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:ad40bd03118ce26faa7ec2c942210d9c4eb1ff2ce12f97432343914cd324d870
+oid sha256:bcbf1f241ae11f9f58bb3db61fba5b46e811619023337596190667dd0d961704
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2380c732e453afa83947da401ca2c93cbdb19eef8144d3dcf59724883eb1dbae
+oid sha256:c5eae3007bdc855fbd432feda41636734bc69e45807746ba56bf932e0a7cb088
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c1742bd3bc2e84133e6cd51a0de3c838aee5d9eb977f8ea761ad0645425404
+oid sha256:0f1844d429bc7d04df0292287bfe221b3fdca5c9984b190a0b25ff0bbc62975a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8c7251375a021d48229ae669d3043b1ce3e864223bbc5d0b8330d78e4294f8
+oid sha256:c3ce916c40a2fa9da8d32553096c7d792cf7a3a6d7c47da2d863282bd9947747
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce4660d367fa5bf6cbba097a1feaca4f77403e5388be6a6c306cd391b484e412
+oid sha256:77d90a9bf5770ab4b51bedd6240fe6225bbbab6cd67ac53cb8b3344279d12370
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:843d5192b4f8c024f1320acaf960fd69c24f52e2f3cb8acfde15375065155787
+oid sha256:ad8c122bfd3c009f38ff3964859fc032e431d1e3de2e7cf62cd19a5548ab6181
 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": 1.0574125051498413,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0222667557336896,
+  "best_metric": 0.913843035697937,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0445335114673792,
   "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": 22.087,
       "eval_steps_per_second": 1.381,
       "step": 25
+    },
+    {
+      "epoch": 0.023157425963037187,
+      "grad_norm": 1.4434211254119873,
+      "learning_rate": 5e-05,
+      "loss": 1.1979,
+      "step": 26
+    },
+    {
+      "epoch": 0.02404809619238477,
+      "grad_norm": 1.282379150390625,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1556,
+      "step": 27
+    },
+    {
+      "epoch": 0.024938766421732355,
+      "grad_norm": 1.0546919107437134,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9802,
+      "step": 28
+    },
+    {
+      "epoch": 0.025829436651079937,
+      "grad_norm": 1.0919930934906006,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9473,
+      "step": 29
+    },
+    {
+      "epoch": 0.026720106880427523,
+      "grad_norm": 1.013401985168457,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9457,
+      "step": 30
+    },
+    {
+      "epoch": 0.027610777109775105,
+      "grad_norm": 1.3264373540878296,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.9195,
+      "step": 31
+    },
+    {
+      "epoch": 0.02850144733912269,
+      "grad_norm": 1.186482548713684,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8382,
+      "step": 32
+    },
+    {
+      "epoch": 0.029392117568470273,
+      "grad_norm": 1.2447603940963745,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7952,
+      "step": 33
+    },
+    {
+      "epoch": 0.03028278779781786,
+      "grad_norm": 1.3419549465179443,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8876,
+      "step": 34
+    },
+    {
+      "epoch": 0.03117345802716544,
+      "grad_norm": 1.4486920833587646,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.928,
+      "step": 35
+    },
+    {
+      "epoch": 0.03206412825651302,
+      "grad_norm": 1.4917124509811401,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9708,
+      "step": 36
+    },
+    {
+      "epoch": 0.03295479848586061,
+      "grad_norm": 1.4312398433685303,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9126,
+      "step": 37
+    },
+    {
+      "epoch": 0.033845468715208195,
+      "grad_norm": 1.4668188095092773,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0575,
+      "step": 38
+    },
+    {
+      "epoch": 0.03473613894455578,
+      "grad_norm": 1.0228489637374878,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1165,
+      "step": 39
+    },
+    {
+      "epoch": 0.03562680917390336,
+      "grad_norm": 1.1922171115875244,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.876,
+      "step": 40
+    },
+    {
+      "epoch": 0.036517479403250945,
+      "grad_norm": 1.4448883533477783,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8162,
+      "step": 41
+    },
+    {
+      "epoch": 0.03740814963259853,
+      "grad_norm": 1.309898853302002,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8612,
+      "step": 42
+    },
+    {
+      "epoch": 0.038298819861946116,
+      "grad_norm": 1.1799569129943848,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7556,
+      "step": 43
+    },
+    {
+      "epoch": 0.039189490091293695,
+      "grad_norm": 1.1924082040786743,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7998,
+      "step": 44
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "grad_norm": 1.1871657371520996,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7922,
+      "step": 45
+    },
+    {
+      "epoch": 0.04097083054998887,
+      "grad_norm": 1.3861472606658936,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8351,
+      "step": 46
+    },
+    {
+      "epoch": 0.04186150077933645,
+      "grad_norm": 1.3767911195755005,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8327,
+      "step": 47
+    },
+    {
+      "epoch": 0.04275217100868404,
+      "grad_norm": 1.8437672853469849,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9629,
+      "step": 48
+    },
+    {
+      "epoch": 0.04364284123803162,
+      "grad_norm": 1.6834858655929565,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0285,
+      "step": 49
+    },
+    {
+      "epoch": 0.0445335114673792,
+      "grad_norm": 1.8425227403640747,
+      "learning_rate": 0.0,
+      "loss": 0.9625,
+      "step": 50
+    },
+    {
+      "epoch": 0.0445335114673792,
+      "eval_loss": 0.913843035697937,
+      "eval_runtime": 685.0025,
+      "eval_samples_per_second": 22.085,
+      "eval_steps_per_second": 1.381,
+      "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": 1.0228361536208896e+18,
+  "total_flos": 2.0456723072417792e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null