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:cf9f7ed671a3faed615a9e1e39ee539e221819e2b87cd17e5b5b472b151b58d0
+oid sha256:3537aa6417165a3e8d1be4b9c307e9b606b115410ec6fa342dc6f76626cfec5d
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e99f376027805023a806c987fc21ef3dcfe11bf5703c29aa0234775e28dd1ad
+oid sha256:b3918662f2b9651a3c68c013d5e68e6d88d87fcd0d4994e4a356457b5d7cb156
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d9014d5762cd7983faebfeb31124d6a7be675ded56b081cebc3b02aa3150816
+oid sha256:cf23bfd3e2d002667876831cf2a08e89cb4a8433ff033a19ccd88d200ec94bae
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a80faee148a795abde65ba45d941388944c73a8b49b89be2271e34514d3a1d7
+oid sha256:62539b97443adfc1371df7fff729b4be5df73e90edb8e842805f284ae1aa7e15
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1c4bca2dacdec0ad570b95d7552cfd2a3561b04d15184509c88440404561483
+oid sha256:699ee7d7a17d45704ea6d2b11b065e63e2eebc43aaf4fcedcec07de948fa6390
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857536cbe798aff60a3d28a9853ad078cc133dfd1e8a7f514b23225e7f124025
+oid sha256:e78a95e06417aca1317b3579ac54c97856ba5e496cbef0e59493b92bb5159444
 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": 0.9844273924827576,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4385964912280702,
+  "best_metric": 0.9738476872444153,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.8771929824561404,
   "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": 68.672,
       "eval_steps_per_second": 8.584,
       "step": 25
+    },
+    {
+      "epoch": 1.4947368421052631,
+      "grad_norm": 2.8815419673919678,
+      "learning_rate": 5e-05,
+      "loss": 0.9999,
+      "step": 26
+    },
+    {
+      "epoch": 1.550877192982456,
+      "grad_norm": 1.6184970140457153,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9744,
+      "step": 27
+    },
+    {
+      "epoch": 1.6070175438596492,
+      "grad_norm": 1.700230598449707,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9848,
+      "step": 28
+    },
+    {
+      "epoch": 1.663157894736842,
+      "grad_norm": 1.7157793045043945,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9861,
+      "step": 29
+    },
+    {
+      "epoch": 1.719298245614035,
+      "grad_norm": 1.1912931203842163,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9686,
+      "step": 30
+    },
+    {
+      "epoch": 1.775438596491228,
+      "grad_norm": 1.9062882661819458,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0133,
+      "step": 31
+    },
+    {
+      "epoch": 1.831578947368421,
+      "grad_norm": 1.5787826776504517,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.9736,
+      "step": 32
+    },
+    {
+      "epoch": 1.8877192982456141,
+      "grad_norm": 3.0003042221069336,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9805,
+      "step": 33
+    },
+    {
+      "epoch": 1.943859649122807,
+      "grad_norm": 1.2490260601043701,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9748,
+      "step": 34
+    },
+    {
+      "epoch": 2.0350877192982457,
+      "grad_norm": 5.135227203369141,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8213,
+      "step": 35
+    },
+    {
+      "epoch": 2.0912280701754384,
+      "grad_norm": 1.504193663597107,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9428,
+      "step": 36
+    },
+    {
+      "epoch": 2.1473684210526316,
+      "grad_norm": 1.865723729133606,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9708,
+      "step": 37
+    },
+    {
+      "epoch": 2.2035087719298247,
+      "grad_norm": 1.2437411546707153,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9747,
+      "step": 38
+    },
+    {
+      "epoch": 2.2596491228070175,
+      "grad_norm": 3.998439073562622,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0126,
+      "step": 39
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 1.3937028646469116,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9638,
+      "step": 40
+    },
+    {
+      "epoch": 2.3719298245614033,
+      "grad_norm": 2.2477951049804688,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9713,
+      "step": 41
+    },
+    {
+      "epoch": 2.4280701754385965,
+      "grad_norm": 1.3327833414077759,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9563,
+      "step": 42
+    },
+    {
+      "epoch": 2.4842105263157896,
+      "grad_norm": 1.937410593032837,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9716,
+      "step": 43
+    },
+    {
+      "epoch": 2.5403508771929824,
+      "grad_norm": 2.531614065170288,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9813,
+      "step": 44
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 1.3599098920822144,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9793,
+      "step": 45
+    },
+    {
+      "epoch": 2.6526315789473687,
+      "grad_norm": 1.3307596445083618,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9686,
+      "step": 46
+    },
+    {
+      "epoch": 2.7087719298245614,
+      "grad_norm": 1.9670759439468384,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.955,
+      "step": 47
+    },
+    {
+      "epoch": 2.7649122807017545,
+      "grad_norm": 3.397104024887085,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0066,
+      "step": 48
+    },
+    {
+      "epoch": 2.8210526315789473,
+      "grad_norm": 1.5758522748947144,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9656,
+      "step": 49
+    },
+    {
+      "epoch": 2.8771929824561404,
+      "grad_norm": 1.1156949996948242,
+      "learning_rate": 0.0,
+      "loss": 0.9643,
+      "step": 50
+    },
+    {
+      "epoch": 2.8771929824561404,
+      "eval_loss": 0.9738476872444153,
+      "eval_runtime": 1.7164,
+      "eval_samples_per_second": 69.914,
+      "eval_steps_per_second": 8.739,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null