Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0757c223cdec0f7ad5b951a53cb53ea4f6c7d436cacaf4decb869d07dbac5e67
+oid sha256:7e38d387feed2d69168a2266250cc73855b825867390903481dbc2c4771012ae
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f3f5b8b33545181b57551874c7cfc517dd17f9456fc661d7784e20e87401bac
+oid sha256:0314d3820151911b6551a5bb0ce672583bca568a12dcddab483523338fa46f14
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792c273a8190908fa5b0cb36823b63262a1f05410c0f34af98e2782701ade32b
+oid sha256:4466dc29755edb8084d16c9c3df1a64a535e2cbfa5f87ae40ea5177989a7dbee
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f777c4580b3f1a0265d299225aa6cbf4b218c3258d55eeb948db6e21a463393
+oid sha256:1d1ea085851dea9da43c98497e079616616b2dacafe664a83afc98b5b055e28b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37a10b3fc797b42a533bd91e31a5ee0eb199b33082928de23252ba2eb8900d1
+oid sha256:5d08323578f98f6a2f8528ec82ea5d703f68e83d6fffa5d0908db68916f70777
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:823ce430f702d1e19596cd07369a738c929f009dfcdbc3c98c3002b93c9d2cc8
+oid sha256:4433cb59576ce6642de18bd37fc8446e9073d9a5566bfc3da44ff9237619b10f
 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": 0.07827573269605637,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.954653937947494,
+  "best_metric": 0.03684283792972565,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.9093078758949882,
   "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": 108.188,
       "eval_steps_per_second": 14.058,
       "step": 25
+    },
+    {
+      "epoch": 0.9928400954653938,
+      "grad_norm": 1.0364090204238892,
+      "learning_rate": 5e-05,
+      "loss": 0.0835,
+      "step": 26
+    },
+    {
+      "epoch": 1.0310262529832936,
+      "grad_norm": 17.326866149902344,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2532,
+      "step": 27
+    },
+    {
+      "epoch": 1.0692124105011933,
+      "grad_norm": 6.2615647315979,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1134,
+      "step": 28
+    },
+    {
+      "epoch": 1.107398568019093,
+      "grad_norm": 3.5731632709503174,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0594,
+      "step": 29
+    },
+    {
+      "epoch": 1.1455847255369929,
+      "grad_norm": 1.441209316253662,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0227,
+      "step": 30
+    },
+    {
+      "epoch": 1.1837708830548925,
+      "grad_norm": 2.8011887073516846,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0682,
+      "step": 31
+    },
+    {
+      "epoch": 1.2219570405727924,
+      "grad_norm": 1.7012304067611694,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0513,
+      "step": 32
+    },
+    {
+      "epoch": 1.260143198090692,
+      "grad_norm": 6.563292980194092,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1411,
+      "step": 33
+    },
+    {
+      "epoch": 1.2983293556085918,
+      "grad_norm": 1.9492319822311401,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1558,
+      "step": 34
+    },
+    {
+      "epoch": 1.3365155131264916,
+      "grad_norm": 3.193370819091797,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1007,
+      "step": 35
+    },
+    {
+      "epoch": 1.3747016706443915,
+      "grad_norm": 6.734858989715576,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0638,
+      "step": 36
+    },
+    {
+      "epoch": 1.4128878281622912,
+      "grad_norm": 6.953091621398926,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0497,
+      "step": 37
+    },
+    {
+      "epoch": 1.4510739856801909,
+      "grad_norm": 3.499946117401123,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0416,
+      "step": 38
+    },
+    {
+      "epoch": 1.4892601431980907,
+      "grad_norm": 3.893627405166626,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0265,
+      "step": 39
+    },
+    {
+      "epoch": 1.5274463007159904,
+      "grad_norm": 1.17046058177948,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0381,
+      "step": 40
+    },
+    {
+      "epoch": 1.5656324582338903,
+      "grad_norm": 1.5724403858184814,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.064,
+      "step": 41
+    },
+    {
+      "epoch": 1.60381861575179,
+      "grad_norm": 1.290392518043518,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0385,
+      "step": 42
+    },
+    {
+      "epoch": 1.6420047732696896,
+      "grad_norm": 0.47391846776008606,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.018,
+      "step": 43
+    },
+    {
+      "epoch": 1.6801909307875895,
+      "grad_norm": 0.229345440864563,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0192,
+      "step": 44
+    },
+    {
+      "epoch": 1.7183770883054894,
+      "grad_norm": 0.7760948538780212,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0231,
+      "step": 45
+    },
+    {
+      "epoch": 1.756563245823389,
+      "grad_norm": 2.864842414855957,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0292,
+      "step": 46
+    },
+    {
+      "epoch": 1.7947494033412887,
+      "grad_norm": 3.478466033935547,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0627,
+      "step": 47
+    },
+    {
+      "epoch": 1.8329355608591884,
+      "grad_norm": 1.9896175861358643,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0599,
+      "step": 48
+    },
+    {
+      "epoch": 1.8711217183770883,
+      "grad_norm": 1.9609580039978027,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0331,
+      "step": 49
+    },
+    {
+      "epoch": 1.9093078758949882,
+      "grad_norm": 0.23864984512329102,
+      "learning_rate": 0.0,
+      "loss": 0.0127,
+      "step": 50
+    },
+    {
+      "epoch": 1.9093078758949882,
+      "eval_loss": 0.03684283792972565,
+      "eval_runtime": 3.5326,
+      "eval_samples_per_second": 50.105,
+      "eval_steps_per_second": 6.511,
+      "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": 3.91521434075136e+16,
+  "total_flos": 7.83042868150272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null