Training in progress, step 71, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52370d7fa880dd345bc97d8a7bdde4a0ad8a78387c93a8042b6b6c5296989060
+oid sha256:bf93efb7177f0a58f11e73c763267091d70f579e5b8f55b493ea13c694439714
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7429c5d07baa105ee893177ffdcdcfd1090b5f2259c197f0c516cab51f40d866
+oid sha256:38ebe4d3c716dc140df266d96934b7c7c8e3e3a5cfd2d50b34eda28e5482a5fe
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30cbebbf11fe1f0ceb1994734cc95df03a1ac214b4c0be10b3cf908b646a2798
+oid sha256:11434625641baa8dcb92440b94cbb378ecac07382da39254d5bfcb9a75253d0f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91390eed23f8017bf1432b55c01065f705f362b2c2e949c597b1f34fb2f67e34
+oid sha256:c95483a82e000a154633703747f8babc8d6e22e1263ddf1e71622b29f960b999
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c245f63d5154c620f0a51a1d8b35ad60ae9e8c4c7d20f0206863d68f01aaf319
+oid sha256:da3d3fb10e6dc5cd32fc8efb22c5c56b4ca8b04d401d0470211fe91156d3aa17
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aebe1f5f41dfde027a0a59ca8eb7e51adaffb64b8c963b1b6d044ae460ee0e89
+oid sha256:909ab5899591151c6f18b6ef23a09b47bee2a4c585dbffb511038923a2cf5f0e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d09c886ce689c5dc6f9fb4f7bfd869ed47d5f69d07d5be044cdd6480e5367062
+oid sha256:544f6ccb4622164946a8bd8e21374fc5cfa8e8262c8720a1374851949c7e26c1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 6.703342437744141,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.024873146950552184,
+  "epoch": 0.0353198686697841,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 71,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,153 @@
       "eval_samples_per_second": 1208.754,
       "eval_steps_per_second": 72.525,
       "step": 50
+    },
+    {
+      "epoch": 0.025370609889563227,
+      "grad_norm": 1.8086193799972534,
+      "learning_rate": 8.220898871169827e-05,
+      "loss": 6.8079,
+      "step": 51
+    },
+    {
+      "epoch": 0.02586807282857427,
+      "grad_norm": 0.7370948195457458,
+      "learning_rate": 7.744141792252794e-05,
+      "loss": 6.8023,
+      "step": 52
+    },
+    {
+      "epoch": 0.026365535767585314,
+      "grad_norm": 1.0690277814865112,
+      "learning_rate": 7.285532566548172e-05,
+      "loss": 6.7905,
+      "step": 53
+    },
+    {
+      "epoch": 0.026862998706596357,
+      "grad_norm": 1.2137597799301147,
+      "learning_rate": 6.846021731708856e-05,
+      "loss": 6.77,
+      "step": 54
+    },
+    {
+      "epoch": 0.027360461645607403,
+      "grad_norm": 0.7531571984291077,
+      "learning_rate": 6.426520241056245e-05,
+      "loss": 6.661,
+      "step": 55
+    },
+    {
+      "epoch": 0.027857924584618447,
+      "grad_norm": 0.8767682313919067,
+      "learning_rate": 6.0278975754903317e-05,
+      "loss": 6.6017,
+      "step": 56
+    },
+    {
+      "epoch": 0.02835538752362949,
+      "grad_norm": 0.7823953628540039,
+      "learning_rate": 5.6509799413577934e-05,
+      "loss": 6.5955,
+      "step": 57
+    },
+    {
+      "epoch": 0.028852850462640533,
+      "grad_norm": 0.8727318048477173,
+      "learning_rate": 5.296548558013161e-05,
+      "loss": 6.7922,
+      "step": 58
+    },
+    {
+      "epoch": 0.029350313401651576,
+      "grad_norm": 0.996519148349762,
+      "learning_rate": 4.9653380386224046e-05,
+      "loss": 6.7956,
+      "step": 59
+    },
+    {
+      "epoch": 0.02984777634066262,
+      "grad_norm": 0.6733922362327576,
+      "learning_rate": 4.658034867564977e-05,
+      "loss": 6.6694,
+      "step": 60
+    },
+    {
+      "epoch": 0.030345239279673666,
+      "grad_norm": 0.8655278086662292,
+      "learning_rate": 4.375275977590104e-05,
+      "loss": 6.5892,
+      "step": 61
+    },
+    {
+      "epoch": 0.03084270221868471,
+      "grad_norm": 0.9837325811386108,
+      "learning_rate": 4.117647429676387e-05,
+      "loss": 6.5165,
+      "step": 62
+    },
+    {
+      "epoch": 0.03134016515769575,
+      "grad_norm": 1.1237236261367798,
+      "learning_rate": 3.885683198330941e-05,
+      "loss": 6.7888,
+      "step": 63
+    },
+    {
+      "epoch": 0.031837628096706795,
+      "grad_norm": 1.0909230709075928,
+      "learning_rate": 3.679864064845691e-05,
+      "loss": 6.8041,
+      "step": 64
+    },
+    {
+      "epoch": 0.03233509103571784,
+      "grad_norm": 0.9223988652229309,
+      "learning_rate": 3.500616620804712e-05,
+      "loss": 6.7929,
+      "step": 65
+    },
+    {
+      "epoch": 0.03283255397472888,
+      "grad_norm": 1.2748134136199951,
+      "learning_rate": 3.348312383908033e-05,
+      "loss": 6.7633,
+      "step": 66
+    },
+    {
+      "epoch": 0.03333001691373993,
+      "grad_norm": 0.5331524014472961,
+      "learning_rate": 3.223267027944483e-05,
+      "loss": 6.7201,
+      "step": 67
+    },
+    {
+      "epoch": 0.03382747985275097,
+      "grad_norm": 0.9274587035179138,
+      "learning_rate": 3.125739728509535e-05,
+      "loss": 6.6011,
+      "step": 68
+    },
+    {
+      "epoch": 0.034324942791762014,
+      "grad_norm": 1.011277198791504,
+      "learning_rate": 3.055932625824328e-05,
+      "loss": 6.5109,
+      "step": 69
+    },
+    {
+      "epoch": 0.03482240573077306,
+      "grad_norm": 0.7799229025840759,
+      "learning_rate": 3.0139904057691777e-05,
+      "loss": 6.6674,
+      "step": 70
+    },
+    {
+      "epoch": 0.0353198686697841,
+      "grad_norm": 1.039928674697876,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 6.8205,
+      "step": 71
     }
   ],
   "logging_steps": 1,
@@ -404,12 +551,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5461671075840.0,
+  "total_flos": 7767234478080.0,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null