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:d4f3fded8f63a675d7c5be4f66cd9f06d7bf1747a357dc9d1f60f23a9e6d5b7d
+oid sha256:522fec858c8522245e73501e38495ebe5d1341ad512b8ab6a4d32de6edcde4a8
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:161e0581bac858eaaac187f5f44a6a8dd34471b10b59d049c8bce8ed7517fc18
+oid sha256:d27b45c08111365f487dea2960a3b21d16da8b96b29e69f7fd1d5339f2da73d1
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e5ca49b12bcba613b8aa1525a7df06d0aaeaa79db1b0d79a8906117e695ce9
+oid sha256:bb4d748d2557fe2cee5c5bc98075ebf8b5e12b202d82ce761ac85afbb41d4309
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:202a920a3b3b309b77c68bfcff3689d00f1bc83ec60347cf0d011b5a94ba849e
+oid sha256:ad0be6660baa40d02de08e01c285b006b3eaeeb2711050e90fbdaacd346e28d3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a235c250721f789e2e5fa683c36a63c52620eb9df31bf60c8c174b8cb6031c32
+oid sha256:83051d74046ab3e2f27831e23988fc04e9a1d362304650a7a5987d077399eb46
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a52b324e96dd466c336dd08ba883ff79b9375f7e113004a9b430be0a3fb0fb1
+oid sha256:32340d5489cae5a44888f4965953370bc24a5fa2f8c34bc59d16350a09227dcd
 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": 0.9366830587387085,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.27434842249657065,
+  "best_metric": 0.9280461072921753,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5486968449931413,
   "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": 10.21,
       "eval_steps_per_second": 1.28,
       "step": 25
+    },
+    {
+      "epoch": 0.28532235939643347,
+      "grad_norm": 2.419912338256836,
+      "learning_rate": 5e-05,
+      "loss": 0.7928,
+      "step": 26
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 1.7259137630462646,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8779,
+      "step": 27
+    },
+    {
+      "epoch": 0.30727023319615915,
+      "grad_norm": 1.8197636604309082,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8595,
+      "step": 28
+    },
+    {
+      "epoch": 0.31824417009602196,
+      "grad_norm": 1.6042948961257935,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.892,
+      "step": 29
+    },
+    {
+      "epoch": 0.3292181069958848,
+      "grad_norm": 1.546321153640747,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8862,
+      "step": 30
+    },
+    {
+      "epoch": 0.3401920438957476,
+      "grad_norm": 1.2811124324798584,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.9036,
+      "step": 31
+    },
+    {
+      "epoch": 0.3511659807956104,
+      "grad_norm": 1.3372602462768555,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.9272,
+      "step": 32
+    },
+    {
+      "epoch": 0.36213991769547327,
+      "grad_norm": 1.331268072128296,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9367,
+      "step": 33
+    },
+    {
+      "epoch": 0.3731138545953361,
+      "grad_norm": 1.6882885694503784,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9741,
+      "step": 34
+    },
+    {
+      "epoch": 0.3840877914951989,
+      "grad_norm": 1.8296782970428467,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.9216,
+      "step": 35
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "grad_norm": 2.422697067260742,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9616,
+      "step": 36
+    },
+    {
+      "epoch": 0.4060356652949246,
+      "grad_norm": 5.263638019561768,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0788,
+      "step": 37
+    },
+    {
+      "epoch": 0.4170096021947874,
+      "grad_norm": 4.142805099487305,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9168,
+      "step": 38
+    },
+    {
+      "epoch": 0.4279835390946502,
+      "grad_norm": 1.098343014717102,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8683,
+      "step": 39
+    },
+    {
+      "epoch": 0.438957475994513,
+      "grad_norm": 1.2079895734786987,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8289,
+      "step": 40
+    },
+    {
+      "epoch": 0.4499314128943759,
+      "grad_norm": 1.21189546585083,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8602,
+      "step": 41
+    },
+    {
+      "epoch": 0.4609053497942387,
+      "grad_norm": 1.1260839700698853,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8711,
+      "step": 42
+    },
+    {
+      "epoch": 0.4718792866941015,
+      "grad_norm": 1.2705676555633545,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8977,
+      "step": 43
+    },
+    {
+      "epoch": 0.4828532235939643,
+      "grad_norm": 1.2326122522354126,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.905,
+      "step": 44
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 1.3834530115127563,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9292,
+      "step": 45
+    },
+    {
+      "epoch": 0.50480109739369,
+      "grad_norm": 1.5778294801712036,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9167,
+      "step": 46
+    },
+    {
+      "epoch": 0.5157750342935528,
+      "grad_norm": 1.755370855331421,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9525,
+      "step": 47
+    },
+    {
+      "epoch": 0.5267489711934157,
+      "grad_norm": 2.129711389541626,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.979,
+      "step": 48
+    },
+    {
+      "epoch": 0.5377229080932785,
+      "grad_norm": 2.775024652481079,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.986,
+      "step": 49
+    },
+    {
+      "epoch": 0.5486968449931413,
+      "grad_norm": 6.473246097564697,
+      "learning_rate": 0.0,
+      "loss": 1.086,
+      "step": 50
+    },
+    {
+      "epoch": 0.5486968449931413,
+      "eval_loss": 0.9280461072921753,
+      "eval_runtime": 58.974,
+      "eval_samples_per_second": 10.411,
+      "eval_steps_per_second": 1.306,
+      "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": 1.527148641905541e+17,
+  "total_flos": 3.0459522160420454e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null