Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7250b765e316fe929476035e04b142a34329b50518e40e717bd8f6272b8e6ce6
+oid sha256:ff7a6d33b12c17ad49ea99b2e660cc8730695f2f38f45dd14f872244982bbe4a
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e614e2920a87121e6e56446d74646e9c1bf1a613e511ca82b97bdd1d93cd060b
+oid sha256:9d4e0e1049514058186478dabb1e5cbe93f2a8e44e2621f43c9810897b3726b1
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afcd18e3f593a840fd05c192049d390540acabeb020168cddeed069d5095c987
+oid sha256:3846a277a4a9ef1d50dab570cb54920be39e80bdea54ff2024f11e4153ad8fc0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f19b50a08d405434de0f90f03a433c12c1ab5268746c6ceda2ea0e4a7e4bb0b4
+oid sha256:364b9790f1f17dbab2912d4060330aa172186d7edd2054222d2d1b602cba2fdf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:796b3e0280dfd52664c48186ab7bf20fd50ada45868d214288d61eb1483f56f8
+oid sha256:e7066e46d6d619b046925faf92e276bb13330399babaaa55e18202b2ce9725af
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2530ee0a8e2e56b4a26e7251583b75f76f21aa3d213b6bf804e8fbff53eabd5
+oid sha256:74754752eb1d75d67b97577c0808a61af59a05a265cf4556299e55d1a2494dfb
 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": 1.6952250003814697,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05136106831022085,
+  "best_metric": 1.6436538696289062,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1027221366204417,
   "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": 15.238,
       "eval_steps_per_second": 1.905,
       "step": 25
+    },
+    {
+      "epoch": 0.05341551104262968,
+      "grad_norm": 44.00088882446289,
+      "learning_rate": 5e-05,
+      "loss": 27.7822,
+      "step": 26
+    },
+    {
+      "epoch": 0.05546995377503852,
+      "grad_norm": 42.3242073059082,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 27.3737,
+      "step": 27
+    },
+    {
+      "epoch": 0.05752439650744735,
+      "grad_norm": 38.348670959472656,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 27.6254,
+      "step": 28
+    },
+    {
+      "epoch": 0.05957883923985619,
+      "grad_norm": 37.97185516357422,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 27.3671,
+      "step": 29
+    },
+    {
+      "epoch": 0.061633281972265024,
+      "grad_norm": 37.6766471862793,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 27.7831,
+      "step": 30
+    },
+    {
+      "epoch": 0.06368772470467386,
+      "grad_norm": 35.792240142822266,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 26.383,
+      "step": 31
+    },
+    {
+      "epoch": 0.0657421674370827,
+      "grad_norm": 30.798736572265625,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 26.7846,
+      "step": 32
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 34.46708679199219,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 26.9403,
+      "step": 33
+    },
+    {
+      "epoch": 0.06985105290190036,
+      "grad_norm": 32.722984313964844,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 25.5387,
+      "step": 34
+    },
+    {
+      "epoch": 0.07190549563430919,
+      "grad_norm": 33.066802978515625,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 27.3704,
+      "step": 35
+    },
+    {
+      "epoch": 0.07395993836671803,
+      "grad_norm": 35.121376037597656,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 26.1383,
+      "step": 36
+    },
+    {
+      "epoch": 0.07601438109912687,
+      "grad_norm": 32.85065841674805,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 26.2707,
+      "step": 37
+    },
+    {
+      "epoch": 0.0780688238315357,
+      "grad_norm": 34.69348907470703,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 27.4932,
+      "step": 38
+    },
+    {
+      "epoch": 0.08012326656394453,
+      "grad_norm": 36.420936584472656,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 26.7692,
+      "step": 39
+    },
+    {
+      "epoch": 0.08217770929635336,
+      "grad_norm": 34.44639587402344,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 26.6481,
+      "step": 40
+    },
+    {
+      "epoch": 0.08423215202876219,
+      "grad_norm": 30.01451301574707,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 25.7843,
+      "step": 41
+    },
+    {
+      "epoch": 0.08628659476117104,
+      "grad_norm": 25.13599395751953,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 26.7225,
+      "step": 42
+    },
+    {
+      "epoch": 0.08834103749357987,
+      "grad_norm": 26.27276039123535,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 25.5646,
+      "step": 43
+    },
+    {
+      "epoch": 0.0903954802259887,
+      "grad_norm": 24.683252334594727,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 25.5756,
+      "step": 44
+    },
+    {
+      "epoch": 0.09244992295839753,
+      "grad_norm": 25.751869201660156,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 26.0279,
+      "step": 45
+    },
+    {
+      "epoch": 0.09450436569080636,
+      "grad_norm": 30.72328758239746,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 24.7662,
+      "step": 46
+    },
+    {
+      "epoch": 0.09655880842321521,
+      "grad_norm": 32.1501579284668,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 26.0407,
+      "step": 47
+    },
+    {
+      "epoch": 0.09861325115562404,
+      "grad_norm": 37.73057174682617,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 25.4584,
+      "step": 48
+    },
+    {
+      "epoch": 0.10066769388803287,
+      "grad_norm": 36.1685791015625,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 25.6212,
+      "step": 49
+    },
+    {
+      "epoch": 0.1027221366204417,
+      "grad_norm": 48.9822883605957,
+      "learning_rate": 0.0,
+      "loss": 28.0915,
+      "step": 50
+    },
+    {
+      "epoch": 0.1027221366204417,
+      "eval_loss": 1.6436538696289062,
+      "eval_runtime": 85.2925,
+      "eval_samples_per_second": 38.456,
+      "eval_steps_per_second": 4.807,
+      "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": 2.829013890367488e+17,
+  "total_flos": 5.658027780734976e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null