Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cc31d7a7c2ccb73fcc0a7f5db4a4e9374a1311eeaa4c395d1d7db21169232e0
+oid sha256:da363994d5d7b2741f5e3dadec69e0602f0e72ca31b4a5ca7911b73b5fd14923
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:409c15e9dcce78fa23ad37c420b30fcb1f94e6bdccf0888cbb8e7d1f1cbf1d4f
+oid sha256:7dd96831ee1f49992de1ac4b2e81c8dc9e169e909819af8fd1ab0a10317e80e6
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6bdde95605385e7c3331bedb961f490e8a0bf6fd5da9663e1ac2742a5d630a6
+oid sha256:37305fa73c6a94f60c64f062b514d85a2d75219213900572855cd8e76bd32786
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c2d5fe68518bcb9520612c15ab445d80654d51adc583152199f4eb49014cf4e
+oid sha256:d78cd1efe6df0b157f3ae996fdf295717eb72fd5ec4e951170b16a2bdf68a36b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54ed2c140fc1bcf31cf8655c857987f83fd5889ce8b82da222263d1b5407d3b0
+oid sha256:fd2c349cee3be21becf021ae4f78b7e193bba322182fadbdb006c4c72b4036fa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63b9382e72aac9c69c32203c0e77593cf73728737bd24aa0641cf6c8ea304f4b
+oid sha256:2f4a8a24bd392c7dc8128426828b559ac6694afc04cdefe99acf8e73270691af
 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": 0.7327967882156372,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5333333333333333,
+  "best_metric": 0.5354008674621582,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0706666666666667,
   "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": 58.121,
       "eval_steps_per_second": 15.112,
       "step": 25
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": 11.328150749206543,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6107,
+      "step": 26
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 11.290071487426758,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.7006,
+      "step": 27
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 5.399608612060547,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.5938,
+      "step": 28
+    },
+    {
+      "epoch": 0.6186666666666667,
+      "grad_norm": 1.1989216804504395,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.5027,
+      "step": 29
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.6115729808807373,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6006,
+      "step": 30
+    },
+    {
+      "epoch": 0.6613333333333333,
+      "grad_norm": 1.794100284576416,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5524,
+      "step": 31
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 2.9884450435638428,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5414,
+      "step": 32
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 2.558598756790161,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.5567,
+      "step": 33
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": 0.707525908946991,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5197,
+      "step": 34
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.9570581316947937,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.4944,
+      "step": 35
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 1.1071268320083618,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4967,
+      "step": 36
+    },
+    {
+      "epoch": 0.7893333333333333,
+      "grad_norm": 1.3137996196746826,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.5275,
+      "step": 37
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": 0.7425646781921387,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4655,
+      "step": 38
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 2.363434314727783,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.493,
+      "step": 39
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.7309908866882324,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5345,
+      "step": 40
+    },
+    {
+      "epoch": 0.8746666666666667,
+      "grad_norm": 1.0935527086257935,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5622,
+      "step": 41
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 1.2434831857681274,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.5019,
+      "step": 42
+    },
+    {
+      "epoch": 0.9173333333333333,
+      "grad_norm": 0.8114237189292908,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.5283,
+      "step": 43
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 1.1921507120132446,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5845,
+      "step": 44
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.1729776859283447,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4877,
+      "step": 45
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": 1.433878779411316,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.5172,
+      "step": 46
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 3.5882816314697266,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6454,
+      "step": 47
+    },
+    {
+      "epoch": 1.028,
+      "grad_norm": 2.6538946628570557,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4888,
+      "step": 48
+    },
+    {
+      "epoch": 1.0493333333333332,
+      "grad_norm": 2.8021609783172607,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.4849,
+      "step": 49
+    },
+    {
+      "epoch": 1.0706666666666667,
+      "grad_norm": 1.217156171798706,
+      "learning_rate": 1e-05,
+      "loss": 0.5087,
+      "step": 50
+    },
+    {
+      "epoch": 1.0706666666666667,
+      "eval_loss": 0.5354008674621582,
+      "eval_runtime": 0.8627,
+      "eval_samples_per_second": 57.959,
+      "eval_steps_per_second": 15.069,
+      "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": 8.061561648604774e+16,
+  "total_flos": 1.6063518385320755e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null