Training in progress, step 36, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cdccbcd3886ce6d0d744b99bf1b3e75b5ae9828a2a51240cfb1ed2a31d93fb1
+oid sha256:159cf4989083048a654994d92cd7e35e620050b41dd612818ed62638290dc1db
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99a9dbfeea433b0ac4157887d6ef9a949873406cb544ea1aa87b58360c4d87ef
+oid sha256:c4570eae62086f5e6e77ae183095e6930e785040de94fe017abd0e2cea88e833
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3232018b6ea222df579a24e6429f5b99be19c6629b92691d51c22745fa721c1b
+oid sha256:0a4965de6fc1dc78695ae70db9aa98ef13a45787bd81e1fd2da38bf9f2301d9a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e77c8101e1b297e52b262e92327ca651cf754bdae0b3fb977e0965255bf46b1d
+oid sha256:118daf0691998d240ce7aa902fb0b91f0291dd2f886ea40b39ce2fc2e5030516
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb595897ccd4ade4834e409b6da44771c17afc31c22f613f2ac839d29ccdcb9
+oid sha256:9d0491832cd4e787214d26a71a9bd9b9e1bbd9b7bbac23a2563db9f0b243065d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8d490043b81d92f2523c5e5743bd899586cd05324668f1c6287fc78466d4341
+oid sha256:83bde02f2e7b736ca94b9c51f0320881be685bc5601886de1775bb4eb0e0862b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2334217506631298,
+  "epoch": 3.222811671087533,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,83 @@
       "eval_samples_per_second": 12.181,
       "eval_steps_per_second": 3.167,
       "step": 25
+    },
+    {
+      "epoch": 2.3183023872679045,
+      "grad_norm": NaN,
+      "learning_rate": 2.7881441362933468e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.4031830238726792,
+      "grad_norm": NaN,
+      "learning_rate": 2.4683696035904928e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.4880636604774535,
+      "grad_norm": NaN,
+      "learning_rate": 2.1744598725070347e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.5729442970822283,
+      "grad_norm": NaN,
+      "learning_rate": 1.9089224772389225e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.6578249336870026,
+      "grad_norm": NaN,
+      "learning_rate": 1.674022889216737e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.7427055702917773,
+      "grad_norm": NaN,
+      "learning_rate": 1.4717651889022202e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": NaN,
+      "learning_rate": 1.3038749676803994e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.9124668435013263,
+      "grad_norm": NaN,
+      "learning_rate": 1.1717846057223144e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 3.053050397877984,
+      "grad_norm": NaN,
+      "learning_rate": 1.076621051422442e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 3.1379310344827585,
+      "grad_norm": NaN,
+      "learning_rate": 1.019196206672345e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 3.222811671087533,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -221,12 +298,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.106485802278584e+17,
+  "total_flos": 5.929429534423122e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null