Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb2c3a25241eecb49f45102a462c1a867c4ddbf41e942761389cc6ef48e982f
+oid sha256:db2deb7f842d74ae78d908a0588bbcd71ce5606120af1344bf5672e8fe8ce687
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54d58dfbbe092a91b74e212276b291539c7d79e08d384cac1684d1fb33d76262
+oid sha256:5fe13c13f699fedc836feabaa8cab48216d6dd354e3a925c01cad32ab755fa92
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07699f63a63508290cf5759d4d7e7a6c445b4a0c82266521f5b2cf69e5cf9911
+oid sha256:75b28266347b805fcca09e41bec39b50e355d2008e7db4d4637820031e112ba1
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cc2de43e15586f6730ab11e4fda8a8670af253f15aaed626e2c896d7573708c
+oid sha256:8c1e18e8c43f600fc8339420f1d48f418c2067ba0306f5a5bfd2492213544878
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f15eeedadf17c57997ba6b24ec6035ae786ea543ddce7ed8f3f088a435855d
+oid sha256:321f694e1d744ed15985579673b36def2ee2c0955d91c721a1c6893e5d2e4464
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99552e27738afbd34aa7b8d180aaf5cc3bae612c804a074188efd7cd44af9ce3
+oid sha256:e2622c656cf80b046070df937a4027bbca6ae7bb5aaa0c5181e307994a6b957c
 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": 0.23825594782829285,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.10934937124111536,
+  "best_metric": 0.19170191884040833,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.21869874248223073,
   "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": 13.511,
       "eval_steps_per_second": 1.692,
       "step": 25
+    },
+    {
+      "epoch": 0.11372334609075997,
+      "grad_norm": 11.166613578796387,
+      "learning_rate": 5e-05,
+      "loss": 0.178,
+      "step": 26
+    },
+    {
+      "epoch": 0.1180973209404046,
+      "grad_norm": 10.714858055114746,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2399,
+      "step": 27
+    },
+    {
+      "epoch": 0.1224712957900492,
+      "grad_norm": 11.066264152526855,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2025,
+      "step": 28
+    },
+    {
+      "epoch": 0.1268452706396938,
+      "grad_norm": 12.516129493713379,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2187,
+      "step": 29
+    },
+    {
+      "epoch": 0.13121924548933844,
+      "grad_norm": 9.812530517578125,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1807,
+      "step": 30
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 9.20337963104248,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1832,
+      "step": 31
+    },
+    {
+      "epoch": 0.13996719518862766,
+      "grad_norm": 9.085219383239746,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.191,
+      "step": 32
+    },
+    {
+      "epoch": 0.1443411700382723,
+      "grad_norm": 13.772695541381836,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.244,
+      "step": 33
+    },
+    {
+      "epoch": 0.1487151448879169,
+      "grad_norm": 12.057571411132812,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2197,
+      "step": 34
+    },
+    {
+      "epoch": 0.1530891197375615,
+      "grad_norm": 12.592830657958984,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2383,
+      "step": 35
+    },
+    {
+      "epoch": 0.15746309458720611,
+      "grad_norm": 16.97599983215332,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2584,
+      "step": 36
+    },
+    {
+      "epoch": 0.16183706943685075,
+      "grad_norm": 11.718450546264648,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.238,
+      "step": 37
+    },
+    {
+      "epoch": 0.16621104428649536,
+      "grad_norm": 11.560559272766113,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.21,
+      "step": 38
+    },
+    {
+      "epoch": 0.17058501913613996,
+      "grad_norm": 8.881017684936523,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1504,
+      "step": 39
+    },
+    {
+      "epoch": 0.17495899398578457,
+      "grad_norm": 10.893447875976562,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.167,
+      "step": 40
+    },
+    {
+      "epoch": 0.1793329688354292,
+      "grad_norm": 14.648825645446777,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2115,
+      "step": 41
+    },
+    {
+      "epoch": 0.18370694368507381,
+      "grad_norm": 10.353060722351074,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2011,
+      "step": 42
+    },
+    {
+      "epoch": 0.18808091853471842,
+      "grad_norm": 11.638842582702637,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2043,
+      "step": 43
+    },
+    {
+      "epoch": 0.19245489338436303,
+      "grad_norm": 7.406494140625,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1753,
+      "step": 44
+    },
+    {
+      "epoch": 0.19682886823400766,
+      "grad_norm": 7.78684663772583,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1552,
+      "step": 45
+    },
+    {
+      "epoch": 0.20120284308365227,
+      "grad_norm": 7.1053595542907715,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2005,
+      "step": 46
+    },
+    {
+      "epoch": 0.20557681793329688,
+      "grad_norm": 9.848479270935059,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2091,
+      "step": 47
+    },
+    {
+      "epoch": 0.2099507927829415,
+      "grad_norm": 10.150044441223145,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1856,
+      "step": 48
+    },
+    {
+      "epoch": 0.21432476763258612,
+      "grad_norm": 8.909294128417969,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2062,
+      "step": 49
+    },
+    {
+      "epoch": 0.21869874248223073,
+      "grad_norm": 9.131242752075195,
+      "learning_rate": 0.0,
+      "loss": 0.2145,
+      "step": 50
+    },
+    {
+      "epoch": 0.21869874248223073,
+      "eval_loss": 0.19170191884040833,
+      "eval_runtime": 114.0536,
+      "eval_samples_per_second": 13.511,
+      "eval_steps_per_second": 1.692,
+      "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": 1.4844960464646963e+17,
+  "total_flos": 2.968064857808568e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null