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:f398087842f048fe0dea1b0d1cda944fae740a2ae56a33245c0cf3cad0c659ca
+oid sha256:5f5ffdb5ff56a74ad7d14a96901be01fe1dca198a93dd83edcd0e45ed659df45
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed9a980a26e4593b016ee1094531a38241225a14a6ff64437d2e6ddecf6f8620
+oid sha256:62870872346be3c6eacb915f4309485f572e717ef0ff565ee554120b008a8537
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7726afbe49139dc6a38c062a81d009e3e7cc13611acb45dd22484e79780b674a
+oid sha256:9e8be44137ccba17f9ff6ea7f8f6402181523ba9465f7ea132feea5cf7233dfa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc04053a0dafbc85cf19d34183cced3544e513ffd7194a6030cf3eacb4fc068
+oid sha256:eabcf4263682cb5e8f296947e083e29554f14e37ec341814ec87c3598be8095c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11a6f32d6df551f63d01f2c213493ac2382b968eae6f643e3fc4b286fc496a16
+oid sha256:fd3f7eca120c750b2c3ff50293e65c4ea860583f779eea4cf36faf4d69e10314
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23f98cca60f7baf587221ae5cbc0a3e25b7937f6a81284b298ff55ca0a60210a
+oid sha256:f2211c091e0ed53d83f300fd91ba1d71860cc26fffbe32160b8359a6e04092a4
 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": 0.4790324866771698,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.16645859342488556,
+  "best_metric": 0.4515899121761322,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3329171868497711,
   "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": 14.816,
       "eval_steps_per_second": 1.859,
       "step": 25
+    },
+    {
+      "epoch": 0.17311693716188098,
+      "grad_norm": 1.0460373163223267,
+      "learning_rate": 5e-05,
+      "loss": 0.3871,
+      "step": 26
+    },
+    {
+      "epoch": 0.1797752808988764,
+      "grad_norm": 1.1974306106567383,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3586,
+      "step": 27
+    },
+    {
+      "epoch": 0.18643362463587182,
+      "grad_norm": 1.1274254322052002,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3886,
+      "step": 28
+    },
+    {
+      "epoch": 0.19309196837286724,
+      "grad_norm": 1.193386435508728,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4036,
+      "step": 29
+    },
+    {
+      "epoch": 0.19975031210986266,
+      "grad_norm": 1.0893070697784424,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4003,
+      "step": 30
+    },
+    {
+      "epoch": 0.2064086558468581,
+      "grad_norm": 1.2256414890289307,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3774,
+      "step": 31
+    },
+    {
+      "epoch": 0.21306699958385353,
+      "grad_norm": 1.1129382848739624,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4126,
+      "step": 32
+    },
+    {
+      "epoch": 0.21972534332084895,
+      "grad_norm": 1.1873247623443604,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4491,
+      "step": 33
+    },
+    {
+      "epoch": 0.22638368705784437,
+      "grad_norm": 1.3507243394851685,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4582,
+      "step": 34
+    },
+    {
+      "epoch": 0.2330420307948398,
+      "grad_norm": 1.5721896886825562,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4969,
+      "step": 35
+    },
+    {
+      "epoch": 0.2397003745318352,
+      "grad_norm": 2.0338633060455322,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5316,
+      "step": 36
+    },
+    {
+      "epoch": 0.24635871826883063,
+      "grad_norm": 2.7098116874694824,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5699,
+      "step": 37
+    },
+    {
+      "epoch": 0.2530170620058261,
+      "grad_norm": 3.2819511890411377,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5692,
+      "step": 38
+    },
+    {
+      "epoch": 0.2596754057428215,
+      "grad_norm": 0.6997650861740112,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3947,
+      "step": 39
+    },
+    {
+      "epoch": 0.2663337494798169,
+      "grad_norm": 0.7984439730644226,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.395,
+      "step": 40
+    },
+    {
+      "epoch": 0.27299209321681234,
+      "grad_norm": 0.9441525936126709,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3733,
+      "step": 41
+    },
+    {
+      "epoch": 0.27965043695380776,
+      "grad_norm": 0.9665208458900452,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3955,
+      "step": 42
+    },
+    {
+      "epoch": 0.2863087806908032,
+      "grad_norm": 1.0408518314361572,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3756,
+      "step": 43
+    },
+    {
+      "epoch": 0.2929671244277986,
+      "grad_norm": 1.1118501424789429,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4042,
+      "step": 44
+    },
+    {
+      "epoch": 0.299625468164794,
+      "grad_norm": 1.1715872287750244,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3959,
+      "step": 45
+    },
+    {
+      "epoch": 0.30628381190178944,
+      "grad_norm": 1.1747242212295532,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4306,
+      "step": 46
+    },
+    {
+      "epoch": 0.31294215563878486,
+      "grad_norm": 1.2841401100158691,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4725,
+      "step": 47
+    },
+    {
+      "epoch": 0.3196004993757803,
+      "grad_norm": 2.1822011470794678,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4955,
+      "step": 48
+    },
+    {
+      "epoch": 0.3262588431127757,
+      "grad_norm": 5.10789155960083,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5343,
+      "step": 49
+    },
+    {
+      "epoch": 0.3329171868497711,
+      "grad_norm": 4.15449857711792,
+      "learning_rate": 0.0,
+      "loss": 0.7024,
+      "step": 50
+    },
+    {
+      "epoch": 0.3329171868497711,
+      "eval_loss": 0.4515899121761322,
+      "eval_runtime": 68.2577,
+      "eval_samples_per_second": 14.826,
+      "eval_steps_per_second": 1.861,
+      "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": 5.1220100210386534e+17,
+  "total_flos": 1.0234452164906844e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null