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:f3ed9cae80840d8cc4649ac0b4f22d9bb152090cbfeac1ce2821ff94a7b77691
+oid sha256:63a64b6636ea3f3f22eb106b974567f9b07ff37ff76024157b54fb6ee85e9ec6
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e500a491e64c302fceb5502940c4aed36a1f0cb08ed4d88e7085ce43bf215f3
+oid sha256:d91ca6b578dad4484ff19c30c249cf761230e15c9bfded881220eb1511820799
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9137ae7518cbb1e88f4c4ec6a53633ab6f3e35caec243ee9e7f3e4cdab14e417
+oid sha256:f6d17a0600242c0e64fe21abd6e7a964fdf37bf7a986e020fbe7f55b0e8b7fb0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b47aa10645607e8f930237fac9f0d293d15bdfdac50df542e29feaab34522a
+oid sha256:1af64d9e5ca598e9e46652e63df0c88628c768e59a3137cb9e4bd4dd166285d3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e49b629c7affb26c96092656ce4a67e3831921adaf86aef352ceeccf166abfa
+oid sha256:f622e886675254457dd050d31905d1436bfc0b9fce8a3994c2b3a25c8ef49e4a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42ffbfa60d2421666fb5239ecf637e6755226c5cd2d0f964be86e15de86e4c97
+oid sha256:f82f3d4827b4f8ca3ec55ccca24af5a8be829c291b2683e46a4ddc17a3554932
 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": 0.0004992838366888463,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.15847860538827258,
+  "best_metric": 0.0002786099212244153,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.31695721077654515,
   "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": 37.403,
       "eval_steps_per_second": 4.68,
       "step": 25
+    },
+    {
+      "epoch": 0.1648177496038035,
+      "grad_norm": 0.2868141531944275,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 26
+    },
+    {
+      "epoch": 0.17115689381933438,
+      "grad_norm": 0.03185323625802994,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0005,
+      "step": 27
+    },
+    {
+      "epoch": 0.1774960380348653,
+      "grad_norm": 0.03331844136118889,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0005,
+      "step": 28
+    },
+    {
+      "epoch": 0.1838351822503962,
+      "grad_norm": 0.010569626465439796,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0004,
+      "step": 29
+    },
+    {
+      "epoch": 0.1901743264659271,
+      "grad_norm": 0.008686893619596958,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0003,
+      "step": 30
+    },
+    {
+      "epoch": 0.196513470681458,
+      "grad_norm": 0.004377232864499092,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0003,
+      "step": 31
+    },
+    {
+      "epoch": 0.20285261489698891,
+      "grad_norm": 0.005554168950766325,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0003,
+      "step": 32
+    },
+    {
+      "epoch": 0.2091917591125198,
+      "grad_norm": 0.004525969736278057,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0003,
+      "step": 33
+    },
+    {
+      "epoch": 0.21553090332805072,
+      "grad_norm": 0.005449299700558186,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0003,
+      "step": 34
+    },
+    {
+      "epoch": 0.2218700475435816,
+      "grad_norm": 0.0035808521788567305,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0003,
+      "step": 35
+    },
+    {
+      "epoch": 0.22820919175911253,
+      "grad_norm": 0.0033939117565751076,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0003,
+      "step": 36
+    },
+    {
+      "epoch": 0.23454833597464342,
+      "grad_norm": 0.003639708273112774,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0004,
+      "step": 37
+    },
+    {
+      "epoch": 0.24088748019017434,
+      "grad_norm": 0.002626145724207163,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0002,
+      "step": 38
+    },
+    {
+      "epoch": 0.24722662440570523,
+      "grad_norm": 0.002726343460381031,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0002,
+      "step": 39
+    },
+    {
+      "epoch": 0.25356576862123614,
+      "grad_norm": 0.002509567653760314,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0002,
+      "step": 40
+    },
+    {
+      "epoch": 0.25990491283676703,
+      "grad_norm": 0.002883738139644265,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0003,
+      "step": 41
+    },
+    {
+      "epoch": 0.2662440570522979,
+      "grad_norm": 0.0029756142757833004,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0003,
+      "step": 42
+    },
+    {
+      "epoch": 0.27258320126782887,
+      "grad_norm": 0.0024971175007522106,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0003,
+      "step": 43
+    },
+    {
+      "epoch": 0.27892234548335976,
+      "grad_norm": 0.003839804558083415,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0003,
+      "step": 44
+    },
+    {
+      "epoch": 0.28526148969889065,
+      "grad_norm": 0.002964878687635064,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0003,
+      "step": 45
+    },
+    {
+      "epoch": 0.29160063391442154,
+      "grad_norm": 0.0027413098141551018,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0003,
+      "step": 46
+    },
+    {
+      "epoch": 0.2979397781299525,
+      "grad_norm": 0.002740249503403902,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0003,
+      "step": 47
+    },
+    {
+      "epoch": 0.30427892234548337,
+      "grad_norm": 0.0029246630147099495,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0003,
+      "step": 48
+    },
+    {
+      "epoch": 0.31061806656101426,
+      "grad_norm": 0.003166801994666457,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0003,
+      "step": 49
+    },
+    {
+      "epoch": 0.31695721077654515,
+      "grad_norm": 0.0033695553429424763,
+      "learning_rate": 0.0,
+      "loss": 0.0003,
+      "step": 50
+    },
+    {
+      "epoch": 0.31695721077654515,
+      "eval_loss": 0.0002786099212244153,
+      "eval_runtime": 28.3691,
+      "eval_samples_per_second": 37.47,
+      "eval_steps_per_second": 4.688,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null