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:bc884815c126a9bcc057e85b4609aafc0b566add0cf47a55eadbfb55a727803d
+oid sha256:2e9226eb0c13650147b5ec8e5b179f1a236c7116deb10fb92ba3aaf368f1a7ab
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c52ae7a5fa365f7f694460996c62193712df4fdfad12b35db4105904d2b000d1
+oid sha256:50af909fbc8792116dca5743caf68131afbd3a176e3bf3ad743b9f09a25677fd
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05803afa19cda5b6abb99394d678e810ac5426335c13e6fdaacfe1b4d370527b
+oid sha256:e320216c8c37453efaf379357cdd82ac7d0fd048ad91bf56ed53f1a26cee7e5f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6bcfd288976efa04b300ce8dfe3482dedae9984ba25cbd81fd57a72e62a6f94
+oid sha256:5499a551a027da9850bb0d6cc4c5b43b0207603310bc02886d35d8c9f52220e0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba0d85e29096cba3540854efbe2eb24b0dcb354bd598c9b0442f1a068e97147
+oid sha256:55dd6ecd6878ebbb700609ac0e8fd3fe1aecf7f8dc7c1eeeed2f63618a2c3bf0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bce6c0f85e52f47ca30e0c92d68100127220279776878577c4b7dbbb15af1305
+oid sha256:1921569be3d944cce0e26410e25c17941f7da5422b1f8f119415d8f59362fc30
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
+oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.558501124382019,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.024680693527488123,
+  "best_metric": 1.517699122428894,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.03702104029123218,
   "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": 23.245,
       "eval_steps_per_second": 6.044,
       "step": 50
+    },
+    {
+      "epoch": 0.025174307398037884,
+      "grad_norm": 0.7213638424873352,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 1.411,
+      "step": 51
+    },
+    {
+      "epoch": 0.02566792126858765,
+      "grad_norm": 0.7571468949317932,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 1.5454,
+      "step": 52
+    },
+    {
+      "epoch": 0.02616153513913741,
+      "grad_norm": 0.717697024345398,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 1.4686,
+      "step": 53
+    },
+    {
+      "epoch": 0.02665514900968717,
+      "grad_norm": 0.7320601344108582,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 1.4823,
+      "step": 54
+    },
+    {
+      "epoch": 0.027148762880236935,
+      "grad_norm": 0.7738489508628845,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 1.4721,
+      "step": 55
+    },
+    {
+      "epoch": 0.027642376750786696,
+      "grad_norm": 0.7395352721214294,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 1.5485,
+      "step": 56
+    },
+    {
+      "epoch": 0.02813599062133646,
+      "grad_norm": 0.7061799764633179,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 1.4671,
+      "step": 57
+    },
+    {
+      "epoch": 0.028629604491886222,
+      "grad_norm": 0.7371093034744263,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 1.5273,
+      "step": 58
+    },
+    {
+      "epoch": 0.029123218362435983,
+      "grad_norm": 0.7502743005752563,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 1.5082,
+      "step": 59
+    },
+    {
+      "epoch": 0.029616832232985748,
+      "grad_norm": 0.7478111982345581,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 1.4492,
+      "step": 60
+    },
+    {
+      "epoch": 0.03011044610353551,
+      "grad_norm": 0.7804875373840332,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 1.5395,
+      "step": 61
+    },
+    {
+      "epoch": 0.03060405997408527,
+      "grad_norm": 0.828667938709259,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 1.4686,
+      "step": 62
+    },
+    {
+      "epoch": 0.031097673844635035,
+      "grad_norm": 0.7223063111305237,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 1.4567,
+      "step": 63
+    },
+    {
+      "epoch": 0.031591287715184796,
+      "grad_norm": 0.8763315677642822,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 1.5132,
+      "step": 64
+    },
+    {
+      "epoch": 0.03208490158573456,
+      "grad_norm": 0.8217432498931885,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 1.4729,
+      "step": 65
+    },
+    {
+      "epoch": 0.03257851545628432,
+      "grad_norm": 0.7187386155128479,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 1.4075,
+      "step": 66
+    },
+    {
+      "epoch": 0.033072129326834086,
+      "grad_norm": 0.7990232110023499,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 1.6426,
+      "step": 67
+    },
+    {
+      "epoch": 0.03356574319738385,
+      "grad_norm": 0.7265430688858032,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 1.4177,
+      "step": 68
+    },
+    {
+      "epoch": 0.03405935706793361,
+      "grad_norm": 0.7410502433776855,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 1.5169,
+      "step": 69
+    },
+    {
+      "epoch": 0.03455297093848337,
+      "grad_norm": 0.8333743214607239,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 1.5395,
+      "step": 70
+    },
+    {
+      "epoch": 0.03504658480903313,
+      "grad_norm": 0.7417758703231812,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 1.4021,
+      "step": 71
+    },
+    {
+      "epoch": 0.0355401986795829,
+      "grad_norm": 0.757122814655304,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.5029,
+      "step": 72
+    },
+    {
+      "epoch": 0.03603381255013266,
+      "grad_norm": 0.8034988045692444,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 1.5196,
+      "step": 73
+    },
+    {
+      "epoch": 0.03652742642068242,
+      "grad_norm": 0.8066292405128479,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 1.4421,
+      "step": 74
+    },
+    {
+      "epoch": 0.03702104029123218,
+      "grad_norm": 0.9166308045387268,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 1.5344,
+      "step": 75
+    },
+    {
+      "epoch": 0.03702104029123218,
+      "eval_loss": 1.517699122428894,
+      "eval_runtime": 2.1573,
+      "eval_samples_per_second": 23.177,
+      "eval_steps_per_second": 6.026,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.62480894509056e+17,
+  "total_flos": 2.43721341763584e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null