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:e6a7f97ac06f3093b28b40f9d24333fdb7112609fe39ad749c21e2f773e244f1
+oid sha256:96bf2650754aa3ab740f1a5753a55bf3fea229d17124a4729a03e223c9d21a7d
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:305f6d076c2ffca4e4628f5fbc0b9f84de915e8f31ba3ceb2e265995ca381f15
+oid sha256:ae1ed9e91c4c1186d2c5ef0749ca9f68cc77a51e0fe98f69091477d665b1ee24
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e8b5d8d3d877231753e2b38ff72c96de862af769613fba577eb627eac053c3f
+oid sha256:ab0ac0ede5bfe190c1d108a43d251305282a8dc06716cd2d5ba4662193a244fa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3648dadb9cee0047e30a25e63512bb0703918766183ab08670d64fedd046837b
+oid sha256:07565a7ed6e9352d9b101d8115b8c452aa4a5c9cf966779022750cc395e532a2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e388c26f8f46430fe59d0f990913010f1668837d829e5967df40d4469ccc3342
+oid sha256:50329c2039e783489f06f7c10e8a1a50f29320164094bb7c5570cdd304a39b24
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6bcf5f3eaedc40fcf8a7d771c3e527d4a6b3954f87cee62336eabd5834ebe3b
+oid sha256:269ed00db64fa91b18939a54a90fc52dc6a897d4ade2cf01191e9503efabb991
 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": 1.5451337099075317,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.37629350893697083,
+  "best_metric": 1.5220385789871216,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7525870178739417,
   "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": 93.367,
       "eval_steps_per_second": 11.671,
       "step": 25
+    },
+    {
+      "epoch": 0.3913452492944497,
+      "grad_norm": 0.28296566009521484,
+      "learning_rate": 5e-05,
+      "loss": 1.7819,
+      "step": 26
+    },
+    {
+      "epoch": 0.4063969896519285,
+      "grad_norm": 0.20274849236011505,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5794,
+      "step": 27
+    },
+    {
+      "epoch": 0.42144873000940736,
+      "grad_norm": 0.21083898842334747,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6308,
+      "step": 28
+    },
+    {
+      "epoch": 0.43650047036688616,
+      "grad_norm": 0.22384609282016754,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.5835,
+      "step": 29
+    },
+    {
+      "epoch": 0.451552210724365,
+      "grad_norm": 0.21215800940990448,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.5756,
+      "step": 30
+    },
+    {
+      "epoch": 0.4666039510818438,
+      "grad_norm": 0.21465682983398438,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.5461,
+      "step": 31
+    },
+    {
+      "epoch": 0.4816556914393227,
+      "grad_norm": 0.22286632657051086,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.5307,
+      "step": 32
+    },
+    {
+      "epoch": 0.4967074317968015,
+      "grad_norm": 0.20866183936595917,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.5032,
+      "step": 33
+    },
+    {
+      "epoch": 0.5117591721542804,
+      "grad_norm": 0.20444150269031525,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5325,
+      "step": 34
+    },
+    {
+      "epoch": 0.5268109125117592,
+      "grad_norm": 0.22169455885887146,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4898,
+      "step": 35
+    },
+    {
+      "epoch": 0.541862652869238,
+      "grad_norm": 0.23709993064403534,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4526,
+      "step": 36
+    },
+    {
+      "epoch": 0.5569143932267169,
+      "grad_norm": 0.24914033710956573,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.4486,
+      "step": 37
+    },
+    {
+      "epoch": 0.5719661335841957,
+      "grad_norm": 0.35478338599205017,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7652,
+      "step": 38
+    },
+    {
+      "epoch": 0.5870178739416745,
+      "grad_norm": 0.23298819363117218,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5998,
+      "step": 39
+    },
+    {
+      "epoch": 0.6020696142991533,
+      "grad_norm": 0.20077332854270935,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6111,
+      "step": 40
+    },
+    {
+      "epoch": 0.6171213546566322,
+      "grad_norm": 0.21949784457683563,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.5686,
+      "step": 41
+    },
+    {
+      "epoch": 0.632173095014111,
+      "grad_norm": 0.19444361329078674,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5757,
+      "step": 42
+    },
+    {
+      "epoch": 0.6472248353715898,
+      "grad_norm": 0.21272796392440796,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.5291,
+      "step": 43
+    },
+    {
+      "epoch": 0.6622765757290687,
+      "grad_norm": 0.20493632555007935,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4783,
+      "step": 44
+    },
+    {
+      "epoch": 0.6773283160865475,
+      "grad_norm": 0.2022678703069687,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.452,
+      "step": 45
+    },
+    {
+      "epoch": 0.6923800564440263,
+      "grad_norm": 0.20927464962005615,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.5121,
+      "step": 46
+    },
+    {
+      "epoch": 0.7074317968015051,
+      "grad_norm": 0.22144973278045654,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.4493,
+      "step": 47
+    },
+    {
+      "epoch": 0.7224835371589841,
+      "grad_norm": 0.2366451472043991,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4798,
+      "step": 48
+    },
+    {
+      "epoch": 0.7375352775164629,
+      "grad_norm": 0.25476348400115967,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.4312,
+      "step": 49
+    },
+    {
+      "epoch": 0.7525870178739417,
+      "grad_norm": 0.30742359161376953,
+      "learning_rate": 0.0,
+      "loss": 1.4504,
+      "step": 50
+    },
+    {
+      "epoch": 0.7525870178739417,
+      "eval_loss": 1.5220385789871216,
+      "eval_runtime": 4.6057,
+      "eval_samples_per_second": 97.271,
+      "eval_steps_per_second": 12.159,
+      "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": 4.331160810920346e+16,
+  "total_flos": 8.672739346874368e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null