Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1f710f1dc56fe656a3b990a58b2c1aaa55b76bb6c090cefb9b608c84a8e14e
+oid sha256:b5f2231057ea97b3eb0da1196a944b81fd107a30c3659eca7500fa1cbcb096e8
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e74ded6ade8e929ffbddec8ebd80cad496b3dc5258ea8b1b6092d25a4020a382
+oid sha256:1abc51d2c216cce94d8001cdcafa7d6336c87cb24caf4b70e7544affb17dffec
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:673ae7a52a50c6a7475ff538f82896bcbf815917a32d98ddc4a9be819e364c21
+oid sha256:326688693e766328e101609b0ff4ea0cff3ff732adf951e6f9163d7588a0c66a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cc4380324b89106e42717852a4e9bdfd31284d87326ca3986b525c773437a1e
+oid sha256:813ba29450486a1690f638b7179a04610ea3d95e73ccff3f11876bc22e6a174e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a79a956126850b2d3650389b62449a18d9d0c9bb89b9a1badee290135e8aa6c
+oid sha256:2463c1bf827757950902d50cf99c46269c4ab62ee6c1dfaa532265d9de4d9e8d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04bb243c047597988d47f7ee79d0982d2f7878a043a705cd7f10b1efebc0dc77
+oid sha256:22af2a10f1bac31a491526da1e6e9939ac3dc5c7bd4f8bd9d1179f50e0270ccb
 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": 0.7767251133918762,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7092198581560284,
+  "best_metric": 0.7183287143707275,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.4184397163120568,
   "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": 30.082,
       "eval_steps_per_second": 3.792,
       "step": 25
+    },
+    {
+      "epoch": 0.7375886524822695,
+      "grad_norm": 1.975343108177185,
+      "learning_rate": 5e-05,
+      "loss": 0.5047,
+      "step": 26
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 1.0302635431289673,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1042,
+      "step": 27
+    },
+    {
+      "epoch": 0.7943262411347518,
+      "grad_norm": 0.9461258053779602,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9609,
+      "step": 28
+    },
+    {
+      "epoch": 0.8226950354609929,
+      "grad_norm": 0.8858218789100647,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.894,
+      "step": 29
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.8415829539299011,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7884,
+      "step": 30
+    },
+    {
+      "epoch": 0.8794326241134752,
+      "grad_norm": 0.7886775732040405,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7462,
+      "step": 31
+    },
+    {
+      "epoch": 0.9078014184397163,
+      "grad_norm": 0.805213212966919,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.635,
+      "step": 32
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.9563062191009521,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5737,
+      "step": 33
+    },
+    {
+      "epoch": 0.9645390070921985,
+      "grad_norm": 1.0272057056427002,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5183,
+      "step": 34
+    },
+    {
+      "epoch": 0.9929078014184397,
+      "grad_norm": 2.298342704772949,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5251,
+      "step": 35
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 1.6830999851226807,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5769,
+      "step": 36
+    },
+    {
+      "epoch": 1.049645390070922,
+      "grad_norm": 1.0642327070236206,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8534,
+      "step": 37
+    },
+    {
+      "epoch": 1.0780141843971631,
+      "grad_norm": 1.0689526796340942,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7813,
+      "step": 38
+    },
+    {
+      "epoch": 1.1063829787234043,
+      "grad_norm": 1.1304749250411987,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7206,
+      "step": 39
+    },
+    {
+      "epoch": 1.1347517730496455,
+      "grad_norm": 1.0267786979675293,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6546,
+      "step": 40
+    },
+    {
+      "epoch": 1.1631205673758864,
+      "grad_norm": 1.0408142805099487,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5775,
+      "step": 41
+    },
+    {
+      "epoch": 1.1914893617021276,
+      "grad_norm": 1.1746472120285034,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4895,
+      "step": 42
+    },
+    {
+      "epoch": 1.2198581560283688,
+      "grad_norm": 1.1773086786270142,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4423,
+      "step": 43
+    },
+    {
+      "epoch": 1.24822695035461,
+      "grad_norm": 1.0412017107009888,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2604,
+      "step": 44
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 1.3813236951828003,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.4494,
+      "step": 45
+    },
+    {
+      "epoch": 1.3049645390070923,
+      "grad_norm": 1.0576671361923218,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8167,
+      "step": 46
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.0873304605484009,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.755,
+      "step": 47
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 1.2028731107711792,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6773,
+      "step": 48
+    },
+    {
+      "epoch": 1.3900709219858156,
+      "grad_norm": 1.0739576816558838,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6052,
+      "step": 49
+    },
+    {
+      "epoch": 1.4184397163120568,
+      "grad_norm": 1.1737654209136963,
+      "learning_rate": 0.0,
+      "loss": 0.5532,
+      "step": 50
+    },
+    {
+      "epoch": 1.4184397163120568,
+      "eval_loss": 0.7183287143707275,
+      "eval_runtime": 7.9142,
+      "eval_samples_per_second": 30.073,
+      "eval_steps_per_second": 3.791,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null