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:cc8b701a6cf9d5c1882271f7eea93df931f729bd2344eadb7121acb5818807d8
+oid sha256:c2e94f534920c5fa1b592f59fd16fc46248051907ac9ac5067829a8b7ec0a445
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9248d48ed7a2ac8188acb7c895e85a5a849ceb10d818fd7a3b0408821527a4be
+oid sha256:7c7c96e42d81229991e265a576897d247fe3253bb9090d7f9c2216ece7f9a093
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7242eaf85ff4288b9448cc6e7acb7ae1be598a4707fb4d29d95f8e6891de3f5f
+oid sha256:00ab022b723590c7e04c6edf50b973f33b20b14982fca27b475233c614dcc734
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9595276117324829,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.008122157244964262,
+  "best_metric": 0.9395787715911865,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.016244314489928524,
   "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": 3.785,
       "eval_steps_per_second": 1.894,
       "step": 25
+    },
+    {
+      "epoch": 0.008447043534762833,
+      "grad_norm": 1.1689411401748657,
+      "learning_rate": 0.0001,
+      "loss": 0.9271,
+      "step": 26
+    },
+    {
+      "epoch": 0.008771929824561403,
+      "grad_norm": 0.98142409324646,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.7725,
+      "step": 27
+    },
+    {
+      "epoch": 0.009096816114359974,
+      "grad_norm": 0.855100154876709,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.8737,
+      "step": 28
+    },
+    {
+      "epoch": 0.009421702404158544,
+      "grad_norm": 0.7963764667510986,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.7265,
+      "step": 29
+    },
+    {
+      "epoch": 0.009746588693957114,
+      "grad_norm": 0.6895178556442261,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.8324,
+      "step": 30
+    },
+    {
+      "epoch": 0.010071474983755685,
+      "grad_norm": 0.8792585730552673,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.7426,
+      "step": 31
+    },
+    {
+      "epoch": 0.010396361273554255,
+      "grad_norm": 0.7640400528907776,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.8364,
+      "step": 32
+    },
+    {
+      "epoch": 0.010721247563352826,
+      "grad_norm": 0.717138409614563,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.8579,
+      "step": 33
+    },
+    {
+      "epoch": 0.011046133853151396,
+      "grad_norm": 0.6296213269233704,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.7416,
+      "step": 34
+    },
+    {
+      "epoch": 0.011371020142949967,
+      "grad_norm": 0.6830035448074341,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.793,
+      "step": 35
+    },
+    {
+      "epoch": 0.011695906432748537,
+      "grad_norm": 0.866948664188385,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.7564,
+      "step": 36
+    },
+    {
+      "epoch": 0.012020792722547108,
+      "grad_norm": 0.7266378998756409,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.9034,
+      "step": 37
+    },
+    {
+      "epoch": 0.012345679012345678,
+      "grad_norm": 0.752968966960907,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.8902,
+      "step": 38
+    },
+    {
+      "epoch": 0.012670565302144249,
+      "grad_norm": 0.6887612342834473,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.7917,
+      "step": 39
+    },
+    {
+      "epoch": 0.01299545159194282,
+      "grad_norm": 0.913896918296814,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.7918,
+      "step": 40
+    },
+    {
+      "epoch": 0.01332033788174139,
+      "grad_norm": 0.7052801847457886,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.6793,
+      "step": 41
+    },
+    {
+      "epoch": 0.01364522417153996,
+      "grad_norm": 0.6854836940765381,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.7743,
+      "step": 42
+    },
+    {
+      "epoch": 0.01397011046133853,
+      "grad_norm": 0.6507396697998047,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.8359,
+      "step": 43
+    },
+    {
+      "epoch": 0.014294996751137101,
+      "grad_norm": 0.7426648139953613,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.8788,
+      "step": 44
+    },
+    {
+      "epoch": 0.014619883040935672,
+      "grad_norm": 0.569381058216095,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.7171,
+      "step": 45
+    },
+    {
+      "epoch": 0.014944769330734242,
+      "grad_norm": 0.7846092581748962,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.7299,
+      "step": 46
+    },
+    {
+      "epoch": 0.015269655620532813,
+      "grad_norm": 0.6389809250831604,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.7145,
+      "step": 47
+    },
+    {
+      "epoch": 0.015594541910331383,
+      "grad_norm": 0.5611962676048279,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.6854,
+      "step": 48
+    },
+    {
+      "epoch": 0.015919428200129954,
+      "grad_norm": 0.8515998125076294,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.7188,
+      "step": 49
+    },
+    {
+      "epoch": 0.016244314489928524,
+      "grad_norm": 1.1273244619369507,
+      "learning_rate": 0.0,
+      "loss": 0.8396,
+      "step": 50
+    },
+    {
+      "epoch": 0.016244314489928524,
+      "eval_loss": 0.9395787715911865,
+      "eval_runtime": 342.6187,
+      "eval_samples_per_second": 3.786,
+      "eval_steps_per_second": 1.894,
+      "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": 3.26732322177024e+16,
+  "total_flos": 6.53464644354048e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null