Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66f91cbecb570e3e26482948c06e8de031ae472470b571d9df7120734d03a79a
+oid sha256:f5e0f9de1bce5f95202ad78b246917997d62c45d8fcafd5c289216265bf7d7ea
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:967bc34c84d1f8d83b12d8004682e52edd037309764d2cfdb59b48cb34604c23
+oid sha256:432c5289691219c4fa483bf8c7e7a92fc99f4f87aa6a7879e4290bbba08d97ad
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:292a7f92b1cb6732ddf91b6b95e587e573a27070789b84253804c60ce351f7d8
+oid sha256:e9df473a16054c5d816635b9697c7f3cb7aea07828670122421541deceb62f13
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec24ac115cb18439724ad35824747dd6f44100ad9d5f97a6c0c1e911bcf8c16d
+oid sha256:23d387b9b65349cecb16f390e4046101a737ef63251b6c314098fd5409071d55
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de842223a688900d464b8a24a2707996e051586f5f3665a23c01c78e5aceede
+oid sha256:48dea8604c1f29c95bb23f97bf45a4cef6c9a14ead31f639c20f80954225ad31
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:162383461de21efc644ec3706d45f491c82612d641d604ae1ddfff12aa39e2f5
+oid sha256:ef5a8cd0cc2655f64103ce9b66245c8d34d68c36eaf942d9ff2d29651be7b7b7
 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": 11.936413764953613,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006816284102721401,
+  "best_metric": 11.935344696044922,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.013632568205442803,
   "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": 234.348,
       "eval_steps_per_second": 29.297,
       "step": 25
+    },
+    {
+      "epoch": 0.007088935466830258,
+      "grad_norm": 0.07601311802864075,
+      "learning_rate": 5e-05,
+      "loss": 11.9352,
+      "step": 26
+    },
+    {
+      "epoch": 0.007361586830939113,
+      "grad_norm": 0.05736768618226051,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9408,
+      "step": 27
+    },
+    {
+      "epoch": 0.00763423819504797,
+      "grad_norm": 0.0675104558467865,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9415,
+      "step": 28
+    },
+    {
+      "epoch": 0.007906889559156825,
+      "grad_norm": 0.06402797251939774,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9409,
+      "step": 29
+    },
+    {
+      "epoch": 0.008179540923265682,
+      "grad_norm": 0.06155916303396225,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9298,
+      "step": 30
+    },
+    {
+      "epoch": 0.008452192287374538,
+      "grad_norm": 0.08942660689353943,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9303,
+      "step": 31
+    },
+    {
+      "epoch": 0.008724843651483394,
+      "grad_norm": 0.08944093436002731,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9482,
+      "step": 32
+    },
+    {
+      "epoch": 0.00899749501559225,
+      "grad_norm": 0.06475299596786499,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9365,
+      "step": 33
+    },
+    {
+      "epoch": 0.009270146379701106,
+      "grad_norm": 0.07812382280826569,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9407,
+      "step": 34
+    },
+    {
+      "epoch": 0.009542797743809962,
+      "grad_norm": 0.08350091427564621,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9416,
+      "step": 35
+    },
+    {
+      "epoch": 0.009815449107918818,
+      "grad_norm": 0.0940701887011528,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.928,
+      "step": 36
+    },
+    {
+      "epoch": 0.010088100472027675,
+      "grad_norm": 0.08712836354970932,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9316,
+      "step": 37
+    },
+    {
+      "epoch": 0.01036075183613653,
+      "grad_norm": 0.08466362208127975,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9293,
+      "step": 38
+    },
+    {
+      "epoch": 0.010633403200245386,
+      "grad_norm": 0.06831790506839752,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9335,
+      "step": 39
+    },
+    {
+      "epoch": 0.010906054564354242,
+      "grad_norm": 0.06954491883516312,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9384,
+      "step": 40
+    },
+    {
+      "epoch": 0.011178705928463099,
+      "grad_norm": 0.10085248202085495,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.9408,
+      "step": 41
+    },
+    {
+      "epoch": 0.011451357292571955,
+      "grad_norm": 0.05636737868189812,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9306,
+      "step": 42
+    },
+    {
+      "epoch": 0.01172400865668081,
+      "grad_norm": 0.07049186527729034,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9382,
+      "step": 43
+    },
+    {
+      "epoch": 0.011996660020789666,
+      "grad_norm": 0.0855134129524231,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9295,
+      "step": 44
+    },
+    {
+      "epoch": 0.012269311384898523,
+      "grad_norm": 0.10347723960876465,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9361,
+      "step": 45
+    },
+    {
+      "epoch": 0.012541962749007379,
+      "grad_norm": 0.06473658233880997,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.9392,
+      "step": 46
+    },
+    {
+      "epoch": 0.012814614113116235,
+      "grad_norm": 0.09248223900794983,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9402,
+      "step": 47
+    },
+    {
+      "epoch": 0.01308726547722509,
+      "grad_norm": 0.08586801588535309,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9338,
+      "step": 48
+    },
+    {
+      "epoch": 0.013359916841333946,
+      "grad_norm": 0.1005331352353096,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9279,
+      "step": 49
+    },
+    {
+      "epoch": 0.013632568205442803,
+      "grad_norm": 0.08666856586933136,
+      "learning_rate": 0.0,
+      "loss": 11.9394,
+      "step": 50
+    },
+    {
+      "epoch": 0.013632568205442803,
+      "eval_loss": 11.935344696044922,
+      "eval_runtime": 105.0647,
+      "eval_samples_per_second": 235.179,
+      "eval_steps_per_second": 29.401,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null