Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11777855d4ef46ed5b6f406649b3042ea1c8aafece33677cd80e52c46678f472
+oid sha256:02243513b9c3cd6f795857ed917bcc89c00b36b96bc6687eea40c38708bf6d2a
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c4286d569c4c4fe861a826a8184caad5386c45dcfe92152c9099f5437077465
+oid sha256:4d90ad6fe11dbcab66f969a79204a0e7b4c217586a491e56f6311a1356abe90a
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819d8c39f58720f44be6fb33a925682261cb7d21305b0fce0eff7a7279372d11
+oid sha256:1494e920634dd53de3c38c7286eacbd602a26d293cc25e433a2270b4709fb6bb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e909f0fd4d81b5540b785de7ecd2e1e48fce067d23e612447da9a5f71efaf412
+oid sha256:c240f7bbd26d9691ebbb2c4aeec4d4c37838b65303a65e5d0699cccf2c276a31
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1941d7ca3e53e979831776ff2463e43c0c5e3a4c70041bfd45e1f29206f5e8c5
+oid sha256:2b5627cd436c95ad048a0fa7049c317025c51796031e7bf6365372b959b16e86
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c1c8a8019bc9f4052ca86d76e2bdc9ce1e2f7d6c3c5c02d695c60277cf41f30
+oid sha256:c8ea43074504cb2fcae97d0b0ecfebf01c9c55941f0940646071828b7bcf1d50
 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": 10.372044563293457,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.034057045551298425,
+  "best_metric": 10.37037181854248,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06811409110259685,
   "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": 1007.254,
       "eval_steps_per_second": 126.059,
       "step": 25
+    },
+    {
+      "epoch": 0.035419327373350365,
+      "grad_norm": 0.06022435054183006,
+      "learning_rate": 5e-05,
+      "loss": 10.3724,
+      "step": 26
+    },
+    {
+      "epoch": 0.0367816091954023,
+      "grad_norm": 0.060626592487096786,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3727,
+      "step": 27
+    },
+    {
+      "epoch": 0.03814389101745424,
+      "grad_norm": 0.06244682893157005,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3713,
+      "step": 28
+    },
+    {
+      "epoch": 0.03950617283950617,
+      "grad_norm": 0.06487547606229782,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3728,
+      "step": 29
+    },
+    {
+      "epoch": 0.04086845466155811,
+      "grad_norm": 0.06838765740394592,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.372,
+      "step": 30
+    },
+    {
+      "epoch": 0.042230736483610046,
+      "grad_norm": 0.06563523411750793,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3722,
+      "step": 31
+    },
+    {
+      "epoch": 0.043593018305661986,
+      "grad_norm": 0.06500206142663956,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3722,
+      "step": 32
+    },
+    {
+      "epoch": 0.04495530012771392,
+      "grad_norm": 0.06630583852529526,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3729,
+      "step": 33
+    },
+    {
+      "epoch": 0.04631758194976586,
+      "grad_norm": 0.06435850262641907,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3709,
+      "step": 34
+    },
+    {
+      "epoch": 0.04767986377181779,
+      "grad_norm": 0.06977062672376633,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3693,
+      "step": 35
+    },
+    {
+      "epoch": 0.04904214559386973,
+      "grad_norm": 0.08564142882823944,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3693,
+      "step": 36
+    },
+    {
+      "epoch": 0.05040442741592167,
+      "grad_norm": 0.074698805809021,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3648,
+      "step": 37
+    },
+    {
+      "epoch": 0.05176670923797361,
+      "grad_norm": 0.07015930861234665,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3707,
+      "step": 38
+    },
+    {
+      "epoch": 0.05312899106002554,
+      "grad_norm": 0.07502926141023636,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3707,
+      "step": 39
+    },
+    {
+      "epoch": 0.05449127288207748,
+      "grad_norm": 0.07593125849962234,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3715,
+      "step": 40
+    },
+    {
+      "epoch": 0.055853554704129414,
+      "grad_norm": 0.07538634538650513,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3715,
+      "step": 41
+    },
+    {
+      "epoch": 0.057215836526181355,
+      "grad_norm": 0.07371652126312256,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3724,
+      "step": 42
+    },
+    {
+      "epoch": 0.05857811834823329,
+      "grad_norm": 0.07424209266901016,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3714,
+      "step": 43
+    },
+    {
+      "epoch": 0.05994040017028523,
+      "grad_norm": 0.07837469130754471,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3715,
+      "step": 44
+    },
+    {
+      "epoch": 0.06130268199233716,
+      "grad_norm": 0.07376153022050858,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3717,
+      "step": 45
+    },
+    {
+      "epoch": 0.0626649638143891,
+      "grad_norm": 0.0708039253950119,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3716,
+      "step": 46
+    },
+    {
+      "epoch": 0.06402724563644104,
+      "grad_norm": 0.0748865082859993,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3695,
+      "step": 47
+    },
+    {
+      "epoch": 0.06538952745849298,
+      "grad_norm": 0.07984250783920288,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3707,
+      "step": 48
+    },
+    {
+      "epoch": 0.06675180928054492,
+      "grad_norm": 0.0698637142777443,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3691,
+      "step": 49
+    },
+    {
+      "epoch": 0.06811409110259685,
+      "grad_norm": 0.08626695722341537,
+      "learning_rate": 0.0,
+      "loss": 10.3653,
+      "step": 50
+    },
+    {
+      "epoch": 0.06811409110259685,
+      "eval_loss": 10.37037181854248,
+      "eval_runtime": 4.9285,
+      "eval_samples_per_second": 1003.558,
+      "eval_steps_per_second": 125.597,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null