Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e54c5e8d0d9fd06e7f93d99bb00f764eeec76620a5c44ed4689b64a51f019d4
+oid sha256:9281e2c9f2dc4df80a0790683ccf14c54a659714760b8c2f94f31e67260790f3
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b733ad26aedbf5dddc21399759a599aa36ca24119c452da8066bf81ef3b85db9
+oid sha256:78ba13880751aa78631431e0006226e7ee8c872ceb423d8b3f79025ba5282ee9
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40fe11d496b578f8bda315fa8e7510218cb21a98e22a5682499d746a441cf76e
+oid sha256:2c624a831f1f7250059efe0ff1b5b4e53bd0f5482056ef8e0b4ab9dda26a73b6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc727d4aa38452dc56ff9913b5529d4ac4fe1fa31f73ee09fecebf0c10a837ca
+oid sha256:8373e309a57d21359c55f2efb780bf43158c4aafa4d47e676c409d8e910a9172
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35296db638910329ab8e436fd6011b4c7e9899641726f7836ae190ed0571b3c2
+oid sha256:9b568f2fb75d9c197edb9908ea401effa2395e216403b540db4ee67066e07290
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f133da5696e3bd7dcf8133f0ef3dd98e4bcfaaad8386acb6a38a4233bca6cfa4
+oid sha256:dab23e121551395df165e8307c721f26bb01c2b10c535bf2a9fed3b0caaa57d5
 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": 0.699822187423706,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.18157058556513844,
+  "best_metric": 0.6934562921524048,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3631411711302769,
   "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": 23.278,
       "eval_steps_per_second": 2.91,
       "step": 25
+    },
+    {
+      "epoch": 0.18883340898774398,
+      "grad_norm": 31.9716796875,
+      "learning_rate": 5e-05,
+      "loss": 11.1079,
+      "step": 26
+    },
+    {
+      "epoch": 0.1960962324103495,
+      "grad_norm": 439.19219970703125,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 12.9629,
+      "step": 27
+    },
+    {
+      "epoch": 0.20335905583295505,
+      "grad_norm": 19.925203323364258,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.2184,
+      "step": 28
+    },
+    {
+      "epoch": 0.2106218792555606,
+      "grad_norm": 22.091087341308594,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.253,
+      "step": 29
+    },
+    {
+      "epoch": 0.21788470267816615,
+      "grad_norm": 15.780365943908691,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.1041,
+      "step": 30
+    },
+    {
+      "epoch": 0.22514752610077168,
+      "grad_norm": 22.305627822875977,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.3212,
+      "step": 31
+    },
+    {
+      "epoch": 0.23241034952337722,
+      "grad_norm": 14.443148612976074,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.0897,
+      "step": 32
+    },
+    {
+      "epoch": 0.23967317294598275,
+      "grad_norm": 20.79016876220703,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.3697,
+      "step": 33
+    },
+    {
+      "epoch": 0.2469359963685883,
+      "grad_norm": 15.159466743469238,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.9596,
+      "step": 34
+    },
+    {
+      "epoch": 0.25419881979119385,
+      "grad_norm": 9.283771514892578,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.1473,
+      "step": 35
+    },
+    {
+      "epoch": 0.2614616432137994,
+      "grad_norm": 10.101941108703613,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.1644,
+      "step": 36
+    },
+    {
+      "epoch": 0.2687244666364049,
+      "grad_norm": 7.609732627868652,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.0647,
+      "step": 37
+    },
+    {
+      "epoch": 0.27598729005901046,
+      "grad_norm": 11.511059761047363,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.1036,
+      "step": 38
+    },
+    {
+      "epoch": 0.283250113481616,
+      "grad_norm": 13.059183120727539,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.1317,
+      "step": 39
+    },
+    {
+      "epoch": 0.29051293690422153,
+      "grad_norm": 12.633243560791016,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.2251,
+      "step": 40
+    },
+    {
+      "epoch": 0.29777576032682707,
+      "grad_norm": 18.697067260742188,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.1338,
+      "step": 41
+    },
+    {
+      "epoch": 0.3050385837494326,
+      "grad_norm": 11.478179931640625,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.1041,
+      "step": 42
+    },
+    {
+      "epoch": 0.31230140717203814,
+      "grad_norm": 15.045670509338379,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.9997,
+      "step": 43
+    },
+    {
+      "epoch": 0.3195642305946437,
+      "grad_norm": 12.63309097290039,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.0959,
+      "step": 44
+    },
+    {
+      "epoch": 0.3268270540172492,
+      "grad_norm": 17.579280853271484,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.1073,
+      "step": 45
+    },
+    {
+      "epoch": 0.33408987743985474,
+      "grad_norm": 6.669552803039551,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.0868,
+      "step": 46
+    },
+    {
+      "epoch": 0.3413527008624603,
+      "grad_norm": 12.905702590942383,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.1601,
+      "step": 47
+    },
+    {
+      "epoch": 0.3486155242850658,
+      "grad_norm": 10.452112197875977,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.0427,
+      "step": 48
+    },
+    {
+      "epoch": 0.35587834770767135,
+      "grad_norm": 5.756313800811768,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.0349,
+      "step": 49
+    },
+    {
+      "epoch": 0.3631411711302769,
+      "grad_norm": 21.877653121948242,
+      "learning_rate": 0.0,
+      "loss": 11.1446,
+      "step": 50
+    },
+    {
+      "epoch": 0.3631411711302769,
+      "eval_loss": 0.6934562921524048,
+      "eval_runtime": 39.8532,
+      "eval_samples_per_second": 23.285,
+      "eval_steps_per_second": 2.911,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null