Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d92f653e67bfb404aff034f4d17a59392d609c6361a556fb46ea933a0f96375
+oid sha256:a5050be1ffb721cf32b0e894338087781633784d4293c60c07d1e8fd76b4070b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68dad0ee64814864b4e3bb3809e96545216f7d6d35645ec96c0bb74be2cc3733
+oid sha256:9db0fa0e1901621c9278f1901401755618afae9e837ecfe6aaade237b9848d02
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42fd0d46d91a9dbbc907580431dc28843e3dc362e36607cac8a3e0214600afb0
+oid sha256:da3c2ad7dc07663638c44550e5269904ddd871cbbdb978968445beedac99da67
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3c25d8770b8399ca86070cd4beebc85ba7fcfd052d46802e0a751af1b6b9d8e
+oid sha256:8c6c5acd314a10d449156637a38972d106d3430a026d1d64354edc928586e1a9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fd36fba0c5ddcf37a7bd8a8886ff887ef5477282dea1dad65b3c54ba79e691d
+oid sha256:a9405e802193b74b98120b7fd5274673d4fe432c75c6a6737b3584cb8591bc18
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51924e125011267acf78f0473e5a2a5f661e40acdad62fb2e7797c88f2d9059b
+oid sha256:0fd04aba88066e6ec7515b2fc1981bbab2b31f877cbb75ba3d995f170bbbb79d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0011842730455100536,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.033783783783783786,
+  "best_metric": 0.0006782332202419639,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06756756756756757,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 33.064,
       "eval_steps_per_second": 4.139,
       "step": 25
+    },
+    {
+      "epoch": 0.03513513513513514,
+      "grad_norm": 0.14307132363319397,
+      "learning_rate": 5e-05,
+      "loss": 0.0022,
+      "step": 26
+    },
+    {
+      "epoch": 0.03648648648648649,
+      "grad_norm": 0.045208968222141266,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0005,
+      "step": 27
+    },
+    {
+      "epoch": 0.03783783783783784,
+      "grad_norm": 0.04789796844124794,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0009,
+      "step": 28
+    },
+    {
+      "epoch": 0.03918918918918919,
+      "grad_norm": 0.023802442476153374,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0005,
+      "step": 29
+    },
+    {
+      "epoch": 0.04054054054054054,
+      "grad_norm": 0.0236771609634161,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0005,
+      "step": 30
+    },
+    {
+      "epoch": 0.041891891891891894,
+      "grad_norm": 0.004636330995708704,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0002,
+      "step": 31
+    },
+    {
+      "epoch": 0.043243243243243246,
+      "grad_norm": 0.04701589047908783,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0006,
+      "step": 32
+    },
+    {
+      "epoch": 0.0445945945945946,
+      "grad_norm": 0.009117241948843002,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0002,
+      "step": 33
+    },
+    {
+      "epoch": 0.04594594594594595,
+      "grad_norm": 0.07297568768262863,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0007,
+      "step": 34
+    },
+    {
+      "epoch": 0.0472972972972973,
+      "grad_norm": 0.011586630716919899,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0002,
+      "step": 35
+    },
+    {
+      "epoch": 0.04864864864864865,
+      "grad_norm": 0.026419680565595627,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0005,
+      "step": 36
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.021272508427500725,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0006,
+      "step": 37
+    },
+    {
+      "epoch": 0.051351351351351354,
+      "grad_norm": 0.10119505971670151,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0047,
+      "step": 38
+    },
+    {
+      "epoch": 0.052702702702702706,
+      "grad_norm": 0.04138147085905075,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.001,
+      "step": 39
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 0.010599342174828053,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0004,
+      "step": 40
+    },
+    {
+      "epoch": 0.05540540540540541,
+      "grad_norm": 0.043806999921798706,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0008,
+      "step": 41
+    },
+    {
+      "epoch": 0.05675675675675676,
+      "grad_norm": 0.00391389848664403,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0001,
+      "step": 42
+    },
+    {
+      "epoch": 0.05810810810810811,
+      "grad_norm": 0.11111900955438614,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0007,
+      "step": 43
+    },
+    {
+      "epoch": 0.05945945945945946,
+      "grad_norm": 0.017778916284441948,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0003,
+      "step": 44
+    },
+    {
+      "epoch": 0.060810810810810814,
+      "grad_norm": 0.03460654616355896,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0011,
+      "step": 45
+    },
+    {
+      "epoch": 0.062162162162162166,
+      "grad_norm": 0.011294426396489143,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.06351351351351352,
+      "grad_norm": 0.008213512599468231,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0002,
+      "step": 47
+    },
+    {
+      "epoch": 0.06486486486486487,
+      "grad_norm": 0.03531975671648979,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0004,
+      "step": 48
+    },
+    {
+      "epoch": 0.06621621621621622,
+      "grad_norm": 0.0346805676817894,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0004,
+      "step": 49
+    },
+    {
+      "epoch": 0.06756756756756757,
+      "grad_norm": 0.31902623176574707,
+      "learning_rate": 0.0,
+      "loss": 0.0028,
+      "step": 50
+    },
+    {
+      "epoch": 0.06756756756756757,
+      "eval_loss": 0.0006782332202419639,
+      "eval_runtime": 152.5444,
+      "eval_samples_per_second": 32.679,
+      "eval_steps_per_second": 4.091,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.9859068337822106e+17,
+  "total_flos": 5.969948642440643e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null