Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b4043ea34f3fce47b72b0c24a7849cacc65bf64a6682b3a9dfbf421dd43818
+oid sha256:efc5e942286ccccacfadc6bf74bec144f3a2c5d175b06c01fc1ed9c70fe66e31
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9a390dcfda27775d17dd7420b952096d813b0361b7c30d99a11234889653feb
+oid sha256:ab0af01acddab90ccc107914af96b6259c321f3df97007fa3cf50abee465264e
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b21bdbe8aca373ad995f9a76c57a6872ff72a266e26a54323a9cc59913d860ad
+oid sha256:e314b9f447b526751c1cae2464621090aaa07d021790ddea743655adb3366059
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77ee1accde4c32b4bd93f53c2fdad3dd8e6652e30f15fe94283665789840eacf
+oid sha256:6fb7d95892b1d8a555ed143124194cc3799d01ddabd2810507a1e6fe0c0ecb3a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ad68abd01cc07bd7248064b72b5ee41519ccdc41fdadd652b9922ba51566ac7
+oid sha256:6a923a212dfecbe5b7fbe559ff17fc85f6db5572aa57169011f95a6d67efc264
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc00eeb23345f2d553bd642c33db100736d7a805834d144ea9034474bb68e324
+oid sha256:f9dba4194f87aae35392b4e638d48086f646423fa53952df3283bc4e3a8d717b
 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": 2.18863844871521,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3333333333333333,
+  "best_metric": 2.090780258178711,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6666666666666666,
   "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": 11.452,
       "eval_steps_per_second": 2.978,
       "step": 25
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 1.2224326133728027,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.3048,
+      "step": 26
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.396775245666504,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.3792,
+      "step": 27
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.2483328580856323,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.2799,
+      "step": 28
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 1.2314733266830444,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.2989,
+      "step": 29
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2569159269332886,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.1545,
+      "step": 30
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 1.2907873392105103,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.1704,
+      "step": 31
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.3969794511795044,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.1555,
+      "step": 32
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.3379676342010498,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.9647,
+      "step": 33
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 1.4092413187026978,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.0784,
+      "step": 34
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 1.5697481632232666,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.0766,
+      "step": 35
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.7258212566375732,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.8866,
+      "step": 36
+    },
+    {
+      "epoch": 0.49333333333333335,
+      "grad_norm": 1.7891632318496704,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.9433,
+      "step": 37
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.2700576782226562,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.362,
+      "step": 38
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0200166702270508,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.2809,
+      "step": 39
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.0682933330535889,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.1866,
+      "step": 40
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 1.077743649482727,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.1098,
+      "step": 41
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.1414793729782104,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.2013,
+      "step": 42
+    },
+    {
+      "epoch": 0.5733333333333334,
+      "grad_norm": 1.2098270654678345,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.9802,
+      "step": 43
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 1.23659348487854,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.1854,
+      "step": 44
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.2232086658477783,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.841,
+      "step": 45
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 1.3701307773590088,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.1626,
+      "step": 46
+    },
+    {
+      "epoch": 0.6266666666666667,
+      "grad_norm": 1.3952895402908325,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.1024,
+      "step": 47
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.5546798706054688,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.0143,
+      "step": 48
+    },
+    {
+      "epoch": 0.6533333333333333,
+      "grad_norm": 1.6422041654586792,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.8915,
+      "step": 49
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.9815845489501953,
+      "learning_rate": 1e-05,
+      "loss": 1.7494,
+      "step": 50
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 2.090780258178711,
+      "eval_runtime": 4.4047,
+      "eval_samples_per_second": 11.352,
+      "eval_steps_per_second": 2.951,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null