Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22364072bb629d3eb396c6bfad8a81a6c05441fdb1c235c39ae3f5b772ec3b79
+oid sha256:c657bced03ee3ac9877f99185ce39d523e473b4cc40ed31ce48a5544a0c77d01
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b99015c0f6f129457c3d0ea188c56db825bbc11ac120d99cb0112e75aee429d
+oid sha256:3da607f9494cf2f98615da301146b68db31df4b7bd6235e6373eef1af2c78776
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8487bdaf4d7d7ed6f788c0769087fcc8cb59e73f87b0700eacb5d9ef9bc77de0
+oid sha256:d0ca3e31f5c1eb0c548a754b98e486d7fa95f280cb083e2bc52e57453479a595
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c579f5f648f371ddcf6d84448bace40e1d46168d2f7b5fae9b6105a9c79d201
+oid sha256:2c9718e38efb2d48aaa61791c4fc8b4a7f9cfd08f355dda43ae7de9f2cb195d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.17636816203594208,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.1699074948083821,
+  "epoch": 0.18878610534264678,
   "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": 41.688,
       "eval_steps_per_second": 10.422,
       "step": 450
+    },
+    {
+      "epoch": 0.17368321691523503,
+      "grad_norm": 0.11420448869466782,
+      "learning_rate": 4.125629382569038e-06,
+      "loss": 0.0557,
+      "step": 460
+    },
+    {
+      "epoch": 0.17745893902208798,
+      "grad_norm": 0.18652790784835815,
+      "learning_rate": 2.327280521849694e-06,
+      "loss": 0.1503,
+      "step": 470
+    },
+    {
+      "epoch": 0.1812346611289409,
+      "grad_norm": 0.2579120099544525,
+      "learning_rate": 1.0364506790227565e-06,
+      "loss": 0.1801,
+      "step": 480
+    },
+    {
+      "epoch": 0.18501038323579386,
+      "grad_norm": 0.36861857771873474,
+      "learning_rate": 2.5942864732872295e-07,
+      "loss": 0.2408,
+      "step": 490
+    },
+    {
+      "epoch": 0.18878610534264678,
+      "grad_norm": 0.9236373901367188,
+      "learning_rate": 0.0,
+      "loss": 0.3463,
+      "step": 500
+    },
+    {
+      "epoch": 0.18878610534264678,
+      "eval_loss": 0.17671090364456177,
+      "eval_runtime": 26.8171,
+      "eval_samples_per_second": 41.615,
+      "eval_steps_per_second": 10.404,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "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": 6466058885529600.0,
+  "total_flos": 7187013186355200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null