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:a754b216e2674eff766ba1d3fe47ea005f0ae93c55b1f4b7c7501acacf8cc2ee
+oid sha256:09553fb2e6824a9edabe52790992cc96c3cb53bb1202295bde710301d62e1b4f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d08447fe1dc27b162c0b51d31ffd503ff1cb6d078ceea0547f16973c59f8ebc
+oid sha256:794754944ca65f57cc58ee0de9286f95930f95e754618936f62d2ccdd2d1adf5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8380068eec9eac88166f331b33b5893e5b681485253dc087897180b8fbfc342a
+oid sha256:0e8d473ea67c945eb211788f7a51037c2f3bd9ccdbe828a726e76d17f49f40c4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333391cdf9401a08d2bd4d1661292724a49ef779213f392e38f9021a1a051622
+oid sha256:46121d01d250e67160ef1cb2bed2666fdc7d8ec2faeb44edba375bdf884bfdb3
 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": 8.218,
       "eval_steps_per_second": 2.137,
       "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