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:f060e1b3a0227edfad6ca1dbacf38dcf00f8fc13ed6b8a3421a311a88282844a
+oid sha256:a700655dcca3cc5edd7ccf5bb7a35f934d4989871dafce3c6f44185e42d4641f
 size 524363632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4822d8c18cd2de1913e6745fe3d6ec6fee40126d98bacb7e42f8ac039b335f9
+oid sha256:0539c1ede4b64354d7b2d1e33d210a736cf988d522ce7505556c0b99a4e35ac4
 size 1049049122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13dcfb623f29ea68e5dd28188c47f7fe3f1132f4127e0c46b736ec98565721f9
+oid sha256:ece95883b612e240f503e36b4ae9b9fc0f91f55eb9b852cf33d825e6c588140d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfab54ae7f14db8d789ac487cb7faf2b1eb28a9f572fbcf888ef58b6e27f7168
+oid sha256:89e436b74253dd5344d89f6f81122cbc7978ad57a3da68db2a846ee2c6000d77
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8bb2f7d239e6605cb72c5e810600c0369ea1afd8d7a701a278938c994bf01c
+oid sha256:d48bbbe7bf1a8c140cca2e67bf7bb23229a6080ac86d16ab40452e993d710b18
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adfb270bf4af70230144f5f38f8161d2463e00c5a12ca69c53cba8bda82966ec
+oid sha256:c03e7224d5111ad56cc34ef27b0f84530aaa8ed2c8f10bc3768788582efb6f2f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6713224649429321,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.003800294522825519,
+  "best_metric": 0.6473457217216492,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.007600589045651038,
   "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": 20.007,
       "eval_steps_per_second": 2.501,
       "step": 25
+    },
+    {
+      "epoch": 0.00395230630373854,
+      "grad_norm": 1.512826681137085,
+      "learning_rate": 5e-05,
+      "loss": 8.0772,
+      "step": 26
+    },
+    {
+      "epoch": 0.00410431808465156,
+      "grad_norm": 1.6408687829971313,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 9.5961,
+      "step": 27
+    },
+    {
+      "epoch": 0.0042563298655645815,
+      "grad_norm": 1.6432344913482666,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 9.4028,
+      "step": 28
+    },
+    {
+      "epoch": 0.004408341646477602,
+      "grad_norm": 1.914554238319397,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 9.7971,
+      "step": 29
+    },
+    {
+      "epoch": 0.0045603534273906225,
+      "grad_norm": 2.6982667446136475,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.672,
+      "step": 30
+    },
+    {
+      "epoch": 0.004712365208303644,
+      "grad_norm": 3.2684669494628906,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.3321,
+      "step": 31
+    },
+    {
+      "epoch": 0.004864376989216664,
+      "grad_norm": 5.5247673988342285,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.4821,
+      "step": 32
+    },
+    {
+      "epoch": 0.005016388770129685,
+      "grad_norm": 7.938380718231201,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.5395,
+      "step": 33
+    },
+    {
+      "epoch": 0.0051684005510427055,
+      "grad_norm": 17.899473190307617,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.4639,
+      "step": 34
+    },
+    {
+      "epoch": 0.005320412331955727,
+      "grad_norm": 15.6568603515625,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.7289,
+      "step": 35
+    },
+    {
+      "epoch": 0.005472424112868747,
+      "grad_norm": 19.337913513183594,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 12.1577,
+      "step": 36
+    },
+    {
+      "epoch": 0.005624435893781768,
+      "grad_norm": 9.574126243591309,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.734,
+      "step": 37
+    },
+    {
+      "epoch": 0.005776447674694789,
+      "grad_norm": 4.890590667724609,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.5739,
+      "step": 38
+    },
+    {
+      "epoch": 0.00592845945560781,
+      "grad_norm": 1.0297945737838745,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 8.4116,
+      "step": 39
+    },
+    {
+      "epoch": 0.00608047123652083,
+      "grad_norm": 1.167446494102478,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 9.198,
+      "step": 40
+    },
+    {
+      "epoch": 0.006232483017433851,
+      "grad_norm": 1.3607698678970337,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 9.9207,
+      "step": 41
+    },
+    {
+      "epoch": 0.006384494798346872,
+      "grad_norm": 2.091355562210083,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 9.8158,
+      "step": 42
+    },
+    {
+      "epoch": 0.006536506579259893,
+      "grad_norm": 2.1468160152435303,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.94,
+      "step": 43
+    },
+    {
+      "epoch": 0.006688518360172913,
+      "grad_norm": 2.633211374282837,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.1247,
+      "step": 44
+    },
+    {
+      "epoch": 0.006840530141085934,
+      "grad_norm": 2.935201644897461,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.9623,
+      "step": 45
+    },
+    {
+      "epoch": 0.006992541921998955,
+      "grad_norm": 11.325116157531738,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.6999,
+      "step": 46
+    },
+    {
+      "epoch": 0.007144553702911976,
+      "grad_norm": 10.919002532958984,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.5474,
+      "step": 47
+    },
+    {
+      "epoch": 0.007296565483824996,
+      "grad_norm": 12.799827575683594,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 12.6207,
+      "step": 48
+    },
+    {
+      "epoch": 0.007448577264738018,
+      "grad_norm": 15.819369316101074,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.777,
+      "step": 49
+    },
+    {
+      "epoch": 0.007600589045651038,
+      "grad_norm": 11.305403709411621,
+      "learning_rate": 0.0,
+      "loss": 12.5455,
+      "step": 50
+    },
+    {
+      "epoch": 0.007600589045651038,
+      "eval_loss": 0.6473457217216492,
+      "eval_runtime": 2211.064,
+      "eval_samples_per_second": 20.044,
+      "eval_steps_per_second": 2.506,
+      "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": 5.537984561503273e+17,
+  "total_flos": 1.1089660061406986e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null