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:fa85d0c575a0b8e4f4a90e86e6081a237847da08c96d2ea20630f29d8c74b536
+oid sha256:0b20886436c85ceddcc6abf2ab9d4f3dbecadcaff7b53cabc19cc51f0f7fee5c
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c1c03c8e071469dda3127aa4761920012b51a4e1cbf1bc20d0da23220a3955
+oid sha256:8ca2bf750c7bb7c76ba395377b094b83ab50b1356a2ebfbcfe87cc17ab4d08f2
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80a2f64624a4517595b8ab458d41b3858dc6bb9921bf93eeef60c02efed78338
+oid sha256:783c6aa076eea79c46e8bb462106198ff31620e9aba7177676c8190ce538bbf5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd32814da516be87f7f6362916fa4411c1c1fc12559679f528e11b98e4047f85
+oid sha256:7150abb9fcb185e17099bbc84fc212dc66a29fbe329f22974acb628bb7516150
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a1d105b7d31d493499cc7ff534f1b97d7155b4606c00bca8384cef77bc6feb
+oid sha256:898153dd11c615be9cbd81e16c8bee8a74666c4083c52895bd042848b5b14a9c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:461a4998509830822568ea3c374b83a4f183346a41392e0425aee8ae060544f8
+oid sha256:4c5a06f1cc0201819e8855735e74ed17790b4531a1f553cf4ec240d6e4367e7f
 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": 0.4300152063369751,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.15311004784688995,
+  "best_metric": 0.3231343924999237,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3062200956937799,
   "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": 33.649,
       "eval_steps_per_second": 8.749,
       "step": 25
+    },
+    {
+      "epoch": 0.15923444976076556,
+      "grad_norm": 0.33280134201049805,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.2019,
+      "step": 26
+    },
+    {
+      "epoch": 0.16535885167464115,
+      "grad_norm": 0.2794322669506073,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.1846,
+      "step": 27
+    },
+    {
+      "epoch": 0.17148325358851674,
+      "grad_norm": 0.4203859567642212,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.1423,
+      "step": 28
+    },
+    {
+      "epoch": 0.17760765550239235,
+      "grad_norm": 0.5897067189216614,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.1647,
+      "step": 29
+    },
+    {
+      "epoch": 0.18373205741626794,
+      "grad_norm": 1.02996826171875,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6039,
+      "step": 30
+    },
+    {
+      "epoch": 0.18985645933014353,
+      "grad_norm": 2.1310155391693115,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.8006,
+      "step": 31
+    },
+    {
+      "epoch": 0.19598086124401914,
+      "grad_norm": 2.2415904998779297,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8306,
+      "step": 32
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 1.361811637878418,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.7494,
+      "step": 33
+    },
+    {
+      "epoch": 0.20822966507177035,
+      "grad_norm": 2.034090757369995,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8148,
+      "step": 34
+    },
+    {
+      "epoch": 0.21435406698564594,
+      "grad_norm": 2.464292049407959,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.658,
+      "step": 35
+    },
+    {
+      "epoch": 0.22047846889952152,
+      "grad_norm": 0.8960682153701782,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.5261,
+      "step": 36
+    },
+    {
+      "epoch": 0.22660287081339714,
+      "grad_norm": 0.8402606844902039,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.479,
+      "step": 37
+    },
+    {
+      "epoch": 0.23272727272727273,
+      "grad_norm": 0.34880414605140686,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.2051,
+      "step": 38
+    },
+    {
+      "epoch": 0.23885167464114831,
+      "grad_norm": 0.3065963387489319,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.1794,
+      "step": 39
+    },
+    {
+      "epoch": 0.24497607655502393,
+      "grad_norm": 0.2842368185520172,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.159,
+      "step": 40
+    },
+    {
+      "epoch": 0.25110047846889955,
+      "grad_norm": 0.7232906818389893,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1185,
+      "step": 41
+    },
+    {
+      "epoch": 0.25722488038277513,
+      "grad_norm": 0.6430230140686035,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.2502,
+      "step": 42
+    },
+    {
+      "epoch": 0.2633492822966507,
+      "grad_norm": 1.1256890296936035,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.5465,
+      "step": 43
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 1.3127527236938477,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5744,
+      "step": 44
+    },
+    {
+      "epoch": 0.2755980861244019,
+      "grad_norm": 1.1628435850143433,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6626,
+      "step": 45
+    },
+    {
+      "epoch": 0.2817224880382775,
+      "grad_norm": 1.0411521196365356,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.5987,
+      "step": 46
+    },
+    {
+      "epoch": 0.28784688995215313,
+      "grad_norm": 1.2186107635498047,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.5531,
+      "step": 47
+    },
+    {
+      "epoch": 0.2939712918660287,
+      "grad_norm": 0.935568630695343,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.5234,
+      "step": 48
+    },
+    {
+      "epoch": 0.3000956937799043,
+      "grad_norm": 0.8467996716499329,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3728,
+      "step": 49
+    },
+    {
+      "epoch": 0.3062200956937799,
+      "grad_norm": 1.2814409732818604,
+      "learning_rate": 1e-05,
+      "loss": 0.4109,
+      "step": 50
+    },
+    {
+      "epoch": 0.3062200956937799,
+      "eval_loss": 0.3231343924999237,
+      "eval_runtime": 1.522,
+      "eval_samples_per_second": 32.851,
+      "eval_steps_per_second": 8.541,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null