Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fa4fd55cd545bbb2fdf31a4ffc213d0303548d4c30c7c26d9f4f3d71807eb15
+oid sha256:97d4525a2cd92d4ac1e1ca68c39845d8727ac299933f5ca0720ca9a64ddfc02f
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:632fc51d4fec9214ab0ac931041ef32f5f1e6b72eb198072c10745f8fe8d77bd
+oid sha256:73d7f6fb96730e2621e08e5111bb63d55dba9bf08219b80eb97ac1d0aa346b54
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ce0adbfe47c5bed96ceddda72478c15e117c146ffa98cd5aee2fcbd5b58574
+oid sha256:5799ae736a18d27e6cdf1da563932903545a12a8ebd06d732e3f07948aea69d5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e809001856ff6bfbc57d13d1ad97d1a3eec69d5f35d99e95c435521749ac78
+oid sha256:5a90f54058b654d5147c17ace29a927b6a086649c364262048f8bec1725b5d63
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d6f4e04b4877f748f8af96be386abf83bea13b0d21649d8a89ad13259667bf
+oid sha256:60598cbe3123adb51b7263246b4d8d9e26afaa436bc3c4a9c1ff56fc071508cd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d6f64e4902ac840ab378bfc0f426633c53d274311fd6f394d9289c09cbb3ed8
+oid sha256:f667e26fd5de5104fb7c83bf1cd49745aee1de09dc36a7de2677765505883fb4
 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": 1.8613815307617188,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.18365472910927455,
+  "best_metric": 1.800140142440796,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3673094582185491,
   "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": 14.765,
       "eval_steps_per_second": 1.852,
       "step": 25
+    },
+    {
+      "epoch": 0.19100091827364554,
+      "grad_norm": 3.4452316761016846,
+      "learning_rate": 5e-05,
+      "loss": 2.4563,
+      "step": 26
+    },
+    {
+      "epoch": 0.19834710743801653,
+      "grad_norm": 2.2789227962493896,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.0484,
+      "step": 27
+    },
+    {
+      "epoch": 0.2056932966023875,
+      "grad_norm": 5.860487937927246,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.8531,
+      "step": 28
+    },
+    {
+      "epoch": 0.2130394857667585,
+      "grad_norm": 2.3761487007141113,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.8806,
+      "step": 29
+    },
+    {
+      "epoch": 0.22038567493112948,
+      "grad_norm": 2.0185317993164062,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.1398,
+      "step": 30
+    },
+    {
+      "epoch": 0.22773186409550045,
+      "grad_norm": 2.3282179832458496,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.7929,
+      "step": 31
+    },
+    {
+      "epoch": 0.23507805325987144,
+      "grad_norm": 2.7504942417144775,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.8338,
+      "step": 32
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 2.712554454803467,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9509,
+      "step": 33
+    },
+    {
+      "epoch": 0.2497704315886134,
+      "grad_norm": 2.105562686920166,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5841,
+      "step": 34
+    },
+    {
+      "epoch": 0.2571166207529844,
+      "grad_norm": 2.9640512466430664,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8982,
+      "step": 35
+    },
+    {
+      "epoch": 0.2644628099173554,
+      "grad_norm": 2.4896340370178223,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.8629,
+      "step": 36
+    },
+    {
+      "epoch": 0.27180899908172634,
+      "grad_norm": 2.146752119064331,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.5085,
+      "step": 37
+    },
+    {
+      "epoch": 0.27915518824609736,
+      "grad_norm": 2.3504111766815186,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7211,
+      "step": 38
+    },
+    {
+      "epoch": 0.2865013774104683,
+      "grad_norm": 2.8673181533813477,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.2549,
+      "step": 39
+    },
+    {
+      "epoch": 0.2938475665748393,
+      "grad_norm": 2.247053384780884,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0768,
+      "step": 40
+    },
+    {
+      "epoch": 0.3011937557392103,
+      "grad_norm": 2.0035057067871094,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.7571,
+      "step": 41
+    },
+    {
+      "epoch": 0.3085399449035813,
+      "grad_norm": 2.2739028930664062,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.9607,
+      "step": 42
+    },
+    {
+      "epoch": 0.31588613406795224,
+      "grad_norm": 2.3509528636932373,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.8713,
+      "step": 43
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 2.5070559978485107,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5904,
+      "step": 44
+    },
+    {
+      "epoch": 0.3305785123966942,
+      "grad_norm": 2.3728628158569336,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.0209,
+      "step": 45
+    },
+    {
+      "epoch": 0.3379247015610652,
+      "grad_norm": 2.24059796333313,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.8248,
+      "step": 46
+    },
+    {
+      "epoch": 0.34527089072543615,
+      "grad_norm": 2.2181599140167236,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.8898,
+      "step": 47
+    },
+    {
+      "epoch": 0.3526170798898072,
+      "grad_norm": 2.4641213417053223,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.727,
+      "step": 48
+    },
+    {
+      "epoch": 0.35996326905417814,
+      "grad_norm": 2.3320772647857666,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.5124,
+      "step": 49
+    },
+    {
+      "epoch": 0.3673094582185491,
+      "grad_norm": 2.855008363723755,
+      "learning_rate": 0.0,
+      "loss": 1.531,
+      "step": 50
+    },
+    {
+      "epoch": 0.3673094582185491,
+      "eval_loss": 1.800140142440796,
+      "eval_runtime": 62.0516,
+      "eval_samples_per_second": 14.778,
+      "eval_steps_per_second": 1.853,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null