Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9422ac6a23e82d9e1d53912f50facba2b99baea88e2b3b3f30aa364ba0a638f5
+oid sha256:2ebfa678baaaa0091758599baae18242a8ca3a72b75ddb0e02c76b453b099ed9
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ea4a79b7b0caf0a174077e0dcee86b6233c54bdc20af6a05014f12484f1d6a
+oid sha256:636b5f06b1010d1a7b574a2f135b039c0d2b72470b45b4f42721193fe4378489
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b64324cd14a08295f33317021099a11dbac93a8b786778146419ad04a4728c
+oid sha256:5389b04893d07ad5e574c8065ff388418c4b472d9024f87f9c13e4d0346c643c
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c7418e94264de168fcd01642eb774f29f470379c5ac291a2fa6f41960ced7c
+oid sha256:4a9ab0a8e616493ed0da89036f15cf8ca983202895781bdfa14d0b8e365cdbf9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e59a72cfe9a7a39f219978e3873e14fb9efa66298ef83c1a8e7cc22a9311206f
+oid sha256:5f224e80a431b21e35ad4051800c61325a707972ddb688d8b8a98ce97f986631
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a8aadc9bfa62d04358abd20979d728c2383bc863bae5f42620e74e8f36c9b8f
+oid sha256:8e22860f08c4cdeabf2e4d9917ad61b983a9f6afa8378879ba5349b56c7df0f9
 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": 1.6207541227340698,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06914433880726016,
+  "best_metric": 1.4909886121749878,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13828867761452032,
   "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": 14.453,
       "eval_steps_per_second": 1.81,
       "step": 25
+    },
+    {
+      "epoch": 0.07191011235955057,
+      "grad_norm": 2.3166110515594482,
+      "learning_rate": 5e-05,
+      "loss": 1.6658,
+      "step": 26
+    },
+    {
+      "epoch": 0.07467588591184096,
+      "grad_norm": 2.2079741954803467,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5891,
+      "step": 27
+    },
+    {
+      "epoch": 0.07744165946413137,
+      "grad_norm": 2.1089913845062256,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.611,
+      "step": 28
+    },
+    {
+      "epoch": 0.08020743301642178,
+      "grad_norm": 2.063892126083374,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.6323,
+      "step": 29
+    },
+    {
+      "epoch": 0.08297320656871218,
+      "grad_norm": 2.1836607456207275,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.5434,
+      "step": 30
+    },
+    {
+      "epoch": 0.08573898012100259,
+      "grad_norm": 2.6283938884735107,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.6996,
+      "step": 31
+    },
+    {
+      "epoch": 0.088504753673293,
+      "grad_norm": 2.6632418632507324,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.7309,
+      "step": 32
+    },
+    {
+      "epoch": 0.0912705272255834,
+      "grad_norm": 2.8932669162750244,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.6558,
+      "step": 33
+    },
+    {
+      "epoch": 0.09403630077787381,
+      "grad_norm": 3.0536949634552,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6094,
+      "step": 34
+    },
+    {
+      "epoch": 0.09680207433016422,
+      "grad_norm": 3.8116891384124756,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.6626,
+      "step": 35
+    },
+    {
+      "epoch": 0.09956784788245462,
+      "grad_norm": 4.177957057952881,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.2707,
+      "step": 36
+    },
+    {
+      "epoch": 0.10233362143474503,
+      "grad_norm": 5.071949005126953,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.4014,
+      "step": 37
+    },
+    {
+      "epoch": 0.10509939498703544,
+      "grad_norm": 2.227691888809204,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.526,
+      "step": 38
+    },
+    {
+      "epoch": 0.10786516853932585,
+      "grad_norm": 1.9869389533996582,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5391,
+      "step": 39
+    },
+    {
+      "epoch": 0.11063094209161625,
+      "grad_norm": 1.6682724952697754,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.4795,
+      "step": 40
+    },
+    {
+      "epoch": 0.11339671564390666,
+      "grad_norm": 1.789174199104309,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.5158,
+      "step": 41
+    },
+    {
+      "epoch": 0.11616248919619707,
+      "grad_norm": 1.8229426145553589,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.545,
+      "step": 42
+    },
+    {
+      "epoch": 0.11892826274848747,
+      "grad_norm": 2.1133134365081787,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.4575,
+      "step": 43
+    },
+    {
+      "epoch": 0.12169403630077788,
+      "grad_norm": 2.527867317199707,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6157,
+      "step": 44
+    },
+    {
+      "epoch": 0.12445980985306827,
+      "grad_norm": 2.451172113418579,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.655,
+      "step": 45
+    },
+    {
+      "epoch": 0.1272255834053587,
+      "grad_norm": 2.618565082550049,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.4986,
+      "step": 46
+    },
+    {
+      "epoch": 0.1299913569576491,
+      "grad_norm": 2.9134609699249268,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.4604,
+      "step": 47
+    },
+    {
+      "epoch": 0.1327571305099395,
+      "grad_norm": 3.504913568496704,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4817,
+      "step": 48
+    },
+    {
+      "epoch": 0.13552290406222992,
+      "grad_norm": 4.311337471008301,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1932,
+      "step": 49
+    },
+    {
+      "epoch": 0.13828867761452032,
+      "grad_norm": 4.128970623016357,
+      "learning_rate": 0.0,
+      "loss": 1.1704,
+      "step": 50
+    },
+    {
+      "epoch": 0.13828867761452032,
+      "eval_loss": 1.4909886121749878,
+      "eval_runtime": 168.4634,
+      "eval_samples_per_second": 14.46,
+      "eval_steps_per_second": 1.81,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null