Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b31375091ca7f5ea000141800dd9dea68286a4970cade48cb2373a07fac979c
+oid sha256:31e0618fc6a8607bbb49ad5a50cb697c042adc60767e750b79613a37cef0b128
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2499e6566495c084502669d9a90cc7093427c5b9e408bea40e5e22270d710cc3
+oid sha256:bdae47392e67c1c7fc0c3d993f69b803f632c0cc37ac536a8a258ee4685c1046
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3070421566c5776414e5e2227d930a884a7b72ffb711065f0c57e5ebeee3500
+oid sha256:2a1a9fbb17e0128b3d66a8d9a8071505c52d19884b05d72e908ad76b3a11be71
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3294ebf4303ff31548f7a435e8b4f9bbb06b52bc16ea2a0c017590bc86bec827
+oid sha256:b7441c245976c20a2f2d187639e7ea723da29fb0ac31e4b88ccd15aad8b370bd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d2942c13edc4eb7a78c363badfe7a14b3811df196dea183b81243f3151f34c8
+oid sha256:cafcaad1da76924cacef18fce0bfd0edeb269bce6cbcff4bf81db23fd3bb4b8a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af492df0b9b803a972db35475e07477deb4520af7ebedd3a3f5a3af482ba8334
+oid sha256:2cf4eadbd7849de393922307bcbda4017128535a71d5958b959c5bfa68b7ddb7
 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": 0.7057486176490784,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.045625641610585146,
+  "best_metric": 0.6615861654281616,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09125128322117029,
   "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": 14.201,
       "eval_steps_per_second": 3.692,
       "step": 25
+    },
+    {
+      "epoch": 0.04745066727500855,
+      "grad_norm": 0.35791102051734924,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3363,
+      "step": 26
+    },
+    {
+      "epoch": 0.04927569293943196,
+      "grad_norm": 0.4550030529499054,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6224,
+      "step": 27
+    },
+    {
+      "epoch": 0.051100718603855365,
+      "grad_norm": 0.48958098888397217,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.6362,
+      "step": 28
+    },
+    {
+      "epoch": 0.05292574426827877,
+      "grad_norm": 0.44201797246932983,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.5601,
+      "step": 29
+    },
+    {
+      "epoch": 0.05475076993270218,
+      "grad_norm": 0.6427817344665527,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.701,
+      "step": 30
+    },
+    {
+      "epoch": 0.05657579559712558,
+      "grad_norm": 0.5233768224716187,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.6829,
+      "step": 31
+    },
+    {
+      "epoch": 0.05840082126154899,
+      "grad_norm": 0.5784444212913513,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.699,
+      "step": 32
+    },
+    {
+      "epoch": 0.060225846925972396,
+      "grad_norm": 0.4978267252445221,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.7049,
+      "step": 33
+    },
+    {
+      "epoch": 0.0620508725903958,
+      "grad_norm": 0.5924655199050903,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8093,
+      "step": 34
+    },
+    {
+      "epoch": 0.06387589825481921,
+      "grad_norm": 0.6393359303474426,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.9385,
+      "step": 35
+    },
+    {
+      "epoch": 0.06570092391924262,
+      "grad_norm": 0.7333190441131592,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0239,
+      "step": 36
+    },
+    {
+      "epoch": 0.06752594958366602,
+      "grad_norm": 0.7314161658287048,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.9217,
+      "step": 37
+    },
+    {
+      "epoch": 0.06935097524808943,
+      "grad_norm": 0.3770674765110016,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4129,
+      "step": 38
+    },
+    {
+      "epoch": 0.07117600091251283,
+      "grad_norm": 0.31523048877716064,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.3984,
+      "step": 39
+    },
+    {
+      "epoch": 0.07300102657693623,
+      "grad_norm": 0.3684380054473877,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5525,
+      "step": 40
+    },
+    {
+      "epoch": 0.07482605224135964,
+      "grad_norm": 0.4422256052494049,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.6015,
+      "step": 41
+    },
+    {
+      "epoch": 0.07665107790578304,
+      "grad_norm": 0.4704034626483917,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.56,
+      "step": 42
+    },
+    {
+      "epoch": 0.07847610357020646,
+      "grad_norm": 0.4587417542934418,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6929,
+      "step": 43
+    },
+    {
+      "epoch": 0.08030112923462986,
+      "grad_norm": 0.5037869215011597,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6836,
+      "step": 44
+    },
+    {
+      "epoch": 0.08212615489905327,
+      "grad_norm": 0.56147301197052,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.8363,
+      "step": 45
+    },
+    {
+      "epoch": 0.08395118056347667,
+      "grad_norm": 0.5316286683082581,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6747,
+      "step": 46
+    },
+    {
+      "epoch": 0.08577620622790008,
+      "grad_norm": 0.5714614987373352,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.7197,
+      "step": 47
+    },
+    {
+      "epoch": 0.08760123189232348,
+      "grad_norm": 0.622653067111969,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9239,
+      "step": 48
+    },
+    {
+      "epoch": 0.0894262575567469,
+      "grad_norm": 0.7487273216247559,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0149,
+      "step": 49
+    },
+    {
+      "epoch": 0.09125128322117029,
+      "grad_norm": 0.8299003839492798,
+      "learning_rate": 1e-05,
+      "loss": 0.959,
+      "step": 50
+    },
+    {
+      "epoch": 0.09125128322117029,
+      "eval_loss": 0.6615861654281616,
+      "eval_runtime": 3.4787,
+      "eval_samples_per_second": 14.373,
+      "eval_steps_per_second": 3.737,
+      "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": 2,
   "trial_name": null,
   "trial_params": null