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:aa2dc4ea9dc36bd8bbe0298b330d76d2eac9fd0dfd3cf192f2170bed59384488
+oid sha256:42be3a2277cd00aab4c16ee2a360272c401e633895e93e2e206da2a5e0427705
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f76af8a33891749b0ea348a4a43fe19ab93d0f109650033dd251ca72fce5b60
+oid sha256:978723ff97768a9f2e516f969231e9c2eb4aa8ece8bd6aeda2f4aae6ba673470
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e2b7cf21205c2008a4a65adf0f3d5300e4054e4e8194c43148c7bb5b8ed662
+oid sha256:7878196e2603e7bcad10e2b08dcb7665d44678039b0d922f0d76278ccaadacdd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c3f03750bf61aa891654eb5574d6cf0e7bede41b58a605125ce36751e639280
+oid sha256:fa5a9a7d61207362eaf69fbcee74e6ca3fa4ac77b72dc02824d8dee7a35f91cd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f3d2cca46bd965117f811def6b1f93ee680ab247a0b09be7c7f74b8a982bc0d
+oid sha256:0b6df70f67068a05893282635fdac0d0ccb99715cf40e40fd9adfd6fd297914e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc8d2f5e93a634d3e9435faf145f789ad185565e0f697d29071284f10cdd109c
+oid sha256:e257d51f466f16532d582d5cb5957b13cee6539c54626659efef3938f38195d7
 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": 1.4000091552734375,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.23923444976076555,
+  "best_metric": 1.3332951068878174,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4784688995215311,
   "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": 56.092,
       "eval_steps_per_second": 7.081,
       "step": 25
+    },
+    {
+      "epoch": 0.24880382775119617,
+      "grad_norm": 0.5103795528411865,
+      "learning_rate": 5e-05,
+      "loss": 1.0142,
+      "step": 26
+    },
+    {
+      "epoch": 0.2583732057416268,
+      "grad_norm": 0.6568211317062378,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.3947,
+      "step": 27
+    },
+    {
+      "epoch": 0.2679425837320574,
+      "grad_norm": 0.5069567561149597,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3821,
+      "step": 28
+    },
+    {
+      "epoch": 0.27751196172248804,
+      "grad_norm": 0.45003873109817505,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4252,
+      "step": 29
+    },
+    {
+      "epoch": 0.28708133971291866,
+      "grad_norm": 0.38148233294487,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.4354,
+      "step": 30
+    },
+    {
+      "epoch": 0.2966507177033493,
+      "grad_norm": 0.42671704292297363,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.4432,
+      "step": 31
+    },
+    {
+      "epoch": 0.3062200956937799,
+      "grad_norm": 0.38906577229499817,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.4877,
+      "step": 32
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.5056963562965393,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.4736,
+      "step": 33
+    },
+    {
+      "epoch": 0.3253588516746411,
+      "grad_norm": 0.6899903416633606,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5067,
+      "step": 34
+    },
+    {
+      "epoch": 0.3349282296650718,
+      "grad_norm": 0.6205446720123291,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4979,
+      "step": 35
+    },
+    {
+      "epoch": 0.3444976076555024,
+      "grad_norm": 0.7472631335258484,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4706,
+      "step": 36
+    },
+    {
+      "epoch": 0.35406698564593303,
+      "grad_norm": 0.8322171568870544,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.587,
+      "step": 37
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.5657007098197937,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0921,
+      "step": 38
+    },
+    {
+      "epoch": 0.37320574162679426,
+      "grad_norm": 0.6003439426422119,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1843,
+      "step": 39
+    },
+    {
+      "epoch": 0.3827751196172249,
+      "grad_norm": 0.3574884533882141,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.374,
+      "step": 40
+    },
+    {
+      "epoch": 0.3923444976076555,
+      "grad_norm": 0.7085531949996948,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.3693,
+      "step": 41
+    },
+    {
+      "epoch": 0.4019138755980861,
+      "grad_norm": 0.42259854078292847,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3471,
+      "step": 42
+    },
+    {
+      "epoch": 0.41148325358851673,
+      "grad_norm": 0.34592199325561523,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.4339,
+      "step": 43
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.3229917585849762,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4168,
+      "step": 44
+    },
+    {
+      "epoch": 0.430622009569378,
+      "grad_norm": 0.38954058289527893,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.4106,
+      "step": 45
+    },
+    {
+      "epoch": 0.44019138755980863,
+      "grad_norm": 0.5214857459068298,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.4866,
+      "step": 46
+    },
+    {
+      "epoch": 0.44976076555023925,
+      "grad_norm": 0.47968587279319763,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.4853,
+      "step": 47
+    },
+    {
+      "epoch": 0.45933014354066987,
+      "grad_norm": 0.5608012676239014,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5451,
+      "step": 48
+    },
+    {
+      "epoch": 0.4688995215311005,
+      "grad_norm": 0.6561995148658752,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.5704,
+      "step": 49
+    },
+    {
+      "epoch": 0.4784688995215311,
+      "grad_norm": 0.9207837581634521,
+      "learning_rate": 0.0,
+      "loss": 1.6039,
+      "step": 50
+    },
+    {
+      "epoch": 0.4784688995215311,
+      "eval_loss": 1.3332951068878174,
+      "eval_runtime": 12.776,
+      "eval_samples_per_second": 55.182,
+      "eval_steps_per_second": 6.966,
+      "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": 4.187917383630848e+16,
+  "total_flos": 8.368021483552768e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null