Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e266e75392258f32eb547255edaeea06d0619e143e7dc50938603bc34d07fdee
+oid sha256:218e913a2a7db4df827e42b0f4a8c1863bed5517695546f706eab8453c5a6833
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691f3aa812f3e4280800e271f9d6ad3695a14b934cb3a354f38f514af1ee6691
+oid sha256:589379e87ee87ca462d69e9af26f4861fbfa09365326531b5b50df0f51ebc336
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00f436e5fb00a5d5f25c590834a43f11d8673bcc1e6228808f3d06e7342e1f7f
+oid sha256:dac8e4f5fd2c1ebfd789e72bc9acd493f90e6a8749bf1704d9dfae1e9b9474b3
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:042a96cf5e4774965074a5cad8519f695e7e99713a229326aef912e9bc430af0
+oid sha256:bf4b3ed4d6beee57baa6b2e89879da453d373dabc0237ff451065abe34b539a5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ceccd5d6c4ebec1c2f89d430c5e97c2150995c754765a9c28b13a9d7b063c9
+oid sha256:9495fb036dbbb89294b35739f1a6d332b40a48a1c9c7b03eb1c7fba55cdff575
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a81c7e30751a346bb5694351b1ab11e801f1365384f4b4197186403f8a5d4c
+oid sha256:0b9bd03e22f54cdccd438fed24ab7cd3883a3335343b3d923270ecceb7008553
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d5f446d81df8b8e6d5d3423a874831fec3d08bffbe4980db71b54ceb3e7bd4
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4859658479690552,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.04156132026460707,
+  "best_metric": 1.4827420711517334,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.055415093686142766,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 56.962,
       "eval_steps_per_second": 3.561,
       "step": 75
+    },
+    {
+      "epoch": 0.0421154712014685,
+      "grad_norm": 0.3435385823249817,
+      "learning_rate": 1.4938160786375572e-05,
+      "loss": 1.3958,
+      "step": 76
+    },
+    {
+      "epoch": 0.04266962213832993,
+      "grad_norm": 0.42353853583335876,
+      "learning_rate": 1.3778739760445552e-05,
+      "loss": 1.57,
+      "step": 77
+    },
+    {
+      "epoch": 0.04322377307519135,
+      "grad_norm": 0.39138633012771606,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 1.5377,
+      "step": 78
+    },
+    {
+      "epoch": 0.043777924012052785,
+      "grad_norm": 0.4724353849887848,
+      "learning_rate": 1.157994445715706e-05,
+      "loss": 1.5676,
+      "step": 79
+    },
+    {
+      "epoch": 0.04433207494891421,
+      "grad_norm": 0.44573283195495605,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 1.5036,
+      "step": 80
+    },
+    {
+      "epoch": 0.044886225885775635,
+      "grad_norm": 0.44128575921058655,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.5197,
+      "step": 81
+    },
+    {
+      "epoch": 0.04544037682263707,
+      "grad_norm": 0.4542405903339386,
+      "learning_rate": 8.599558442598998e-06,
+      "loss": 1.4969,
+      "step": 82
+    },
+    {
+      "epoch": 0.04599452775949849,
+      "grad_norm": 0.44254857301712036,
+      "learning_rate": 7.695237378953223e-06,
+      "loss": 1.4735,
+      "step": 83
+    },
+    {
+      "epoch": 0.046548678696359924,
+      "grad_norm": 0.47012338042259216,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 1.525,
+      "step": 84
+    },
+    {
+      "epoch": 0.04710282963322135,
+      "grad_norm": 0.5244672894477844,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 1.4543,
+      "step": 85
+    },
+    {
+      "epoch": 0.047656980570082774,
+      "grad_norm": 0.5304999351501465,
+      "learning_rate": 5.263533508961827e-06,
+      "loss": 1.4387,
+      "step": 86
+    },
+    {
+      "epoch": 0.048211131506944206,
+      "grad_norm": 0.6247049570083618,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 1.4606,
+      "step": 87
+    },
+    {
+      "epoch": 0.04876528244380563,
+      "grad_norm": 0.40863263607025146,
+      "learning_rate": 3.885512251130763e-06,
+      "loss": 1.5058,
+      "step": 88
+    },
+    {
+      "epoch": 0.049319433380667056,
+      "grad_norm": 0.3656030297279358,
+      "learning_rate": 3.271776770026963e-06,
+      "loss": 1.4232,
+      "step": 89
+    },
+    {
+      "epoch": 0.04987358431752849,
+      "grad_norm": 0.39725741744041443,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 1.4841,
+      "step": 90
+    },
+    {
+      "epoch": 0.05042773525438991,
+      "grad_norm": 0.4447474777698517,
+      "learning_rate": 2.1982109232821178e-06,
+      "loss": 1.5307,
+      "step": 91
+    },
+    {
+      "epoch": 0.050981886191251345,
+      "grad_norm": 0.4279220998287201,
+      "learning_rate": 1.7395544861325718e-06,
+      "loss": 1.5223,
+      "step": 92
+    },
+    {
+      "epoch": 0.05153603712811277,
+      "grad_norm": 0.45289361476898193,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 1.5057,
+      "step": 93
+    },
+    {
+      "epoch": 0.052090188064974195,
+      "grad_norm": 0.4581681787967682,
+      "learning_rate": 9.810017062595322e-07,
+      "loss": 1.4999,
+      "step": 94
+    },
+    {
+      "epoch": 0.05264433900183563,
+      "grad_norm": 0.47461172938346863,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 1.481,
+      "step": 95
+    },
+    {
+      "epoch": 0.05319848993869705,
+      "grad_norm": 0.4691740870475769,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 1.453,
+      "step": 96
+    },
+    {
+      "epoch": 0.05375264087555848,
+      "grad_norm": 0.4813995063304901,
+      "learning_rate": 2.458548727494292e-07,
+      "loss": 1.4591,
+      "step": 97
+    },
+    {
+      "epoch": 0.05430679181241991,
+      "grad_norm": 0.598747730255127,
+      "learning_rate": 1.0931863906127327e-07,
+      "loss": 1.4327,
+      "step": 98
+    },
+    {
+      "epoch": 0.054860942749281334,
+      "grad_norm": 0.6092488765716553,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 1.4965,
+      "step": 99
+    },
+    {
+      "epoch": 0.055415093686142766,
+      "grad_norm": 0.6786034107208252,
+      "learning_rate": 0.0,
+      "loss": 1.5936,
+      "step": 100
+    },
+    {
+      "epoch": 0.055415093686142766,
+      "eval_loss": 1.4827420711517334,
+      "eval_runtime": 418.5722,
+      "eval_samples_per_second": 58.088,
+      "eval_steps_per_second": 3.631,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.687756927369216e+17,
+  "total_flos": 8.917009236492288e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null