Training in progress, step 42, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b8f9a814fbedfae287949e37072faa0ffdbfabfbb91bb02a3a9e244e0438f21
+oid sha256:c025a9bfb81ee226889c007aab69f0782e9d75c10eaab2b535a94ce7af04715a
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c9022bd6d7e67b215b7f507cd73f13e35d3c007e8614306506da72de4b57929
+oid sha256:84c46c3fb027c20fbdf01d561cba032d8837c29f5b80ba942ba8543ce83cf13c
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc9740cb9fb7a979c8f00ce98fa38369fb15ef75c77ad8b23f53c82eab6583c
+oid sha256:44ad38e38ab91de5802d98c086cac92b9d83efa8fdd42f1ac18d811c2cf64739
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c45e8ac1925feaa5778fa650c1247f36464662cf3770ed96ef120fb68076b451
+oid sha256:545d06d2755e036a966f804870530450328351fffcfd65cfececc2b0afa7e0a6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f47615c09e27370f70b6e179ad9af94369b4d3c8fd552ee5be45809dc9726e44
+oid sha256:85b4284da286f82aab4a9eec92cfce141d18fe5700fbc6a54d8c552b98f6b7e6
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:270f031239c90143a69a5e3103494133e68e56d7495d4d43bd4cf80bb106050c
+oid sha256:1d29324a0d5877763002861a44f469da99d01dae7b8684c45bb1b74d6def2b49
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.8227272727272728,
+  "epoch": 3.0681818181818183,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 42,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,125 @@
       "eval_samples_per_second": 35.935,
       "eval_steps_per_second": 4.637,
       "step": 25
+    },
+    {
+      "epoch": 1.8954545454545455,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.9681818181818183,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.0454545454545454,
+      "grad_norm": NaN,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.118181818181818,
+      "grad_norm": NaN,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.190909090909091,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.2636363636363637,
+      "grad_norm": NaN,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.3363636363636364,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.409090909090909,
+      "grad_norm": NaN,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.481818181818182,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.5545454545454547,
+      "grad_norm": NaN,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.6272727272727274,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.7727272727272725,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.8454545454545457,
+      "grad_norm": NaN,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.918181818181818,
+      "grad_norm": NaN,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.990909090909091,
+      "grad_norm": NaN,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 3.0681818181818183,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 42
     }
   ],
   "logging_steps": 1,
@@ -221,12 +340,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.829013890367488e+17,
+  "total_flos": 4.75274333581738e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null