Training in progress, step 41, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4bb5e14e592797900f9828ecd62e75298eb9db6a493f528dfa4bf2add9878ed
+oid sha256:36854da82eebc6281470a8f98759334be3028312727cf6f7c3ef7111ed34ccf2
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ebda057d15e589658b07ffe6fd297d9c047b65a5524332301bbe34a54892d36
+oid sha256:e8e579bbb64047e35b5086ee08705a3117a1264dcc04f46b4ce5e877273d6a84
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbab0fe64584e228408ee18dbc4745f97514a619332250a7f28cac441b7402a7
+oid sha256:35f5a00da87e0e7f8772e65613b5a277e974060d84c4e83037248c2146b9d4a5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c68619994d73234e76ddd1feb92e295accbcd602dc8c18b3c0d5a55adb7c9728
+oid sha256:46f36017186ab7e98a20cde4ecde42ac920b3534bb3e710e8217c29764c24792
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681e69596f33514e4bd1f691f19deb4cab37122c2d4131ad35fffb1a163a8ea8
+oid sha256:723c4ff9e188854a21de5586b39861a9f813f4568d36b829bc73c882fae5c0d8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc6b77c0cbcc35c1c43ee60e2766b6027d2e111edae589e45f75af1b1040b32d
+oid sha256:84fc982e8229d2121603832a24f4c07bbdbf63985ed1d38e11762164a04dad3b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.8518518518518519,
+  "epoch": 3.037037037037037,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 41,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,118 @@
       "eval_samples_per_second": 56.048,
       "eval_steps_per_second": 7.391,
       "step": 25
+    },
+    {
+      "epoch": 1.925925925925926,
+      "grad_norm": NaN,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": NaN,
+      "learning_rate": 2.8565371929847284e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.148148148148148,
+      "grad_norm": NaN,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": NaN,
+      "learning_rate": 1.837773122023114e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.2962962962962963,
+      "grad_norm": NaN,
+      "learning_rate": 1.536378232452003e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": NaN,
+      "learning_rate": 1.257446259144494e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": NaN,
+      "learning_rate": 1.0027861829824952e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.5185185185185186,
+      "grad_norm": NaN,
+      "learning_rate": 7.740495722810271e-06,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": NaN,
+      "learning_rate": 5.727198717339511e-06,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": NaN,
+      "learning_rate": 4.001027817058789e-06,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.7407407407407405,
+      "grad_norm": NaN,
+      "learning_rate": 2.573177902642726e-06,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": NaN,
+      "learning_rate": 1.4529091286973995e-06,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": NaN,
+      "learning_rate": 6.474868681043578e-07,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": NaN,
+      "learning_rate": 1.6213459328950352e-07,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 3.037037037037037,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 41
     }
   ],
   "logging_steps": 1,
@@ -221,12 +333,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.114626154561536e+17,
+  "total_flos": 1.827986893480919e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null