Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58797087fc7eb9a48e833833f7a25540df9519aa8bc88422b68e43b91d3a860c
+oid sha256:049e0e5cbff75c911e575aecea483928824474f41f154f353e9ac7d58fba196b
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b123b99b8b417e991d772a79f8c62be6654bb491a1c9e1c0c896d2dbeaaf2516
+oid sha256:7691a2c31e7b934fc9403676cc837b4a52c43c6c146aa37bce46272175fc4604
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:401a6ad0233dcf747a1f20d108e7eee6508d00f5412ed72d8088b00309a0c0ac
+oid sha256:5d9ff052cf4d6359349f4ac5a430d14190f87a74b28ca92b5664f1f2b1308862
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3471d05e3348c2d09ac8f683c9bccbba1381567533fb80cb90dbac597ed324b
+oid sha256:f9404bed15a454ddc21606c1dca61472d8428ca7cb16475e34f96f8923c6b2a2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66394ce0f91a834fca18f21c75f943818a0462af0e2ba6e3110402685598b6ba
+oid sha256:3a2e5971bb73e87cfa314cb092c01b39dece1e1346042c080153e759294b44f8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107607e336ff02e6e3fc135f6b55fc089901c7172808564e7046a8e836a537c9
+oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.024715768660405337,
+  "epoch": 0.049431537320810674,
   "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": 32.378,
       "eval_steps_per_second": 8.418,
       "step": 25
+    },
+    {
+      "epoch": 0.02570439940682155,
+      "grad_norm": NaN,
+      "learning_rate": 8.957804998855866e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.026693030153237766,
+      "grad_norm": NaN,
+      "learning_rate": 8.860696646428693e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.02768166089965398,
+      "grad_norm": NaN,
+      "learning_rate": 8.759913421559902e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.028670291646070194,
+      "grad_norm": NaN,
+      "learning_rate": 8.655565529226198e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.029658922392486405,
+      "grad_norm": NaN,
+      "learning_rate": 8.547767072315835e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03064755313890262,
+      "grad_norm": NaN,
+      "learning_rate": 8.436635926858759e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.03163618388531883,
+      "grad_norm": NaN,
+      "learning_rate": 8.322293613130917e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.03262481463173505,
+      "grad_norm": NaN,
+      "learning_rate": 8.204865162773613e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.03361344537815126,
+      "grad_norm": NaN,
+      "learning_rate": 8.084478982073247e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.03460207612456748,
+      "grad_norm": NaN,
+      "learning_rate": 7.961266711550922e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.03559070687098369,
+      "grad_norm": NaN,
+      "learning_rate": 7.835363082015468e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0365793376173999,
+      "grad_norm": NaN,
+      "learning_rate": 7.706905767237288e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.037567968363816116,
+      "grad_norm": NaN,
+      "learning_rate": 7.576035233404096e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.03855659911023233,
+      "grad_norm": NaN,
+      "learning_rate": 7.442894585523218e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.039545229856648545,
+      "grad_norm": NaN,
+      "learning_rate": 7.307629410938363e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.040533860603064756,
+      "grad_norm": NaN,
+      "learning_rate": 7.170387620131993e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.04152249134948097,
+      "grad_norm": NaN,
+      "learning_rate": 7.031319284987394e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.042511122095897184,
+      "grad_norm": NaN,
+      "learning_rate": 6.890576474687263e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.043499752842313395,
+      "grad_norm": NaN,
+      "learning_rate": 6.7483130894283e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.044488383588729606,
+      "grad_norm": NaN,
+      "learning_rate": 6.604684692133597e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.045477014335145824,
+      "grad_norm": NaN,
+      "learning_rate": 6.459848338346861e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.046465645081562035,
+      "grad_norm": NaN,
+      "learning_rate": 6.313962404494496e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.04745427582797825,
+      "grad_norm": NaN,
+      "learning_rate": 6.167186414703289e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.04844290657439446,
+      "grad_norm": NaN,
+      "learning_rate": 6.019680866363139e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.049431537320810674,
+      "grad_norm": NaN,
+      "learning_rate": 5.8716070546254966e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.049431537320810674,
+      "eval_loss": NaN,
+      "eval_runtime": 1.5438,
+      "eval_samples_per_second": 32.388,
+      "eval_steps_per_second": 8.421,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null