Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b9415115dd38aa20008fd5a5267a285bd500d811ac7f4cb60165d2074c7c67
+oid sha256:79603fcc8d12c6a5f8e8bf149ff5d59229af5e7bc84d15a509e0bb43d8be4ce4
 size 478528978

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa93ced6976d022a763e93076fdf29f5798f4b06080fcf5b07210c4cd8ce316
+oid sha256:f18c97bcc1fc47ffec3f4ef4277b0fad3d23bb8bd1e8e519531adf48e762a1a2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45948cf035d6f1ecde0de2527cfd9bb3c33ba4ec9c043ecd43c4f03575bbf097
+oid sha256:6aa196167c37cbb1ef7ad81fe49ad03df72fd47dd06066cbc814ff37ddbf6932
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d65cfb4df3e87f46acec3ad7ad0be2020e1b7d2675147e1e6adb448559a5a45
+oid sha256:fd25a486f796a627fd1ec160e52d3b48e207073a8533233f906167c7a2728e00
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c35cca2727c86cb4436c1e96cf63e7acdf18bed62352104291c07f88318b1b2
+oid sha256:6ccde1b7cb81e82139fa144f73ec8922838383a0a96ae6c4aea37f7614f5926c
 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": 0.017158912982862536,
+  "epoch": 0.03431782596572507,
   "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": 15.068,
       "eval_steps_per_second": 3.918,
       "step": 25
+    },
+    {
+      "epoch": 0.017845269502177036,
+      "grad_norm": NaN,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.01853162602149154,
+      "grad_norm": NaN,
+      "learning_rate": 7.75e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.01921798254080604,
+      "grad_norm": NaN,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.01990433906012054,
+      "grad_norm": NaN,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.020590695579435044,
+      "grad_norm": NaN,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.021277052098749544,
+      "grad_norm": NaN,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.021963408618064045,
+      "grad_norm": NaN,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.02264976513737855,
+      "grad_norm": NaN,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.02333612165669305,
+      "grad_norm": NaN,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.02402247817600755,
+      "grad_norm": NaN,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.024708834695322052,
+      "grad_norm": NaN,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.025395191214636553,
+      "grad_norm": NaN,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.026081547733951053,
+      "grad_norm": NaN,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.026767904253265556,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.027454260772580057,
+      "grad_norm": NaN,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.028140617291894557,
+      "grad_norm": NaN,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.02882697381120906,
+      "grad_norm": NaN,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.02951333033052356,
+      "grad_norm": NaN,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.030199686849838064,
+      "grad_norm": NaN,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.030886043369152565,
+      "grad_norm": NaN,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.031572399888467065,
+      "grad_norm": NaN,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.032258756407781565,
+      "grad_norm": NaN,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.032945112927096065,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.03363146944641057,
+      "grad_norm": NaN,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.03431782596572507,
+      "grad_norm": NaN,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.03431782596572507,
+      "eval_loss": NaN,
+      "eval_runtime": 3.3187,
+      "eval_samples_per_second": 15.066,
+      "eval_steps_per_second": 3.917,
+      "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": 1.488209212122071e+17,
+  "total_flos": 2.9768831987613696e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null