Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d8e5f76396d65fd18e899df4aa66616717d19500caba77bb0da827769391c3
+oid sha256:29948979b97fd2e475bdae791a266d3d4f3abb3d6e3b9e8a04bb3374afcc7f22
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff372d12c70ce5d4cf293ee43211d9f6a9341c85b0b82f61cc222e0f3cc22d1
+oid sha256:b4e70f9eef38d627b87ab03abddefcc9ef19b4e98fe329a0a42e7c8a314568f6
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4216d775bbea8abd1a026545913af74ad5ad66158e4f5daceda9966e1a61a061
+oid sha256:d97d7669cc5080425b2c591693547e485768bd58c1ab978d69a0058c00e37d9c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3473916053771973,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.00408313257931485,
+  "best_metric": 1.2520782947540283,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0081662651586297,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 13.816,
       "eval_steps_per_second": 6.908,
       "step": 25
+    },
+    {
+      "epoch": 0.004246457882487445,
+      "grad_norm": 0.9192604422569275,
+      "learning_rate": 0.0001,
+      "loss": 1.182,
+      "step": 26
+    },
+    {
+      "epoch": 0.004409783185660038,
+      "grad_norm": 0.9144134521484375,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.1901,
+      "step": 27
+    },
+    {
+      "epoch": 0.0045731084888326326,
+      "grad_norm": 0.9117483496665955,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.1575,
+      "step": 28
+    },
+    {
+      "epoch": 0.004736433792005226,
+      "grad_norm": 1.0398228168487549,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.2178,
+      "step": 29
+    },
+    {
+      "epoch": 0.0048997590951778205,
+      "grad_norm": 0.9837586283683777,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.016,
+      "step": 30
+    },
+    {
+      "epoch": 0.005063084398350414,
+      "grad_norm": 1.0707706212997437,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.3534,
+      "step": 31
+    },
+    {
+      "epoch": 0.0052264097015230085,
+      "grad_norm": 1.2883225679397583,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.2281,
+      "step": 32
+    },
+    {
+      "epoch": 0.005389735004695602,
+      "grad_norm": 0.973362386226654,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 1.0841,
+      "step": 33
+    },
+    {
+      "epoch": 0.0055530603078681965,
+      "grad_norm": 1.18382728099823,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.2332,
+      "step": 34
+    },
+    {
+      "epoch": 0.005716385611040791,
+      "grad_norm": 1.353372573852539,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.2308,
+      "step": 35
+    },
+    {
+      "epoch": 0.0058797109142133845,
+      "grad_norm": 1.5076109170913696,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.3734,
+      "step": 36
+    },
+    {
+      "epoch": 0.006043036217385979,
+      "grad_norm": 1.4926120042800903,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.2896,
+      "step": 37
+    },
+    {
+      "epoch": 0.0062063615205585725,
+      "grad_norm": 1.3520236015319824,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.2777,
+      "step": 38
+    },
+    {
+      "epoch": 0.006369686823731167,
+      "grad_norm": 1.809522032737732,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 1.2962,
+      "step": 39
+    },
+    {
+      "epoch": 0.0065330121269037604,
+      "grad_norm": 1.8173556327819824,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.5552,
+      "step": 40
+    },
+    {
+      "epoch": 0.006696337430076355,
+      "grad_norm": 2.030938148498535,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.5041,
+      "step": 41
+    },
+    {
+      "epoch": 0.006859662733248948,
+      "grad_norm": 2.2760345935821533,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.502,
+      "step": 42
+    },
+    {
+      "epoch": 0.007022988036421543,
+      "grad_norm": 3.6226515769958496,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 1.8339,
+      "step": 43
+    },
+    {
+      "epoch": 0.007186313339594136,
+      "grad_norm": 3.4638423919677734,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.6236,
+      "step": 44
+    },
+    {
+      "epoch": 0.007349638642766731,
+      "grad_norm": 5.1530442237854,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 1.895,
+      "step": 45
+    },
+    {
+      "epoch": 0.007512963945939324,
+      "grad_norm": 4.3372578620910645,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.6363,
+      "step": 46
+    },
+    {
+      "epoch": 0.007676289249111919,
+      "grad_norm": 4.029924392700195,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 1.799,
+      "step": 47
+    },
+    {
+      "epoch": 0.007839614552284513,
+      "grad_norm": 6.649318218231201,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.1027,
+      "step": 48
+    },
+    {
+      "epoch": 0.008002939855457107,
+      "grad_norm": 7.667248249053955,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 2.1851,
+      "step": 49
+    },
+    {
+      "epoch": 0.0081662651586297,
+      "grad_norm": 9.058297157287598,
+      "learning_rate": 0.0,
+      "loss": 2.5236,
+      "step": 50
+    },
+    {
+      "epoch": 0.0081662651586297,
+      "eval_loss": 1.2520782947540283,
+      "eval_runtime": 186.6215,
+      "eval_samples_per_second": 13.814,
+      "eval_steps_per_second": 6.907,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5146843860172800.0,
+  "total_flos": 1.02936877203456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null