Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f26b7fdca7cf86427cfb789c196a00a4d0316539c716c5bdb38fe7fedcdc316
+oid sha256:25a4878228cc769a30da86e4d1e035c7bd585001d9cb2914da288353eca04dcf
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e690692e96a111e83e1ba5d0e180cede9468c27112947abedeea8b32a222d63
+oid sha256:2dddf1aad2843da3bd6c35a7b58db120c8d44db9a2f7a6866ce76f60f0b5dbc7
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:223e82255515d979e73c21c81965e5e1ae05ddecb3f1b198290297bf1d967c87
+oid sha256:26fb36513ae96468e2e3db91d8b12a94d30f0a5bb51726fbc628bb989da7735a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59fb30b31fc7b4cc8a77d469d50169ad2d70607b43a02f5d60d3fc2c87e1bd47
+oid sha256:3a4be15ebee0d15559f21767b823f60c5985d265bd7773086c89ca438b62dc53
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cec640f97fe7d17d4de2efb3fd682f22d82fe6e4d32ae0d3dcc11798fa7e5768
+oid sha256:a9ff28b38f32fa54628d7645b3c371b7e129acc62ce870a586bcc2d1a188db9b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792f5b62e206f2949f60ce8eaeefa408b4a6da0c5a453e2a5c56d7ee17ccb6a6
+oid sha256:e418c84c46f6adcf55890b8e4c699e6cd0ce47a4e59e388fbb43dbfd1e40dc71
 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": 0.009557968936860561,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8849557522123894,
+  "best_metric": 0.004239150322973728,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.7699115044247788,
   "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": 32.536,
       "eval_steps_per_second": 4.11,
       "step": 25
+    },
+    {
+      "epoch": 0.9203539823008849,
+      "grad_norm": 0.17116095125675201,
+      "learning_rate": 5e-05,
+      "loss": 0.0109,
+      "step": 26
+    },
+    {
+      "epoch": 0.9557522123893806,
+      "grad_norm": 0.374548077583313,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0133,
+      "step": 27
+    },
+    {
+      "epoch": 0.9911504424778761,
+      "grad_norm": 0.458191454410553,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.015,
+      "step": 28
+    },
+    {
+      "epoch": 1.0265486725663717,
+      "grad_norm": 0.30738526582717896,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0112,
+      "step": 29
+    },
+    {
+      "epoch": 1.0619469026548674,
+      "grad_norm": 0.13246457278728485,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0026,
+      "step": 30
+    },
+    {
+      "epoch": 1.0973451327433628,
+      "grad_norm": 0.18884605169296265,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0055,
+      "step": 31
+    },
+    {
+      "epoch": 1.1327433628318584,
+      "grad_norm": 0.021148117259144783,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0027,
+      "step": 32
+    },
+    {
+      "epoch": 1.168141592920354,
+      "grad_norm": 0.2229768931865692,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0058,
+      "step": 33
+    },
+    {
+      "epoch": 1.2035398230088497,
+      "grad_norm": 0.1037597805261612,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0024,
+      "step": 34
+    },
+    {
+      "epoch": 1.238938053097345,
+      "grad_norm": 0.2901352345943451,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0197,
+      "step": 35
+    },
+    {
+      "epoch": 1.2743362831858407,
+      "grad_norm": 0.2113533914089203,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0057,
+      "step": 36
+    },
+    {
+      "epoch": 1.3097345132743363,
+      "grad_norm": 0.36708688735961914,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0125,
+      "step": 37
+    },
+    {
+      "epoch": 1.3451327433628317,
+      "grad_norm": 0.20552334189414978,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0029,
+      "step": 38
+    },
+    {
+      "epoch": 1.3805309734513274,
+      "grad_norm": 0.08920054882764816,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.006,
+      "step": 39
+    },
+    {
+      "epoch": 1.415929203539823,
+      "grad_norm": 0.6489487886428833,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0039,
+      "step": 40
+    },
+    {
+      "epoch": 1.4513274336283186,
+      "grad_norm": 0.10894274711608887,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0014,
+      "step": 41
+    },
+    {
+      "epoch": 1.4867256637168142,
+      "grad_norm": 0.07067730277776718,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0032,
+      "step": 42
+    },
+    {
+      "epoch": 1.5221238938053099,
+      "grad_norm": 1.4301823377609253,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0046,
+      "step": 43
+    },
+    {
+      "epoch": 1.5575221238938053,
+      "grad_norm": 0.07354891300201416,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0052,
+      "step": 44
+    },
+    {
+      "epoch": 1.592920353982301,
+      "grad_norm": 0.15491953492164612,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0052,
+      "step": 45
+    },
+    {
+      "epoch": 1.6283185840707963,
+      "grad_norm": 0.07862751930952072,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.003,
+      "step": 46
+    },
+    {
+      "epoch": 1.663716814159292,
+      "grad_norm": 0.031061874702572823,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0011,
+      "step": 47
+    },
+    {
+      "epoch": 1.6991150442477876,
+      "grad_norm": 0.2089461386203766,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0015,
+      "step": 48
+    },
+    {
+      "epoch": 1.7345132743362832,
+      "grad_norm": 0.2084563821554184,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0051,
+      "step": 49
+    },
+    {
+      "epoch": 1.7699115044247788,
+      "grad_norm": 0.07801011949777603,
+      "learning_rate": 0.0,
+      "loss": 0.0054,
+      "step": 50
+    },
+    {
+      "epoch": 1.7699115044247788,
+      "eval_loss": 0.004239150322973728,
+      "eval_runtime": 5.8375,
+      "eval_samples_per_second": 32.548,
+      "eval_steps_per_second": 4.111,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null