Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b645e28aa9807ddd47cb4cfba9ace999339e6b1c20b09c4be01d476121b3308
+oid sha256:856cd84ad9b2b58c78f175f72225af494bda899061b34dde5315a20ce76ca2f2
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc02c88b0059984d11527b4b2c008d38bd0a61d4df4c0dc707426ddf2f030637
+oid sha256:b677f5b2e8eabc166c5545928a10cae41d2256d8d6c1a32bf9fa67cf8f86dfe6
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b7998f41fb6c297515fd3417ba6b7292f068b29a236aa8be3531b63c16ea97d
+oid sha256:3eb5792358af5b638d77c0874fadcb7b976462b30c0f9be506327468457c5b71
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14069f8224a409be65a3182298aab223eb531a06bc7d6131eea1ce5e90dea54a
+oid sha256:fc48474e1af9186a0104a346dbc997e6c8d181155be8329cef5d355a3ade32b0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d72e3ddd7cc5ab627ee7128faa28f75ea8bce13041a0c45b7d1f1779460d4ae3
+oid sha256:7880318b70c49897d881b59cb4530c5e1875b439247c8eb436344ed701cf80cb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f87294c2ae3abbee501e8b632c1aa841e189ebdcda3a340112b437e24f6d9b71
+oid sha256:1bee9cf7b77d18360ad9adb6955248635a375777cc864a209ce1abe84a82003b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6821223497390747,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3065134099616858,
+  "best_metric": 0.6303707361221313,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6130268199233716,
   "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": 14.407,
       "eval_steps_per_second": 3.746,
       "step": 25
+    },
+    {
+      "epoch": 0.31877394636015327,
+      "grad_norm": 8.646349906921387,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 12.6015,
+      "step": 26
+    },
+    {
+      "epoch": 0.3310344827586207,
+      "grad_norm": 9.114627838134766,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9859,
+      "step": 27
+    },
+    {
+      "epoch": 0.3432950191570881,
+      "grad_norm": 8.983087539672852,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.828,
+      "step": 28
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 8.055755615234375,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.2362,
+      "step": 29
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 7.169692516326904,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.4835,
+      "step": 30
+    },
+    {
+      "epoch": 0.3800766283524904,
+      "grad_norm": 6.012217044830322,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.0008,
+      "step": 31
+    },
+    {
+      "epoch": 0.39233716475095787,
+      "grad_norm": 4.796036243438721,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 9.9654,
+      "step": 32
+    },
+    {
+      "epoch": 0.4045977011494253,
+      "grad_norm": 3.7424519062042236,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 9.3905,
+      "step": 33
+    },
+    {
+      "epoch": 0.4168582375478927,
+      "grad_norm": 3.024531602859497,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 9.0075,
+      "step": 34
+    },
+    {
+      "epoch": 0.42911877394636017,
+      "grad_norm": 3.2817485332489014,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 7.9566,
+      "step": 35
+    },
+    {
+      "epoch": 0.4413793103448276,
+      "grad_norm": 3.8038198947906494,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 8.1924,
+      "step": 36
+    },
+    {
+      "epoch": 0.453639846743295,
+      "grad_norm": 6.050798416137695,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 7.1592,
+      "step": 37
+    },
+    {
+      "epoch": 0.46590038314176246,
+      "grad_norm": 5.559319496154785,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 9.4112,
+      "step": 38
+    },
+    {
+      "epoch": 0.4781609195402299,
+      "grad_norm": 3.019770383834839,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.8928,
+      "step": 39
+    },
+    {
+      "epoch": 0.4904214559386973,
+      "grad_norm": 4.159815311431885,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.3034,
+      "step": 40
+    },
+    {
+      "epoch": 0.5026819923371647,
+      "grad_norm": 2.9123547077178955,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.6206,
+      "step": 41
+    },
+    {
+      "epoch": 0.5149425287356322,
+      "grad_norm": 3.187201499938965,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.1798,
+      "step": 42
+    },
+    {
+      "epoch": 0.5272030651340996,
+      "grad_norm": 2.4112672805786133,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 9.9942,
+      "step": 43
+    },
+    {
+      "epoch": 0.539463601532567,
+      "grad_norm": 2.671354293823242,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 9.4394,
+      "step": 44
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 2.70517897605896,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 9.0841,
+      "step": 45
+    },
+    {
+      "epoch": 0.563984674329502,
+      "grad_norm": 2.947141408920288,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 8.7662,
+      "step": 46
+    },
+    {
+      "epoch": 0.5762452107279693,
+      "grad_norm": 3.5247323513031006,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 8.6785,
+      "step": 47
+    },
+    {
+      "epoch": 0.5885057471264368,
+      "grad_norm": 4.2779541015625,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 7.7403,
+      "step": 48
+    },
+    {
+      "epoch": 0.6007662835249042,
+      "grad_norm": 5.184771537780762,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 7.5488,
+      "step": 49
+    },
+    {
+      "epoch": 0.6130268199233716,
+      "grad_norm": 7.278592586517334,
+      "learning_rate": 1e-05,
+      "loss": 6.822,
+      "step": 50
+    },
+    {
+      "epoch": 0.6130268199233716,
+      "eval_loss": 0.6303707361221313,
+      "eval_runtime": 3.4739,
+      "eval_samples_per_second": 14.393,
+      "eval_steps_per_second": 3.742,
+      "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": 1.483568811343872e+17,
+  "total_flos": 2.967137622687744e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null