Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17bbf1125a8c3cf1d8dcab5f1e15b5d16a835029e979dc50a0914f55df1b8f48
+oid sha256:f59d11d8f774454496bc3683faace9c16479d5542cb0fbe1132a7a0c446fda6c
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5d531f1e19f3589184a6f8c39025b9bb979efbf3b9241ba3e18b55d6b0aadf3
+oid sha256:a9c42cb6d5e367fd05b6db7dd05958fbf4d70258e7d371015bb6538cf7c8e5ab
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e42c320f18ac88d998af3bd25966a7aaee87fe1b5a7efd85c4ee548b5e2f84
+oid sha256:8851e7afe4ec44aa6c90c6ca634496b65bd0417c3632d643709ef5e5f359ab72
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab9548e18f71fb347b8ac0f81db22bc8e5ea93e3a032345fb639069843dc697
+oid sha256:973787102fa8b0964166dca1b56c0a9587e75700377745cec864a9ed74a984a7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eacecb82d4b8761dc9d6a321089da2f1f4b7af9f1d5a796aa3be7c60edb70480
+oid sha256:7bcd82d3bcb8e4e069d46fa47b01befe4b2e3041855a90b09272323633ead148
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08d26518fb209980d8738c7be345edd76debc8b82ddd2c47fb37bf4ba72ee26d
+oid sha256:709858d20fb6b877147dda57d641ea566a10b6fdfdd59726b64bbc595e2216b5
 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": 0.6153441071510315,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.27932960893854747,
+  "best_metric": 0.3493710160255432,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5586592178770949,
   "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": 16.333,
       "eval_steps_per_second": 2.059,
       "step": 25
+    },
+    {
+      "epoch": 0.2905027932960894,
+      "grad_norm": 3.640821933746338,
+      "learning_rate": 5e-05,
+      "loss": 0.773,
+      "step": 26
+    },
+    {
+      "epoch": 0.3016759776536313,
+      "grad_norm": 2.355128526687622,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5255,
+      "step": 27
+    },
+    {
+      "epoch": 0.3128491620111732,
+      "grad_norm": 2.0450501441955566,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4143,
+      "step": 28
+    },
+    {
+      "epoch": 0.3240223463687151,
+      "grad_norm": 1.4887375831604004,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3391,
+      "step": 29
+    },
+    {
+      "epoch": 0.33519553072625696,
+      "grad_norm": 1.2593166828155518,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3544,
+      "step": 30
+    },
+    {
+      "epoch": 0.3463687150837989,
+      "grad_norm": 1.853230595588684,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3347,
+      "step": 31
+    },
+    {
+      "epoch": 0.3575418994413408,
+      "grad_norm": 1.62923264503479,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3906,
+      "step": 32
+    },
+    {
+      "epoch": 0.3687150837988827,
+      "grad_norm": 1.8756768703460693,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3795,
+      "step": 33
+    },
+    {
+      "epoch": 0.37988826815642457,
+      "grad_norm": 1.8412232398986816,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3968,
+      "step": 34
+    },
+    {
+      "epoch": 0.39106145251396646,
+      "grad_norm": 2.1290626525878906,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.458,
+      "step": 35
+    },
+    {
+      "epoch": 0.4022346368715084,
+      "grad_norm": 2.3173768520355225,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5238,
+      "step": 36
+    },
+    {
+      "epoch": 0.4134078212290503,
+      "grad_norm": 4.143202304840088,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.6603,
+      "step": 37
+    },
+    {
+      "epoch": 0.4245810055865922,
+      "grad_norm": 2.3867380619049072,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5852,
+      "step": 38
+    },
+    {
+      "epoch": 0.43575418994413406,
+      "grad_norm": 2.476198434829712,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3394,
+      "step": 39
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "grad_norm": 2.8215203285217285,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3283,
+      "step": 40
+    },
+    {
+      "epoch": 0.4581005586592179,
+      "grad_norm": 2.8288891315460205,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2943,
+      "step": 41
+    },
+    {
+      "epoch": 0.4692737430167598,
+      "grad_norm": 2.5968244075775146,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2975,
+      "step": 42
+    },
+    {
+      "epoch": 0.48044692737430167,
+      "grad_norm": 1.5942438840866089,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.264,
+      "step": 43
+    },
+    {
+      "epoch": 0.49162011173184356,
+      "grad_norm": 1.9241458177566528,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3016,
+      "step": 44
+    },
+    {
+      "epoch": 0.5027932960893855,
+      "grad_norm": 2.264237403869629,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3179,
+      "step": 45
+    },
+    {
+      "epoch": 0.5139664804469274,
+      "grad_norm": 2.3775475025177,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3435,
+      "step": 46
+    },
+    {
+      "epoch": 0.5251396648044693,
+      "grad_norm": 2.234323263168335,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3742,
+      "step": 47
+    },
+    {
+      "epoch": 0.5363128491620112,
+      "grad_norm": 1.941105842590332,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4158,
+      "step": 48
+    },
+    {
+      "epoch": 0.547486033519553,
+      "grad_norm": 2.362673759460449,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4802,
+      "step": 49
+    },
+    {
+      "epoch": 0.5586592178770949,
+      "grad_norm": 2.9098291397094727,
+      "learning_rate": 0.0,
+      "loss": 0.6609,
+      "step": 50
+    },
+    {
+      "epoch": 0.5586592178770949,
+      "eval_loss": 0.3493710160255432,
+      "eval_runtime": 16.8321,
+      "eval_samples_per_second": 35.824,
+      "eval_steps_per_second": 4.515,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null