Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:affba243cc7646e23a452a6a4312ea4e6bdfa6d46c3f6c2fa16389358a23d4f7
+oid sha256:c72d35160ac630e0301c952fca9129d1e46596acbf386121778f4d2ab8d404c4
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d510543524271f376d0fc06bd8f69d3ef46366f618b4d3f7c7c1b5c4eb934e3
+oid sha256:e01eca418e55d1ca9f9c098d896e4827e112579a044fc7a0e566a80bf642948e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc7f5458f93151626c720ab36e0af0f335bc5fc25c9230eea0e9ad3ea34c4fd5
+oid sha256:90761459bba63bff6507567662b7774a1b4c5f52b8e9c702bd57b11a9ed45409
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12a1131fd73182ada1f1ac707ad01201696eee0b836242744a474fbc79556ccf
+oid sha256:c4bd3d29f9dff48b2fbcac35e5b3852daf4c8619035fb33f65c422c02e6e3ee4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac547c17d69a79575cd95d9c9a3f268670b01ce8244919307e39c8031dd5cdc3
+oid sha256:0d57da45a688717e40ca87886f2df98c9b23bc58f314da09838fe6b852fe476e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8084206b6cd1415e1849491552a60e62e2e86620c9c709dbdb2660ce0e04aaa
+oid sha256:42e835247ff52684d3a7e28d9a457677e4fcbf72138da879846fe67ca4bce802
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.335559265442404,
+  "epoch": 2.671118530884808,
   "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": 15.395,
       "eval_steps_per_second": 4.003,
       "step": 25
+    },
+    {
+      "epoch": 1.3889816360601002,
+      "grad_norm": NaN,
+      "learning_rate": 6.393657099905855e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.4424040066777963,
+      "grad_norm": NaN,
+      "learning_rate": 6.140416772229784e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.4958263772954925,
+      "grad_norm": NaN,
+      "learning_rate": 5.88508753815478e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.5492487479131887,
+      "grad_norm": NaN,
+      "learning_rate": 5.628502228571633e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.6026711185308848,
+      "grad_norm": NaN,
+      "learning_rate": 5.3714977714283674e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.656093489148581,
+      "grad_norm": NaN,
+      "learning_rate": 5.114912461845223e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.7095158597662772,
+      "grad_norm": NaN,
+      "learning_rate": 4.859583227770218e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.7629382303839733,
+      "grad_norm": NaN,
+      "learning_rate": 4.606342900094147e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.8163606010016693,
+      "grad_norm": NaN,
+      "learning_rate": 4.3560174961293097e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 1.8697829716193657,
+      "grad_norm": NaN,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 1.9232053422370616,
+      "grad_norm": NaN,
+      "learning_rate": 3.8673653259221166e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 1.976627712854758,
+      "grad_norm": NaN,
+      "learning_rate": 3.630632441491512e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.030050083472454,
+      "grad_norm": NaN,
+      "learning_rate": 3.399997045484469e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.0834724540901504,
+      "grad_norm": NaN,
+      "learning_rate": 3.176211422624672e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.1368948247078463,
+      "grad_norm": NaN,
+      "learning_rate": 2.9600055150995398e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.1903171953255427,
+      "grad_norm": NaN,
+      "learning_rate": 2.7520845416405282e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.2437395659432386,
+      "grad_norm": NaN,
+      "learning_rate": 2.5531266972462177e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.297161936560935,
+      "grad_norm": NaN,
+      "learning_rate": 2.36378094105118e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.350584307178631,
+      "grad_norm": NaN,
+      "learning_rate": 2.1846648795561774e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.4040066777963274,
+      "grad_norm": NaN,
+      "learning_rate": 2.0163627521241292e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 2.4574290484140233,
+      "grad_norm": NaN,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 2.5108514190317193,
+      "grad_norm": NaN,
+      "learning_rate": 1.7143591022596845e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 2.5642737896494157,
+      "grad_norm": NaN,
+      "learning_rate": 1.5816426529610035e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 2.617696160267112,
+      "grad_norm": NaN,
+      "learning_rate": 1.4617070708888881e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 2.671118530884808,
+      "grad_norm": NaN,
+      "learning_rate": 1.3549435609831752e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.671118530884808,
+      "eval_loss": NaN,
+      "eval_runtime": 3.2463,
+      "eval_samples_per_second": 15.402,
+      "eval_steps_per_second": 4.005,
+      "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