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:f8a0a7e76898383f7db97a2ab6846d8bdb9da707611c650100934e6df2255892
+oid sha256:ddc3c889db1f40b8618b1c7eb3e5b053e0180b9741bf37540bde6a50fa6e8b13
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba88bf68b7514e643ad9b8ab8c6a7850a219aabeec8233655b7c66be13c07dc
+oid sha256:050aabb65d287db568ed0f1c53305f464da66e81f858cd7627810510de89b575
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e6be224bc4038c58f65c1688fca80d25323074567e65faad8fbc8da4db44f1d
+oid sha256:91b913015bfec13ce6072d40c5ee8089d2210caee084d54b3ac9c43df6e0366f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a27267f63b10760bf1f5be56ee5cd69424634f831d330ffc526e6cee9683227
+oid sha256:217a8c02a392f207f1660428bfcbb156eda5dcbd1f3f3d1010e85a307c460687
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f6ced0f1442129febf7fe016bfd99c804f04814cc707fe229f2ce7c56ebd460
+oid sha256:3b402383c0d40a829ae5305ab03e22b37a960aef942e111de5ba3ccdbd086d4c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab9fe8abdd1da75c7073511e790fee733785b6a023e294c14fe51497c4d847d1
+oid sha256:5e4495cc3469886e50fd4d11ffd78a146f474f0d8e18cb7b04b72d44c4102937
 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": 0.7485018968582153,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.008886519150448769,
+  "best_metric": 0.6602135300636292,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.017773038300897537,
   "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": 14.743,
       "eval_steps_per_second": 1.844,
       "step": 25
+    },
+    {
+      "epoch": 0.00924197991646672,
+      "grad_norm": 1.5790648460388184,
+      "learning_rate": 5e-05,
+      "loss": 0.7336,
+      "step": 26
+    },
+    {
+      "epoch": 0.00959744068248467,
+      "grad_norm": 1.6744600534439087,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8472,
+      "step": 27
+    },
+    {
+      "epoch": 0.009952901448502622,
+      "grad_norm": 1.9266607761383057,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8284,
+      "step": 28
+    },
+    {
+      "epoch": 0.010308362214520573,
+      "grad_norm": 1.427903652191162,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7542,
+      "step": 29
+    },
+    {
+      "epoch": 0.010663822980538524,
+      "grad_norm": 1.314942717552185,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7155,
+      "step": 30
+    },
+    {
+      "epoch": 0.011019283746556474,
+      "grad_norm": 1.3423740863800049,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6615,
+      "step": 31
+    },
+    {
+      "epoch": 0.011374744512574425,
+      "grad_norm": 1.670693278312683,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8312,
+      "step": 32
+    },
+    {
+      "epoch": 0.011730205278592375,
+      "grad_norm": 1.2509427070617676,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6077,
+      "step": 33
+    },
+    {
+      "epoch": 0.012085666044610326,
+      "grad_norm": 1.5091224908828735,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7917,
+      "step": 34
+    },
+    {
+      "epoch": 0.012441126810628277,
+      "grad_norm": 1.3459668159484863,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6583,
+      "step": 35
+    },
+    {
+      "epoch": 0.012796587576646227,
+      "grad_norm": 1.6527843475341797,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7191,
+      "step": 36
+    },
+    {
+      "epoch": 0.013152048342664178,
+      "grad_norm": 1.5868197679519653,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7099,
+      "step": 37
+    },
+    {
+      "epoch": 0.013507509108682128,
+      "grad_norm": 1.563650131225586,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7105,
+      "step": 38
+    },
+    {
+      "epoch": 0.01386296987470008,
+      "grad_norm": 1.5005427598953247,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6326,
+      "step": 39
+    },
+    {
+      "epoch": 0.014218430640718031,
+      "grad_norm": 1.6985749006271362,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6293,
+      "step": 40
+    },
+    {
+      "epoch": 0.014573891406735982,
+      "grad_norm": 1.3856974840164185,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6698,
+      "step": 41
+    },
+    {
+      "epoch": 0.014929352172753933,
+      "grad_norm": 1.5392625331878662,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6759,
+      "step": 42
+    },
+    {
+      "epoch": 0.015284812938771883,
+      "grad_norm": 1.4249393939971924,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6719,
+      "step": 43
+    },
+    {
+      "epoch": 0.015640273704789834,
+      "grad_norm": 1.3689143657684326,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6939,
+      "step": 44
+    },
+    {
+      "epoch": 0.015995734470807786,
+      "grad_norm": 1.7862446308135986,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7344,
+      "step": 45
+    },
+    {
+      "epoch": 0.016351195236825735,
+      "grad_norm": 1.6102662086486816,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7434,
+      "step": 46
+    },
+    {
+      "epoch": 0.016706656002843687,
+      "grad_norm": 1.3429709672927856,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6105,
+      "step": 47
+    },
+    {
+      "epoch": 0.017062116768861636,
+      "grad_norm": 1.4946287870407104,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6974,
+      "step": 48
+    },
+    {
+      "epoch": 0.01741757753487959,
+      "grad_norm": 1.599914312362671,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7955,
+      "step": 49
+    },
+    {
+      "epoch": 0.017773038300897537,
+      "grad_norm": 1.4792672395706177,
+      "learning_rate": 0.0,
+      "loss": 0.7427,
+      "step": 50
+    },
+    {
+      "epoch": 0.017773038300897537,
+      "eval_loss": 0.6602135300636292,
+      "eval_runtime": 1286.2227,
+      "eval_samples_per_second": 14.735,
+      "eval_steps_per_second": 1.843,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null