Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ee729c8814e8433d8429a96cdcd53366287f8b013cd7807af8be42d538879ba
+oid sha256:bb30615cb45e90d67401cd3c5aca04d5631b13fa7c7f0c9863cce6340a506fe3
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54458e0859c82437213e797ba75ccb31a5f3c9f04fad2cfd362fe5f825c7b572
+oid sha256:9113cbe857ea7b8c1e4cfa66148e4ecd486b9b00809a4b1160edbea82aeb51d6
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97e2399a8fd4bcbeee3077e2903e5ec13cf2ae07ffafdcc6f7382a1a74e89de5
+oid sha256:4e96b647c1e29d5ad2fdba9b515dacc9606c23799b3054871ed77cb94da08ffc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c92a62207479dfb90ca5356092a3e850ec168a264c3be2b020cd3f9593861cf4
+oid sha256:bf980d4abad6ec4fc3408408be0eafb96b406cd16d7314146536b665c7ff6c6a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e690099d8956e502223acaf7c538f8039f7dd51549d09a742a058df5db08d55
+oid sha256:7674eeca78eca4e66304a5c130169676f62e1dbe0f1aa8b11369fcaec0210723
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53abbbffeaddd96cae664390582b5ec51de2acc90bc536847472e8991d1083e7
+oid sha256:5560a8629dd5857a2dd78399e18bbc4693542756708a70c27a68159290510ea8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.374122619628906,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.028694404591104734,
+  "best_metric": 10.372344017028809,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05738880918220947,
   "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": 514.095,
       "eval_steps_per_second": 133.665,
       "step": 25
+    },
+    {
+      "epoch": 0.029842180774748924,
+      "grad_norm": 0.03204667568206787,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3744,
+      "step": 26
+    },
+    {
+      "epoch": 0.030989956958393114,
+      "grad_norm": 0.03463904932141304,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.375,
+      "step": 27
+    },
+    {
+      "epoch": 0.0321377331420373,
+      "grad_norm": 0.0373113639652729,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3748,
+      "step": 28
+    },
+    {
+      "epoch": 0.033285509325681494,
+      "grad_norm": 0.038027435541152954,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3747,
+      "step": 29
+    },
+    {
+      "epoch": 0.03443328550932568,
+      "grad_norm": 0.04169121012091637,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3736,
+      "step": 30
+    },
+    {
+      "epoch": 0.03558106169296987,
+      "grad_norm": 0.043524134904146194,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.373,
+      "step": 31
+    },
+    {
+      "epoch": 0.03672883787661406,
+      "grad_norm": 0.04519710689783096,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3734,
+      "step": 32
+    },
+    {
+      "epoch": 0.03787661406025825,
+      "grad_norm": 0.04633459076285362,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3719,
+      "step": 33
+    },
+    {
+      "epoch": 0.03902439024390244,
+      "grad_norm": 0.050218332558870316,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3713,
+      "step": 34
+    },
+    {
+      "epoch": 0.040172166427546625,
+      "grad_norm": 0.049278732389211655,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3723,
+      "step": 35
+    },
+    {
+      "epoch": 0.04131994261119082,
+      "grad_norm": 0.04763339087367058,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3733,
+      "step": 36
+    },
+    {
+      "epoch": 0.042467718794835005,
+      "grad_norm": 0.0534612238407135,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3728,
+      "step": 37
+    },
+    {
+      "epoch": 0.0436154949784792,
+      "grad_norm": 0.044117774814367294,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3734,
+      "step": 38
+    },
+    {
+      "epoch": 0.044763271162123384,
+      "grad_norm": 0.0443359836935997,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3731,
+      "step": 39
+    },
+    {
+      "epoch": 0.04591104734576758,
+      "grad_norm": 0.047672707587480545,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3736,
+      "step": 40
+    },
+    {
+      "epoch": 0.047058823529411764,
+      "grad_norm": 0.04800671711564064,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3732,
+      "step": 41
+    },
+    {
+      "epoch": 0.04820659971305596,
+      "grad_norm": 0.04492698982357979,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.372,
+      "step": 42
+    },
+    {
+      "epoch": 0.049354375896700144,
+      "grad_norm": 0.05303284153342247,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3719,
+      "step": 43
+    },
+    {
+      "epoch": 0.05050215208034433,
+      "grad_norm": 0.055283885449171066,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3719,
+      "step": 44
+    },
+    {
+      "epoch": 0.05164992826398852,
+      "grad_norm": 0.05048627033829689,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3714,
+      "step": 45
+    },
+    {
+      "epoch": 0.05279770444763271,
+      "grad_norm": 0.058030229061841965,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3722,
+      "step": 46
+    },
+    {
+      "epoch": 0.0539454806312769,
+      "grad_norm": 0.05614259093999863,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3701,
+      "step": 47
+    },
+    {
+      "epoch": 0.05509325681492109,
+      "grad_norm": 0.06042291969060898,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3713,
+      "step": 48
+    },
+    {
+      "epoch": 0.05624103299856528,
+      "grad_norm": 0.05883251503109932,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3707,
+      "step": 49
+    },
+    {
+      "epoch": 0.05738880918220947,
+      "grad_norm": 0.05974884703755379,
+      "learning_rate": 1e-05,
+      "loss": 10.3726,
+      "step": 50
+    },
+    {
+      "epoch": 0.05738880918220947,
+      "eval_loss": 10.372344017028809,
+      "eval_runtime": 0.1035,
+      "eval_samples_per_second": 482.877,
+      "eval_steps_per_second": 125.548,
+      "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": 21397394817024.0,
+  "total_flos": 42781424615424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null