Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999dc95bd58017c8af57d5f56bac999e41df4edce4a168c3a31aee99b56d9f83
+oid sha256:c60e8c2c3cf57f7eedbcc76f18d783c81894e26554e93fcd3287f34be57b7477
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e281dda68b21df2842ef99a2eadc3f3568d98c2bc60823b275e5553b390c7d15
+oid sha256:5bd49ac99d6bea1dac38bd649de9e293f195453f54b0c4d62b228bb64840578a
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de17ee4063c46c9f34031d3009605fcbf8ead19062f7ea1ec893b4b3fa23a0e2
+oid sha256:251b3093271ccab23b3bfa7329ce7b7ffd7bd5734a12207ada579704527d8c40
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2b961e1ccf7ebf12343efaa6d74f1ac9ccc4fb28a3f53cfc60bb103126ab813
+oid sha256:011714df9943de0c2313fd913bc1178655900d187f4216883346e8a983a1fe01
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f57f079baa9fa8aaab2e2a119b6517c58be8a3199ccf586a6b8109fd3cb12aee
+oid sha256:e678af7e692d4c0a232731b7bf43ed89a086dc2575c10c885272a36fb24ca339
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e478fa74405757c4ef5ed2021712f7beb696357dc75152ebff33266f12d80d
+oid sha256:626c4e376fcc700514710d87c7c1786a850e92adce9c5a5c183003dd7c8cd6b2
 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": 11.936851501464844,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22727272727272727,
+  "best_metric": 11.935591697692871,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.45454545454545453,
   "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": 470.181,
       "eval_steps_per_second": 59.011,
       "step": 25
+    },
+    {
+      "epoch": 0.23636363636363636,
+      "grad_norm": 0.02547423541545868,
+      "learning_rate": 5e-05,
+      "loss": 11.9328,
+      "step": 26
+    },
+    {
+      "epoch": 0.24545454545454545,
+      "grad_norm": 0.032784029841423035,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9333,
+      "step": 27
+    },
+    {
+      "epoch": 0.2545454545454545,
+      "grad_norm": 0.03990747034549713,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9346,
+      "step": 28
+    },
+    {
+      "epoch": 0.2636363636363636,
+      "grad_norm": 0.04943360760807991,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9343,
+      "step": 29
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 0.06197665259242058,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9335,
+      "step": 30
+    },
+    {
+      "epoch": 0.2818181818181818,
+      "grad_norm": 0.07167532294988632,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9344,
+      "step": 31
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 0.07756704837083817,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9335,
+      "step": 32
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.09547356516122818,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9343,
+      "step": 33
+    },
+    {
+      "epoch": 0.3090909090909091,
+      "grad_norm": 0.1049596518278122,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9362,
+      "step": 34
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 0.12272288650274277,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9367,
+      "step": 35
+    },
+    {
+      "epoch": 0.32727272727272727,
+      "grad_norm": 0.1635354906320572,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.9389,
+      "step": 36
+    },
+    {
+      "epoch": 0.33636363636363636,
+      "grad_norm": 0.2163349837064743,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9403,
+      "step": 37
+    },
+    {
+      "epoch": 0.34545454545454546,
+      "grad_norm": 0.04375721141695976,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9328,
+      "step": 38
+    },
+    {
+      "epoch": 0.35454545454545455,
+      "grad_norm": 0.03665831312537193,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9324,
+      "step": 39
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.050286322832107544,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9341,
+      "step": 40
+    },
+    {
+      "epoch": 0.37272727272727274,
+      "grad_norm": 0.04947338625788689,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.9333,
+      "step": 41
+    },
+    {
+      "epoch": 0.38181818181818183,
+      "grad_norm": 0.06359462440013885,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9332,
+      "step": 42
+    },
+    {
+      "epoch": 0.39090909090909093,
+      "grad_norm": 0.07127209007740021,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9336,
+      "step": 43
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.07325005531311035,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9339,
+      "step": 44
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 0.09760692715644836,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9347,
+      "step": 45
+    },
+    {
+      "epoch": 0.41818181818181815,
+      "grad_norm": 0.10781180113554001,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.9351,
+      "step": 46
+    },
+    {
+      "epoch": 0.42727272727272725,
+      "grad_norm": 0.1281491219997406,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9344,
+      "step": 47
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 0.14875389635562897,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9376,
+      "step": 48
+    },
+    {
+      "epoch": 0.44545454545454544,
+      "grad_norm": 0.20203977823257446,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9389,
+      "step": 49
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.2914524972438812,
+      "learning_rate": 0.0,
+      "loss": 11.9421,
+      "step": 50
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "eval_loss": 11.935591697692871,
+      "eval_runtime": 1.5904,
+      "eval_samples_per_second": 465.919,
+      "eval_steps_per_second": 58.476,
+      "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": 523201806336.0,
+  "total_flos": 1046077833216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null