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:fda5eee944a46b51e86ee5c344d691d13730d3b9e5461a5e06f3e419c18fa6dc
+oid sha256:a80f37c6efc50dadabf86fa081d4be8202f7d8a71ca0bf36c58abf42cb692ed3
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:567e501cf1c60d9aa0dc00d97331f50a1cf4b1f55fb19faf8db9245e3b91e76e
+oid sha256:c7d4313f87ad88b5ac21f64be2953b0afa1461ea2911522707616863c07ba6eb
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8734794b57f099e49146f36a59467556de1d79340c59a9177c6460ff0372e70f
+oid sha256:325700c454c54cc42ae8d487607a41e61900ee9db7f16c5e1de8ce7503682e72
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:101e4b5f5f906c7f837b1959a5bde0841b1108df9c14206a1e01a7597b617863
+oid sha256:34704581c3a5aed2f55dd99b368895dea03eeeb8a02707a6b61da67cda3d75c3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b269ed6099beb363eeae0fdeb90af5d9899651bdc04a70bbb5a565f5c16c4b2f
+oid sha256:09096ee93c23778990a8965314b08b6b85bdf4068ea3fefbbd9fc9a4df7aee24
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72217a7202071b9c05a548b70dd6d9c2c6f6118c0eaeb7212d7c73a71194a692
+oid sha256:ec8fd4cce1f03e61a1690307147d3ae951a6ebfb559a6004d482052ead29a58a
 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": 0.13366584479808807,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.009680307833789115,
+  "best_metric": 0.125091552734375,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01936061566757823,
   "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": 85.25,
       "eval_steps_per_second": 22.165,
       "step": 25
+    },
+    {
+      "epoch": 0.01006752014714068,
+      "grad_norm": 15.704390525817871,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.4165,
+      "step": 26
+    },
+    {
+      "epoch": 0.010454732460492243,
+      "grad_norm": 13.66524600982666,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.1935,
+      "step": 27
+    },
+    {
+      "epoch": 0.010841944773843808,
+      "grad_norm": 7.263870716094971,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0652,
+      "step": 28
+    },
+    {
+      "epoch": 0.011229157087195372,
+      "grad_norm": 0.8715264797210693,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0094,
+      "step": 29
+    },
+    {
+      "epoch": 0.011616369400546937,
+      "grad_norm": 0.25349822640419006,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0031,
+      "step": 30
+    },
+    {
+      "epoch": 0.012003581713898502,
+      "grad_norm": 0.12796880304813385,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0017,
+      "step": 31
+    },
+    {
+      "epoch": 0.012390794027250067,
+      "grad_norm": 0.08409107476472855,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0011,
+      "step": 32
+    },
+    {
+      "epoch": 0.012778006340601632,
+      "grad_norm": 0.06334452331066132,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0008,
+      "step": 33
+    },
+    {
+      "epoch": 0.013165218653953197,
+      "grad_norm": 0.04625517874956131,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0006,
+      "step": 34
+    },
+    {
+      "epoch": 0.01355243096730476,
+      "grad_norm": 0.034825753420591354,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0004,
+      "step": 35
+    },
+    {
+      "epoch": 0.013939643280656324,
+      "grad_norm": 3.619255542755127,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3384,
+      "step": 36
+    },
+    {
+      "epoch": 0.01432685559400789,
+      "grad_norm": 10.225979804992676,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.9736,
+      "step": 37
+    },
+    {
+      "epoch": 0.014714067907359454,
+      "grad_norm": 8.408079147338867,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.1675,
+      "step": 38
+    },
+    {
+      "epoch": 0.015101280220711019,
+      "grad_norm": 0.10028885304927826,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0011,
+      "step": 39
+    },
+    {
+      "epoch": 0.015488492534062584,
+      "grad_norm": 0.1408945918083191,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0016,
+      "step": 40
+    },
+    {
+      "epoch": 0.015875704847414147,
+      "grad_norm": 0.1793322116136551,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.002,
+      "step": 41
+    },
+    {
+      "epoch": 0.01626291716076571,
+      "grad_norm": 0.20124785602092743,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0023,
+      "step": 42
+    },
+    {
+      "epoch": 0.016650129474117276,
+      "grad_norm": 0.20105940103530884,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0024,
+      "step": 43
+    },
+    {
+      "epoch": 0.01703734178746884,
+      "grad_norm": 0.18423613905906677,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0022,
+      "step": 44
+    },
+    {
+      "epoch": 0.017424554100820406,
+      "grad_norm": 0.15948553383350372,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.002,
+      "step": 45
+    },
+    {
+      "epoch": 0.01781176641417197,
+      "grad_norm": 0.1380118727684021,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0017,
+      "step": 46
+    },
+    {
+      "epoch": 0.018198978727523536,
+      "grad_norm": 0.1117352768778801,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0014,
+      "step": 47
+    },
+    {
+      "epoch": 0.0185861910408751,
+      "grad_norm": 0.09928926080465317,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0013,
+      "step": 48
+    },
+    {
+      "epoch": 0.018973403354226665,
+      "grad_norm": 7.759567737579346,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.5652,
+      "step": 49
+    },
+    {
+      "epoch": 0.01936061566757823,
+      "grad_norm": 7.83549165725708,
+      "learning_rate": 1e-05,
+      "loss": 0.5574,
+      "step": 50
+    },
+    {
+      "epoch": 0.01936061566757823,
+      "eval_loss": 0.125091552734375,
+      "eval_runtime": 0.5635,
+      "eval_samples_per_second": 88.738,
+      "eval_steps_per_second": 23.072,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null