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:b81977e5abda932f92e2061922418d17f5a03ebd65e12dc78de3fc6d161dcf42
+oid sha256:134962344da6ce00de02fa3a59973e526d25b5945908bb36d999ebb20b7472d7
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024cf150a69f80eed0056ae258fd59aaaa3b577d02bd6cbab7b84366667d3fe8
+oid sha256:c142267c68dd0a566744ba5804dd94074aa29499ffc1a5da6c8fb4284d69f278
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44fb359c12f56079f9fecf4fa22f98247367eedaa57c6dc9e20d8339c920e4b0
+oid sha256:13dc3801663f36b6fc92586b3a6152fb2a9b17e64c94fab8aaff759f5d9b725e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62e229653c0aa7e6c5ea0f92dfe7df6a8d798e4b81bcef29892b53120954224c
+oid sha256:70dd4c7f3ff838dacc2e327dfb8be623597537dcec759b66a87cfe7b5787485f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4013c09f1cf74a72033f5764b5fcd093499c455f6eb2bcff608bd50d473db9b2
+oid sha256:68f8a420c21b9ace22b8ca584730b3b3979e6be8d680b084ce83f24cd91d8078
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06b1dc939eb396b71c18e7e501c789ec0a581080c65263dcd1ec13d4cbed2d9
+oid sha256:b697105cbc88820845f9fb01196da69fc01c6c219cd35b1e8268fc3291196142
 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": 10.36435317993164,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9111617312072893,
+  "best_metric": 10.360739707946777,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.8314350797266514,
   "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": 1044.023,
       "eval_steps_per_second": 135.441,
       "step": 25
+    },
+    {
+      "epoch": 0.9476082004555809,
+      "grad_norm": 0.25196874141693115,
+      "learning_rate": 5e-05,
+      "loss": 10.3584,
+      "step": 26
+    },
+    {
+      "epoch": 0.9840546697038725,
+      "grad_norm": 0.3380187153816223,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.353,
+      "step": 27
+    },
+    {
+      "epoch": 1.029612756264237,
+      "grad_norm": 0.30297839641571045,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 19.0658,
+      "step": 28
+    },
+    {
+      "epoch": 1.0660592255125285,
+      "grad_norm": 0.14603254199028015,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.264,
+      "step": 29
+    },
+    {
+      "epoch": 1.10250569476082,
+      "grad_norm": 0.15991508960723877,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3639,
+      "step": 30
+    },
+    {
+      "epoch": 1.1389521640091116,
+      "grad_norm": 0.19101238250732422,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3875,
+      "step": 31
+    },
+    {
+      "epoch": 1.1753986332574031,
+      "grad_norm": 0.20625823736190796,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3873,
+      "step": 32
+    },
+    {
+      "epoch": 1.2118451025056949,
+      "grad_norm": 0.24794551730155945,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3639,
+      "step": 33
+    },
+    {
+      "epoch": 1.2482915717539864,
+      "grad_norm": 0.15549078583717346,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.8354,
+      "step": 34
+    },
+    {
+      "epoch": 1.284738041002278,
+      "grad_norm": 0.19828249514102936,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 13.8538,
+      "step": 35
+    },
+    {
+      "epoch": 1.3211845102505695,
+      "grad_norm": 0.15714150667190552,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.345,
+      "step": 36
+    },
+    {
+      "epoch": 1.357630979498861,
+      "grad_norm": 0.1823427975177765,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.4047,
+      "step": 37
+    },
+    {
+      "epoch": 1.3940774487471526,
+      "grad_norm": 0.1794886589050293,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.395,
+      "step": 38
+    },
+    {
+      "epoch": 1.430523917995444,
+      "grad_norm": 0.22187049686908722,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3162,
+      "step": 39
+    },
+    {
+      "epoch": 1.4669703872437356,
+      "grad_norm": 0.2668076157569885,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.4429,
+      "step": 40
+    },
+    {
+      "epoch": 1.5034168564920274,
+      "grad_norm": 0.15169256925582886,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 8.8337,
+      "step": 41
+    },
+    {
+      "epoch": 1.539863325740319,
+      "grad_norm": 0.15748904645442963,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.7664,
+      "step": 42
+    },
+    {
+      "epoch": 1.5763097949886105,
+      "grad_norm": 0.15284818410873413,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.4053,
+      "step": 43
+    },
+    {
+      "epoch": 1.6127562642369022,
+      "grad_norm": 0.1644909381866455,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3361,
+      "step": 44
+    },
+    {
+      "epoch": 1.6492027334851938,
+      "grad_norm": 0.18126553297042847,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3664,
+      "step": 45
+    },
+    {
+      "epoch": 1.6856492027334853,
+      "grad_norm": 0.23220454156398773,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3932,
+      "step": 46
+    },
+    {
+      "epoch": 1.7220956719817768,
+      "grad_norm": 0.2918383777141571,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.4925,
+      "step": 47
+    },
+    {
+      "epoch": 1.7585421412300684,
+      "grad_norm": 0.18016327917575836,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 9.7463,
+      "step": 48
+    },
+    {
+      "epoch": 1.79498861047836,
+      "grad_norm": 0.166108638048172,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.7557,
+      "step": 49
+    },
+    {
+      "epoch": 1.8314350797266514,
+      "grad_norm": 0.16405977308750153,
+      "learning_rate": 0.0,
+      "loss": 10.3726,
+      "step": 50
+    },
+    {
+      "epoch": 1.8314350797266514,
+      "eval_loss": 10.360739707946777,
+      "eval_runtime": 0.1753,
+      "eval_samples_per_second": 1055.129,
+      "eval_steps_per_second": 136.882,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null