Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a0a30186463e1ff11361d1d286d55bba8b4206bb9948d455f40ae8c06f50f57
+oid sha256:3debc6cd130eb2243a4c132a1a7d7cf022648308f2ae1bb66dfbe48b4088b99e
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a098e0ac662ef62a7cb5292ee75f9e0ddf14f2fe68c7f0650d6aac0aece30a76
+oid sha256:f7fa76a3c5671e8eb6ec2baa556b0846978ed249edb3a11d204555d4702e55ce
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daffcc23d1d263f7b0145f1ae0edfc6363fce60cfbc4982d244cc73b4ebc1b55
+oid sha256:13c87654199b0fb50f3f7332b8ec7a348a98e08641ae59bfea79dd82e50e251c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3adb854aa64280bb90ea7e0abaf23587245297be79cbb959e2946d6d6f7568e2
+oid sha256:c8fabcb7916b68756e5caa4258f2b5132d082ee05c05bd062a246bbe1a73ed14
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a9e06f632f74c9e42da73f40152a381d18a3c83875a0aa0e1c5d615cd4d35d2
+oid sha256:d532212ec3c2c2cca22fa25df2d7ee1478e88fbb99647a3268fe5d9cbb3b0496
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3da484b3ec6ea9f4055984bb82904f483b1fdc4a4e027ad2318ce84567a57ba3
+oid sha256:9f3a37913969eb5b5a43defbcc383564bd8b39f52bcaa397ffaaaebe2a513967
 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": 0.5971322655677795,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4106776180698152,
+  "best_metric": 0.4655110836029053,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8213552361396304,
   "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": 8.755,
       "eval_steps_per_second": 2.276,
       "step": 25
+    },
+    {
+      "epoch": 0.4271047227926078,
+      "grad_norm": 24.593185424804688,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 14.0883,
+      "step": 26
+    },
+    {
+      "epoch": 0.44353182751540043,
+      "grad_norm": 20.8594970703125,
+      "learning_rate": 7.75e-05,
+      "loss": 14.9155,
+      "step": 27
+    },
+    {
+      "epoch": 0.459958932238193,
+      "grad_norm": 14.129776954650879,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 16.0266,
+      "step": 28
+    },
+    {
+      "epoch": 0.47638603696098564,
+      "grad_norm": 11.421152114868164,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 16.268,
+      "step": 29
+    },
+    {
+      "epoch": 0.4928131416837782,
+      "grad_norm": 8.77751350402832,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 15.4968,
+      "step": 30
+    },
+    {
+      "epoch": 0.5092402464065708,
+      "grad_norm": 8.126062393188477,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 16.2933,
+      "step": 31
+    },
+    {
+      "epoch": 0.5256673511293635,
+      "grad_norm": 9.534149169921875,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 18.2007,
+      "step": 32
+    },
+    {
+      "epoch": 0.5420944558521561,
+      "grad_norm": 9.915535926818848,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 16.2263,
+      "step": 33
+    },
+    {
+      "epoch": 0.5585215605749486,
+      "grad_norm": 10.236954689025879,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 17.5051,
+      "step": 34
+    },
+    {
+      "epoch": 0.5749486652977412,
+      "grad_norm": 12.080739974975586,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 16.8991,
+      "step": 35
+    },
+    {
+      "epoch": 0.5913757700205339,
+      "grad_norm": 13.376237869262695,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 17.6223,
+      "step": 36
+    },
+    {
+      "epoch": 0.6078028747433265,
+      "grad_norm": 15.929511070251465,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 18.6204,
+      "step": 37
+    },
+    {
+      "epoch": 0.6242299794661191,
+      "grad_norm": 11.249287605285645,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 13.2654,
+      "step": 38
+    },
+    {
+      "epoch": 0.6406570841889117,
+      "grad_norm": 8.463708877563477,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 14.5936,
+      "step": 39
+    },
+    {
+      "epoch": 0.6570841889117043,
+      "grad_norm": 9.492480278015137,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 13.5542,
+      "step": 40
+    },
+    {
+      "epoch": 0.6735112936344969,
+      "grad_norm": 9.737853050231934,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 14.0081,
+      "step": 41
+    },
+    {
+      "epoch": 0.6899383983572895,
+      "grad_norm": 8.300447463989258,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 13.108,
+      "step": 42
+    },
+    {
+      "epoch": 0.7063655030800822,
+      "grad_norm": 7.692556858062744,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 15.0314,
+      "step": 43
+    },
+    {
+      "epoch": 0.7227926078028748,
+      "grad_norm": 9.348422050476074,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 16.3044,
+      "step": 44
+    },
+    {
+      "epoch": 0.7392197125256673,
+      "grad_norm": 9.944343566894531,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 14.7704,
+      "step": 45
+    },
+    {
+      "epoch": 0.75564681724846,
+      "grad_norm": 11.046955108642578,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 15.9394,
+      "step": 46
+    },
+    {
+      "epoch": 0.7720739219712526,
+      "grad_norm": 11.804484367370605,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 15.4152,
+      "step": 47
+    },
+    {
+      "epoch": 0.7885010266940452,
+      "grad_norm": 11.646093368530273,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 14.4148,
+      "step": 48
+    },
+    {
+      "epoch": 0.8049281314168378,
+      "grad_norm": 14.222677230834961,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 17.4141,
+      "step": 49
+    },
+    {
+      "epoch": 0.8213552361396304,
+      "grad_norm": 13.688545227050781,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 15.3378,
+      "step": 50
+    },
+    {
+      "epoch": 0.8213552361396304,
+      "eval_loss": 0.4655110836029053,
+      "eval_runtime": 5.7595,
+      "eval_samples_per_second": 8.681,
+      "eval_steps_per_second": 2.257,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null