Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:364e04179bd92a405d8a4596a933ced5816d6cbf7c9fa32509c54b9d9db27e4b
+oid sha256:bc13d1b3bad447dbaab98b8c1d648187af1df697402ceef0f5627c1d8788a9eb
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180f2ead24fab1900e9bf67652a487b17479a6aeba9be8a59fa1c13f73370ca4
+oid sha256:3ffcabe5802ef4444fbeeeb1a50bfe0821a4284330f434be4d95e7f877d0c1bc
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51e024a02cc48470ff9f7b962a2d1bdbddfbec6433c49729e7dd884a8c9cdaf9
+oid sha256:ad3825b553246ef1a1049f6ef26978f608c1f3779072ac7ac935d92b2e900f8b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0d7a1d92b169b8e535dd9c21a311e850657cba10c33d1c186be3fe001cb2562
+oid sha256:7efafad6f8384c0b4231da3861a23d255bff59161bba26d492732d275f5e01b1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5f7df4ede52bd6c868a46c3bff7709f354d17650bfe4458b6ca478650ab4e13
+oid sha256:286f855fedc7d589b97114a9b473c1e879784710106fb6133824e510b65bbc59
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dff2d147f0116ee1bd4cbfac4a515b9480b994236a805bdc01ebfc6077f083b
+oid sha256:f1f0c98508495b08c5ce780ffdd16aa610ff42360d42e05c7744a3cb00041553
 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": 10.375431060791016,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04815795810257645,
+  "best_metric": 10.375041007995605,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0963159162051529,
   "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": 775.167,
       "eval_steps_per_second": 97.062,
       "step": 25
+    },
+    {
+      "epoch": 0.05008427642667951,
+      "grad_norm": 0.017374927178025246,
+      "learning_rate": 5e-05,
+      "loss": 10.3758,
+      "step": 26
+    },
+    {
+      "epoch": 0.05201059475078257,
+      "grad_norm": 0.01883726380765438,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3753,
+      "step": 27
+    },
+    {
+      "epoch": 0.05393691307488562,
+      "grad_norm": 0.0194549597799778,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.375,
+      "step": 28
+    },
+    {
+      "epoch": 0.05586323139898868,
+      "grad_norm": 0.02029833383858204,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3754,
+      "step": 29
+    },
+    {
+      "epoch": 0.05778954972309174,
+      "grad_norm": 0.02029760368168354,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3755,
+      "step": 30
+    },
+    {
+      "epoch": 0.0597158680471948,
+      "grad_norm": 0.019594980403780937,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3748,
+      "step": 31
+    },
+    {
+      "epoch": 0.061642186371297855,
+      "grad_norm": 0.016207123175263405,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3758,
+      "step": 32
+    },
+    {
+      "epoch": 0.06356850469540092,
+      "grad_norm": 0.014481107704341412,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3754,
+      "step": 33
+    },
+    {
+      "epoch": 0.06549482301950398,
+      "grad_norm": 0.01565168984234333,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3749,
+      "step": 34
+    },
+    {
+      "epoch": 0.06742114134360704,
+      "grad_norm": 0.01421188935637474,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3751,
+      "step": 35
+    },
+    {
+      "epoch": 0.0693474596677101,
+      "grad_norm": 0.020938636735081673,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3757,
+      "step": 36
+    },
+    {
+      "epoch": 0.07127377799181314,
+      "grad_norm": 0.03991640731692314,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3748,
+      "step": 37
+    },
+    {
+      "epoch": 0.0732000963159162,
+      "grad_norm": 0.017153754830360413,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3752,
+      "step": 38
+    },
+    {
+      "epoch": 0.07512641464001926,
+      "grad_norm": 0.020170168951153755,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3758,
+      "step": 39
+    },
+    {
+      "epoch": 0.07705273296412232,
+      "grad_norm": 0.02071978710591793,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3752,
+      "step": 40
+    },
+    {
+      "epoch": 0.07897905128822538,
+      "grad_norm": 0.021749036386609077,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3754,
+      "step": 41
+    },
+    {
+      "epoch": 0.08090536961232844,
+      "grad_norm": 0.02003314718604088,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3752,
+      "step": 42
+    },
+    {
+      "epoch": 0.08283168793643149,
+      "grad_norm": 0.02103583887219429,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3756,
+      "step": 43
+    },
+    {
+      "epoch": 0.08475800626053455,
+      "grad_norm": 0.01838034950196743,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3757,
+      "step": 44
+    },
+    {
+      "epoch": 0.08668432458463761,
+      "grad_norm": 0.017888696864247322,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3758,
+      "step": 45
+    },
+    {
+      "epoch": 0.08861064290874067,
+      "grad_norm": 0.014699080027639866,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.375,
+      "step": 46
+    },
+    {
+      "epoch": 0.09053696123284373,
+      "grad_norm": 0.014515848830342293,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3747,
+      "step": 47
+    },
+    {
+      "epoch": 0.09246327955694679,
+      "grad_norm": 0.01529916375875473,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3752,
+      "step": 48
+    },
+    {
+      "epoch": 0.09438959788104985,
+      "grad_norm": 0.030164409428834915,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3744,
+      "step": 49
+    },
+    {
+      "epoch": 0.0963159162051529,
+      "grad_norm": 0.03701487183570862,
+      "learning_rate": 0.0,
+      "loss": 10.375,
+      "step": 50
+    },
+    {
+      "epoch": 0.0963159162051529,
+      "eval_loss": 10.375041007995605,
+      "eval_runtime": 4.3206,
+      "eval_samples_per_second": 809.616,
+      "eval_steps_per_second": 101.376,
+      "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": 21704790245376.0,
+  "total_flos": 43369485434880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null