Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:322efbfc2826cd8284d6a167aa1381b7179f9c165e9d594163c90e9f2868facd
+oid sha256:1288e74bf85ba3ac1355a2a7c6109043e39e91991d013a108f71348232e2a8e4
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aee1cf7699e161e1abd54b23abaa03c5c617fc9908c7262309ca54975ae13233
+oid sha256:84e55f669db5ead97536ade25e7d9c0e1403a879eab92ea4b9570a6a492831cc
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d561b3ef7ee9b81d79b5719a65ce49d5b209cf2f4ef7bd942f690a989aa0c5d
+oid sha256:fe8575f5e3996fc878ec799488c71c97da751188021128f90d1a6227e39f6286
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8236191272735596,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.042034468263976464,
+  "best_metric": 1.7662628889083862,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08406893652795293,
   "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": 18.517,
       "eval_steps_per_second": 2.328,
       "step": 25
+    },
+    {
+      "epoch": 0.04371584699453552,
+      "grad_norm": 5.956356048583984,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.0353,
+      "step": 26
+    },
+    {
+      "epoch": 0.04539722572509458,
+      "grad_norm": 4.612515449523926,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.6238,
+      "step": 27
+    },
+    {
+      "epoch": 0.047078604455653636,
+      "grad_norm": 4.8809123039245605,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.9787,
+      "step": 28
+    },
+    {
+      "epoch": 0.0487599831862127,
+      "grad_norm": 3.906742811203003,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.485,
+      "step": 29
+    },
+    {
+      "epoch": 0.05044136191677175,
+      "grad_norm": 4.447406768798828,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.7703,
+      "step": 30
+    },
+    {
+      "epoch": 0.052122740647330815,
+      "grad_norm": 4.723405361175537,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.8074,
+      "step": 31
+    },
+    {
+      "epoch": 0.05380411937788987,
+      "grad_norm": 4.21617317199707,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.551,
+      "step": 32
+    },
+    {
+      "epoch": 0.05548549810844893,
+      "grad_norm": 4.369323253631592,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.7616,
+      "step": 33
+    },
+    {
+      "epoch": 0.057166876839007986,
+      "grad_norm": 4.459974765777588,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.6983,
+      "step": 34
+    },
+    {
+      "epoch": 0.05884825556956705,
+      "grad_norm": 4.366460800170898,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.511,
+      "step": 35
+    },
+    {
+      "epoch": 0.0605296343001261,
+      "grad_norm": 4.228405952453613,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.783,
+      "step": 36
+    },
+    {
+      "epoch": 0.062211013030685165,
+      "grad_norm": 5.334435939788818,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.7047,
+      "step": 37
+    },
+    {
+      "epoch": 0.06389239176124423,
+      "grad_norm": 4.155223846435547,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.5862,
+      "step": 38
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 4.632593154907227,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8208,
+      "step": 39
+    },
+    {
+      "epoch": 0.06725514922236234,
+      "grad_norm": 3.9671783447265625,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.5067,
+      "step": 40
+    },
+    {
+      "epoch": 0.06893652795292139,
+      "grad_norm": 4.850368022918701,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6973,
+      "step": 41
+    },
+    {
+      "epoch": 0.07061790668348046,
+      "grad_norm": 4.238636016845703,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.475,
+      "step": 42
+    },
+    {
+      "epoch": 0.07229928541403952,
+      "grad_norm": 4.3667311668396,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.7199,
+      "step": 43
+    },
+    {
+      "epoch": 0.07398066414459857,
+      "grad_norm": 4.188448429107666,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.6647,
+      "step": 44
+    },
+    {
+      "epoch": 0.07566204287515763,
+      "grad_norm": 4.366857528686523,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.5364,
+      "step": 45
+    },
+    {
+      "epoch": 0.0773434216057167,
+      "grad_norm": 3.411229372024536,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.2497,
+      "step": 46
+    },
+    {
+      "epoch": 0.07902480033627575,
+      "grad_norm": 4.079202651977539,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.5037,
+      "step": 47
+    },
+    {
+      "epoch": 0.0807061790668348,
+      "grad_norm": 4.219734191894531,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.255,
+      "step": 48
+    },
+    {
+      "epoch": 0.08238755779739386,
+      "grad_norm": 4.017161846160889,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.2695,
+      "step": 49
+    },
+    {
+      "epoch": 0.08406893652795293,
+      "grad_norm": 4.850399017333984,
+      "learning_rate": 0.0,
+      "loss": 1.3426,
+      "step": 50
+    },
+    {
+      "epoch": 0.08406893652795293,
+      "eval_loss": 1.7662628889083862,
+      "eval_runtime": 54.1007,
+      "eval_samples_per_second": 18.521,
+      "eval_steps_per_second": 2.329,
+      "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": 3.02966221307904e+16,
+  "total_flos": 4.86582113009664e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null