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:cbb3448c1c922b5bb01d4e2194ba3c7e4858fe881704b563b090baa1e497fac4
+oid sha256:9c1a1bd8096366ddc482930b51c1d187f2860dabf838683a91cd2e7f7efc65e7
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba77c840138a3109d3cb3a1736f04277b658ce243576bfdda4c9a4b676a94ce4
+oid sha256:f780a17e8528e9d9b38a282ca06a39e17ac7291384a5b97f605ca0f7bbf3f84e
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50318cf4431ffc2ec6a067006ddb52dba590849dc9f5bfeb18ff820f92fec2ad
+oid sha256:a132b8182a21b2c36a170a78c3daf9957a0573dea2b10a411d9b66537b84c299
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf6f78d02f4560a16ce2dcb24cea1acb40a721da6ae439f68188d048b5fdb61
+oid sha256:585c59b0cc184024ab2dcf9875c08ebdf93253fd26eaed574ce35853a89e33a8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec4174df4cc11b35e7d2462e3a20e49b532627994532427e61268281c8bd8c4
+oid sha256:c15d9b580937c542ab836c7ed358d65bc0e2a4a8b5c98480fc8ba94fc455d053
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a210114ef0feca1e80c89ecdb824ee3e5186c98e9378b08eb68c049bcb6971f
+oid sha256:59a1d5713bbbd78dee1ca392b829407bf783d9edc36309be51566ccdb011232f
 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": 0.05587536096572876,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8620689655172413,
+  "best_metric": 0.03805486857891083,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.7241379310344827,
   "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": 56.629,
       "eval_steps_per_second": 7.26,
       "step": 25
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.3312021791934967,
+      "learning_rate": 5e-05,
+      "loss": 0.0124,
+      "step": 26
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.46960943937301636,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0381,
+      "step": 27
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 1.4453366994857788,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1324,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.372202068567276,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0386,
+      "step": 29
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.1700638085603714,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.023,
+      "step": 30
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.18088839948177338,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0189,
+      "step": 31
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.1496821790933609,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0136,
+      "step": 32
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.2612413465976715,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.029,
+      "step": 33
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 0.26097986102104187,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0222,
+      "step": 34
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.1584685891866684,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0124,
+      "step": 35
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 0.7986224889755249,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.113,
+      "step": 36
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.12980884313583374,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0224,
+      "step": 37
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 0.08840180188417435,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0153,
+      "step": 38
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.19424304366111755,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0212,
+      "step": 39
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.1392383873462677,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.011,
+      "step": 40
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.16765029728412628,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0189,
+      "step": 41
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 0.22004911303520203,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0218,
+      "step": 42
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 1.6118639707565308,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0886,
+      "step": 43
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 0.18371054530143738,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0234,
+      "step": 44
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.18104659020900726,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0233,
+      "step": 45
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 0.13094978034496307,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0115,
+      "step": 46
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.12079468369483948,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0153,
+      "step": 47
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.2212318331003189,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0227,
+      "step": 48
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.24219997227191925,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0172,
+      "step": 49
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.7112542390823364,
+      "learning_rate": 0.0,
+      "loss": 0.0526,
+      "step": 50
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "eval_loss": 0.03805486857891083,
+      "eval_runtime": 3.4427,
+      "eval_samples_per_second": 56.642,
+      "eval_steps_per_second": 7.262,
+      "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