Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac440f3bfda95f3c309df63c4ec97679fb018f356b6efe3e5da566c919ce57a
+oid sha256:2be26991b818eab085f981b806b743b7da5ec435da964f05831c22fca65d33f8
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c970ec90478afffefebe676adb000d4056f3aefdde15e5be05e65405cb2fa00
+oid sha256:611e5a3ef8cf1846e74690fbb6c7a2b06235a74b4a957516d5c4e476e1af2d9a
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311cc331d499d19e9e6eae2bcbe34ced87efe083bbc6047aaafa1f2f11cbb9d0
+oid sha256:cad0d4e6a88ea386f8abf2677982cddeac96d178a90ef06004506cd6a030138e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0773ddfdf86f961d785e81532fa715a2e4435a871f6c919fa60675c08c295fbd
+oid sha256:2c8526811c0ee68733bcd48c1ceaa08e2d7f6ca66207c667c7b363a279727946
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b8678ef505a886985c0de8235e35a2a1c7e1b05c7c067984ef6b5548490387d
+oid sha256:3c9e147370d47e8faecf0d1c12d344e6cb01b494177262c261095f197c02201d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f8fecd1381bd3aad69660f58a933a7dae1b3bf3f4cfb7f35798c5043e32c5ff
+oid sha256:94e831b56258dfabd310b25b088b9c021b28177b35000039aa4f3a9dc2010c62
 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": 0.648818850517273,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.3071895424836601,
+  "best_metric": 0.526287853717804,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.6143790849673203,
   "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": 138.623,
       "eval_steps_per_second": 18.268,
       "step": 25
+    },
+    {
+      "epoch": 1.3594771241830066,
+      "grad_norm": 1.6588599681854248,
+      "learning_rate": 5e-05,
+      "loss": 0.5987,
+      "step": 26
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 1.7340439558029175,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5583,
+      "step": 27
+    },
+    {
+      "epoch": 1.4640522875816995,
+      "grad_norm": 1.5749491453170776,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.602,
+      "step": 28
+    },
+    {
+      "epoch": 1.5163398692810457,
+      "grad_norm": 1.7133127450942993,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6292,
+      "step": 29
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 2.0184829235076904,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.6021,
+      "step": 30
+    },
+    {
+      "epoch": 1.6209150326797386,
+      "grad_norm": 1.7977181673049927,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5567,
+      "step": 31
+    },
+    {
+      "epoch": 1.673202614379085,
+      "grad_norm": 1.6275135278701782,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5543,
+      "step": 32
+    },
+    {
+      "epoch": 1.7254901960784315,
+      "grad_norm": 1.8324847221374512,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5745,
+      "step": 33
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 1.6420360803604126,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.52,
+      "step": 34
+    },
+    {
+      "epoch": 1.8300653594771243,
+      "grad_norm": 1.4819954633712769,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4934,
+      "step": 35
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 1.4158824682235718,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5388,
+      "step": 36
+    },
+    {
+      "epoch": 1.934640522875817,
+      "grad_norm": 1.7841893434524536,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4938,
+      "step": 37
+    },
+    {
+      "epoch": 1.9869281045751634,
+      "grad_norm": 1.9757091999053955,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5301,
+      "step": 38
+    },
+    {
+      "epoch": 2.0392156862745097,
+      "grad_norm": 3.0482711791992188,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.9327,
+      "step": 39
+    },
+    {
+      "epoch": 2.0915032679738563,
+      "grad_norm": 1.5659737586975098,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4755,
+      "step": 40
+    },
+    {
+      "epoch": 2.1437908496732025,
+      "grad_norm": 1.4230481386184692,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5159,
+      "step": 41
+    },
+    {
+      "epoch": 2.196078431372549,
+      "grad_norm": 1.5947973728179932,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4792,
+      "step": 42
+    },
+    {
+      "epoch": 2.2483660130718954,
+      "grad_norm": 1.546298623085022,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4841,
+      "step": 43
+    },
+    {
+      "epoch": 2.3006535947712417,
+      "grad_norm": 1.5563234090805054,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5057,
+      "step": 44
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 1.8946163654327393,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4677,
+      "step": 45
+    },
+    {
+      "epoch": 2.4052287581699345,
+      "grad_norm": 1.349687933921814,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4777,
+      "step": 46
+    },
+    {
+      "epoch": 2.457516339869281,
+      "grad_norm": 1.4442392587661743,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4766,
+      "step": 47
+    },
+    {
+      "epoch": 2.5098039215686274,
+      "grad_norm": 1.3940331935882568,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5297,
+      "step": 48
+    },
+    {
+      "epoch": 2.5620915032679736,
+      "grad_norm": 1.1987098455429077,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5222,
+      "step": 49
+    },
+    {
+      "epoch": 2.6143790849673203,
+      "grad_norm": 1.7109036445617676,
+      "learning_rate": 0.0,
+      "loss": 0.4988,
+      "step": 50
+    },
+    {
+      "epoch": 2.6143790849673203,
+      "eval_loss": 0.526287853717804,
+      "eval_runtime": 0.9308,
+      "eval_samples_per_second": 138.584,
+      "eval_steps_per_second": 18.263,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null