Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241f1bdc4e33ec52859d45885afd568a08bc62b657c3c55ee9ff739bc2a35090
+oid sha256:c1626f8ae03557ceac791e6b5d02413e572f0ecf653ac679b243380ada6822d2
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4021c53a0ceb220159c2dd485a2035593fe4fcdc10697d56173ae28b36d0f879
+oid sha256:4f32286ba984cac6b9c8558ec37ca1fa3f4661685d320c92351d9f3b78a66903
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21ecd10e63dd1dc47ea1d5233b1ac327cc02c43fbc564f225d030b34110a24e7
+oid sha256:b4bd6ba35d984bd6017eb86e40fdf0fbab09c54a4361bc810f5cfe9344041467
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a205a36e1199fa1a62d56eabcae6bef09a1212122b94deb4f4fee3067f0c983
+oid sha256:c56e01a8b6b159ee2202d41557f1256ebfb7623c93415a64d3dba7238597a5d3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf9dcc60c06c1cdb4108eb0c175dca02f76f149672ae2907f80238dc2b858e32
+oid sha256:5ba2c7e08f7977c6c711c1913cf8219741cb20c0f031c16a32ab6ab21603a9ab
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fa2da854882864457511f2652ef9cd9c12d9adeb9536976834560a78cfea688
+oid sha256:ac118f38e76685a7b5ac7e1aec78a9740dca5c4217e037e92ece5f57ce6cf3bc
 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": 10.373350143432617,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7272727272727273,
+  "best_metric": 10.371206283569336,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.4545454545454546,
   "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": 1094.239,
       "eval_steps_per_second": 136.78,
       "step": 25
+    },
+    {
+      "epoch": 0.7563636363636363,
+      "grad_norm": 0.07291626930236816,
+      "learning_rate": 5e-05,
+      "loss": 10.3713,
+      "step": 26
+    },
+    {
+      "epoch": 0.7854545454545454,
+      "grad_norm": 0.06883475184440613,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.37,
+      "step": 27
+    },
+    {
+      "epoch": 0.8145454545454546,
+      "grad_norm": 0.07164252549409866,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3727,
+      "step": 28
+    },
+    {
+      "epoch": 0.8436363636363636,
+      "grad_norm": 0.07420614361763,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3716,
+      "step": 29
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "grad_norm": 0.07898180931806564,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3718,
+      "step": 30
+    },
+    {
+      "epoch": 0.9018181818181819,
+      "grad_norm": 0.08564016222953796,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3744,
+      "step": 31
+    },
+    {
+      "epoch": 0.9309090909090909,
+      "grad_norm": 0.08289813995361328,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3717,
+      "step": 32
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.10542256385087967,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.37,
+      "step": 33
+    },
+    {
+      "epoch": 0.9890909090909091,
+      "grad_norm": 0.11940684914588928,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3709,
+      "step": 34
+    },
+    {
+      "epoch": 1.018181818181818,
+      "grad_norm": 0.14024017751216888,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 17.4511,
+      "step": 35
+    },
+    {
+      "epoch": 1.0472727272727274,
+      "grad_norm": 0.06805068999528885,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 9.9872,
+      "step": 36
+    },
+    {
+      "epoch": 1.0763636363636364,
+      "grad_norm": 0.08220560103654861,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3888,
+      "step": 37
+    },
+    {
+      "epoch": 1.1054545454545455,
+      "grad_norm": 0.10088109970092773,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3326,
+      "step": 38
+    },
+    {
+      "epoch": 1.1345454545454545,
+      "grad_norm": 0.09310103207826614,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.332,
+      "step": 39
+    },
+    {
+      "epoch": 1.1636363636363636,
+      "grad_norm": 0.09103864431381226,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.4093,
+      "step": 40
+    },
+    {
+      "epoch": 1.1927272727272726,
+      "grad_norm": 0.09932649880647659,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.4759,
+      "step": 41
+    },
+    {
+      "epoch": 1.221818181818182,
+      "grad_norm": 0.12177771329879761,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.4992,
+      "step": 42
+    },
+    {
+      "epoch": 1.250909090909091,
+      "grad_norm": 0.06674141436815262,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 7.3741,
+      "step": 43
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.104917012155056,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 13.2692,
+      "step": 44
+    },
+    {
+      "epoch": 1.309090909090909,
+      "grad_norm": 0.07617160677909851,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.2841,
+      "step": 45
+    },
+    {
+      "epoch": 1.3381818181818181,
+      "grad_norm": 0.08638501167297363,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3278,
+      "step": 46
+    },
+    {
+      "epoch": 1.3672727272727272,
+      "grad_norm": 0.09070190787315369,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3126,
+      "step": 47
+    },
+    {
+      "epoch": 1.3963636363636365,
+      "grad_norm": 0.08757533878087997,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.4069,
+      "step": 48
+    },
+    {
+      "epoch": 1.4254545454545455,
+      "grad_norm": 0.10536868870258331,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.4002,
+      "step": 49
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.08869392424821854,
+      "learning_rate": 0.0,
+      "loss": 10.4616,
+      "step": 50
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "eval_loss": 10.371206283569336,
+      "eval_runtime": 0.2127,
+      "eval_samples_per_second": 1090.833,
+      "eval_steps_per_second": 136.354,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null