
+oid sha256:3f2619504f1ab87b13b03212c606deced14f9928264cbacfe9aa4698fdbf74a5
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d2b4a02e01c09bc8f14d311c746cec54544f6273f5a8a64490dafc11709aad
+oid sha256:888e1a2d75db1df484ef9bfa339a65ec2690ea1c03dc7252f154645447372db2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:428f70cb061335504d3cc2aecaedf454ed9dfb3ebdf7c0a802ddf768dad463c0
+oid sha256:300ab6a656172b6b9e0387948183d63231774d7e584b636f0fb60c8509403d87
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:782c69e5b2987684d672fac79a791922aec8bb71e7c3569b5a9ccf7e49544d48
+oid sha256:2de4acc2331ca271ba5dbad26887edef5ae8dfadca6d309d11c4325e7184ccb0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eda2a7e4aa6b926b9b00b067e2ee1bc924ce9e0985938a7cbb2024dc6449856
+oid sha256:5215fc163b417483f789acc250ad5e96c57d4cbb022fbde5137018c52f5c4dee
 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": 10.377211570739746,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7976071784646062,
+  "best_metric": 10.374171257019043,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.5952143569292123,
   "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": 275.802,
       "eval_steps_per_second": 71.709,
       "step": 25
+    },
+    {
+      "epoch": 0.8295114656031904,
+      "grad_norm": 0.0448242649435997,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 10.3768,
+      "step": 26
+    },
+    {
+      "epoch": 0.8614157527417746,
+      "grad_norm": 0.03327423706650734,
+      "learning_rate": 7.75e-05,
+      "loss": 10.3765,
+      "step": 27
+    },
+    {
+      "epoch": 0.8933200398803589,
+      "grad_norm": 0.029801176860928535,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 10.3774,
+      "step": 28
+    },
+    {
+      "epoch": 0.9252243270189432,
+      "grad_norm": 0.031676966696977615,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 10.378,
+      "step": 29
+    },
+    {
+      "epoch": 0.9571286141575274,
+      "grad_norm": 0.032815348356962204,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 10.3778,
+      "step": 30
+    },
+    {
+      "epoch": 0.9890329012961117,
+      "grad_norm": 0.05490710586309433,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 10.3771,
+      "step": 31
+    },
+    {
+      "epoch": 1.0209371884346958,
+      "grad_norm": 0.10271252691745758,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 17.344,
+      "step": 32
+    },
+    {
+      "epoch": 1.0528414755732802,
+      "grad_norm": 0.06409234553575516,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 10.2565,
+      "step": 33
+    },
+    {
+      "epoch": 1.0847457627118644,
+      "grad_norm": 0.05500740185379982,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 10.3753,
+      "step": 34
+    },
+    {
+      "epoch": 1.1166500498504486,
+      "grad_norm": 0.03728007897734642,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 10.3715,
+      "step": 35
+    },
+    {
+      "epoch": 1.148554336989033,
+      "grad_norm": 0.03842683136463165,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 10.4211,
+      "step": 36
+    },
+    {
+      "epoch": 1.1804586241276172,
+      "grad_norm": 0.03933300822973251,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 10.6714,
+      "step": 37
+    },
+    {
+      "epoch": 1.2123629112662013,
+      "grad_norm": 0.03183865174651146,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 10.4574,
+      "step": 38
+    },
+    {
+      "epoch": 1.2442671984047857,
+      "grad_norm": 0.036480437964200974,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 6.8814,
+      "step": 39
+    },
+    {
+      "epoch": 1.27617148554337,
+      "grad_norm": 0.1208992525935173,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 13.486,
+      "step": 40
+    },
+    {
+      "epoch": 1.308075772681954,
+      "grad_norm": 0.058902185410261154,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 10.3354,
+      "step": 41
+    },
+    {
+      "epoch": 1.3399800598205385,
+      "grad_norm": 0.05739002674818039,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3683,
+      "step": 42
+    },
+    {
+      "epoch": 1.3718843469591226,
+      "grad_norm": 0.050218719989061356,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 10.3865,
+      "step": 43
+    },
+    {
+      "epoch": 1.4037886340977068,
+      "grad_norm": 0.03760230913758278,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 10.4672,
+      "step": 44
+    },
+    {
+      "epoch": 1.4356929212362912,
+      "grad_norm": 0.03762374445796013,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.6383,
+      "step": 45
+    },
+    {
+      "epoch": 1.4675972083748754,
+      "grad_norm": 0.03604252636432648,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 10.726,
+      "step": 46
+    },
+    {
+      "epoch": 1.4995014955134596,
+      "grad_norm": 0.07998944073915482,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 7.2666,
+      "step": 47
+    },
+    {
+      "epoch": 1.531405782652044,
+      "grad_norm": 0.11271944642066956,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 12.796,
+      "step": 48
+    },
+    {
+      "epoch": 1.5633100697906281,
+      "grad_norm": 0.0690908133983612,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 10.352,
+      "step": 49
+    },
+    {
+      "epoch": 1.5952143569292123,
+      "grad_norm": 0.056807372719049454,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 10.3753,
+      "step": 50
+    },
+    {
+      "epoch": 1.5952143569292123,
+      "eval_loss": 10.374171257019043,
+      "eval_runtime": 0.1795,
+      "eval_samples_per_second": 278.624,
+      "eval_steps_per_second": 72.442,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null