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:e99eed57506186bf2934f182e9adb5db9daff8c8a05da6da303870e5b0ae4a29
+oid sha256:c636be3299000ca6e3d7f6f3090e0f187a3175ff6e41c1d03c0dd4a6c75901eb
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1cef65472dbdbbac93b2ae5826969163acf20aba9b6e64bd884ee61fbaedb20
+oid sha256:3de956a8eae8ffd641b07396e6862adfb2566620c360c61a744a837def30eaab
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:295b816b2032a4f602c4dc02701c5590d174df2916c38f4d74bafe90584b28ad
+oid sha256:d9c94b61ccdb23baa6d72baf6e87d741fed7d6973708ab15badbea487510d215
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af43deb306ce7233a53ff7977bc86f50b99475a26eab332068b5d6a5bb7df12
+oid sha256:faf04cc54e4ed9348165301bf9324784db23491502412c8597c066c796a7ae12
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1c744577d95d8c868e337d0f85afd759d7153f33f03faed734c80de3146c1e5
+oid sha256:1608e3e51f6b0ef5a97a99f62b93246f27c931fb5d28ee9357293eca0e2a695d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4942d4ea95a184724a599ee717a7d38f37dfaa66d24b0f8fa7e1cf48661cf2a
+oid sha256:15020c03d63b6bc19821c95d06af9abd62b1d94874457f7ac8bc37753238d2b9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.871764600276947,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12439744985227803,
+  "best_metric": 0.8090626001358032,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.24879489970455607,
   "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": 48.774,
       "eval_steps_per_second": 12.681,
       "step": 25
+    },
+    {
+      "epoch": 0.12937334784636914,
+      "grad_norm": 0.1513061821460724,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 1.0278,
+      "step": 26
+    },
+    {
+      "epoch": 0.13434924584046026,
+      "grad_norm": 0.1964515596628189,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 0.8645,
+      "step": 27
+    },
+    {
+      "epoch": 0.13932514383455138,
+      "grad_norm": 0.24235105514526367,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 0.8915,
+      "step": 28
+    },
+    {
+      "epoch": 0.1443010418286425,
+      "grad_norm": 0.20897287130355835,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 0.9104,
+      "step": 29
+    },
+    {
+      "epoch": 0.14927693982273363,
+      "grad_norm": 0.20914201438426971,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 0.9081,
+      "step": 30
+    },
+    {
+      "epoch": 0.15425283781682475,
+      "grad_norm": 0.20824605226516724,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 0.9098,
+      "step": 31
+    },
+    {
+      "epoch": 0.15922873581091587,
+      "grad_norm": 0.19852378964424133,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 0.9486,
+      "step": 32
+    },
+    {
+      "epoch": 0.164204633805007,
+      "grad_norm": 0.306395024061203,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 0.955,
+      "step": 33
+    },
+    {
+      "epoch": 0.16918053179909812,
+      "grad_norm": 0.2190617471933365,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 0.9907,
+      "step": 34
+    },
+    {
+      "epoch": 0.17415642979318924,
+      "grad_norm": 0.21145637333393097,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 0.9608,
+      "step": 35
+    },
+    {
+      "epoch": 0.17913232778728036,
+      "grad_norm": 0.24957385659217834,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 0.9218,
+      "step": 36
+    },
+    {
+      "epoch": 0.18410822578137148,
+      "grad_norm": 0.2624641954898834,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 0.8877,
+      "step": 37
+    },
+    {
+      "epoch": 0.1890841237754626,
+      "grad_norm": 0.15153071284294128,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 1.0023,
+      "step": 38
+    },
+    {
+      "epoch": 0.19406002176955373,
+      "grad_norm": 0.1561977118253708,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 0.8461,
+      "step": 39
+    },
+    {
+      "epoch": 0.19903591976364485,
+      "grad_norm": 0.18604518473148346,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 0.8691,
+      "step": 40
+    },
+    {
+      "epoch": 0.20401181775773597,
+      "grad_norm": 0.16946768760681152,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 0.8581,
+      "step": 41
+    },
+    {
+      "epoch": 0.2089877157518271,
+      "grad_norm": 0.1662844568490982,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 0.8686,
+      "step": 42
+    },
+    {
+      "epoch": 0.2139636137459182,
+      "grad_norm": 0.16444341838359833,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 0.8854,
+      "step": 43
+    },
+    {
+      "epoch": 0.21893951174000933,
+      "grad_norm": 0.17267289757728577,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 0.8595,
+      "step": 44
+    },
+    {
+      "epoch": 0.22391540973410046,
+      "grad_norm": 0.20546430349349976,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 0.9038,
+      "step": 45
+    },
+    {
+      "epoch": 0.22889130772819158,
+      "grad_norm": 0.1972435861825943,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 0.9723,
+      "step": 46
+    },
+    {
+      "epoch": 0.2338672057222827,
+      "grad_norm": 0.2849563658237457,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 0.9412,
+      "step": 47
+    },
+    {
+      "epoch": 0.23884310371637382,
+      "grad_norm": 0.2184210568666458,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 0.9191,
+      "step": 48
+    },
+    {
+      "epoch": 0.24381900171046494,
+      "grad_norm": 0.23135943710803986,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.8842,
+      "step": 49
+    },
+    {
+      "epoch": 0.24879489970455607,
+      "grad_norm": 0.3442687690258026,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 0.8583,
+      "step": 50
+    },
+    {
+      "epoch": 0.24879489970455607,
+      "eval_loss": 0.8090626001358032,
+      "eval_runtime": 1.0254,
+      "eval_samples_per_second": 48.761,
+      "eval_steps_per_second": 12.678,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null