Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6492ff83b8e1622a0af2bb2b2ecc8399e1f83bd2e61fa69a60012cd3e6e0e747
+oid sha256:c581bd095fdaaca30fd46e31a643b2d84fbb78ca73066920676cd6a4a31b5c26
 size 4525640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a549969bbd740091c445f687f113815d92879ea5f1fa5e019b691092873568
+oid sha256:59249b814c32769ffcecb5b67b6fc637713383c9cef89e759b56d449189be3af
 size 9067978

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac30e4cdb404b98f4132b8622b95bbab39cf71990ae778befde89cb9c5153de
+oid sha256:a97ab10adab548f7b7aaaecbed0ec8480e4bd317ef01fa538a5a4cfd089cb041
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4ade5ba96e30b05398f85c43181202524605a975cb9c9ab9f99ce33a314ab4
+oid sha256:e7d66a2ad1f5c6cb61a02917a22ebb7fa24def598ee1e24a4f37014da3dc6068
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:007906c29c010d785bdb2cd5781bce175fb7d6779a327d3def2f172d563a0d82
+oid sha256:8ed522ee42db7d555ca8ae74da75530fd6a4dcbb505137510e85e2bbcf62717b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c501ced189ce2db09edf771c889224243674672bcd71ac86290485da98c6f480
+oid sha256:bae243710d4d1d462a03dc10e3986adef773214cff4ecd7ec23b4b182d8d3f47
 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": 3.041290760040283,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010544352181362857,
+  "best_metric": 2.9394378662109375,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.021088704362725714,
   "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": 958.195,
       "eval_steps_per_second": 119.797,
       "step": 25
+    },
+    {
+      "epoch": 0.010966126268617371,
+      "grad_norm": 0.711467981338501,
+      "learning_rate": 5e-05,
+      "loss": 3.0241,
+      "step": 26
+    },
+    {
+      "epoch": 0.011387900355871887,
+      "grad_norm": 0.515529215335846,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.919,
+      "step": 27
+    },
+    {
+      "epoch": 0.011809674443126401,
+      "grad_norm": 0.5799137949943542,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.9172,
+      "step": 28
+    },
+    {
+      "epoch": 0.012231448530380915,
+      "grad_norm": 0.5831902027130127,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.8513,
+      "step": 29
+    },
+    {
+      "epoch": 0.01265322261763543,
+      "grad_norm": 0.6149861216545105,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.8322,
+      "step": 30
+    },
+    {
+      "epoch": 0.013074996704889943,
+      "grad_norm": 0.6361252665519714,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.9744,
+      "step": 31
+    },
+    {
+      "epoch": 0.013496770792144458,
+      "grad_norm": 0.6748908758163452,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.8639,
+      "step": 32
+    },
+    {
+      "epoch": 0.013918544879398972,
+      "grad_norm": 0.7482442855834961,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.8446,
+      "step": 33
+    },
+    {
+      "epoch": 0.014340318966653486,
+      "grad_norm": 0.8180491924285889,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.8883,
+      "step": 34
+    },
+    {
+      "epoch": 0.014762093053908,
+      "grad_norm": 0.9697517156600952,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.9138,
+      "step": 35
+    },
+    {
+      "epoch": 0.015183867141162514,
+      "grad_norm": 1.127631425857544,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.0415,
+      "step": 36
+    },
+    {
+      "epoch": 0.015605641228417028,
+      "grad_norm": 1.7890645265579224,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.1437,
+      "step": 37
+    },
+    {
+      "epoch": 0.016027415315671544,
+      "grad_norm": 0.8554721474647522,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.1099,
+      "step": 38
+    },
+    {
+      "epoch": 0.016449189402926057,
+      "grad_norm": 0.7087699174880981,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.9339,
+      "step": 39
+    },
+    {
+      "epoch": 0.016870963490180572,
+      "grad_norm": 0.6325855255126953,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.9197,
+      "step": 40
+    },
+    {
+      "epoch": 0.017292737577435085,
+      "grad_norm": 0.6757078766822815,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.9094,
+      "step": 41
+    },
+    {
+      "epoch": 0.0177145116646896,
+      "grad_norm": 0.6649094223976135,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.8939,
+      "step": 42
+    },
+    {
+      "epoch": 0.018136285751944117,
+      "grad_norm": 0.6372946500778198,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.8133,
+      "step": 43
+    },
+    {
+      "epoch": 0.01855805983919863,
+      "grad_norm": 0.6511436700820923,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.8358,
+      "step": 44
+    },
+    {
+      "epoch": 0.018979833926453145,
+      "grad_norm": 0.6909969449043274,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.8616,
+      "step": 45
+    },
+    {
+      "epoch": 0.019401608013707657,
+      "grad_norm": 0.7018306851387024,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.8483,
+      "step": 46
+    },
+    {
+      "epoch": 0.019823382100962173,
+      "grad_norm": 0.816609263420105,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.8795,
+      "step": 47
+    },
+    {
+      "epoch": 0.020245156188216686,
+      "grad_norm": 1.0902043581008911,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.9522,
+      "step": 48
+    },
+    {
+      "epoch": 0.0206669302754712,
+      "grad_norm": 1.5287140607833862,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.0308,
+      "step": 49
+    },
+    {
+      "epoch": 0.021088704362725714,
+      "grad_norm": 2.4891648292541504,
+      "learning_rate": 0.0,
+      "loss": 3.3932,
+      "step": 50
+    },
+    {
+      "epoch": 0.021088704362725714,
+      "eval_loss": 2.9394378662109375,
+      "eval_runtime": 16.6471,
+      "eval_samples_per_second": 959.509,
+      "eval_steps_per_second": 119.961,
+      "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": 1753141896806400.0,
+  "total_flos": 3506283793612800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null