Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c28ea5300e575415540bb1ba14ca047552236041b5d4d048f271dbc1cccdfd05
+oid sha256:572298944eb8899cb0e879c2b7f626ccebe8627eca7b205c52d57b8e8f7023c2
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d504d67e81e8461b651ab3df2ef386f69ac321680a76e50445d37a594e835d
+oid sha256:d819b2cd24f404dc450476dc9eda9faa8a60be9fa974a325bff4cef55e018e0c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d394b5c1cee3524c2e9e36815f4811933a615f0aedb2ab40c77282b48686ea20
+oid sha256:deaec7712ba624db1e3382a8fb0ed43703bc1f5f9dbe06c82aef4c4860b169ff
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88e495704322c4559310078027030d164b2831968f7f8f38d7f06009977a3084
+oid sha256:8495787b5608f11be0108c94ffe9a4fc75beb91a4d625a2152531eee9467c065
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d625804322c9c992164d55d8ba441bfc7f0fccb4f8d51d9419a4827237c806cb
+oid sha256:798cfa232d7e4ea18ddd0735a86a39eb6127f2d0e24ff765884eadfe2f0d2077
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bdea63d8d6ce2a737c0dc983cfa0e50ba201b216c669570d472feb33d157749
+oid sha256:c284aa43022d4e2b203e8de4c02e3fa16a4e6d4abbedd180ad3bf4fb3b266332
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8705114254624592,
+  "epoch": 1.7410228509249184,
   "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": 33.546,
       "eval_steps_per_second": 8.722,
       "step": 25
+    },
+    {
+      "epoch": 0.9053318824809575,
+      "grad_norm": NaN,
+      "learning_rate": 8.527926359678135e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.940152339499456,
+      "grad_norm": NaN,
+      "learning_rate": 8.399786637091947e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.9749727965179543,
+      "grad_norm": NaN,
+      "learning_rate": 8.267492998080791e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.0097932535364527,
+      "grad_norm": NaN,
+      "learning_rate": 8.131234952008212e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.0446137105549511,
+      "grad_norm": NaN,
+      "learning_rate": 7.99120768721268e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.0794341675734493,
+      "grad_norm": NaN,
+      "learning_rate": 7.847611791402181e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.1142546245919478,
+      "grad_norm": NaN,
+      "learning_rate": 7.70065296431425e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.1490750816104462,
+      "grad_norm": NaN,
+      "learning_rate": 7.550541723053088e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.1838955386289445,
+      "grad_norm": NaN,
+      "learning_rate": 7.397493100525829e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 1.218715995647443,
+      "grad_norm": NaN,
+      "learning_rate": 7.241726337409979e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 1.2535364526659412,
+      "grad_norm": NaN,
+      "learning_rate": 7.083464568093249e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 1.2883569096844396,
+      "grad_norm": NaN,
+      "learning_rate": 6.922934501035709e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 1.323177366702938,
+      "grad_norm": NaN,
+      "learning_rate": 6.760366094012083e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 1.3579978237214363,
+      "grad_norm": NaN,
+      "learning_rate": 6.595992224699463e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 1.3928182807399347,
+      "grad_norm": NaN,
+      "learning_rate": 6.430048357082287e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.427638737758433,
+      "grad_norm": NaN,
+      "learning_rate": 6.262772204152436e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 1.4624591947769314,
+      "grad_norm": NaN,
+      "learning_rate": 6.0944033873876616e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 1.4972796517954299,
+      "grad_norm": NaN,
+      "learning_rate": 5.9251830934961414e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 1.5321001088139283,
+      "grad_norm": NaN,
+      "learning_rate": 5.755353728918834e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 1.5669205658324266,
+      "grad_norm": NaN,
+      "learning_rate": 5.5851585725845854e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 1.6017410228509248,
+      "grad_norm": NaN,
+      "learning_rate": 5.4148414274154156e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 1.6365614798694232,
+      "grad_norm": NaN,
+      "learning_rate": 5.2446462710811675e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 1.6713819368879217,
+      "grad_norm": NaN,
+      "learning_rate": 5.0748169065038596e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 1.7062023939064201,
+      "grad_norm": NaN,
+      "learning_rate": 4.905596612612341e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 1.7410228509249184,
+      "grad_norm": NaN,
+      "learning_rate": 4.737227795847565e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 1.7410228509249184,
+      "eval_loss": NaN,
+      "eval_runtime": 1.4904,
+      "eval_samples_per_second": 33.548,
+      "eval_steps_per_second": 8.722,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.652642132099072e+17,
+  "total_flos": 5.305284264198144e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null