Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:984c8f51c316ddee2c8c4057acd29c5af93d08f9daf32a1b4f5e9e50718dc85d
+oid sha256:52ddf7430f43f7bb4f7fe818ff3237251819a1a1581f5c75fd064f7400820a42
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0ee4c759b1a28d270bfa3be948fc7fb1b5edd2373778f511ef135cc2edf7ff0
+oid sha256:73c8fe83598a8b99926bf8cf449d5703a0cd14fff55defb90592895179d76d1e
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f34967511e9c0c6b990403a86930545938976e3006f61527b311042075fdf6e
+oid sha256:de456f0cda4ded45539b127beeade50f79db6f5f9ca00dfc5ce87717168a90ab
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ced07717fe511713a8b54a221648310d4367f9cbc4d5c7a2d8cd912e0c448d01
+oid sha256:99fa427ee7bc495f09a25978d583baa2133a7b7e65ba29071c170d5d9e54e5a4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccdf74fb4cb8b62bda9ba6971b54b3f19e311c28913ff06c4209c74eff8a86b3
+oid sha256:bb853eda42c797d3a6f4a4b3519889e30c70dd217b5182c4d6feef8f3c4004a0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c33d6956f59ff01a1187c574132e3b2f5f88b7293598adc007420b9275647c3c
+oid sha256:1fd9a870b8e8ef12cffc9417532cabfb4c08839f52f6bbb0ae402a8d7a74570e
 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": 2.180121660232544,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.046216060080878106,
+  "best_metric": 2.125446319580078,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09243212016175621,
   "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": 18.577,
       "eval_steps_per_second": 2.325,
       "step": 25
+    },
+    {
+      "epoch": 0.04806470248411323,
+      "grad_norm": 6.43618631362915,
+      "learning_rate": 5e-05,
+      "loss": 35.4224,
+      "step": 26
+    },
+    {
+      "epoch": 0.04991334488734835,
+      "grad_norm": 5.413757801055908,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 35.036,
+      "step": 27
+    },
+    {
+      "epoch": 0.051761987290583476,
+      "grad_norm": 5.203230857849121,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 34.8169,
+      "step": 28
+    },
+    {
+      "epoch": 0.0536106296938186,
+      "grad_norm": 4.647735595703125,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 34.5951,
+      "step": 29
+    },
+    {
+      "epoch": 0.05545927209705372,
+      "grad_norm": 4.8249030113220215,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 35.1794,
+      "step": 30
+    },
+    {
+      "epoch": 0.057307914500288853,
+      "grad_norm": 4.604319095611572,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 34.3148,
+      "step": 31
+    },
+    {
+      "epoch": 0.05915655690352398,
+      "grad_norm": 4.745401382446289,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 34.8345,
+      "step": 32
+    },
+    {
+      "epoch": 0.0610051993067591,
+      "grad_norm": 5.0841827392578125,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 34.4468,
+      "step": 33
+    },
+    {
+      "epoch": 0.06285384170999422,
+      "grad_norm": 5.102455139160156,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 35.1716,
+      "step": 34
+    },
+    {
+      "epoch": 0.06470248411322935,
+      "grad_norm": 5.342426776885986,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 35.2404,
+      "step": 35
+    },
+    {
+      "epoch": 0.06655112651646447,
+      "grad_norm": 5.370707035064697,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 34.8448,
+      "step": 36
+    },
+    {
+      "epoch": 0.0683997689196996,
+      "grad_norm": 5.79181432723999,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 33.7319,
+      "step": 37
+    },
+    {
+      "epoch": 0.07024841132293472,
+      "grad_norm": 6.2982048988342285,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 33.9213,
+      "step": 38
+    },
+    {
+      "epoch": 0.07209705372616984,
+      "grad_norm": 5.291693687438965,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 34.5111,
+      "step": 39
+    },
+    {
+      "epoch": 0.07394569612940496,
+      "grad_norm": 4.546117782592773,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 34.1011,
+      "step": 40
+    },
+    {
+      "epoch": 0.07579433853264009,
+      "grad_norm": 4.630704879760742,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 34.2026,
+      "step": 41
+    },
+    {
+      "epoch": 0.07764298093587521,
+      "grad_norm": 5.070968151092529,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 33.7099,
+      "step": 42
+    },
+    {
+      "epoch": 0.07949162333911033,
+      "grad_norm": 4.362644672393799,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 34.7216,
+      "step": 43
+    },
+    {
+      "epoch": 0.08134026574234547,
+      "grad_norm": 4.545483112335205,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 34.2825,
+      "step": 44
+    },
+    {
+      "epoch": 0.0831889081455806,
+      "grad_norm": 4.54011869430542,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 34.3374,
+      "step": 45
+    },
+    {
+      "epoch": 0.08503755054881572,
+      "grad_norm": 4.860706806182861,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 34.3632,
+      "step": 46
+    },
+    {
+      "epoch": 0.08688619295205084,
+      "grad_norm": 4.582858085632324,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 34.2021,
+      "step": 47
+    },
+    {
+      "epoch": 0.08873483535528597,
+      "grad_norm": 5.009143829345703,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 34.2615,
+      "step": 48
+    },
+    {
+      "epoch": 0.09058347775852109,
+      "grad_norm": 5.0846967697143555,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 34.5984,
+      "step": 49
+    },
+    {
+      "epoch": 0.09243212016175621,
+      "grad_norm": 7.233031272888184,
+      "learning_rate": 0.0,
+      "loss": 33.5723,
+      "step": 50
+    },
+    {
+      "epoch": 0.09243212016175621,
+      "eval_loss": 2.125446319580078,
+      "eval_runtime": 123.502,
+      "eval_samples_per_second": 29.506,
+      "eval_steps_per_second": 3.692,
+      "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": 1.483568811343872e+17,
+  "total_flos": 2.967137622687744e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null