Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5344e7a7add3e89e41aeb337ebdae046fd6fa892d2b80e735f340c3fd78d3fdc
+oid sha256:c96a7bbc22e591a80ec30b0d266bc76c0ecad277abedf761a89de7da38a9899a
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab9bb1a6b28590e8cdf6d5d97f56111d741105fe7bd97b6899e8ea18bef4415
+oid sha256:b1a123e086d936cf8da831264a5c24b60f97c0d84a63de6c5a91cf7bb931f40e
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69df9800e8b1c5e00d6d519768544bf65506150c1bb390d68da7ce38e537e541
+oid sha256:099e3b3ec7346c34835b0aff5f54050462d9647eef25fe8194d29bfcdeca6713
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8511a77015534d7db2081b11e409298541ddd24cdcdc646e445d3c1a4528b1fe
+oid sha256:33a3144b6acaf405a5c988057c3b0f6d64546f6b2967d86f16487ec9cb7de0f3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55aeb9f99504e02c5ea1678e1fb16f17a93f84c005df4f32b00f4c3797da054c
+oid sha256:743c0ffc81ebc4cd6e3620423405ad0497e04f340aafdb48f5af9ab1671896e2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2e36554bfd0557463ab58deaa94a8390a208db7b006d5908d842dc58c2ba8e3
+oid sha256:0df6f5a11f5cb4a7d9153c5397414121230ba31550fe0dc8edfc8dbe4c66f782
 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": 6.9282989501953125,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005348094072974744,
+  "best_metric": 6.924746990203857,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.010696188145949487,
   "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": 1368.531,
       "eval_steps_per_second": 171.088,
       "step": 25
+    },
+    {
+      "epoch": 0.005562017835893733,
+      "grad_norm": 0.0925169289112091,
+      "learning_rate": 5e-05,
+      "loss": 6.9306,
+      "step": 26
+    },
+    {
+      "epoch": 0.005775941598812723,
+      "grad_norm": 0.09849868714809418,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 6.9295,
+      "step": 27
+    },
+    {
+      "epoch": 0.005989865361731713,
+      "grad_norm": 0.10103553533554077,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 6.927,
+      "step": 28
+    },
+    {
+      "epoch": 0.0062037891246507024,
+      "grad_norm": 0.10405988246202469,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 6.9273,
+      "step": 29
+    },
+    {
+      "epoch": 0.006417712887569692,
+      "grad_norm": 0.11038113385438919,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 6.9269,
+      "step": 30
+    },
+    {
+      "epoch": 0.006631636650488682,
+      "grad_norm": 0.11047299206256866,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 6.9259,
+      "step": 31
+    },
+    {
+      "epoch": 0.0068455604134076715,
+      "grad_norm": 0.11552471667528152,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 6.9253,
+      "step": 32
+    },
+    {
+      "epoch": 0.007059484176326661,
+      "grad_norm": 0.12445191293954849,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 6.9267,
+      "step": 33
+    },
+    {
+      "epoch": 0.007273407939245652,
+      "grad_norm": 0.11612529307603836,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.9276,
+      "step": 34
+    },
+    {
+      "epoch": 0.007487331702164641,
+      "grad_norm": 0.13253656029701233,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 6.925,
+      "step": 35
+    },
+    {
+      "epoch": 0.007701255465083631,
+      "grad_norm": 0.13963279128074646,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 6.9247,
+      "step": 36
+    },
+    {
+      "epoch": 0.00791517922800262,
+      "grad_norm": 0.14887762069702148,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 6.922,
+      "step": 37
+    },
+    {
+      "epoch": 0.00812910299092161,
+      "grad_norm": 0.10967689752578735,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.9273,
+      "step": 38
+    },
+    {
+      "epoch": 0.0083430267538406,
+      "grad_norm": 0.10133490711450577,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 6.9261,
+      "step": 39
+    },
+    {
+      "epoch": 0.00855695051675959,
+      "grad_norm": 0.10881227254867554,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 6.9287,
+      "step": 40
+    },
+    {
+      "epoch": 0.00877087427967858,
+      "grad_norm": 0.10970684885978699,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 6.9248,
+      "step": 41
+    },
+    {
+      "epoch": 0.00898479804259757,
+      "grad_norm": 0.11278239637613297,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 6.9259,
+      "step": 42
+    },
+    {
+      "epoch": 0.00919872180551656,
+      "grad_norm": 0.12211595475673676,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 6.9251,
+      "step": 43
+    },
+    {
+      "epoch": 0.00941264556843555,
+      "grad_norm": 0.11529412865638733,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.9224,
+      "step": 44
+    },
+    {
+      "epoch": 0.009626569331354539,
+      "grad_norm": 0.11878494918346405,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 6.9249,
+      "step": 45
+    },
+    {
+      "epoch": 0.009840493094273529,
+      "grad_norm": 0.1319645345211029,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 6.9217,
+      "step": 46
+    },
+    {
+      "epoch": 0.010054416857192518,
+      "grad_norm": 0.11767640709877014,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 6.9275,
+      "step": 47
+    },
+    {
+      "epoch": 0.010268340620111508,
+      "grad_norm": 0.1403781920671463,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 6.922,
+      "step": 48
+    },
+    {
+      "epoch": 0.010482264383030498,
+      "grad_norm": 0.14114433526992798,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 6.9211,
+      "step": 49
+    },
+    {
+      "epoch": 0.010696188145949487,
+      "grad_norm": 0.1653960794210434,
+      "learning_rate": 0.0,
+      "loss": 6.9217,
+      "step": 50
+    },
+    {
+      "epoch": 0.010696188145949487,
+      "eval_loss": 6.924746990203857,
+      "eval_runtime": 22.575,
+      "eval_samples_per_second": 1394.997,
+      "eval_steps_per_second": 174.397,
+      "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": 2852978688000.0,
+  "total_flos": 5705957376000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null