Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dbed73f7f18ac9c8100ae6673cddcccc5a3bb2d99650b7465005ebfeeb9bc44
+oid sha256:72e2aeaf137d3a1206b4aced6cf18448c1485ef1f1344d2064f305dc77f08961
 size 37352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e252e9476ba60b925fa505c97822ffcc67e2db5ddeef0dddd52de718e660a9d
+oid sha256:f6a905c858b1c1daa4f2e59824e8f9d53a1bcb99168da0b6f843063a36f13cac
 size 83444

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4481f53ad37c736f6e12dfa6da1052da6a98a6863b25449a5f05d8c4d14e67ce
+oid sha256:d6402797b170d72647eb8e0d767547f34da624a0d91fa174ef336ad62dce81df
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb31f0a0eadfde0bfe752b580abbbd2f54060a20ff4244053740550534dc49b
+oid sha256:c8cf6481a443364d7f809c7aebb97c59d9cbbb03175744a5e14e0c34764dfe3b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6adba297b75cdee0fda4d47f7e5086576b798175aeff57ce0cb0981b956d2881
+oid sha256:651e9a232a7fd941738af1d16af0de2bdb1eb0d4b06f51f15e9c77e763eeb58e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f36a332f7fbf2760c95cc3cabb1c8c4a03c80528a2dfb22a6a1d424148a26e9
+oid sha256:f431337a6e2ffb3e440aab23c3020e1776dfff4e358af1c7f2f4e759e109775c
 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": 12.458169937133789,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12626262626262627,
+  "best_metric": 12.457971572875977,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.25252525252525254,
   "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": 379.697,
       "eval_steps_per_second": 47.533,
       "step": 25
+    },
+    {
+      "epoch": 0.13131313131313133,
+      "grad_norm": 0.009966455399990082,
+      "learning_rate": 5e-05,
+      "loss": 12.4584,
+      "step": 26
+    },
+    {
+      "epoch": 0.13636363636363635,
+      "grad_norm": 0.00917417835444212,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 12.4572,
+      "step": 27
+    },
+    {
+      "epoch": 0.1414141414141414,
+      "grad_norm": 0.011121945455670357,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 12.4588,
+      "step": 28
+    },
+    {
+      "epoch": 0.14646464646464646,
+      "grad_norm": 0.010699532926082611,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 12.4575,
+      "step": 29
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 0.010851383209228516,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 12.4564,
+      "step": 30
+    },
+    {
+      "epoch": 0.15656565656565657,
+      "grad_norm": 0.012371523305773735,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 12.4582,
+      "step": 31
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 0.012677067890763283,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 12.4582,
+      "step": 32
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.013413293287158012,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 12.4587,
+      "step": 33
+    },
+    {
+      "epoch": 0.1717171717171717,
+      "grad_norm": 0.016384758055210114,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 12.4577,
+      "step": 34
+    },
+    {
+      "epoch": 0.17676767676767677,
+      "grad_norm": 0.015265684574842453,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 12.4589,
+      "step": 35
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.015503032132983208,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 12.46,
+      "step": 36
+    },
+    {
+      "epoch": 0.18686868686868688,
+      "grad_norm": 0.01569039560854435,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 12.4601,
+      "step": 37
+    },
+    {
+      "epoch": 0.1919191919191919,
+      "grad_norm": 0.012827031314373016,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 12.4605,
+      "step": 38
+    },
+    {
+      "epoch": 0.19696969696969696,
+      "grad_norm": 0.010645854286849499,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 12.4548,
+      "step": 39
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 0.01111725252121687,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 12.4581,
+      "step": 40
+    },
+    {
+      "epoch": 0.20707070707070707,
+      "grad_norm": 0.012351098470389843,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 12.4571,
+      "step": 41
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 0.012415647506713867,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 12.4576,
+      "step": 42
+    },
+    {
+      "epoch": 0.21717171717171718,
+      "grad_norm": 0.011739925481379032,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 12.4579,
+      "step": 43
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.01330937072634697,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 12.4567,
+      "step": 44
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 0.01405568327754736,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 12.4572,
+      "step": 45
+    },
+    {
+      "epoch": 0.23232323232323232,
+      "grad_norm": 0.015090607106685638,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 12.4593,
+      "step": 46
+    },
+    {
+      "epoch": 0.23737373737373738,
+      "grad_norm": 0.015863122418522835,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 12.4583,
+      "step": 47
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.0159890316426754,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 12.4579,
+      "step": 48
+    },
+    {
+      "epoch": 0.2474747474747475,
+      "grad_norm": 0.01518325787037611,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 12.4595,
+      "step": 49
+    },
+    {
+      "epoch": 0.25252525252525254,
+      "grad_norm": 0.02028408646583557,
+      "learning_rate": 0.0,
+      "loss": 12.4622,
+      "step": 50
+    },
+    {
+      "epoch": 0.25252525252525254,
+      "eval_loss": 12.457971572875977,
+      "eval_runtime": 3.5105,
+      "eval_samples_per_second": 380.002,
+      "eval_steps_per_second": 47.571,
+      "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": 421527552000.0,
+  "total_flos": 843055104000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null