Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d9214de4e057864b006ecc8ba47dfbae619be71db3ecdb65de9b26c5a3b934f
+oid sha256:eb26d6e8d3547f8e509856cd93fe772f7d35750d318074d4788a6d0449c64807
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a923e6026fdde0bb91d0898eb5c1fa1d8ba31ae0071007307318d7f86cdf26e5
+oid sha256:53e8629c3e75b11a35cc31ad9c46724d2bf70a91cf5e6cbbe307f2f9e299a498
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e291c1e5ddac21c4a1b392cae7f3047d6d59a5b8579f6aa34cd2008ad17fab
+oid sha256:eaa2f8d6922058b9ec0d3bdbd8cb566ea4df9155a0436d32d6833a7baa73fbb5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa00242471c7046052744493fbb51e57e1cd8834965a003261e10d9d351e6ab3
+oid sha256:363626abc27f8777c5e6665c3a9bc05c0c85da237a3c68b8613eaeaadd65f1a7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38fd75e0669d892569f5f62a07a5fcb98e32a1683904049c171ceabc7344c900
+oid sha256:06df35eb117d71e87030cb26e1e6473864512c1384786e8a4522aebfd7267ac2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5f6e38a22582ec77a17dd3b6ded81d7b8a1e0b7be21f8d2132087fb99b3d01
+oid sha256:e49f27149f6d756c3ce36ea28784415cb223406f34a959ac72687eb6e39e1e2d
 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": 1.3429416418075562,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.14727540500736377,
+  "best_metric": 0.6226815581321716,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.29455081001472755,
   "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": 39.451,
       "eval_steps_per_second": 4.931,
       "step": 25
+    },
+    {
+      "epoch": 0.15316642120765833,
+      "grad_norm": 3.405451774597168,
+      "learning_rate": 5e-05,
+      "loss": 1.216,
+      "step": 26
+    },
+    {
+      "epoch": 0.15905743740795286,
+      "grad_norm": 3.620307445526123,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.3363,
+      "step": 27
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 3.1116671562194824,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1192,
+      "step": 28
+    },
+    {
+      "epoch": 0.17083946980854198,
+      "grad_norm": 2.9447152614593506,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.0844,
+      "step": 29
+    },
+    {
+      "epoch": 0.17673048600883653,
+      "grad_norm": 3.7199738025665283,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1033,
+      "step": 30
+    },
+    {
+      "epoch": 0.18262150220913106,
+      "grad_norm": 2.903928756713867,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.9522,
+      "step": 31
+    },
+    {
+      "epoch": 0.18851251840942562,
+      "grad_norm": 3.3113131523132324,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8444,
+      "step": 32
+    },
+    {
+      "epoch": 0.19440353460972018,
+      "grad_norm": 2.6979331970214844,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7607,
+      "step": 33
+    },
+    {
+      "epoch": 0.20029455081001474,
+      "grad_norm": 3.231203556060791,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7709,
+      "step": 34
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 3.6387054920196533,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7232,
+      "step": 35
+    },
+    {
+      "epoch": 0.21207658321060383,
+      "grad_norm": 2.7801897525787354,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5396,
+      "step": 36
+    },
+    {
+      "epoch": 0.21796759941089838,
+      "grad_norm": 2.580199718475342,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7473,
+      "step": 37
+    },
+    {
+      "epoch": 0.22385861561119294,
+      "grad_norm": 1.9330986738204956,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6726,
+      "step": 38
+    },
+    {
+      "epoch": 0.22974963181148747,
+      "grad_norm": 2.1914916038513184,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5355,
+      "step": 39
+    },
+    {
+      "epoch": 0.23564064801178203,
+      "grad_norm": 2.175992488861084,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6397,
+      "step": 40
+    },
+    {
+      "epoch": 0.24153166421207659,
+      "grad_norm": 3.0352063179016113,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6349,
+      "step": 41
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 3.7624361515045166,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5524,
+      "step": 42
+    },
+    {
+      "epoch": 0.2533136966126657,
+      "grad_norm": 2.5523576736450195,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4813,
+      "step": 43
+    },
+    {
+      "epoch": 0.25920471281296026,
+      "grad_norm": 2.155388593673706,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4657,
+      "step": 44
+    },
+    {
+      "epoch": 0.2650957290132548,
+      "grad_norm": 1.2593159675598145,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.491,
+      "step": 45
+    },
+    {
+      "epoch": 0.2709867452135493,
+      "grad_norm": 1.8870849609375,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4691,
+      "step": 46
+    },
+    {
+      "epoch": 0.2768777614138439,
+      "grad_norm": 1.8218656778335571,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4868,
+      "step": 47
+    },
+    {
+      "epoch": 0.28276877761413843,
+      "grad_norm": 1.4828749895095825,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5507,
+      "step": 48
+    },
+    {
+      "epoch": 0.28865979381443296,
+      "grad_norm": 1.5562994480133057,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4537,
+      "step": 49
+    },
+    {
+      "epoch": 0.29455081001472755,
+      "grad_norm": 2.369784116744995,
+      "learning_rate": 0.0,
+      "loss": 0.6343,
+      "step": 50
+    },
+    {
+      "epoch": 0.29455081001472755,
+      "eval_loss": 0.6226815581321716,
+      "eval_runtime": 29.0409,
+      "eval_samples_per_second": 39.393,
+      "eval_steps_per_second": 4.924,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null