Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f22a4448e592e29d020c67c6cf2b2b72050d657aab7e740b4cde58a54dd81b8
+oid sha256:e13682518cb723d3d499b404d0eb5c799843be1eff4ccbb169f8750d51a41540
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c49311c6fba2a231661d5085276389173ab510498b1219dcb46c6246c48e74a1
+oid sha256:74fb3b07f957b00e64575826c4bdb9f24153edab4791304cec0c038ea42e1d5e
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79d969f1a2c98fb08c30a096b34a2e61bf87c7f69b575937f7a0b7c8efd13484
+oid sha256:9cd84017d7a45649ab4b602dd4b32c386d449c9e5dbcaa9d31e2c1dab8834ea0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d66904108cd7c23c4f04d424a35487440ab0d8755fe6630bbc54ff1ffe96f52b
+oid sha256:945b478f0683f5f1de6a8e7b70e971d13eae00048bbf09dfd05f6821263770bf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d208c72c4c3f20d4c3f17256f6a6fcd4a2520e9350f5cdb0030dffd1404f076
+oid sha256:87a50460e0aaf5b8ef80783169e5d7bfd133adc474093fd8c944b58733b99b02
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d974818fb8608f37fa9fc42ad2d4832b2d1f47fd529c8ccdb6b0cc17fc7f8a72
+oid sha256:c0809f1ef07bc038f80e0c26d2634aa5671635abc0c4a8b8b7eee6465e6bde43
 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": 10.371033668518066,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05670541536716756,
+  "best_metric": 10.364799499511719,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11341083073433512,
   "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": 977.536,
       "eval_steps_per_second": 122.439,
       "step": 25
+    },
+    {
+      "epoch": 0.05897363198185427,
+      "grad_norm": 0.20476947724819183,
+      "learning_rate": 5e-05,
+      "loss": 10.3699,
+      "step": 26
+    },
+    {
+      "epoch": 0.06124184859654097,
+      "grad_norm": 0.23112817108631134,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3707,
+      "step": 27
+    },
+    {
+      "epoch": 0.06351006521122768,
+      "grad_norm": 0.23180252313613892,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3711,
+      "step": 28
+    },
+    {
+      "epoch": 0.06577828182591437,
+      "grad_norm": 0.22128894925117493,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3708,
+      "step": 29
+    },
+    {
+      "epoch": 0.06804649844060108,
+      "grad_norm": 0.2330835610628128,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3695,
+      "step": 30
+    },
+    {
+      "epoch": 0.07031471505528777,
+      "grad_norm": 0.2294759452342987,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3689,
+      "step": 31
+    },
+    {
+      "epoch": 0.07258293166997448,
+      "grad_norm": 0.23074816167354584,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3672,
+      "step": 32
+    },
+    {
+      "epoch": 0.07485114828466119,
+      "grad_norm": 0.2303849160671234,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3683,
+      "step": 33
+    },
+    {
+      "epoch": 0.07711936489934788,
+      "grad_norm": 0.22095413506031036,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3697,
+      "step": 34
+    },
+    {
+      "epoch": 0.07938758151403459,
+      "grad_norm": 0.2163832187652588,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3694,
+      "step": 35
+    },
+    {
+      "epoch": 0.0816557981287213,
+      "grad_norm": 0.20412799715995789,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3699,
+      "step": 36
+    },
+    {
+      "epoch": 0.08392401474340799,
+      "grad_norm": 0.21430176496505737,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3699,
+      "step": 37
+    },
+    {
+      "epoch": 0.0861922313580947,
+      "grad_norm": 0.240758016705513,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3665,
+      "step": 38
+    },
+    {
+      "epoch": 0.0884604479727814,
+      "grad_norm": 0.24734526872634888,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3648,
+      "step": 39
+    },
+    {
+      "epoch": 0.0907286645874681,
+      "grad_norm": 0.25556033849716187,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3649,
+      "step": 40
+    },
+    {
+      "epoch": 0.09299688120215481,
+      "grad_norm": 0.25022992491722107,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3659,
+      "step": 41
+    },
+    {
+      "epoch": 0.0952650978168415,
+      "grad_norm": 0.2543710768222809,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3659,
+      "step": 42
+    },
+    {
+      "epoch": 0.09753331443152821,
+      "grad_norm": 0.2404075562953949,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3647,
+      "step": 43
+    },
+    {
+      "epoch": 0.09980153104621492,
+      "grad_norm": 0.24763478338718414,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.365,
+      "step": 44
+    },
+    {
+      "epoch": 0.10206974766090161,
+      "grad_norm": 0.2456260770559311,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3668,
+      "step": 45
+    },
+    {
+      "epoch": 0.10433796427558832,
+      "grad_norm": 0.23241014778614044,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3673,
+      "step": 46
+    },
+    {
+      "epoch": 0.10660618089027502,
+      "grad_norm": 0.2225053906440735,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3674,
+      "step": 47
+    },
+    {
+      "epoch": 0.10887439750496172,
+      "grad_norm": 0.21233010292053223,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3674,
+      "step": 48
+    },
+    {
+      "epoch": 0.11114261411964843,
+      "grad_norm": 0.21536342799663544,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.369,
+      "step": 49
+    },
+    {
+      "epoch": 0.11341083073433512,
+      "grad_norm": 0.2400255799293518,
+      "learning_rate": 0.0,
+      "loss": 10.3672,
+      "step": 50
+    },
+    {
+      "epoch": 0.11341083073433512,
+      "eval_loss": 10.364799499511719,
+      "eval_runtime": 3.032,
+      "eval_samples_per_second": 979.564,
+      "eval_steps_per_second": 122.693,
+      "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": 21397394817024.0,
+  "total_flos": 42781424615424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null