Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5ff5c5e9337c53de9cc882ab1dbf589fef27b8f07c16e366781fa72a6a96416
+oid sha256:3fa062c12334ba5afd5ed200dbe2646578c24466c1d054e96ffc62e96e39c451
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba3136ff1c8268b4e37bbffab113d0c15b7412ae5f3ac57f880c7a4104ec369
+oid sha256:0bef89421d46a6e1917b28651035a952fac33160ddbb27dac383a2f136f45da4
 size 82461044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172770bc7d4a5b9e9219303aaf163c05e787784b7e036214c8c64f82c016581a
+oid sha256:6b7ea069030604f2ccec07192cdd0177153255339b28b103eb861b17c6755e9f
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae0a5f636e3b7efad4ad765d67a451cd40f8f2e24e01c5d42929e454a337257
+oid sha256:4f23fa0ef01cbb776456cad40209cd1c0c6a02d9fdf8c0632982552f2f542168
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2878045439720154,
   "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.01397233477714126,
+  "epoch": 0.015524816419045845,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 11.656,
       "eval_steps_per_second": 2.915,
       "step": 450
+    },
+    {
+      "epoch": 0.014282831105522177,
+      "grad_norm": 0.4557628333568573,
+      "learning_rate": 4.067521926476516e-06,
+      "loss": 0.279,
+      "step": 460
+    },
+    {
+      "epoch": 0.014593327433903094,
+      "grad_norm": 0.6577253937721252,
+      "learning_rate": 2.294501922950403e-06,
+      "loss": 0.2616,
+      "step": 470
+    },
+    {
+      "epoch": 0.01490382376228401,
+      "grad_norm": 0.9276712536811829,
+      "learning_rate": 1.021852782135112e-06,
+      "loss": 0.3579,
+      "step": 480
+    },
+    {
+      "epoch": 0.015214320090664929,
+      "grad_norm": 0.30626097321510315,
+      "learning_rate": 2.5577472271845927e-07,
+      "loss": 0.2979,
+      "step": 490
+    },
+    {
+      "epoch": 0.015524816419045845,
+      "grad_norm": 0.38989588618278503,
+      "learning_rate": 0.0,
+      "loss": 0.281,
+      "step": 500
+    },
+    {
+      "epoch": 0.015524816419045845,
+      "eval_loss": 0.2878083884716034,
+      "eval_runtime": 1162.4078,
+      "eval_samples_per_second": 11.666,
+      "eval_steps_per_second": 2.917,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.2573958496216678e+17,
+  "total_flos": 1.3972035882870374e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null