Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8451435c6b33d74771effdd5509d9d9106046b813cb02afe0bcab6eea9eb0167
+oid sha256:933ecda4bebd0c702b7cd2e8537fcbe734d2163fa993dce8795e1c7ab76444a1
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55965dabb8e037d38b9a602cdeec097f95dbd117dd3ff11a61a0f4a64ef9e257
+oid sha256:7f9571a63ba72843de20fcab4aba75a2d0e9fb3561fb426c8787cb0b5f0cdebb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:751f856afacb32dc73d46ccd596828e60c3212d461c97bc6c5e4fa599a0da46f
+oid sha256:91a78bbd9a4c2fe00f7165f0343e950aefce88a8c11ad18515fe4c04c3eb4a0a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28408a8c7cb51ffc41121dcd69d72aafe190050d5205f820c1512f4fe3bbff2a
+oid sha256:1584a8754269fa45ec3d4f1a4560456afebf538a0ec9920e9a9460920e9e8a23
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ec77ec730b03b53341846cdd1dc639a2011644dd39f1a2afb9cc6d40effc53
+oid sha256:5a118c130775b7d361cdf93fca3cb9124f0964de1b77c98c28d00bc36ecc050d
 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": 0.8859357696566998,
+  "epoch": 1.7718715393133997,
   "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": 6.579,
       "eval_steps_per_second": 1.71,
       "step": 25
+    },
+    {
+      "epoch": 0.9213732004429679,
+      "grad_norm": NaN,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.9568106312292359,
+      "grad_norm": NaN,
+      "learning_rate": 7.75e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.9922480620155039,
+      "grad_norm": NaN,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.0276854928017718,
+      "grad_norm": NaN,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.06312292358804,
+      "grad_norm": NaN,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.0985603543743079,
+      "grad_norm": NaN,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.1339977851605758,
+      "grad_norm": NaN,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.169435215946844,
+      "grad_norm": NaN,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.204872646733112,
+      "grad_norm": NaN,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 1.2403100775193798,
+      "grad_norm": NaN,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 1.2757475083056478,
+      "grad_norm": NaN,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 1.311184939091916,
+      "grad_norm": NaN,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 1.3466223698781838,
+      "grad_norm": NaN,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 1.3820598006644518,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 1.41749723145072,
+      "grad_norm": NaN,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.4529346622369879,
+      "grad_norm": NaN,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 1.4883720930232558,
+      "grad_norm": NaN,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": NaN,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 1.5592469545957917,
+      "grad_norm": NaN,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 1.5946843853820598,
+      "grad_norm": NaN,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 1.6301218161683277,
+      "grad_norm": NaN,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 1.665559246954596,
+      "grad_norm": NaN,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 1.7009966777408638,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 1.7364341085271318,
+      "grad_norm": NaN,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 1.7718715393133997,
+      "grad_norm": NaN,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 1.7718715393133997,
+      "eval_loss": NaN,
+      "eval_runtime": 7.6468,
+      "eval_samples_per_second": 6.539,
+      "eval_steps_per_second": 1.7,
+      "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": 5.638906500433838e+17,
+  "total_flos": 1.1152856242412585e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null