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 sha256:891a1b29f08801cdb0e539359949589e9bf663c09fe30d8848e6f67d38afd42c
+oid sha256:aa8cd38c825076bb0b6ba127a85563e42a697d5a19e7316aa424335f5cf248b7
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5603cf7eab8391beba157e4aaadb79f97eef05189198f3595a61749378879d72
+oid sha256:18bc4cd3356591cc3bd988c42e99390db254d5827afac72521441d16b779d6ac
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c93bb4d411ee7f271e4a5c93525db9921fc52bac1cd3c0b87b588259225eeda
+oid sha256:ff6b554c8f9cb45d51c5f030d56be7b9c968fe94d436e3fbf40dfecdad44c521
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a8ce0fae2f0728af8fcd7ba82e67b9b45a863a54d97f6faac8cc7fb09a4e54
+oid sha256:a15d09d84e552ad6139530a92d7fbb09e5675e269c85af627facc6c242a57ba0
 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": 2.1952506596306067,
+  "epoch": 3.16622691292876,
   "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": 10.048,
       "eval_steps_per_second": 2.613,
       "step": 25
+    },
+    {
+      "epoch": 2.2796833773087073,
+      "grad_norm": NaN,
+      "learning_rate": 2.7881441362933468e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.3641160949868074,
+      "grad_norm": NaN,
+      "learning_rate": 2.4683696035904928e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.4485488126649075,
+      "grad_norm": NaN,
+      "learning_rate": 2.1744598725070347e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.532981530343008,
+      "grad_norm": NaN,
+      "learning_rate": 1.9089224772389225e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.6174142480211082,
+      "grad_norm": NaN,
+      "learning_rate": 1.674022889216737e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.7018469656992083,
+      "grad_norm": NaN,
+      "learning_rate": 1.4717651889022202e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.786279683377309,
+      "grad_norm": NaN,
+      "learning_rate": 1.3038749676803994e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.870712401055409,
+      "grad_norm": NaN,
+      "learning_rate": 1.1717846057223144e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.955145118733509,
+      "grad_norm": NaN,
+      "learning_rate": 1.076621051422442e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 3.0817941952506596,
+      "grad_norm": NaN,
+      "learning_rate": 1.019196206672345e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 3.16622691292876,
+      "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": 3.2815135091746406e+17,
+  "total_flos": 4.725976251372667e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null