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:bbc050fe7816a14c82486462a0a05d2193e23b4a29dee9b81c8c4b9fac60d37f
+oid sha256:0370633aeff90b9da4dcfd7579f7b9ee6bd7e7748357f0e2d9944594bad8f087
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:996c69050d4bd438fe525811c3c2081577130e51ae8814c472d0b435470da077
+oid sha256:d7d12a2140b97115c1067bbf8999fec5a51fae5354c5ee11e347b10ce6153463
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c9836dcb3576bc73dd2bb541cea71b4445ee53c431fc98ee71b93f407590396
+oid sha256:9a4b4a89905f4469e718a42f20443aa33f5e22f7e3d2b767838b281f552b1795
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18273130a3312ce2d9326560f85ce3f1b60a59ec8f9437272e96eb21e27b5e72
+oid sha256:767bf950f65c318e981703f65fb17c978be14c0f9dd37c8d0609a10604e5dc25
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2b26bd30d0d7348b6d103fcf765ea585e8215ed63e969fcd40fe15ceba7bfe5
+oid sha256:b0da7d62f7d0b0ccf1433a34ff8db8ba6c6032fd51a8209cfc8a2d2f6d881c04
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:718a94b6f0581ee0d601ee24194a0f091b6a436a438ef8e67042f73378f5e6c9
+oid sha256:c264dd3401bbba9e6c3e55ec97ac7bcb88e75a616adba1a42042a0a435763182
 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": 10.356481552124023,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.30143180105501133,
+  "best_metric": 10.347929954528809,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6028636021100227,
   "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": 329.576,
       "eval_steps_per_second": 41.271,
       "step": 25
+    },
+    {
+      "epoch": 0.31348907309721175,
+      "grad_norm": 0.37799665331840515,
+      "learning_rate": 5e-05,
+      "loss": 10.3576,
+      "step": 26
+    },
+    {
+      "epoch": 0.3255463451394122,
+      "grad_norm": 0.3761814832687378,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3566,
+      "step": 27
+    },
+    {
+      "epoch": 0.33760361718161264,
+      "grad_norm": 0.38003864884376526,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3568,
+      "step": 28
+    },
+    {
+      "epoch": 0.3496608892238131,
+      "grad_norm": 0.3890228867530823,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3543,
+      "step": 29
+    },
+    {
+      "epoch": 0.3617181612660136,
+      "grad_norm": 0.38857603073120117,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3538,
+      "step": 30
+    },
+    {
+      "epoch": 0.373775433308214,
+      "grad_norm": 0.39215660095214844,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3541,
+      "step": 31
+    },
+    {
+      "epoch": 0.3858327053504145,
+      "grad_norm": 0.4006653428077698,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3533,
+      "step": 32
+    },
+    {
+      "epoch": 0.39788997739261495,
+      "grad_norm": 0.3988947868347168,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3514,
+      "step": 33
+    },
+    {
+      "epoch": 0.40994724943481536,
+      "grad_norm": 0.4035243093967438,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3511,
+      "step": 34
+    },
+    {
+      "epoch": 0.42200452147701584,
+      "grad_norm": 0.39984676241874695,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3517,
+      "step": 35
+    },
+    {
+      "epoch": 0.43406179351921625,
+      "grad_norm": 0.40296873450279236,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3515,
+      "step": 36
+    },
+    {
+      "epoch": 0.4461190655614167,
+      "grad_norm": 0.3979630470275879,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.35,
+      "step": 37
+    },
+    {
+      "epoch": 0.4581763376036172,
+      "grad_norm": 0.39856386184692383,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3502,
+      "step": 38
+    },
+    {
+      "epoch": 0.4702336096458176,
+      "grad_norm": 0.4138854146003723,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3502,
+      "step": 39
+    },
+    {
+      "epoch": 0.4822908816880181,
+      "grad_norm": 0.4107336401939392,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3497,
+      "step": 40
+    },
+    {
+      "epoch": 0.49434815373021856,
+      "grad_norm": 0.4137466549873352,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3504,
+      "step": 41
+    },
+    {
+      "epoch": 0.506405425772419,
+      "grad_norm": 0.4083769619464874,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3496,
+      "step": 42
+    },
+    {
+      "epoch": 0.5184626978146194,
+      "grad_norm": 0.4133431911468506,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3482,
+      "step": 43
+    },
+    {
+      "epoch": 0.5305199698568199,
+      "grad_norm": 0.41160884499549866,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3485,
+      "step": 44
+    },
+    {
+      "epoch": 0.5425772418990203,
+      "grad_norm": 0.4080004096031189,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3491,
+      "step": 45
+    },
+    {
+      "epoch": 0.5546345139412208,
+      "grad_norm": 0.4072157144546509,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3493,
+      "step": 46
+    },
+    {
+      "epoch": 0.5666917859834213,
+      "grad_norm": 0.41588732600212097,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3482,
+      "step": 47
+    },
+    {
+      "epoch": 0.5787490580256217,
+      "grad_norm": 0.40861016511917114,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3485,
+      "step": 48
+    },
+    {
+      "epoch": 0.5908063300678221,
+      "grad_norm": 0.4074612259864807,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.347,
+      "step": 49
+    },
+    {
+      "epoch": 0.6028636021100227,
+      "grad_norm": 0.4056658446788788,
+      "learning_rate": 0.0,
+      "loss": 10.3471,
+      "step": 50
+    },
+    {
+      "epoch": 0.6028636021100227,
+      "eval_loss": 10.347929954528809,
+      "eval_runtime": 1.7039,
+      "eval_samples_per_second": 328.078,
+      "eval_steps_per_second": 41.083,
+      "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": 33492736671744.0,
+  "total_flos": 66784998064128.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null