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:fc84e52e00f0ebb21730190da01060d8776a5cf93ac69e84f325f2fd310675af
+oid sha256:46bb98f074dc376f4667c94d57e0d0ffcff9a7a5b71a2eaeb48be6fb108fdad3
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f9eb795dccc6ca6188f95ec2f78c3c0ca7d9c6702f0adb6939eb1d5c3a59d5
+oid sha256:61cb03fdc2bc724c25065740bd80c3f5d9315529cbac978666ef25fe859f9372
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a68ef8585fab30da2521ed3069d61cbcee2b252e345c6c44d9a420ec501e15
+oid sha256:b1f60efb20253e0da4a9bdd413f57da509beb95f8acfc1122c6b956056259628
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5a18eea5ca3d1dd4e1e6c2591d04db41112b3aa237f32ee4729da9305aea31e
+oid sha256:f235a40d798056959a6c702d97b511b572cea37a4d06f2206ed37691ce6eefbf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e127efbba422272f06dbd874dce79bf2862b3f6d7ef00393e9f7d5e71c87852b
+oid sha256:b268d6d3b65a740a8424b85ea047725c3f378b4f5303abcd8ee30fc2dffd6b34
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e226a2e165fcac3addc9ad3cbdddfa4c323434664ff7f9f8a86c9c5be27d6546
+oid sha256:4a80f3e3db456edc468b7536efedbcc30c577b93784ab956812bfbc9556c6806
 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": 0.6534027457237244,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.42598509052183176,
+  "best_metric": 0.6340692639350891,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8519701810436635,
   "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": 145.0,
       "eval_steps_per_second": 18.354,
       "step": 25
+    },
+    {
+      "epoch": 0.443024494142705,
+      "grad_norm": 0.4085734486579895,
+      "learning_rate": 5e-05,
+      "loss": 0.489,
+      "step": 26
+    },
+    {
+      "epoch": 0.46006389776357826,
+      "grad_norm": 0.5824640989303589,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5703,
+      "step": 27
+    },
+    {
+      "epoch": 0.47710330138445156,
+      "grad_norm": 0.5090480446815491,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6093,
+      "step": 28
+    },
+    {
+      "epoch": 0.4941427050053248,
+      "grad_norm": 0.581184983253479,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6804,
+      "step": 29
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 0.5396629571914673,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5947,
+      "step": 30
+    },
+    {
+      "epoch": 0.5282215122470714,
+      "grad_norm": 0.6579256653785706,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.739,
+      "step": 31
+    },
+    {
+      "epoch": 0.5452609158679447,
+      "grad_norm": 0.8383941650390625,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.777,
+      "step": 32
+    },
+    {
+      "epoch": 0.5623003194888179,
+      "grad_norm": 0.760420560836792,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.648,
+      "step": 33
+    },
+    {
+      "epoch": 0.5793397231096912,
+      "grad_norm": 0.8806910514831543,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7601,
+      "step": 34
+    },
+    {
+      "epoch": 0.5963791267305645,
+      "grad_norm": 0.8053391575813293,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.684,
+      "step": 35
+    },
+    {
+      "epoch": 0.6134185303514377,
+      "grad_norm": 0.9814860820770264,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7502,
+      "step": 36
+    },
+    {
+      "epoch": 0.630457933972311,
+      "grad_norm": 1.2074640989303589,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7318,
+      "step": 37
+    },
+    {
+      "epoch": 0.6474973375931843,
+      "grad_norm": 0.5072846412658691,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4753,
+      "step": 38
+    },
+    {
+      "epoch": 0.6645367412140575,
+      "grad_norm": 0.528431236743927,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.655,
+      "step": 39
+    },
+    {
+      "epoch": 0.6815761448349308,
+      "grad_norm": 0.5640473365783691,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6813,
+      "step": 40
+    },
+    {
+      "epoch": 0.6986155484558041,
+      "grad_norm": 0.5057714581489563,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4823,
+      "step": 41
+    },
+    {
+      "epoch": 0.7156549520766773,
+      "grad_norm": 0.6331304311752319,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5428,
+      "step": 42
+    },
+    {
+      "epoch": 0.7326943556975506,
+      "grad_norm": 0.6265454888343811,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6965,
+      "step": 43
+    },
+    {
+      "epoch": 0.7497337593184239,
+      "grad_norm": 0.7418725490570068,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8041,
+      "step": 44
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 0.681201696395874,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7309,
+      "step": 45
+    },
+    {
+      "epoch": 0.7838125665601704,
+      "grad_norm": 0.6290284395217896,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5944,
+      "step": 46
+    },
+    {
+      "epoch": 0.8008519701810437,
+      "grad_norm": 0.8113570809364319,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6793,
+      "step": 47
+    },
+    {
+      "epoch": 0.8178913738019169,
+      "grad_norm": 0.9687185287475586,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7957,
+      "step": 48
+    },
+    {
+      "epoch": 0.8349307774227902,
+      "grad_norm": 1.0296266078948975,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7558,
+      "step": 49
+    },
+    {
+      "epoch": 0.8519701810436635,
+      "grad_norm": 1.4596647024154663,
+      "learning_rate": 0.0,
+      "loss": 0.8699,
+      "step": 50
+    },
+    {
+      "epoch": 0.8519701810436635,
+      "eval_loss": 0.6340692639350891,
+      "eval_runtime": 2.7254,
+      "eval_samples_per_second": 144.935,
+      "eval_steps_per_second": 18.346,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null