Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81921c18868c6ef2e7cecd2219e369ac64373149ef38fb6eaf8fcc8c43983207
+oid sha256:d65c826ef247dcda03af769e03a5cb9001cc9ef57fe56da437760a34ea51ea6e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd19cda809f79258dee510c63dd576de5574317fb2e513a11d3fd006eab8a716
+oid sha256:8f0fef25c3578407754c87a5976a7f0f16aefb9400262e20592e4b6b199c48f4
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90797e75e23dba771118db4f98831ea4de60383decfdd9be8d52d0c895daf90
+oid sha256:f5871527e07fb7eb1ad42f08294583e2ee8bd802d1e46a878a16dad319923c7e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ddff00e6f096eab48b17ae107b8ddcb121e258e4579ef946cef23e8d0327bd
+oid sha256:ae5ecdf4b6c77e02d9c0b5d9c86fef7d63b4b301ba8ccececef2043808a932ae
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8d14891ffe632c20ebd5bd11e4a5da8c9e47bf0e4260a41edea261928ef750
+oid sha256:9b95845d95a3c67f2e4a55ff236d51a808a98d2aa152e5f2f8dbb4976b86c243
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10c8c45e4bef2e4e58eee7876f4433420d8493a69254828900d559f3557112b4
+oid sha256:c392992e83e0d20214bb0a4b6edb29f12c5a45ae4b5ca5b1b12ee97d31511e29
 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": 1.3714919090270996,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9852216748768473,
+  "best_metric": 1.3098337650299072,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.9704433497536946,
   "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": 14.34,
       "eval_steps_per_second": 1.845,
       "step": 25
+    },
+    {
+      "epoch": 1.0246305418719213,
+      "grad_norm": 0.9618764519691467,
+      "learning_rate": 5e-05,
+      "loss": 2.154,
+      "step": 26
+    },
+    {
+      "epoch": 1.064039408866995,
+      "grad_norm": 0.5749042630195618,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.2959,
+      "step": 27
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.7094845771789551,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3819,
+      "step": 28
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.7971547842025757,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2207,
+      "step": 29
+    },
+    {
+      "epoch": 1.1822660098522166,
+      "grad_norm": 0.7469020485877991,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2043,
+      "step": 30
+    },
+    {
+      "epoch": 1.2216748768472907,
+      "grad_norm": 0.7728456258773804,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.4655,
+      "step": 31
+    },
+    {
+      "epoch": 1.2610837438423645,
+      "grad_norm": 0.5634871125221252,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8603,
+      "step": 32
+    },
+    {
+      "epoch": 1.3004926108374384,
+      "grad_norm": 0.8294857740402222,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3913,
+      "step": 33
+    },
+    {
+      "epoch": 1.3399014778325122,
+      "grad_norm": 0.7319616675376892,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4166,
+      "step": 34
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.5748394131660461,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1102,
+      "step": 35
+    },
+    {
+      "epoch": 1.4187192118226601,
+      "grad_norm": 0.5485185384750366,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1237,
+      "step": 36
+    },
+    {
+      "epoch": 1.458128078817734,
+      "grad_norm": 0.7056682705879211,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.4578,
+      "step": 37
+    },
+    {
+      "epoch": 1.4975369458128078,
+      "grad_norm": 0.49516087770462036,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7405,
+      "step": 38
+    },
+    {
+      "epoch": 1.5369458128078817,
+      "grad_norm": 0.6058965921401978,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5931,
+      "step": 39
+    },
+    {
+      "epoch": 1.5763546798029555,
+      "grad_norm": 0.5580366253852844,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3807,
+      "step": 40
+    },
+    {
+      "epoch": 1.6157635467980296,
+      "grad_norm": 0.4432365298271179,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.0635,
+      "step": 41
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.537194013595581,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2266,
+      "step": 42
+    },
+    {
+      "epoch": 1.6945812807881775,
+      "grad_norm": 0.5397228002548218,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2694,
+      "step": 43
+    },
+    {
+      "epoch": 1.7339901477832513,
+      "grad_norm": 0.5041022896766663,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8196,
+      "step": 44
+    },
+    {
+      "epoch": 1.7733990147783252,
+      "grad_norm": 0.5393572449684143,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.588,
+      "step": 45
+    },
+    {
+      "epoch": 1.812807881773399,
+      "grad_norm": 0.4689037501811981,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2798,
+      "step": 46
+    },
+    {
+      "epoch": 1.8522167487684729,
+      "grad_norm": 0.5147009491920471,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.2285,
+      "step": 47
+    },
+    {
+      "epoch": 1.8916256157635467,
+      "grad_norm": 0.4669371545314789,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1595,
+      "step": 48
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 0.47628194093704224,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1712,
+      "step": 49
+    },
+    {
+      "epoch": 1.9704433497536946,
+      "grad_norm": 0.9145755767822266,
+      "learning_rate": 0.0,
+      "loss": 1.5987,
+      "step": 50
+    },
+    {
+      "epoch": 1.9704433497536946,
+      "eval_loss": 1.3098337650299072,
+      "eval_runtime": 11.9272,
+      "eval_samples_per_second": 14.337,
+      "eval_steps_per_second": 1.845,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null