Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0776da48c31f5b9bbaa2639649c3d42a485c332523c2060c0370b5f65de35103
+oid sha256:db6573bd21f049ac82c5ce969dca01a50f5cb39416f9624ec30c555728e35424
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:769492cb6cbf4624002893fa97c24fc648906353798b29649dab883d68c4e76b
+oid sha256:e27c4fa300691426cadb7cf233c2b6e26c2ece4bc41c9b13ef4fcf7df16e2c27
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba9e28f1c65106af5c8efab014c20db9c498c9a241fbd043676c6117294c0627
+oid sha256:6a1dbff46b1a9426d346d440dc9769cfaa1178a01bcb0ee0d1f81dfbf56def65
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d992e9c5a67c49f5f0624c8b3856ee14ca85bf904ae1bbde001aea22955c14
+oid sha256:a1aa7615bb74f836b0c837f4c9efa26e7341b108eff66376bd5f16e03afb200a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28e3f0f55ed0d14dd5e4ed8e5f4eecca5a46754eddadc7729735a68a9e311c65
+oid sha256:3a0122089092180188babd317853180a52d0a24fed83844e8e9533b2cac41c17
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d8d42cfd7b92d7d5544ec3565a64d3b749199b50dcf8db9fc90a74ae1a21f42
+oid sha256:cca30376a87120f65462ad288768f647a3bd206bb215ffcdd56a93b47f150127
 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": 3.0447850227355957,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.015534583867334653,
+  "best_metric": 2.295586347579956,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.031069167734669306,
   "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": 108.96,
       "eval_steps_per_second": 13.627,
       "step": 25
+    },
+    {
+      "epoch": 0.01615596722202804,
+      "grad_norm": 6.254918575286865,
+      "learning_rate": 5e-05,
+      "loss": 2.7294,
+      "step": 26
+    },
+    {
+      "epoch": 0.016777350576721427,
+      "grad_norm": 7.319060802459717,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.8813,
+      "step": 27
+    },
+    {
+      "epoch": 0.017398733931414813,
+      "grad_norm": 8.43337345123291,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.8859,
+      "step": 28
+    },
+    {
+      "epoch": 0.0180201172861082,
+      "grad_norm": 8.820302963256836,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.0777,
+      "step": 29
+    },
+    {
+      "epoch": 0.018641500640801584,
+      "grad_norm": 7.4783854484558105,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.5522,
+      "step": 30
+    },
+    {
+      "epoch": 0.01926288399549497,
+      "grad_norm": 7.428519248962402,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.7819,
+      "step": 31
+    },
+    {
+      "epoch": 0.019884267350188358,
+      "grad_norm": 7.079680442810059,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.6707,
+      "step": 32
+    },
+    {
+      "epoch": 0.020505650704881744,
+      "grad_norm": 6.271028995513916,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.4942,
+      "step": 33
+    },
+    {
+      "epoch": 0.02112703405957513,
+      "grad_norm": 8.533285140991211,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.8131,
+      "step": 34
+    },
+    {
+      "epoch": 0.021748417414268514,
+      "grad_norm": 7.770425796508789,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.6253,
+      "step": 35
+    },
+    {
+      "epoch": 0.0223698007689619,
+      "grad_norm": 7.423771381378174,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.7925,
+      "step": 36
+    },
+    {
+      "epoch": 0.02299118412365529,
+      "grad_norm": 8.581366539001465,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.6777,
+      "step": 37
+    },
+    {
+      "epoch": 0.023612567478348674,
+      "grad_norm": 7.073851108551025,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3883,
+      "step": 38
+    },
+    {
+      "epoch": 0.02423395083304206,
+      "grad_norm": 6.073333740234375,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.2233,
+      "step": 39
+    },
+    {
+      "epoch": 0.024855334187735445,
+      "grad_norm": 7.236076354980469,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.2824,
+      "step": 40
+    },
+    {
+      "epoch": 0.025476717542428834,
+      "grad_norm": 8.7551851272583,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.2064,
+      "step": 41
+    },
+    {
+      "epoch": 0.02609810089712222,
+      "grad_norm": 7.784063339233398,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2192,
+      "step": 42
+    },
+    {
+      "epoch": 0.026719484251815605,
+      "grad_norm": 7.144655227661133,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.3833,
+      "step": 43
+    },
+    {
+      "epoch": 0.02734086760650899,
+      "grad_norm": 6.632129669189453,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1774,
+      "step": 44
+    },
+    {
+      "epoch": 0.027962250961202376,
+      "grad_norm": 6.696552276611328,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.2596,
+      "step": 45
+    },
+    {
+      "epoch": 0.028583634315895765,
+      "grad_norm": 6.228443622589111,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.3508,
+      "step": 46
+    },
+    {
+      "epoch": 0.02920501767058915,
+      "grad_norm": 7.7984538078308105,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.3823,
+      "step": 47
+    },
+    {
+      "epoch": 0.029826401025282535,
+      "grad_norm": 9.903982162475586,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.5122,
+      "step": 48
+    },
+    {
+      "epoch": 0.03044778437997592,
+      "grad_norm": 7.956427097320557,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.5993,
+      "step": 49
+    },
+    {
+      "epoch": 0.031069167734669306,
+      "grad_norm": 8.152593612670898,
+      "learning_rate": 0.0,
+      "loss": 2.592,
+      "step": 50
+    },
+    {
+      "epoch": 0.031069167734669306,
+      "eval_loss": 2.295586347579956,
+      "eval_runtime": 99.4875,
+      "eval_samples_per_second": 108.979,
+      "eval_steps_per_second": 13.63,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null