Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58fff64a84d6cd7b07ee217121a9891a92a36327487e6f983259ecff03c6f596
+oid sha256:bc4f3d7eb9363f1513c93fb72f8d8fc251a8e3e3a2d87ac8ef99121aaba703a5
 size 800116456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebe8ff515da2071fd982917b3b86e2afd861758cd552bc44071c0935d2a2a8dc
+oid sha256:0a7ee491ce55e97bbf32cdfe7424de50b50d9467b72e27e0214c56842ed0d83a
 size 406743412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c85d9288c51eaa7d2c1111e01e6d9ee843f460e8a388a3fd01a7ff38de7a191
+oid sha256:83d93fed6efecf1ebac1b8d0693a14b59f022796240821fda02be65ed6b0b803
 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": 1.4752330780029297,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03346720214190094,
+  "best_metric": 1.404244303703308,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06693440428380187,
   "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": 17.366,
       "eval_steps_per_second": 2.181,
       "step": 25
+    },
+    {
+      "epoch": 0.03480589022757698,
+      "grad_norm": 1.196060299873352,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.0636,
+      "step": 26
+    },
+    {
+      "epoch": 0.03614457831325301,
+      "grad_norm": 1.449025273323059,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.1377,
+      "step": 27
+    },
+    {
+      "epoch": 0.03748326639892905,
+      "grad_norm": 1.8445948362350464,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.2107,
+      "step": 28
+    },
+    {
+      "epoch": 0.038821954484605084,
+      "grad_norm": 1.9364060163497925,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.4555,
+      "step": 29
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "grad_norm": 2.409740447998047,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.6639,
+      "step": 30
+    },
+    {
+      "epoch": 0.041499330655957165,
+      "grad_norm": 2.1676015853881836,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.3554,
+      "step": 31
+    },
+    {
+      "epoch": 0.0428380187416332,
+      "grad_norm": 2.1554808616638184,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3832,
+      "step": 32
+    },
+    {
+      "epoch": 0.04417670682730924,
+      "grad_norm": 2.084815740585327,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.4907,
+      "step": 33
+    },
+    {
+      "epoch": 0.04551539491298527,
+      "grad_norm": 2.2933266162872314,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.5189,
+      "step": 34
+    },
+    {
+      "epoch": 0.04685408299866131,
+      "grad_norm": 2.28518009185791,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5068,
+      "step": 35
+    },
+    {
+      "epoch": 0.04819277108433735,
+      "grad_norm": 2.2734827995300293,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.5619,
+      "step": 36
+    },
+    {
+      "epoch": 0.049531459170013385,
+      "grad_norm": 2.4875550270080566,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.6357,
+      "step": 37
+    },
+    {
+      "epoch": 0.050870147255689425,
+      "grad_norm": 2.4092066287994385,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.6984,
+      "step": 38
+    },
+    {
+      "epoch": 0.05220883534136546,
+      "grad_norm": 2.840477466583252,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.5653,
+      "step": 39
+    },
+    {
+      "epoch": 0.0535475234270415,
+      "grad_norm": 2.624983310699463,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.702,
+      "step": 40
+    },
+    {
+      "epoch": 0.05488621151271754,
+      "grad_norm": 2.8492836952209473,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6325,
+      "step": 41
+    },
+    {
+      "epoch": 0.05622489959839357,
+      "grad_norm": 3.2326295375823975,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.8388,
+      "step": 42
+    },
+    {
+      "epoch": 0.05756358768406961,
+      "grad_norm": 4.206023216247559,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.9769,
+      "step": 43
+    },
+    {
+      "epoch": 0.058902275769745646,
+      "grad_norm": 5.246030330657959,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.1044,
+      "step": 44
+    },
+    {
+      "epoch": 0.060240963855421686,
+      "grad_norm": 8.100854873657227,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.7415,
+      "step": 45
+    },
+    {
+      "epoch": 0.06157965194109773,
+      "grad_norm": 7.93204927444458,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.3497,
+      "step": 46
+    },
+    {
+      "epoch": 0.06291834002677377,
+      "grad_norm": 9.60119915008545,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.1179,
+      "step": 47
+    },
+    {
+      "epoch": 0.0642570281124498,
+      "grad_norm": 9.609639167785645,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.4892,
+      "step": 48
+    },
+    {
+      "epoch": 0.06559571619812583,
+      "grad_norm": 10.633676528930664,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.7826,
+      "step": 49
+    },
+    {
+      "epoch": 0.06693440428380187,
+      "grad_norm": 20.666841506958008,
+      "learning_rate": 0.0,
+      "loss": 3.1652,
+      "step": 50
+    },
+    {
+      "epoch": 0.06693440428380187,
+      "eval_loss": 1.404244303703308,
+      "eval_runtime": 72.11,
+      "eval_samples_per_second": 17.446,
+      "eval_steps_per_second": 2.191,
+      "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": 3.0679414421323776e+16,
+  "total_flos": 5.022044271516058e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null