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:eef065e4c367d36698872ef7df7e4b0ef2b8e8c2370d6d90b829a730d487f8fa
+oid sha256:b9e7bac97b0175198b98edf7a8b6da36f4c6899d71d83c7f3ac368001b6fe4b2
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e80bf9b3271ed59ff77aa0d66afc86a66df68b384a4276c32616f1fe9beaac
+oid sha256:37f058bc35615c346051578512ecb79bc5aa922ddbdab5413f90565a8aea795e
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7e4843d03a825c56d6d3dba930276e0c5734972304dd0e54abc3635394deefb
+oid sha256:8e87afda82f474bdb3d369ca770efe9b73e9ac50df0b7d86eac5b65e081f334b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578aae4836cbd3269011719b5be79bd8add1eeaca6a5cfbc39cfde3b5111ac35
+oid sha256:5a58cf7ff5a519913903564794827e4acf3665d620a1ea7688377d542746ae20
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d6d3ab99b65d77fc78f9ecf5a6b213dd239554e210bedeeeecf95c5fdc2ea10
+oid sha256:9b92d82be0d27ad99b247d2067e9cd4c43ff4cd034c96495193d3a6056b26151
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1420d15a213ca6b02e6a9402508b2f8d9404aad2d2c50ffdefc15af5c31aaad7
+oid sha256:904aa25deb2293901cb204ddc1131ffaa31a72c0559c68ac38bfe81911342df6
 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": 0.7862718105316162,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.025106703489831784,
+  "best_metric": 0.6432160139083862,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05021340697966357,
   "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": 123.331,
       "eval_steps_per_second": 15.423,
       "step": 25
+    },
+    {
+      "epoch": 0.026110971629425057,
+      "grad_norm": 1.1455990076065063,
+      "learning_rate": 5e-05,
+      "loss": 0.7459,
+      "step": 26
+    },
+    {
+      "epoch": 0.027115239769018327,
+      "grad_norm": 1.5568510293960571,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7928,
+      "step": 27
+    },
+    {
+      "epoch": 0.028119507908611598,
+      "grad_norm": 1.0878664255142212,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7083,
+      "step": 28
+    },
+    {
+      "epoch": 0.02912377604820487,
+      "grad_norm": 0.949036717414856,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6149,
+      "step": 29
+    },
+    {
+      "epoch": 0.03012804418779814,
+      "grad_norm": 0.7017745971679688,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.6841,
+      "step": 30
+    },
+    {
+      "epoch": 0.031132312327391415,
+      "grad_norm": 0.8500891923904419,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6332,
+      "step": 31
+    },
+    {
+      "epoch": 0.032136580466984685,
+      "grad_norm": 0.685302734375,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.629,
+      "step": 32
+    },
+    {
+      "epoch": 0.033140848606577955,
+      "grad_norm": 0.7081299424171448,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.643,
+      "step": 33
+    },
+    {
+      "epoch": 0.034145116746171225,
+      "grad_norm": 0.7412989139556885,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6929,
+      "step": 34
+    },
+    {
+      "epoch": 0.0351493848857645,
+      "grad_norm": 0.747283399105072,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6811,
+      "step": 35
+    },
+    {
+      "epoch": 0.03615365302535777,
+      "grad_norm": 0.8888285756111145,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6998,
+      "step": 36
+    },
+    {
+      "epoch": 0.03715792116495104,
+      "grad_norm": 0.8620653748512268,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8258,
+      "step": 37
+    },
+    {
+      "epoch": 0.03816218930454431,
+      "grad_norm": 0.8505666255950928,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6338,
+      "step": 38
+    },
+    {
+      "epoch": 0.03916645744413758,
+      "grad_norm": 0.9013793468475342,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6493,
+      "step": 39
+    },
+    {
+      "epoch": 0.04017072558373085,
+      "grad_norm": 0.7170226573944092,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6643,
+      "step": 40
+    },
+    {
+      "epoch": 0.04117499372332413,
+      "grad_norm": 0.7864304184913635,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.65,
+      "step": 41
+    },
+    {
+      "epoch": 0.0421792618629174,
+      "grad_norm": 0.5616835355758667,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5628,
+      "step": 42
+    },
+    {
+      "epoch": 0.04318353000251067,
+      "grad_norm": 0.644270658493042,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5768,
+      "step": 43
+    },
+    {
+      "epoch": 0.04418779814210394,
+      "grad_norm": 0.650669276714325,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6751,
+      "step": 44
+    },
+    {
+      "epoch": 0.04519206628169721,
+      "grad_norm": 0.6862338185310364,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6439,
+      "step": 45
+    },
+    {
+      "epoch": 0.04619633442129049,
+      "grad_norm": 0.7162413597106934,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5825,
+      "step": 46
+    },
+    {
+      "epoch": 0.04720060256088376,
+      "grad_norm": 0.7476317286491394,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6402,
+      "step": 47
+    },
+    {
+      "epoch": 0.04820487070047703,
+      "grad_norm": 0.6151590347290039,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.65,
+      "step": 48
+    },
+    {
+      "epoch": 0.0492091388400703,
+      "grad_norm": 0.767148494720459,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7045,
+      "step": 49
+    },
+    {
+      "epoch": 0.05021340697966357,
+      "grad_norm": 0.6965320706367493,
+      "learning_rate": 0.0,
+      "loss": 0.7126,
+      "step": 50
+    },
+    {
+      "epoch": 0.05021340697966357,
+      "eval_loss": 0.6432160139083862,
+      "eval_runtime": 54.4393,
+      "eval_samples_per_second": 123.238,
+      "eval_steps_per_second": 15.412,
+      "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": 4.169686388310016e+16,
+  "total_flos": 8.336768348717056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null