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:dc9b8f1b2b1fbf0c6919db0f1a160b058fbf3b1d8defa1d4467cf858ee9454f8
+oid sha256:c1dbb8356759f5988f6c5cbfc8f13512eb46353b6f330952811c103cf75b8775
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fd1f04d979e1c7c90a62984e95fe8b5cc1663c697a619b0272e420cab6cedd0
+oid sha256:c4f6c9d7e244afa28bfbb6672f60baf33997b15b7023d4606fdcb75500e836f0
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf1123e22727d4bd29dfc3f7986580b709e7262fb445b3a59fd272b0ec3f6329
+oid sha256:b4bc4454a44b59df9eb79dca1bcef9567150ca655415cca9b443452bfe769754
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4984f416a70f5fb132a77837eba1f7aba5c1fb013bbb694bee0333203728ee5
+oid sha256:c5def7b04d55347c0da2c49a00f2ee9711d9ed0caa071fcf33bfe7bf0c0d5344
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e65dd4c3493cb2fdb41f8c4ceb8163b73437d72cd9206a2d6e74022294248aa
+oid sha256:f4a437c7b38a78c7914db9971f1aed255c877e8d5296ffd9fc4fa5b57503e80a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed54a3c588821715b929ffab3aca65f17c4d739d827dd351ac64e2162c692576
+oid sha256:c3c8b552385e22627197a2669cd06da7fb77f6f10d4404daaabfac3497bca7fd
 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": 1.8273491859436035,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2336448598130841,
+  "best_metric": 1.7651193141937256,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4672897196261682,
   "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": 44.88,
       "eval_steps_per_second": 5.664,
       "step": 25
+    },
+    {
+      "epoch": 0.24299065420560748,
+      "grad_norm": 0.3034875690937042,
+      "learning_rate": 5e-05,
+      "loss": 1.5706,
+      "step": 26
+    },
+    {
+      "epoch": 0.2523364485981308,
+      "grad_norm": 0.6375843286514282,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.8791,
+      "step": 27
+    },
+    {
+      "epoch": 0.2616822429906542,
+      "grad_norm": 0.803412139415741,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.7813,
+      "step": 28
+    },
+    {
+      "epoch": 0.27102803738317754,
+      "grad_norm": 0.855148196220398,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.9444,
+      "step": 29
+    },
+    {
+      "epoch": 0.2803738317757009,
+      "grad_norm": 0.8513876795768738,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8844,
+      "step": 30
+    },
+    {
+      "epoch": 0.2897196261682243,
+      "grad_norm": 0.5708866715431213,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.0226,
+      "step": 31
+    },
+    {
+      "epoch": 0.29906542056074764,
+      "grad_norm": 0.487387090921402,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.9533,
+      "step": 32
+    },
+    {
+      "epoch": 0.308411214953271,
+      "grad_norm": 0.4321051836013794,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.8319,
+      "step": 33
+    },
+    {
+      "epoch": 0.3177570093457944,
+      "grad_norm": 0.47179585695266724,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7397,
+      "step": 34
+    },
+    {
+      "epoch": 0.32710280373831774,
+      "grad_norm": 0.8138007521629333,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.7525,
+      "step": 35
+    },
+    {
+      "epoch": 0.3364485981308411,
+      "grad_norm": 1.496353030204773,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.7203,
+      "step": 36
+    },
+    {
+      "epoch": 0.34579439252336447,
+      "grad_norm": 2.553820848464966,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.6391,
+      "step": 37
+    },
+    {
+      "epoch": 0.35514018691588783,
+      "grad_norm": 0.33150145411491394,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6745,
+      "step": 38
+    },
+    {
+      "epoch": 0.3644859813084112,
+      "grad_norm": 0.23893839120864868,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.6146,
+      "step": 39
+    },
+    {
+      "epoch": 0.37383177570093457,
+      "grad_norm": 0.2919956147670746,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.8551,
+      "step": 40
+    },
+    {
+      "epoch": 0.38317757009345793,
+      "grad_norm": 0.33135730028152466,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.8577,
+      "step": 41
+    },
+    {
+      "epoch": 0.3925233644859813,
+      "grad_norm": 0.3283659815788269,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.8772,
+      "step": 42
+    },
+    {
+      "epoch": 0.40186915887850466,
+      "grad_norm": 0.30547505617141724,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.9234,
+      "step": 43
+    },
+    {
+      "epoch": 0.411214953271028,
+      "grad_norm": 0.3091796636581421,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9524,
+      "step": 44
+    },
+    {
+      "epoch": 0.4205607476635514,
+      "grad_norm": 0.3936629891395569,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.9619,
+      "step": 45
+    },
+    {
+      "epoch": 0.42990654205607476,
+      "grad_norm": 0.4935019910335541,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.8527,
+      "step": 46
+    },
+    {
+      "epoch": 0.4392523364485981,
+      "grad_norm": 0.6257709264755249,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.6672,
+      "step": 47
+    },
+    {
+      "epoch": 0.4485981308411215,
+      "grad_norm": 1.0982800722122192,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.9316,
+      "step": 48
+    },
+    {
+      "epoch": 0.45794392523364486,
+      "grad_norm": 1.8124440908432007,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7562,
+      "step": 49
+    },
+    {
+      "epoch": 0.4672897196261682,
+      "grad_norm": 5.867586135864258,
+      "learning_rate": 0.0,
+      "loss": 2.547,
+      "step": 50
+    },
+    {
+      "epoch": 0.4672897196261682,
+      "eval_loss": 1.7651193141937256,
+      "eval_runtime": 16.0955,
+      "eval_samples_per_second": 44.795,
+      "eval_steps_per_second": 5.654,
+      "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": 5.317548060128051e+16,
+  "total_flos": 1.0635096147099648e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null