Training in progress, step 43, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:742d7d6b09eceb8a893ef3294602a4da77806a229682af265a781d9889815994
+oid sha256:d7d5ff2a0d108e41ae85e53bbf492ec1fae97e2b7e8e4ead0320e0d738b36e65
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f490d9b058452de6083933609031da97b25e8e1cdc93810a66cee409bc28d1
+oid sha256:a9d691571bd89d18e6b4b42a66c68be3ffe2ca8a8d5439985b59322304de5aba
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e24003942246a09c0a69fa8eaaf3bcd568ef637269087c244f7c448f5da6ed
+oid sha256:4fee0ac0c86b2d59028e0f36191745084fe97d08f197f12d214d956586dfa17a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8dc3237e263eaee1953872b5ad5a2c51be988ac2b027bdd863cf4c7b6180cd4
+oid sha256:8c813d5de458dcb1d7994b2f7e8380036fd8607256752118412cb24172050092
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424ee3a629fc9373914465bc1852754a127d7bf9f43491d8ce9f1f4a94971500
+oid sha256:121cdd9f8267544c4a2a2b19947b5a84a8887c53209ba520ebbe39b62a519ed9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f73e6deadf3f08547d8bef9e9b3d87995c0c2ef87d51b8801270b8b2d32ac55
+oid sha256:d9ca16dc5125aa616f8880e7477dabd4029e096d950b1e4b31474d314c00eace
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7665198237885462,
+  "epoch": 3.0440528634361232,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 43,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,132 @@
       "eval_samples_per_second": 13.815,
       "eval_steps_per_second": 3.592,
       "step": 25
+    },
+    {
+      "epoch": 1.8370044052863435,
+      "grad_norm": NaN,
+      "learning_rate": 4.307583240115024e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.907488986784141,
+      "grad_norm": NaN,
+      "learning_rate": 3.9789240471617385e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.9779735682819384,
+      "grad_norm": NaN,
+      "learning_rate": 3.659191132728971e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.052863436123348,
+      "grad_norm": NaN,
+      "learning_rate": 3.350260816694816e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.1233480176211454,
+      "grad_norm": NaN,
+      "learning_rate": 3.0539460249945056e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.193832599118943,
+      "grad_norm": NaN,
+      "learning_rate": 2.7719856506501306e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.26431718061674,
+      "grad_norm": NaN,
+      "learning_rate": 2.5060343492549566e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.3348017621145374,
+      "grad_norm": NaN,
+      "learning_rate": 2.257652828796459e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.405286343612335,
+      "grad_norm": NaN,
+      "learning_rate": 2.0282986908012567e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.4757709251101323,
+      "grad_norm": NaN,
+      "learning_rate": 1.819317876549771e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.5462555066079293,
+      "grad_norm": NaN,
+      "learning_rate": 1.631936768557596e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.616740088105727,
+      "grad_norm": NaN,
+      "learning_rate": 1.4672549936752506e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.6872246696035242,
+      "grad_norm": NaN,
+      "learning_rate": 1.3262389700405744e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.7577092511013217,
+      "grad_norm": NaN,
+      "learning_rate": 1.2097162357528127e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.828193832599119,
+      "grad_norm": NaN,
+      "learning_rate": 1.1183705925499948e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.898678414096916,
+      "grad_norm": NaN,
+      "learning_rate": 1.0527380929884324e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.9691629955947136,
+      "grad_norm": NaN,
+      "learning_rate": 1.013203894673168e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 3.0440528634361232,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 43
     }
   ],
   "logging_steps": 1,
@@ -221,12 +347,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.0677119162279526e+17,
+  "total_flos": 5.251356976952115e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null