Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:275c65ff6cb0e0ea4c4bf7c9a3e0036e1877867ec705d9570770940a7db73c29
+oid sha256:75eb23fb7867b9a0a307f4555e0aee4a03f464810d395714b89a335dc694d4ff
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54eb4a1729b23b64099969a777190ef8064fbd3b100f67379a02c7d1347d3d67
+oid sha256:6e664a92dced9058a7a315818ed9dd34e925ac0fd0d0684bbb21a20d3273c190
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc4ac655b18cb0d247a2d875611255406fae414822e56e0732698e8144828612
+oid sha256:434e31df711017c4ac3fad32303936ccdfbce107cb8d02c8b90f392b12d84b22
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec6d0a07d203d66ad0915f6bc92d079802bc2a9f06919418e8b855c7023ba12a
+oid sha256:038c432dc8c8bf8609c5742df0c97e1b96aadac42cd623895ebd4abf49e47b58
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a971eaa7f1c484f2799fff8777839bf4a02a07c8bcb1a22fb5817a4f152f8b36
+oid sha256:26801a541ccf0b351eb3ca8277b7c1f3ba51b629eec76e4e708ae9e4c58d6354
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006265860459287571,
+  "epoch": 0.012531720918575143,
   "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": 16.25,
       "eval_steps_per_second": 4.225,
       "step": 25
+    },
+    {
+      "epoch": 0.006516494877659074,
+      "grad_norm": NaN,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.006767129296030577,
+      "grad_norm": NaN,
+      "learning_rate": 7.75e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.007017763714402081,
+      "grad_norm": NaN,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.0072683981327735835,
+      "grad_norm": NaN,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.007519032551145086,
+      "grad_norm": NaN,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.007769666969516589,
+      "grad_norm": NaN,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.008020301387888092,
+      "grad_norm": NaN,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.008270935806259594,
+      "grad_norm": NaN,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.008521570224631098,
+      "grad_norm": NaN,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.0087722046430026,
+      "grad_norm": NaN,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.009022839061374103,
+      "grad_norm": NaN,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.009273473479745607,
+      "grad_norm": NaN,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.009524107898117109,
+      "grad_norm": NaN,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.009774742316488613,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.010025376734860115,
+      "grad_norm": NaN,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.010276011153231618,
+      "grad_norm": NaN,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.01052664557160312,
+      "grad_norm": NaN,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.010777279989974624,
+      "grad_norm": NaN,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.011027914408346126,
+      "grad_norm": NaN,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.01127854882671763,
+      "grad_norm": NaN,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.011529183245089131,
+      "grad_norm": NaN,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.011779817663460635,
+      "grad_norm": NaN,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.012030452081832137,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.01228108650020364,
+      "grad_norm": NaN,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.012531720918575143,
+      "grad_norm": NaN,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.012531720918575143,
+      "eval_loss": NaN,
+      "eval_runtime": 3.1091,
+      "eval_samples_per_second": 16.082,
+      "eval_steps_per_second": 4.181,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null