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:a8c4847ccab7dcf0c92d5efc43e2bb3e1afa96feba6b0c5b931ec391b91ed66c
+oid sha256:090024df88ed174c72f2728bf7f3b71ca82a6fcc03ef823eb463c1ef17f82dcc
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f86b3f3f7abd627aa691a8d39e6e23fe4f2b84a38372aafc3ab3306bfec5b4
+oid sha256:4cbb490756c53c5049c6874e2925a0e9c23f442b295902ecfc2e9d21f596132e
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ccc373d75ea8573fcdea661d5322a6e47ad1a3c157cda058e77132d626602e1
+oid sha256:fd2696fb1ac2fa651d9a3058ba2a02116b9e3b124f0a4d1a35dad3c5e7d699e8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:530a6e4d34b861ada907bd6f3b399b5bde8f1cd64f9cceaf7707b8322615e09e
+oid sha256:e79759ff77f61eea77f4fcda73c34fb0a7b3520873aee6f40ea3edac6a1146bb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb4c113132ad50dc5ce21f78c9a0e88af1fb58cd423c0c74bf449ac6bc3801a
+oid sha256:a7deb6d696efe503ac32c9e6b4273c962e62c445ea3c8f387e7cc9a5a80ccd48
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6979706fe93d8137b17f7e6f32db667420fca3aae54a413038db8105f72cb3ee
+oid sha256:d99fa14c8acde40a884e28237faba4be234701ffedd754358d1c32976d05cfde
 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": 6.834086894989014,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.10575296108291032,
+  "epoch": 0.15016920473773265,
   "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": 1765.963,
       "eval_steps_per_second": 105.958,
       "step": 50
+    },
+    {
+      "epoch": 0.10786802030456853,
+      "grad_norm": 0.13285735249519348,
+      "learning_rate": 8.220898871169827e-05,
+      "loss": 6.8746,
+      "step": 51
+    },
+    {
+      "epoch": 0.10998307952622674,
+      "grad_norm": 0.13434718549251556,
+      "learning_rate": 7.744141792252794e-05,
+      "loss": 6.8609,
+      "step": 52
+    },
+    {
+      "epoch": 0.11209813874788493,
+      "grad_norm": 0.11735495179891586,
+      "learning_rate": 7.285532566548172e-05,
+      "loss": 6.8562,
+      "step": 53
+    },
+    {
+      "epoch": 0.11421319796954314,
+      "grad_norm": 0.11429435014724731,
+      "learning_rate": 6.846021731708856e-05,
+      "loss": 6.8485,
+      "step": 54
+    },
+    {
+      "epoch": 0.11632825719120135,
+      "grad_norm": 0.11410648375749588,
+      "learning_rate": 6.426520241056245e-05,
+      "loss": 6.8427,
+      "step": 55
+    },
+    {
+      "epoch": 0.11844331641285956,
+      "grad_norm": 0.11699143052101135,
+      "learning_rate": 6.0278975754903317e-05,
+      "loss": 6.8345,
+      "step": 56
+    },
+    {
+      "epoch": 0.12055837563451777,
+      "grad_norm": 0.12481831759214401,
+      "learning_rate": 5.6509799413577934e-05,
+      "loss": 6.8253,
+      "step": 57
+    },
+    {
+      "epoch": 0.12267343485617598,
+      "grad_norm": 0.11899716407060623,
+      "learning_rate": 5.296548558013161e-05,
+      "loss": 6.8305,
+      "step": 58
+    },
+    {
+      "epoch": 0.12478849407783418,
+      "grad_norm": 0.13607801496982574,
+      "learning_rate": 4.9653380386224046e-05,
+      "loss": 6.8211,
+      "step": 59
+    },
+    {
+      "epoch": 0.12690355329949238,
+      "grad_norm": 0.12612339854240417,
+      "learning_rate": 4.658034867564977e-05,
+      "loss": 6.8198,
+      "step": 60
+    },
+    {
+      "epoch": 0.1290186125211506,
+      "grad_norm": 0.1588858664035797,
+      "learning_rate": 4.375275977590104e-05,
+      "loss": 6.8081,
+      "step": 61
+    },
+    {
+      "epoch": 0.1311336717428088,
+      "grad_norm": 0.17566712200641632,
+      "learning_rate": 4.117647429676387e-05,
+      "loss": 6.7919,
+      "step": 62
+    },
+    {
+      "epoch": 0.13324873096446702,
+      "grad_norm": 0.13542258739471436,
+      "learning_rate": 3.885683198330941e-05,
+      "loss": 6.8634,
+      "step": 63
+    },
+    {
+      "epoch": 0.1353637901861252,
+      "grad_norm": 0.1318742036819458,
+      "learning_rate": 3.679864064845691e-05,
+      "loss": 6.8648,
+      "step": 64
+    },
+    {
+      "epoch": 0.1374788494077834,
+      "grad_norm": 0.11358034610748291,
+      "learning_rate": 3.500616620804712e-05,
+      "loss": 6.8556,
+      "step": 65
+    },
+    {
+      "epoch": 0.13959390862944163,
+      "grad_norm": 0.12224390357732773,
+      "learning_rate": 3.348312383908033e-05,
+      "loss": 6.8466,
+      "step": 66
+    },
+    {
+      "epoch": 0.14170896785109982,
+      "grad_norm": 0.10986880213022232,
+      "learning_rate": 3.223267027944483e-05,
+      "loss": 6.8404,
+      "step": 67
+    },
+    {
+      "epoch": 0.14382402707275804,
+      "grad_norm": 0.11291032284498215,
+      "learning_rate": 3.125739728509535e-05,
+      "loss": 6.835,
+      "step": 68
+    },
+    {
+      "epoch": 0.14593908629441624,
+      "grad_norm": 0.12116565555334091,
+      "learning_rate": 3.055932625824328e-05,
+      "loss": 6.8245,
+      "step": 69
+    },
+    {
+      "epoch": 0.14805414551607446,
+      "grad_norm": 0.12444450706243515,
+      "learning_rate": 3.0139904057691777e-05,
+      "loss": 6.8277,
+      "step": 70
+    },
+    {
+      "epoch": 0.15016920473773265,
+      "grad_norm": 0.13196779787540436,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 6.8199,
+      "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": 5349335040000.0,
+  "total_flos": 7596055756800.0,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null