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:c7c606f3ec6092e9f6754a19d19da41c2db88b148858acdb23dd44d550ac9329
+oid sha256:f6404eb21f64f0fd0495017d0d23caaec61252653ab90a1588bbb3c531463c3c
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f29de210c45c07b3170ad15d40db2c3310ed36a0a77f6f99511fab8814e569a
+oid sha256:6704fcb92df52ce2a4fd1ee2c475016dae08da655885600db67dc4c7b475ab86
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2edfa45f33fab1e4ef439a0c57573a48a6cce909aaf4e89c07ffc7665c5dbf2f
+oid sha256:3c453a58c4bf4312ef0a30c0b43d19fc75e51ae316fb27c948d9633e8580b938
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:590775605cd813196fc85dac96b9894ed963fd457008ecd542374b5377cc4ff2
+oid sha256:4e7dff3eab3ccb4a7c3120630c486dd2cff179895632db0ffcb893f2176156c6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb3c72c1591cfb4e4980f314657d27cdfd68f1dd571892a8ea18b5a54757edf
+oid sha256:a827522647025d34e47663465b058aa44ac5e109e57377e97716e2276fb8fe36
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015c6ec189245107367b9e11c21b45829c2a1895662daaf501436ab85e386106
+oid sha256:dda0c85b48e6d17862dee43bbd5a51b1e593b03910bbd2f556f8212c0007227e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7101312875747681,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03241885156218341,
+  "best_metric": 0.652353048324585,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06483770312436682,
   "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": 16.84,
       "eval_steps_per_second": 4.378,
       "step": 25
+    },
+    {
+      "epoch": 0.03371560562467075,
+      "grad_norm": 9.792278289794922,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 36.8223,
+      "step": 26
+    },
+    {
+      "epoch": 0.03501235968715808,
+      "grad_norm": 15.209010124206543,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 28.8723,
+      "step": 27
+    },
+    {
+      "epoch": 0.03630911374964542,
+      "grad_norm": 15.312687873840332,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 20.8671,
+      "step": 28
+    },
+    {
+      "epoch": 0.03760586781213276,
+      "grad_norm": 11.13228988647461,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 15.874,
+      "step": 29
+    },
+    {
+      "epoch": 0.03890262187462009,
+      "grad_norm": 12.170778274536133,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 9.841,
+      "step": 30
+    },
+    {
+      "epoch": 0.04019937593710743,
+      "grad_norm": 8.809076309204102,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 12.2626,
+      "step": 31
+    },
+    {
+      "epoch": 0.04149612999959477,
+      "grad_norm": 8.72727108001709,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 9.9618,
+      "step": 32
+    },
+    {
+      "epoch": 0.0427928840620821,
+      "grad_norm": 8.521458625793457,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 11.9306,
+      "step": 33
+    },
+    {
+      "epoch": 0.04408963812456944,
+      "grad_norm": 10.72695255279541,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 17.8682,
+      "step": 34
+    },
+    {
+      "epoch": 0.04538639218705677,
+      "grad_norm": 12.048954963684082,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 24.6443,
+      "step": 35
+    },
+    {
+      "epoch": 0.04668314624954411,
+      "grad_norm": 14.231986045837402,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 30.6334,
+      "step": 36
+    },
+    {
+      "epoch": 0.04797990031203145,
+      "grad_norm": 16.270370483398438,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 36.3834,
+      "step": 37
+    },
+    {
+      "epoch": 0.04927665437451878,
+      "grad_norm": 14.480351448059082,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 41.1031,
+      "step": 38
+    },
+    {
+      "epoch": 0.05057340843700612,
+      "grad_norm": 9.69229507446289,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 30.1462,
+      "step": 39
+    },
+    {
+      "epoch": 0.05187016249949346,
+      "grad_norm": 10.705002784729004,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 23.4604,
+      "step": 40
+    },
+    {
+      "epoch": 0.05316691656198079,
+      "grad_norm": 11.107697486877441,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 13.1305,
+      "step": 41
+    },
+    {
+      "epoch": 0.05446367062446813,
+      "grad_norm": 7.914254665374756,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 10.4824,
+      "step": 42
+    },
+    {
+      "epoch": 0.05576042468695547,
+      "grad_norm": 7.241426467895508,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 12.7372,
+      "step": 43
+    },
+    {
+      "epoch": 0.0570571787494428,
+      "grad_norm": 7.243592262268066,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 8.7167,
+      "step": 44
+    },
+    {
+      "epoch": 0.05835393281193014,
+      "grad_norm": 8.968466758728027,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 11.5413,
+      "step": 45
+    },
+    {
+      "epoch": 0.05965068687441747,
+      "grad_norm": 10.867255210876465,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 14.4485,
+      "step": 46
+    },
+    {
+      "epoch": 0.06094744093690481,
+      "grad_norm": 10.397505760192871,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 14.4408,
+      "step": 47
+    },
+    {
+      "epoch": 0.06224419499939215,
+      "grad_norm": 11.32922077178955,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 21.16,
+      "step": 48
+    },
+    {
+      "epoch": 0.06354094906187949,
+      "grad_norm": 15.780669212341309,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 29.0683,
+      "step": 49
+    },
+    {
+      "epoch": 0.06483770312436682,
+      "grad_norm": 21.16714096069336,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 35.8908,
+      "step": 50
+    },
+    {
+      "epoch": 0.06483770312436682,
+      "eval_loss": 0.652353048324585,
+      "eval_runtime": 2.9375,
+      "eval_samples_per_second": 17.021,
+      "eval_steps_per_second": 4.426,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6303741225336832e+17,
+  "total_flos": 5.259926510449459e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null