Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2455e0ef07cad11f26ee16e5b4f1791a290cd56e7276fde91e6a5c514387d2e7
+oid sha256:b5ff5c5e9337c53de9cc882ab1dbf589fef27b8f07c16e366781fa72a6a96416
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d09766f89306d2244932ddcaf6170a9392879627e72d7237e3855c2085155a0d
+oid sha256:dba3136ff1c8268b4e37bbffab113d0c15b7412ae5f3ac57f880c7a4104ec369
 size 82461044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86946726b178b698d37c6fd9411fb5faf6e0ced97c28c1f7f7aafc482ed0544e
+oid sha256:172770bc7d4a5b9e9219303aaf163c05e787784b7e036214c8c64f82c016581a
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af8c70a94900d9b287ae32cb4f95d47fb8ad712363557219eb89e270f8b96010
+oid sha256:3ae0a5f636e3b7efad4ad765d67a451cd40f8f2e24e01c5d42929e454a337257
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2878045439720154,
   "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.012419853135236676,
+  "epoch": 0.01397233477714126,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 11.67,
       "eval_steps_per_second": 2.918,
       "step": 400
+    },
+    {
+      "epoch": 0.012730349463617592,
+      "grad_norm": 0.39656543731689453,
+      "learning_rate": 2.005321559063053e-05,
+      "loss": 0.2632,
+      "step": 410
+    },
+    {
+      "epoch": 0.013040845791998509,
+      "grad_norm": 0.670808732509613,
+      "learning_rate": 1.5954949903575276e-05,
+      "loss": 0.2898,
+      "step": 420
+    },
+    {
+      "epoch": 0.013351342120379427,
+      "grad_norm": 1.3960740566253662,
+      "learning_rate": 1.2290502749812666e-05,
+      "loss": 0.3984,
+      "step": 430
+    },
+    {
+      "epoch": 0.013661838448760344,
+      "grad_norm": 0.302166223526001,
+      "learning_rate": 9.077726947526898e-06,
+      "loss": 0.2883,
+      "step": 440
+    },
+    {
+      "epoch": 0.01397233477714126,
+      "grad_norm": 0.5265788435935974,
+      "learning_rate": 6.332274817479627e-06,
+      "loss": 0.2646,
+      "step": 450
+    },
+    {
+      "epoch": 0.01397233477714126,
+      "eval_loss": 0.28790345788002014,
+      "eval_runtime": 1163.433,
+      "eval_samples_per_second": 11.656,
+      "eval_steps_per_second": 2.915,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -373,7 +416,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1158405142229811e+17,
+  "total_flos": 1.2573958496216678e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null