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:ea28bccd73e7a2ea15b20360431c28e5a05b05ea7f807c8985f050d57939193c
+oid sha256:b37f4993ea7e574bffe93f88a643429e342b227219a022fca2d4b32f3738f010
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b274c1eab4f7c11fd78d4954699bae734d470b607286707f75fc7d02017035
+oid sha256:0a2fe079d98bfa7e490c943ae5cf7d37a5134e5e20387b40c32b31fa9fbc835f
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e843c325284c11aa605490b8dac4e81805d38d7a9633170789fe0bae153a85f1
+oid sha256:c19c966559f2cc001e72fe494f140731aac14644c4d55a5b91fa427348ea7903
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acfb15c2aa4bed6d49c73ffad83b32d788f01cc71e46293daaf8f3e0b0b29a70
+oid sha256:dc55a8d66b37776cfda0e0cdc40110713eb339adf90701be7a6214bb5197255f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7c5baac8f1c9a5498ff64f5d7e3e3a13f5d1cb6c610f6bad8a193699b99f09
+oid sha256:daa09287947bec6c5e7a9264efb7fb3aa60646d231cd7639a9983e58dcf9ab4b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96bff3511e5641b8de008f4ed5fded14745e1b53d934017ce2544c937137d7a3
+oid sha256:0f9257ee552bfaddda2c3ffff624fc3e5dedb21037e13a084d4f56d2ea36f9f4
 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": 1.0383129119873047,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.21929824561403508,
+  "best_metric": 1.0091651678085327,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.43859649122807015,
   "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": 30.322,
       "eval_steps_per_second": 3.79,
       "step": 25
+    },
+    {
+      "epoch": 0.22807017543859648,
+      "grad_norm": 0.5108039975166321,
+      "learning_rate": 5e-05,
+      "loss": 0.8292,
+      "step": 26
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 0.40441370010375977,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9462,
+      "step": 27
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 0.4196081757545471,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.0118,
+      "step": 28
+    },
+    {
+      "epoch": 0.2543859649122807,
+      "grad_norm": 0.4395890235900879,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.0664,
+      "step": 29
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.38672029972076416,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.0271,
+      "step": 30
+    },
+    {
+      "epoch": 0.2719298245614035,
+      "grad_norm": 0.3793441355228424,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0811,
+      "step": 31
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 0.4024253189563751,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0329,
+      "step": 32
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 0.4041074514389038,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0725,
+      "step": 33
+    },
+    {
+      "epoch": 0.2982456140350877,
+      "grad_norm": 0.41783076524734497,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1259,
+      "step": 34
+    },
+    {
+      "epoch": 0.30701754385964913,
+      "grad_norm": 0.43029075860977173,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1461,
+      "step": 35
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.42224910855293274,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0811,
+      "step": 36
+    },
+    {
+      "epoch": 0.32456140350877194,
+      "grad_norm": 0.45067015290260315,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0835,
+      "step": 37
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.4447973072528839,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.853,
+      "step": 38
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 0.4372630715370178,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.9161,
+      "step": 39
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.38782182335853577,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9418,
+      "step": 40
+    },
+    {
+      "epoch": 0.35964912280701755,
+      "grad_norm": 0.33929508924484253,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9558,
+      "step": 41
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.390170156955719,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.985,
+      "step": 42
+    },
+    {
+      "epoch": 0.37719298245614036,
+      "grad_norm": 0.37908726930618286,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.95,
+      "step": 43
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 0.3707427382469177,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0245,
+      "step": 44
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 0.37403151392936707,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.0319,
+      "step": 45
+    },
+    {
+      "epoch": 0.40350877192982454,
+      "grad_norm": 0.3797858655452728,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0585,
+      "step": 46
+    },
+    {
+      "epoch": 0.41228070175438597,
+      "grad_norm": 0.39287111163139343,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0661,
+      "step": 47
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.3905193507671356,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0028,
+      "step": 48
+    },
+    {
+      "epoch": 0.4298245614035088,
+      "grad_norm": 0.4534038007259369,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1291,
+      "step": 49
+    },
+    {
+      "epoch": 0.43859649122807015,
+      "grad_norm": 0.4350319504737854,
+      "learning_rate": 0.0,
+      "loss": 1.0738,
+      "step": 50
+    },
+    {
+      "epoch": 0.43859649122807015,
+      "eval_loss": 1.0091651678085327,
+      "eval_runtime": 25.3044,
+      "eval_samples_per_second": 30.35,
+      "eval_steps_per_second": 3.794,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null