Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87753b5a029cc00f45cf52f1947f4c14dc306d268e863ccb9c3cea338f25d157
+oid sha256:be8ba9cea9179a819985347868ee5307e4c96120c96a999215dd48123eee8e6f
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063d379b68e17029a24589ad36234d354680a550e95613f54a644ca2b012d6bb
+oid sha256:0a0afaace4410a53b457ac879fb69b5a6a4659d42254af3b94c93444d9a933e9
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615b9a33d3eba9e9f3108326e1f613f0d9fcef0ece1f51978c6c264f48d08048
+oid sha256:9d977c7d60755df04d794dfe4d20c46bd6f31ccc6456b8293e1cda56732d9ead
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb46053649ed8c51e4d33813c0ff581a61d2fe985421b49fbfb983c4defd946
+oid sha256:01c551e5f0772387466cda11c44b8b80493a061a4176aa4f7520b14a0f9dc036
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139c06ca56313f66fdc0abd16be2312233d15a5696337e03d1b9cc81b494c3ff
+oid sha256:0b312c2b5260be59be040f569a7f5248fbffaa84c286d5a9b535524d4bea8a0e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90edf23ff75fbe5e073511aa716bb3fcdadd0c4b5f428223c97adfb065e7fe43
+oid sha256:9e970a5d8a322b4bd60bc84d0239acea0c9be6550ca99cb9dfdb311a2cf84cde
 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": 3.499747981550172e-05,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12403100775193798,
+  "best_metric": 2.2997690393822268e-05,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.24806201550387597,
   "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": 39.569,
       "eval_steps_per_second": 4.953,
       "step": 25
+    },
+    {
+      "epoch": 0.1289922480620155,
+      "grad_norm": 0.0009804804576560855,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.13395348837209303,
+      "grad_norm": 0.0011718858731910586,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.13891472868217053,
+      "grad_norm": 0.0011278550373390317,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.14387596899224805,
+      "grad_norm": 0.0011067610466852784,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.14883720930232558,
+      "grad_norm": 0.0009319029632024467,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.1537984496124031,
+      "grad_norm": 0.001149399671703577,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.15875968992248063,
+      "grad_norm": 0.0009815137600526214,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.16372093023255813,
+      "grad_norm": 0.0009451531805098057,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.16868217054263565,
+      "grad_norm": 0.0009667045087553561,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.17364341085271318,
+      "grad_norm": 0.0008827492711134255,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.1786046511627907,
+      "grad_norm": 0.0009160165209323168,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.18356589147286823,
+      "grad_norm": 0.0013087359257042408,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.18852713178294572,
+      "grad_norm": 0.0009455772233195603,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.19348837209302325,
+      "grad_norm": 0.0009561454644426703,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.19844961240310077,
+      "grad_norm": 0.0007501421496272087,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.2034108527131783,
+      "grad_norm": 0.0008627751376479864,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.20837209302325582,
+      "grad_norm": 0.0007621397380717099,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.0006791076739318669,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.21829457364341084,
+      "grad_norm": 0.0007713348604738712,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.22325581395348837,
+      "grad_norm": 0.000771517341490835,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.2282170542635659,
+      "grad_norm": 0.000766627723351121,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.23317829457364342,
+      "grad_norm": 0.001595512148924172,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.23813953488372094,
+      "grad_norm": 0.0008882001275196671,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.24310077519379844,
+      "grad_norm": 0.0010015094885602593,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.24806201550387597,
+      "grad_norm": 0.0012133317068219185,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.24806201550387597,
+      "eval_loss": 2.2997690393822268e-05,
+      "eval_runtime": 34.3546,
+      "eval_samples_per_second": 39.529,
+      "eval_steps_per_second": 4.948,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null