Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003f747e72ded802f7214a60aacc3e686e8a1fe007476c5da493fe228f977651
+oid sha256:35d4c7802eee86bc9ac04eb7f75b05c0b8cea378b4c5a637ccace63201d3c198
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c9877bb3d5afef4c0e581e18423fc490cf8af3d1160a8619cd6c79db201c1ee
+oid sha256:8a170a1351ff5023a2c13cf7d49a4e006514f17985a13983457fdb8091d3fc86
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c111eecd247e6923522e5b1fdaecc7f1064e00cdba78b29faa118538f5e03c52
+oid sha256:cc938ee67e93fd70b66f0e0a394c51e3ef226fca1f6cc6a764ecf81e5cd79300
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:143b9bc77cdfe0520b035e3bca0e8d080e9a939fd2cd94dda18b5b84aa7c8aba
+oid sha256:c63f0c49534dea4914dd9449742fcf0fb1707088516146d900b7d317382795be
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01debf61833f18398ac1bb1420d0b563736473a52bfe6e95e32ff08ae52a1324
+oid sha256:42f170e0aeef300172f6582e0f234232de7c8c8e88fbbd29b218dca91c10430c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa2d1baca11ce6c46e97b42402aa35bbb1ae7c787847d52786b7cd34bd205b37
+oid sha256:d9b8ac4fe1527f7f6478148722852f909a3329506d0d82c27d15b352090c25d8
 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": 1.2333778142929077,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06532745386248572,
+  "best_metric": 1.1957429647445679,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13065490772497143,
   "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": 15.414,
       "eval_steps_per_second": 1.931,
       "step": 25
+    },
+    {
+      "epoch": 0.06794055201698514,
+      "grad_norm": 7.437511920928955,
+      "learning_rate": 5e-05,
+      "loss": 0.9982,
+      "step": 26
+    },
+    {
+      "epoch": 0.07055365017148457,
+      "grad_norm": 6.7867207527160645,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0384,
+      "step": 27
+    },
+    {
+      "epoch": 0.073166748325984,
+      "grad_norm": 6.633565902709961,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.0307,
+      "step": 28
+    },
+    {
+      "epoch": 0.07577984648048343,
+      "grad_norm": 7.300943851470947,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.0679,
+      "step": 29
+    },
+    {
+      "epoch": 0.07839294463498285,
+      "grad_norm": 8.290701866149902,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.0623,
+      "step": 30
+    },
+    {
+      "epoch": 0.08100604278948229,
+      "grad_norm": 10.008981704711914,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1515,
+      "step": 31
+    },
+    {
+      "epoch": 0.0836191409439817,
+      "grad_norm": 12.658711433410645,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2007,
+      "step": 32
+    },
+    {
+      "epoch": 0.08623223909848114,
+      "grad_norm": 17.597726821899414,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.24,
+      "step": 33
+    },
+    {
+      "epoch": 0.08884533725298056,
+      "grad_norm": 21.86583709716797,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3628,
+      "step": 34
+    },
+    {
+      "epoch": 0.09145843540748,
+      "grad_norm": 26.087900161743164,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3616,
+      "step": 35
+    },
+    {
+      "epoch": 0.09407153356197942,
+      "grad_norm": 33.14945983886719,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4062,
+      "step": 36
+    },
+    {
+      "epoch": 0.09668463171647886,
+      "grad_norm": 39.74778747558594,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.6848,
+      "step": 37
+    },
+    {
+      "epoch": 0.09929772987097828,
+      "grad_norm": 36.329551696777344,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3833,
+      "step": 38
+    },
+    {
+      "epoch": 0.10191082802547771,
+      "grad_norm": 6.016417503356934,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0036,
+      "step": 39
+    },
+    {
+      "epoch": 0.10452392617997713,
+      "grad_norm": 6.548324108123779,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0207,
+      "step": 40
+    },
+    {
+      "epoch": 0.10713702433447657,
+      "grad_norm": 6.872424602508545,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.0523,
+      "step": 41
+    },
+    {
+      "epoch": 0.10975012248897599,
+      "grad_norm": 7.7177734375,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0816,
+      "step": 42
+    },
+    {
+      "epoch": 0.11236322064347543,
+      "grad_norm": 8.686575889587402,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1517,
+      "step": 43
+    },
+    {
+      "epoch": 0.11497631879797485,
+      "grad_norm": 9.739227294921875,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.115,
+      "step": 44
+    },
+    {
+      "epoch": 0.11758941695247428,
+      "grad_norm": 12.140241622924805,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1213,
+      "step": 45
+    },
+    {
+      "epoch": 0.1202025151069737,
+      "grad_norm": 16.49872398376465,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2322,
+      "step": 46
+    },
+    {
+      "epoch": 0.12281561326147314,
+      "grad_norm": 21.253034591674805,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3385,
+      "step": 47
+    },
+    {
+      "epoch": 0.12542871141597256,
+      "grad_norm": 28.797561645507812,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.363,
+      "step": 48
+    },
+    {
+      "epoch": 0.12804180957047198,
+      "grad_norm": 35.98500442504883,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.3961,
+      "step": 49
+    },
+    {
+      "epoch": 0.13065490772497143,
+      "grad_norm": 53.93410873413086,
+      "learning_rate": 0.0,
+      "loss": 1.7542,
+      "step": 50
+    },
+    {
+      "epoch": 0.13065490772497143,
+      "eval_loss": 1.1957429647445679,
+      "eval_runtime": 167.2329,
+      "eval_samples_per_second": 15.416,
+      "eval_steps_per_second": 1.931,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null