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:f6cb7572afb482bb914ca604b6ef75b0b4bd6ea0b70903a29b52f91df6b40961
+oid sha256:9b482a78f8886307d07becfa8ae0bfa1a89b4aa211294530cc0794cab9049fd3
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf3a02498f3f946029f33fd597743ade2902ef5cdf01a575aa26cdcce2a3cd0
+oid sha256:1aa7c8594350a93acb5162710cc7bb068c236b1408907dda1e0ecc071acaeb81
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfb9bd1fbbe29ef5d7f537a8f6fe881daff9640214f599a1a2e16fb2e64c79e4
+oid sha256:0c4d52dc7cec8cee8076738848352abd3041bd28d0b53353e4c66b37691fe351
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1ad02031e3fa04c85d76eb5243159ea466a6ffaca547e141c6735c32bb4ec7
+oid sha256:c81b926d0ec8a0251e8a367496b8a801bf203cdf8684ce1adb738ab4029cdaf7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46075205bb485f8bef9968980e7ddd9ad6acb4d75079254578499e5639d476d7
+oid sha256:4becfeded40b9c512755ac5fe999d2b946accf88574ee43e878b42074188cbfe
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db39a627553af76ab2ddfd9688cdc46f1ec9e0d8f8f02955d8fa2a50542139cd
+oid sha256:2747fd36941f2e74668a584854ce75c3fdcf2eb0e9a016ef7c1ac282e9c9a601
 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": 0.4174307584762573,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.04538852578068264,
+  "epoch": 0.06445170660856936,
   "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": 90.651,
       "eval_steps_per_second": 5.439,
       "step": 50
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 1.3294329643249512,
+      "learning_rate": 8.220898871169827e-05,
+      "loss": 0.4636,
+      "step": 51
+    },
+    {
+      "epoch": 0.04720406681190995,
+      "grad_norm": 2.0037238597869873,
+      "learning_rate": 7.744141792252794e-05,
+      "loss": 0.4724,
+      "step": 52
+    },
+    {
+      "epoch": 0.0481118373275236,
+      "grad_norm": 1.1318916082382202,
+      "learning_rate": 7.285532566548172e-05,
+      "loss": 0.4087,
+      "step": 53
+    },
+    {
+      "epoch": 0.049019607843137254,
+      "grad_norm": 1.4578465223312378,
+      "learning_rate": 6.846021731708856e-05,
+      "loss": 0.4232,
+      "step": 54
+    },
+    {
+      "epoch": 0.049927378358750905,
+      "grad_norm": 1.3899105787277222,
+      "learning_rate": 6.426520241056245e-05,
+      "loss": 0.4321,
+      "step": 55
+    },
+    {
+      "epoch": 0.050835148874364564,
+      "grad_norm": 2.062777280807495,
+      "learning_rate": 6.0278975754903317e-05,
+      "loss": 0.4482,
+      "step": 56
+    },
+    {
+      "epoch": 0.051742919389978215,
+      "grad_norm": 1.4643654823303223,
+      "learning_rate": 5.6509799413577934e-05,
+      "loss": 0.4259,
+      "step": 57
+    },
+    {
+      "epoch": 0.052650689905591866,
+      "grad_norm": 0.6832600831985474,
+      "learning_rate": 5.296548558013161e-05,
+      "loss": 0.3983,
+      "step": 58
+    },
+    {
+      "epoch": 0.05355846042120552,
+      "grad_norm": 1.1169804334640503,
+      "learning_rate": 4.9653380386224046e-05,
+      "loss": 0.4179,
+      "step": 59
+    },
+    {
+      "epoch": 0.054466230936819175,
+      "grad_norm": 0.9044225215911865,
+      "learning_rate": 4.658034867564977e-05,
+      "loss": 0.4399,
+      "step": 60
+    },
+    {
+      "epoch": 0.055374001452432826,
+      "grad_norm": 1.9690494537353516,
+      "learning_rate": 4.375275977590104e-05,
+      "loss": 0.4101,
+      "step": 61
+    },
+    {
+      "epoch": 0.05628177196804648,
+      "grad_norm": 1.005382776260376,
+      "learning_rate": 4.117647429676387e-05,
+      "loss": 0.4439,
+      "step": 62
+    },
+    {
+      "epoch": 0.05718954248366013,
+      "grad_norm": 0.960736870765686,
+      "learning_rate": 3.885683198330941e-05,
+      "loss": 0.4619,
+      "step": 63
+    },
+    {
+      "epoch": 0.05809731299927379,
+      "grad_norm": 2.0352001190185547,
+      "learning_rate": 3.679864064845691e-05,
+      "loss": 0.4336,
+      "step": 64
+    },
+    {
+      "epoch": 0.05900508351488744,
+      "grad_norm": 1.5896925926208496,
+      "learning_rate": 3.500616620804712e-05,
+      "loss": 0.4203,
+      "step": 65
+    },
+    {
+      "epoch": 0.05991285403050109,
+      "grad_norm": 1.4820246696472168,
+      "learning_rate": 3.348312383908033e-05,
+      "loss": 0.448,
+      "step": 66
+    },
+    {
+      "epoch": 0.06082062454611474,
+      "grad_norm": 1.3695192337036133,
+      "learning_rate": 3.223267027944483e-05,
+      "loss": 0.4138,
+      "step": 67
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 0.8941169381141663,
+      "learning_rate": 3.125739728509535e-05,
+      "loss": 0.4117,
+      "step": 68
+    },
+    {
+      "epoch": 0.06263616557734204,
+      "grad_norm": 1.1938544511795044,
+      "learning_rate": 3.055932625824328e-05,
+      "loss": 0.3943,
+      "step": 69
+    },
+    {
+      "epoch": 0.0635439360929557,
+      "grad_norm": 1.3432084321975708,
+      "learning_rate": 3.0139904057691777e-05,
+      "loss": 0.4143,
+      "step": 70
+    },
+    {
+      "epoch": 0.06445170660856936,
+      "grad_norm": 1.550041913986206,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 0.4373,
+      "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": 7.81327834021888e+16,
+  "total_flos": 1.109485524311081e+17,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null