Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d72bc4b12e41e8394fa39eb86a92fb8b6c9aaebb11d7e6fab4dabb2f60b12fd
+oid sha256:9869c08c651fa62549d5ef6b5a5ef6f676e756b7a9c7e36f4450d2f0cd452db9
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5504d3c6426ec82a0cd7c24935a8ee6516dac471270d443d6f322aef4492ceca
+oid sha256:c2fd26d65f94271f27a0bdcf0c4b1b0050e808ea0388b679ecce425cf3618dda
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2def1ed023b621e15f9f9ba82387ae0ed5bf28abd69f693488a33419d7a23f09
+oid sha256:a435603993625db467ca78e20b490633c15a1122602231067af9c7b3297d541c
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:879f65aeef29dffdc7242cd3b7be474ded6a08f609cdf7cc3dec50478a94c787
+oid sha256:5bbd3de6e12f9c37a3f0f0411087445a602a0a4b727a9e0c94fc533f18e82fcd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3600f9553dd7e1ac036da32b7b366bbcdc674be992cee46e19420025a82dedc6
+oid sha256:543e99892d23e062aa14f5158e25bf6550db4d6d0e1b1414568f33293b7e5abc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a66bcfba35f9e3dcc1d9dea2eef4912ff5ab198a9fa3acdf189b220d899ebe8f
+oid sha256:6e0a8e2e33b66eb835d32e20eae1005a4d59f3e0488e7c85bde14ccbbc0935ab
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
+oid sha256:1fd9769bcb04586b7ead175b588f12a0bbbeba72d5f308b868ba8f36b77aa801
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.36422646045684814,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.30441400304414,
+  "epoch": 0.38559107052257735,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,146 @@
       "eval_samples_per_second": 14.251,
       "eval_steps_per_second": 3.705,
       "step": 75
+    },
+    {
+      "epoch": 0.3084728564180619,
+      "grad_norm": 0.09115864336490631,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 0.2235,
+      "step": 76
+    },
+    {
+      "epoch": 0.31253170979198375,
+      "grad_norm": 0.1393779069185257,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 0.3149,
+      "step": 77
+    },
+    {
+      "epoch": 0.3165905631659056,
+      "grad_norm": 0.14699040353298187,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 0.3251,
+      "step": 78
+    },
+    {
+      "epoch": 0.3206494165398275,
+      "grad_norm": 0.1531774252653122,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 0.3349,
+      "step": 79
+    },
+    {
+      "epoch": 0.32470826991374935,
+      "grad_norm": 0.1625107377767563,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 0.3474,
+      "step": 80
+    },
+    {
+      "epoch": 0.3287671232876712,
+      "grad_norm": 0.1845567524433136,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 0.3567,
+      "step": 81
+    },
+    {
+      "epoch": 0.3328259766615931,
+      "grad_norm": 0.18067772686481476,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 0.3791,
+      "step": 82
+    },
+    {
+      "epoch": 0.33688483003551495,
+      "grad_norm": 0.20357079803943634,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 0.3848,
+      "step": 83
+    },
+    {
+      "epoch": 0.3409436834094368,
+      "grad_norm": 0.20797663927078247,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 0.3734,
+      "step": 84
+    },
+    {
+      "epoch": 0.3450025367833587,
+      "grad_norm": 0.23876087367534637,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 0.4123,
+      "step": 85
+    },
+    {
+      "epoch": 0.34906139015728055,
+      "grad_norm": 0.2859575152397156,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 0.4115,
+      "step": 86
+    },
+    {
+      "epoch": 0.3531202435312024,
+      "grad_norm": 0.3142327666282654,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 0.3819,
+      "step": 87
+    },
+    {
+      "epoch": 0.3571790969051243,
+      "grad_norm": 0.10286320745944977,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 0.179,
+      "step": 88
+    },
+    {
+      "epoch": 0.36123795027904615,
+      "grad_norm": 0.1432906836271286,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 0.3092,
+      "step": 89
+    },
+    {
+      "epoch": 0.365296803652968,
+      "grad_norm": 0.15591755509376526,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 0.3168,
+      "step": 90
+    },
+    {
+      "epoch": 0.3693556570268899,
+      "grad_norm": 0.16477596759796143,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 0.3352,
+      "step": 91
+    },
+    {
+      "epoch": 0.37341451040081175,
+      "grad_norm": 0.16704893112182617,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 0.3432,
+      "step": 92
+    },
+    {
+      "epoch": 0.3774733637747336,
+      "grad_norm": 0.1805972009897232,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 0.3548,
+      "step": 93
+    },
+    {
+      "epoch": 0.3815322171486555,
+      "grad_norm": 0.1912754327058792,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 0.3728,
+      "step": 94
+    },
+    {
+      "epoch": 0.38559107052257735,
+      "grad_norm": 0.1889467090368271,
+      "learning_rate": 1e-05,
+      "loss": 0.3875,
+      "step": 95
     }
   ],
   "logging_steps": 1,
@@ -587,12 +727,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.963315576717967e+17,
+  "total_flos": 1.1352414048768492e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null