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:bf76adca4a35388dc3625005ef5dbe86610f32030b56d07c31d9de8c7b56b7d7
+oid sha256:a7095a0035d9aa88a5d01c3464c81067f9975022bc9e9027038a35f32a0a42e3
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c15839ca5f44f682b4c0f0eab9fc308d3cd7c05fe2f42cb28127c72ad2d3bc1c
+oid sha256:b55f5c07e52fea4dbcc00cae77f1ed3688955702d205a2a9080450760bdcb059
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c86e3f82aea950556f1ba645e98248bc4f70c3775621dcc8998c0f9bef8d50
+oid sha256:8275bf410637fa45b6a9421edf225a2ed7c4b8844d7881ec7ddd304b1ff880a0
 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": 0.37796109914779663,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0028715828164484264,
+  "best_metric": 0.3237687349319458,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.005743165632896853,
   "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": 23.615,
       "eval_steps_per_second": 2.952,
       "step": 25
+    },
+    {
+      "epoch": 0.0029864461291063634,
+      "grad_norm": 2.292692184448242,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.4062,
+      "step": 26
+    },
+    {
+      "epoch": 0.0031013094417643005,
+      "grad_norm": 2.8349287509918213,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.679,
+      "step": 27
+    },
+    {
+      "epoch": 0.0032161727544222376,
+      "grad_norm": 2.254132032394409,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.5455,
+      "step": 28
+    },
+    {
+      "epoch": 0.0033310360670801746,
+      "grad_norm": 2.188596248626709,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.591,
+      "step": 29
+    },
+    {
+      "epoch": 0.0034458993797381117,
+      "grad_norm": 1.725136399269104,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.467,
+      "step": 30
+    },
+    {
+      "epoch": 0.003560762692396049,
+      "grad_norm": 1.6573512554168701,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.4838,
+      "step": 31
+    },
+    {
+      "epoch": 0.003675626005053986,
+      "grad_norm": 2.2952048778533936,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.5725,
+      "step": 32
+    },
+    {
+      "epoch": 0.003790489317711923,
+      "grad_norm": 1.939889907836914,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.6289,
+      "step": 33
+    },
+    {
+      "epoch": 0.00390535263036986,
+      "grad_norm": 1.8188632726669312,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.3653,
+      "step": 34
+    },
+    {
+      "epoch": 0.004020215943027797,
+      "grad_norm": 2.1988892555236816,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6012,
+      "step": 35
+    },
+    {
+      "epoch": 0.004135079255685734,
+      "grad_norm": 2.2693634033203125,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.5576,
+      "step": 36
+    },
+    {
+      "epoch": 0.004249942568343671,
+      "grad_norm": 1.932142734527588,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.3468,
+      "step": 37
+    },
+    {
+      "epoch": 0.004364805881001608,
+      "grad_norm": 3.0825328826904297,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.333,
+      "step": 38
+    },
+    {
+      "epoch": 0.004479669193659545,
+      "grad_norm": 1.783441424369812,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.1038,
+      "step": 39
+    },
+    {
+      "epoch": 0.004594532506317482,
+      "grad_norm": 1.5691484212875366,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.1039,
+      "step": 40
+    },
+    {
+      "epoch": 0.0047093958189754195,
+      "grad_norm": 1.9904344081878662,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.3097,
+      "step": 41
+    },
+    {
+      "epoch": 0.004824259131633356,
+      "grad_norm": 2.1154487133026123,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.5107,
+      "step": 42
+    },
+    {
+      "epoch": 0.004939122444291294,
+      "grad_norm": 1.9345293045043945,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.3873,
+      "step": 43
+    },
+    {
+      "epoch": 0.00505398575694923,
+      "grad_norm": 1.7051095962524414,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.3449,
+      "step": 44
+    },
+    {
+      "epoch": 0.005168849069607168,
+      "grad_norm": 1.8302801847457886,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.483,
+      "step": 45
+    },
+    {
+      "epoch": 0.005283712382265104,
+      "grad_norm": 1.9598950147628784,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3838,
+      "step": 46
+    },
+    {
+      "epoch": 0.005398575694923042,
+      "grad_norm": 1.9354257583618164,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.422,
+      "step": 47
+    },
+    {
+      "epoch": 0.005513439007580979,
+      "grad_norm": 2.225748062133789,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.5035,
+      "step": 48
+    },
+    {
+      "epoch": 0.005628302320238916,
+      "grad_norm": 1.9461932182312012,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.1787,
+      "step": 49
+    },
+    {
+      "epoch": 0.005743165632896853,
+      "grad_norm": 1.6582098007202148,
+      "learning_rate": 0.0,
+      "loss": 1.359,
+      "step": 50
+    },
+    {
+      "epoch": 0.005743165632896853,
+      "eval_loss": 0.3237687349319458,
+      "eval_runtime": 620.993,
+      "eval_samples_per_second": 23.612,
+      "eval_steps_per_second": 2.952,
+      "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": 1.78874751123456e+16,
+  "total_flos": 3.57749502246912e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null