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:cb7998a2fb082a8a5c5e4f8d6ca50be8bc9d2bd9a05c274fe033938f3a407873
+oid sha256:446db79b7aab7e8f1edd1a99b6a1a5bd492102899f1b40800b362b59f1d32128
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8420ce7d69a0bd89502cddacec67fc53168a361c696ac09add6e229f3310d62e
+oid sha256:fe5ea2102f2cffc7e2e657cdf1c2bdf8163f48d413f7a3470304327dddd0cc70
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec198b1060039fd8514061367ed0a728f0354f8468cc6305e03bdda9844e17e
+oid sha256:5fdf30f9baa559a838bfb643f380070365f8846eaecdd8b2829f900de1fc74e8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99b8aa6b1933c41b302b0ace7ae7106346132ef009b6ec708ca08efaeecc673d
+oid sha256:b696caab3de5f046d43fd3e99454944c8f0766986d6a18593ab51c972920cbb0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca23f3c75b7d729bc5219bcb016d260342c73f351ec2df9ec5dfc8ed76ac4a8b
+oid sha256:3d28f6cbaf00c90dd7be63473885e78eebbded42d14de9bceff001d565e5f174
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74bff08497fd0291b2d7b767807be532e991400c45530896f177bfd14b550b6a
+oid sha256:744ce80e842f946263b1afbb473c3f422be637e741e0a807ffdef117119c90b7
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.14931216835975647,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.056290458767238954,
+  "best_metric": 0.1350458711385727,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11258091753447791,
   "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": 9.907,
       "eval_steps_per_second": 2.576,
       "step": 25
+    },
+    {
+      "epoch": 0.05854207711792851,
+      "grad_norm": 0.22340703010559082,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7026,
+      "step": 26
+    },
+    {
+      "epoch": 0.06079369546861807,
+      "grad_norm": 0.16258461773395538,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.5279,
+      "step": 27
+    },
+    {
+      "epoch": 0.06304531381930763,
+      "grad_norm": 0.11411070823669434,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.2314,
+      "step": 28
+    },
+    {
+      "epoch": 0.06529693216999718,
+      "grad_norm": 0.10004908591508865,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.078,
+      "step": 29
+    },
+    {
+      "epoch": 0.06754855052068674,
+      "grad_norm": 0.09968353807926178,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0667,
+      "step": 30
+    },
+    {
+      "epoch": 0.0698001688713763,
+      "grad_norm": 0.07578547298908234,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0551,
+      "step": 31
+    },
+    {
+      "epoch": 0.07205178722206586,
+      "grad_norm": 0.06284698843955994,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0419,
+      "step": 32
+    },
+    {
+      "epoch": 0.07430340557275542,
+      "grad_norm": 0.04809579625725746,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0316,
+      "step": 33
+    },
+    {
+      "epoch": 0.07655502392344497,
+      "grad_norm": 0.06147637590765953,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0265,
+      "step": 34
+    },
+    {
+      "epoch": 0.07880664227413453,
+      "grad_norm": 0.05939394608139992,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0215,
+      "step": 35
+    },
+    {
+      "epoch": 0.08105826062482409,
+      "grad_norm": 0.07469132542610168,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0228,
+      "step": 36
+    },
+    {
+      "epoch": 0.08330987897551365,
+      "grad_norm": 0.09178522974252701,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0268,
+      "step": 37
+    },
+    {
+      "epoch": 0.0855614973262032,
+      "grad_norm": 0.142929345369339,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.716,
+      "step": 38
+    },
+    {
+      "epoch": 0.08781311567689276,
+      "grad_norm": 0.12526343762874603,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.6382,
+      "step": 39
+    },
+    {
+      "epoch": 0.09006473402758232,
+      "grad_norm": 0.09536906331777573,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4273,
+      "step": 40
+    },
+    {
+      "epoch": 0.09231635237827188,
+      "grad_norm": 0.06540685892105103,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1129,
+      "step": 41
+    },
+    {
+      "epoch": 0.09456797072896145,
+      "grad_norm": 0.0592995211482048,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0623,
+      "step": 42
+    },
+    {
+      "epoch": 0.096819589079651,
+      "grad_norm": 0.058583199977874756,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0565,
+      "step": 43
+    },
+    {
+      "epoch": 0.09907120743034056,
+      "grad_norm": 0.0441153347492218,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0401,
+      "step": 44
+    },
+    {
+      "epoch": 0.10132282578103012,
+      "grad_norm": 0.04472954943776131,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0368,
+      "step": 45
+    },
+    {
+      "epoch": 0.10357444413171968,
+      "grad_norm": 0.039391275495290756,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0274,
+      "step": 46
+    },
+    {
+      "epoch": 0.10582606248240924,
+      "grad_norm": 0.04694681242108345,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0162,
+      "step": 47
+    },
+    {
+      "epoch": 0.1080776808330988,
+      "grad_norm": 0.048730507493019104,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0169,
+      "step": 48
+    },
+    {
+      "epoch": 0.11032929918378835,
+      "grad_norm": 0.058839570730924606,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0234,
+      "step": 49
+    },
+    {
+      "epoch": 0.11258091753447791,
+      "grad_norm": 0.08322292566299438,
+      "learning_rate": 1e-05,
+      "loss": 0.0285,
+      "step": 50
+    },
+    {
+      "epoch": 0.11258091753447791,
+      "eval_loss": 0.1350458711385727,
+      "eval_runtime": 4.8159,
+      "eval_samples_per_second": 10.382,
+      "eval_steps_per_second": 2.699,
+      "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": 3.88587245562495e+17,
+  "total_flos": 7.72780696631509e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null