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:b09751eb4bb52f17cc5b6a4da979fc435832d93d0eebef4a9453a2bc14da34bf
+oid sha256:25d146acaae9c8f8a87fd00ebe72818b79f6ed0d50b28cfb37cd47f3ed80bf6d
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aed710c9e1315e346d051d33d27a54bd0fe1be2944ccf23f660a4220c3d5bc78
+oid sha256:22f5ef5b56b3f40ea5812aed5722297ad7df61aa46be20540a9e632cf9d39b62
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5c51d188d5887fc1e06303791c8ba29bb7f9043781cf9d6fe0933dcef05e1ca
+oid sha256:9558f9bec5577f72bf66ded6aa8318de7c6a75914dc3d787355f2d5d20f66d63
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd890c33f27e30b4abae3b5ac0d90107541f91843960734d739e8f1eac4d62b
+oid sha256:032656a4a948492b4c5d06220444fb477c48c104cd652f03f356e28dac534cae
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e14f649ad1a2ad267ace42e8923d6874c604df0218fa8140c77b007af5057f0
+oid sha256:c05d71981e0f6ebd05e69f8887ad883046caafd267b26ef31131f59a6ab086a0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1c05f52849399c0fb804992c3959ff7262b582aa781ce78e1eda742f0e4f8d3
+oid sha256:8145d95c50c69d8217343a4830b616c00315a72f462a0b22858de3b251bb8fe2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.3605375289917,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4287245444801715,
+  "best_metric": 10.352457046508789,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.857449088960343,
   "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": 387.662,
       "eval_steps_per_second": 100.792,
       "step": 25
+    },
+    {
+      "epoch": 0.44587352625937837,
+      "grad_norm": 0.34039604663848877,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3547,
+      "step": 26
+    },
+    {
+      "epoch": 0.4630225080385852,
+      "grad_norm": 0.3508872091770172,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3533,
+      "step": 27
+    },
+    {
+      "epoch": 0.48017148981779206,
+      "grad_norm": 0.3430570065975189,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3551,
+      "step": 28
+    },
+    {
+      "epoch": 0.49732047159699894,
+      "grad_norm": 0.3169425129890442,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3567,
+      "step": 29
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "grad_norm": 0.34082862734794617,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3553,
+      "step": 30
+    },
+    {
+      "epoch": 0.5316184351554126,
+      "grad_norm": 0.32129889726638794,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3557,
+      "step": 31
+    },
+    {
+      "epoch": 0.5487674169346195,
+      "grad_norm": 0.3115546703338623,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3563,
+      "step": 32
+    },
+    {
+      "epoch": 0.5659163987138264,
+      "grad_norm": 0.2841951847076416,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3599,
+      "step": 33
+    },
+    {
+      "epoch": 0.5830653804930332,
+      "grad_norm": 0.24529126286506653,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3589,
+      "step": 34
+    },
+    {
+      "epoch": 0.6002143622722401,
+      "grad_norm": 0.22551962733268738,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3594,
+      "step": 35
+    },
+    {
+      "epoch": 0.617363344051447,
+      "grad_norm": 0.19762487709522247,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.361,
+      "step": 36
+    },
+    {
+      "epoch": 0.6345123258306538,
+      "grad_norm": 0.21796438097953796,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3592,
+      "step": 37
+    },
+    {
+      "epoch": 0.6516613076098606,
+      "grad_norm": 0.38318026065826416,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3482,
+      "step": 38
+    },
+    {
+      "epoch": 0.6688102893890675,
+      "grad_norm": 0.3688681721687317,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3481,
+      "step": 39
+    },
+    {
+      "epoch": 0.6859592711682744,
+      "grad_norm": 0.3773597478866577,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3506,
+      "step": 40
+    },
+    {
+      "epoch": 0.7031082529474812,
+      "grad_norm": 0.3649727404117584,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3506,
+      "step": 41
+    },
+    {
+      "epoch": 0.7202572347266881,
+      "grad_norm": 0.38561907410621643,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3485,
+      "step": 42
+    },
+    {
+      "epoch": 0.737406216505895,
+      "grad_norm": 0.3504658043384552,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3508,
+      "step": 43
+    },
+    {
+      "epoch": 0.7545551982851019,
+      "grad_norm": 0.3569239377975464,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3515,
+      "step": 44
+    },
+    {
+      "epoch": 0.7717041800643086,
+      "grad_norm": 0.30078503489494324,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3536,
+      "step": 45
+    },
+    {
+      "epoch": 0.7888531618435155,
+      "grad_norm": 0.2712373733520508,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3563,
+      "step": 46
+    },
+    {
+      "epoch": 0.8060021436227224,
+      "grad_norm": 0.21626907587051392,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3594,
+      "step": 47
+    },
+    {
+      "epoch": 0.8231511254019293,
+      "grad_norm": 0.2447448968887329,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3575,
+      "step": 48
+    },
+    {
+      "epoch": 0.8403001071811361,
+      "grad_norm": 0.2010498046875,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3599,
+      "step": 49
+    },
+    {
+      "epoch": 0.857449088960343,
+      "grad_norm": 0.24134501814842224,
+      "learning_rate": 1e-05,
+      "loss": 10.3564,
+      "step": 50
+    },
+    {
+      "epoch": 0.857449088960343,
+      "eval_loss": 10.352457046508789,
+      "eval_runtime": 0.1235,
+      "eval_samples_per_second": 404.722,
+      "eval_steps_per_second": 105.228,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 25700930813952.0,
+  "total_flos": 51188021329920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null