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:c97bd0f16e60b48c575b81500f8a153830ee5172797f60363081e54818a75c4c
+oid sha256:dafb7c7238f5b01114e8457c65690be4b0e59d392b66082b749515b35dcb9b56
 size 239135488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:707def372e8e33eac1d168c4445f926e540b41cdd06629e383b1f00f2a3a2dc5
+oid sha256:b2ad5c97eb253b09f653eea884d6c1c9187f2ae86ea98307e5e7e2c13e880a1b
 size 478528978

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b7579239dae0fa8129ad41bd625130aa0ceb0afae93361515399def42d42362
+oid sha256:9814a760fde1dbb9135acc41a279ce8c5f27bb8b7c27daf0c938b143913450be
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8dbc6de683f06b4a8a59bee147842798faead63d077056b5f771d01fab00809
+oid sha256:8dc3c0202e34c63af8b16ae817270b2fa303a9e7ed3852b0880d43c6732f12d8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370e04adee99fd7df7eb2d452562cebc1ae30e97d917136df5a25a3a648adcac
+oid sha256:ab980f6df19c85e2e2bdadcf4dc8473c798b3258888074cac4638d9d8500cd88
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dce8b4af5469b63cacf483f099e59d69eabd36e10651b3f5387273ea9d2a392a
+oid sha256:818489fda53dc3e2ba48c889e2028acc7e8ea7c6cbc7bc78ef438ed71f149108
 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": 2.2178146839141846,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01805706031058144,
+  "best_metric": 2.191683053970337,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03611412062116288,
   "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": 20.561,
       "eval_steps_per_second": 2.57,
       "step": 25
+    },
+    {
+      "epoch": 0.018779342723004695,
+      "grad_norm": 2.463944435119629,
+      "learning_rate": 5e-05,
+      "loss": 2.2202,
+      "step": 26
+    },
+    {
+      "epoch": 0.01950162513542795,
+      "grad_norm": 2.5546419620513916,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.2016,
+      "step": 27
+    },
+    {
+      "epoch": 0.020223907547851208,
+      "grad_norm": 3.138413429260254,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.236,
+      "step": 28
+    },
+    {
+      "epoch": 0.020946189960274468,
+      "grad_norm": 3.267152786254883,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.2221,
+      "step": 29
+    },
+    {
+      "epoch": 0.021668472372697724,
+      "grad_norm": 2.7643165588378906,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.1869,
+      "step": 30
+    },
+    {
+      "epoch": 0.02239075478512098,
+      "grad_norm": 2.357870578765869,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.1428,
+      "step": 31
+    },
+    {
+      "epoch": 0.02311303719754424,
+      "grad_norm": 2.3059284687042236,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.1879,
+      "step": 32
+    },
+    {
+      "epoch": 0.023835319609967497,
+      "grad_norm": 2.3275415897369385,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.1146,
+      "step": 33
+    },
+    {
+      "epoch": 0.024557602022390754,
+      "grad_norm": 2.5051019191741943,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1424,
+      "step": 34
+    },
+    {
+      "epoch": 0.025279884434814014,
+      "grad_norm": 2.978761911392212,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.1838,
+      "step": 35
+    },
+    {
+      "epoch": 0.02600216684723727,
+      "grad_norm": 2.9468026161193848,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.1519,
+      "step": 36
+    },
+    {
+      "epoch": 0.026724449259660527,
+      "grad_norm": 4.417997360229492,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.266,
+      "step": 37
+    },
+    {
+      "epoch": 0.027446731672083786,
+      "grad_norm": 3.7377946376800537,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4016,
+      "step": 38
+    },
+    {
+      "epoch": 0.028169014084507043,
+      "grad_norm": 1.8437291383743286,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.2582,
+      "step": 39
+    },
+    {
+      "epoch": 0.0288912964969303,
+      "grad_norm": 2.100909948348999,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.2269,
+      "step": 40
+    },
+    {
+      "epoch": 0.029613578909353556,
+      "grad_norm": 2.0871973037719727,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.1468,
+      "step": 41
+    },
+    {
+      "epoch": 0.030335861321776816,
+      "grad_norm": 2.019470691680908,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1884,
+      "step": 42
+    },
+    {
+      "epoch": 0.031058143734200072,
+      "grad_norm": 2.251432418823242,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.1517,
+      "step": 43
+    },
+    {
+      "epoch": 0.03178042614662333,
+      "grad_norm": 2.1813924312591553,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1458,
+      "step": 44
+    },
+    {
+      "epoch": 0.032502708559046585,
+      "grad_norm": 2.3104052543640137,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.1803,
+      "step": 45
+    },
+    {
+      "epoch": 0.033224990971469845,
+      "grad_norm": 2.5009100437164307,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.1618,
+      "step": 46
+    },
+    {
+      "epoch": 0.033947273383893105,
+      "grad_norm": 2.5242321491241455,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.1527,
+      "step": 47
+    },
+    {
+      "epoch": 0.03466955579631636,
+      "grad_norm": 2.7807717323303223,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.1826,
+      "step": 48
+    },
+    {
+      "epoch": 0.03539183820873962,
+      "grad_norm": 3.412902593612671,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.2023,
+      "step": 49
+    },
+    {
+      "epoch": 0.03611412062116288,
+      "grad_norm": 4.9823317527771,
+      "learning_rate": 0.0,
+      "loss": 2.3556,
+      "step": 50
+    },
+    {
+      "epoch": 0.03611412062116288,
+      "eval_loss": 2.191683053970337,
+      "eval_runtime": 453.534,
+      "eval_samples_per_second": 20.565,
+      "eval_steps_per_second": 2.571,
+      "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": 1.4891387718939443e+17,
+  "total_flos": 2.9773479893847245e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null