Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36b34fa7f76282a169fea591002a7737e2e8e3e9da9080257544a1dcc9bb390b
+oid sha256:3fd086b37129477d20f20e7c45619ec7bbe93ebe62d97ab47684c5c16b5f011e
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ddbf3f1533ed9d782f950136604a2ac70a483f771808beff6667f614031f2d4
+oid sha256:180e0782f622b7cf357c9c55ed45516703cdfdb6ed950b40d23773c4facd2793
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0987dbf4e3937de64d41186d8103799d38067b811dcbe9ec063fc16447b16252
+oid sha256:db4491a353c82ae39b5c399a38a97c85fb8fdf2b00b5351aa4f3e352dc16195e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e351eb224debd1d4c234963c665e521e332e846ce3154a697bd5ab6c74a3e7ff
+oid sha256:c2a20fd0750c0a6524ddaa091e1426810da14097978dfd2bc1c6992ea2131299
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c57e2c97e9005fec427a8c7742f939f8081ca6aaad2ae5b23b960747f7cd96bf
+oid sha256:bd8071c5f6666fc2d62d5ba3e10fddea478f4a49959f67bc36e80a470eaa8293
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b73cdf1ad38476f82f1dfb947eede46059caed90d32c0da65a717882d01e585b
+oid sha256:ee73dd1960c4aa12e8f2c290b1f7970702eca4c59b12c45f8c3a9e97fe04fefa
 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": 1.7881389169360773e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.003480106839279966,
+  "best_metric": 3.973642748178463e-08,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.006960213678559932,
   "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": 9.627,
       "eval_steps_per_second": 2.503,
       "step": 25
+    },
+    {
+      "epoch": 0.0036193111128511647,
+      "grad_norm": 6.752758054062724e-05,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.0037585153864223633,
+      "grad_norm": 5.6042164942482486e-05,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.003897719659993562,
+      "grad_norm": 4.698020711657591e-05,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.004036923933564761,
+      "grad_norm": 4.064290624228306e-05,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.004176128207135959,
+      "grad_norm": 3.3646061638137326e-05,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.004315332480707158,
+      "grad_norm": 2.9114757126080804e-05,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.004454536754278356,
+      "grad_norm": 3.0572762625524774e-05,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.004593741027849555,
+      "grad_norm": 2.7114840122521855e-05,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0047329453014207535,
+      "grad_norm": 2.4281154765048996e-05,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.004872149574991953,
+      "grad_norm": 2.2557736883754842e-05,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.005011353848563151,
+      "grad_norm": 2.0800394850084558e-05,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.00515055812213435,
+      "grad_norm": 2.0314013454481028e-05,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.005289762395705548,
+      "grad_norm": 1.936802436830476e-05,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.005428966669276747,
+      "grad_norm": 1.9238419554312713e-05,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.0055681709428479454,
+      "grad_norm": 1.91349427041132e-05,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.005707375216419144,
+      "grad_norm": 1.6851270629558712e-05,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.005846579489990343,
+      "grad_norm": 1.6155534467543475e-05,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.005985783763561541,
+      "grad_norm": 1.6756492186686955e-05,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.00612498803713274,
+      "grad_norm": 1.688018710410688e-05,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.006264192310703938,
+      "grad_norm": 1.6521807992830873e-05,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.006403396584275137,
+      "grad_norm": 1.6070989659056067e-05,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.006542600857846336,
+      "grad_norm": 1.5321618775487877e-05,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.006681805131417535,
+      "grad_norm": 1.7318605387117714e-05,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.006821009404988733,
+      "grad_norm": 1.6765192413004115e-05,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.006960213678559932,
+      "grad_norm": 1.6366233467124403e-05,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.006960213678559932,
+      "eval_loss": 3.973642748178463e-08,
+      "eval_runtime": 5.1019,
+      "eval_samples_per_second": 9.8,
+      "eval_steps_per_second": 2.548,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null