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:e50c9ea40e73cb0b690e2f963acdec0d039ed19010ce16e88025cb30d92f3ed5
+oid sha256:e6ed7f0ea796d82f96181059a9b40ed82d7120ef2c3f9ca6e08f45d707f4141a
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a441e59e584bf9452f62e9244cbf369c81a8b037427917d90b0c35ba8c4ede3c
+oid sha256:b7a0f6185f581a1ee93042f39a244eb08d08e869015bb80306d0f5dace7bc219
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6998de8c7c774f27d8322f18ed12d9bbee0f042a23951c79f4a08bd2d3f9914
+oid sha256:ea9e8c14f6fdf664533c56e924e9745aea5a865b204155096f1f12d310d3a970
 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": 0.2671048045158386,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.18148820326678766,
+  "best_metric": 0.0873224139213562,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3629764065335753,
   "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": 16.121,
       "eval_steps_per_second": 2.015,
       "step": 25
+    },
+    {
+      "epoch": 0.18874773139745918,
+      "grad_norm": 12.08178997039795,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.8011,
+      "step": 26
+    },
+    {
+      "epoch": 0.19600725952813067,
+      "grad_norm": 6.6806440353393555,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.6513,
+      "step": 27
+    },
+    {
+      "epoch": 0.20326678765880218,
+      "grad_norm": 5.073172092437744,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.3096,
+      "step": 28
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 9.08521842956543,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.8236,
+      "step": 29
+    },
+    {
+      "epoch": 0.2177858439201452,
+      "grad_norm": 8.419458389282227,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.7502,
+      "step": 30
+    },
+    {
+      "epoch": 0.2250453720508167,
+      "grad_norm": 13.598421096801758,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.3274,
+      "step": 31
+    },
+    {
+      "epoch": 0.2323049001814882,
+      "grad_norm": 17.529741287231445,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.9063,
+      "step": 32
+    },
+    {
+      "epoch": 0.2395644283121597,
+      "grad_norm": 22.427534103393555,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.4676,
+      "step": 33
+    },
+    {
+      "epoch": 0.24682395644283123,
+      "grad_norm": 11.120813369750977,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.2306,
+      "step": 34
+    },
+    {
+      "epoch": 0.2540834845735027,
+      "grad_norm": 66.51551818847656,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1779,
+      "step": 35
+    },
+    {
+      "epoch": 0.2613430127041742,
+      "grad_norm": 25.5261287689209,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.3193,
+      "step": 36
+    },
+    {
+      "epoch": 0.26860254083484575,
+      "grad_norm": 17.919849395751953,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.2592,
+      "step": 37
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 19.765296936035156,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.2518,
+      "step": 38
+    },
+    {
+      "epoch": 0.2831215970961887,
+      "grad_norm": 18.46579933166504,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8273,
+      "step": 39
+    },
+    {
+      "epoch": 0.29038112522686027,
+      "grad_norm": 15.463048934936523,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.4909,
+      "step": 40
+    },
+    {
+      "epoch": 0.29764065335753176,
+      "grad_norm": 5.132680416107178,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.359,
+      "step": 41
+    },
+    {
+      "epoch": 0.30490018148820325,
+      "grad_norm": 3.2728233337402344,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.2565,
+      "step": 42
+    },
+    {
+      "epoch": 0.3121597096188748,
+      "grad_norm": 3.4045944213867188,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.1952,
+      "step": 43
+    },
+    {
+      "epoch": 0.3194192377495463,
+      "grad_norm": 8.596439361572266,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.7799,
+      "step": 44
+    },
+    {
+      "epoch": 0.32667876588021777,
+      "grad_norm": 4.2560038566589355,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2737,
+      "step": 45
+    },
+    {
+      "epoch": 0.3339382940108893,
+      "grad_norm": 3.327805757522583,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.238,
+      "step": 46
+    },
+    {
+      "epoch": 0.3411978221415608,
+      "grad_norm": 4.551213264465332,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3053,
+      "step": 47
+    },
+    {
+      "epoch": 0.3484573502722323,
+      "grad_norm": 3.6048531532287598,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.2353,
+      "step": 48
+    },
+    {
+      "epoch": 0.35571687840290384,
+      "grad_norm": 4.764666557312012,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.3829,
+      "step": 49
+    },
+    {
+      "epoch": 0.3629764065335753,
+      "grad_norm": 5.7592291831970215,
+      "learning_rate": 0.0,
+      "loss": 0.3659,
+      "step": 50
+    },
+    {
+      "epoch": 0.3629764065335753,
+      "eval_loss": 0.0873224139213562,
+      "eval_runtime": 14.3869,
+      "eval_samples_per_second": 16.126,
+      "eval_steps_per_second": 2.016,
+      "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": 3.4179843562143744e+16,
+  "total_flos": 6.352798148984832e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null