Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01dc44c6ed6745427a9ea32f0ace8b41fb56697e72378abbcf9ab0938048723a
+oid sha256:b7a6f34774f59073c0a04d1a257790fc59d7d0c04ddc24e25ca671fed15cf415
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0f920c09d5cff7b05b4c063e49641b2cbafbc661da3d18f56923eb3b4a21e28
+oid sha256:db09f17bd9c930ac793c476dacdd0ff98295468ad9061e842c29b575e170b06e
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d3478c36bc89efcfae483b6f40f4b9b900e6729414f2d70432c8b1bb328c52e
+oid sha256:8c7d73a472f245b99172ca1d92eefda05a21dcd4f934855784c3477e37f0ab6d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1671a0e23cc8904f7e46bf35a26469944cea1778c7b64fca8616227fa51cecad
+oid sha256:892c2304a3ea6b3c860e793528cb418f952350ff9a5e893c9c31471f96dcb5be
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b254a7a7224900526ae014de53bf139b9250cb39e4e3a4a86d5c7e5a762361eb
+oid sha256:a0db7d452ecf561890eeec0652612c012c65f41e76d9e9036863a96be0fa0c7e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:942c828eb301b9ac8055e479e8caa30ee37d9335b64e5da7baf63ad563932eb0
+oid sha256:a42d8fb3b92068142797c9be43cdc9310e9dcf06a9b5b72190d9df224a514667
 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": 0.4589807689189911,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6125574272588055,
+  "best_metric": 0.24187077581882477,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2404287901990811,
   "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": 56.428,
       "eval_steps_per_second": 7.182,
       "step": 25
+    },
+    {
+      "epoch": 0.6370597243491577,
+      "grad_norm": 2.1377835273742676,
+      "learning_rate": 5e-05,
+      "loss": 0.5157,
+      "step": 26
+    },
+    {
+      "epoch": 0.6615620214395099,
+      "grad_norm": 1.5148195028305054,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.433,
+      "step": 27
+    },
+    {
+      "epoch": 0.6860643185298622,
+      "grad_norm": 1.4420621395111084,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3174,
+      "step": 28
+    },
+    {
+      "epoch": 0.7105666156202144,
+      "grad_norm": 1.1410839557647705,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1947,
+      "step": 29
+    },
+    {
+      "epoch": 0.7350689127105666,
+      "grad_norm": 1.9239609241485596,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2838,
+      "step": 30
+    },
+    {
+      "epoch": 0.7595712098009189,
+      "grad_norm": 5.68244743347168,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3531,
+      "step": 31
+    },
+    {
+      "epoch": 0.7840735068912711,
+      "grad_norm": 3.725841999053955,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2338,
+      "step": 32
+    },
+    {
+      "epoch": 0.8085758039816233,
+      "grad_norm": 1.9642903804779053,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.344,
+      "step": 33
+    },
+    {
+      "epoch": 0.8330781010719756,
+      "grad_norm": 2.0756185054779053,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3264,
+      "step": 34
+    },
+    {
+      "epoch": 0.8575803981623277,
+      "grad_norm": 1.829140067100525,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.305,
+      "step": 35
+    },
+    {
+      "epoch": 0.8820826952526799,
+      "grad_norm": 1.982605218887329,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.332,
+      "step": 36
+    },
+    {
+      "epoch": 0.9065849923430321,
+      "grad_norm": 2.051780939102173,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2816,
+      "step": 37
+    },
+    {
+      "epoch": 0.9310872894333844,
+      "grad_norm": 1.5406379699707031,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.282,
+      "step": 38
+    },
+    {
+      "epoch": 0.9555895865237366,
+      "grad_norm": 1.2900100946426392,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2143,
+      "step": 39
+    },
+    {
+      "epoch": 0.9800918836140888,
+      "grad_norm": 1.1195809841156006,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1592,
+      "step": 40
+    },
+    {
+      "epoch": 1.0199081163859112,
+      "grad_norm": 4.075118064880371,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1757,
+      "step": 41
+    },
+    {
+      "epoch": 1.0444104134762635,
+      "grad_norm": 1.5390416383743286,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0712,
+      "step": 42
+    },
+    {
+      "epoch": 1.0689127105666156,
+      "grad_norm": 1.3608794212341309,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1826,
+      "step": 43
+    },
+    {
+      "epoch": 1.0934150076569678,
+      "grad_norm": 1.574169635772705,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2734,
+      "step": 44
+    },
+    {
+      "epoch": 1.11791730474732,
+      "grad_norm": 1.5508663654327393,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1916,
+      "step": 45
+    },
+    {
+      "epoch": 1.1424196018376722,
+      "grad_norm": 1.973125696182251,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2452,
+      "step": 46
+    },
+    {
+      "epoch": 1.1669218989280246,
+      "grad_norm": 1.5092109441757202,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3022,
+      "step": 47
+    },
+    {
+      "epoch": 1.1914241960183767,
+      "grad_norm": 1.2294275760650635,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.21,
+      "step": 48
+    },
+    {
+      "epoch": 1.215926493108729,
+      "grad_norm": 0.9760370850563049,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1576,
+      "step": 49
+    },
+    {
+      "epoch": 1.2404287901990811,
+      "grad_norm": 1.2469154596328735,
+      "learning_rate": 0.0,
+      "loss": 0.139,
+      "step": 50
+    },
+    {
+      "epoch": 1.2404287901990811,
+      "eval_loss": 0.24187077581882477,
+      "eval_runtime": 4.871,
+      "eval_samples_per_second": 56.457,
+      "eval_steps_per_second": 7.185,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null