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:a0867044f89219e7bf248f90823e34b8b3005dc6fb20b2ecd672e706bcd127ad
+oid sha256:8b1fdfd03a8c7f5933c89aa8e0d04dc0f5c4483ace56a237de683279ec7c5ada
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7400eb8d4e5fe90646ba625daee64382fa6a9f6d9dbf00f0dcdeb58c02e0365b
+oid sha256:71b58ef49df551aef717e6e9b9a4078a9d87750dbb021f4edbfb6d2aa790164c
 size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fe222ec08da0ef777f28c6076d04ba38e29a5b31983c7471293059e4668bbea
+oid sha256:1af43dc01cf36475443725a8056d3819ccee8c5edc9cbbe9c0832696dffe1df6
 size 14244

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": 1.1736711263656616,
   "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.2557544757033248,
+  "epoch": 0.2841716396703609,
   "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": 35.596,
       "eval_steps_per_second": 8.935,
       "step": 450
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.19276390969753265,
+      "learning_rate": 4.067521926476516e-06,
+      "loss": 1.1466,
+      "step": 460
+    },
+    {
+      "epoch": 0.26712134129013926,
+      "grad_norm": 0.2616647779941559,
+      "learning_rate": 2.294501922950403e-06,
+      "loss": 1.1233,
+      "step": 470
+    },
+    {
+      "epoch": 0.2728047740835465,
+      "grad_norm": 0.3395529091358185,
+      "learning_rate": 1.021852782135112e-06,
+      "loss": 1.0534,
+      "step": 480
+    },
+    {
+      "epoch": 0.2784882068769537,
+      "grad_norm": 0.5176828503608704,
+      "learning_rate": 2.5577472271845927e-07,
+      "loss": 1.208,
+      "step": 490
+    },
+    {
+      "epoch": 0.2841716396703609,
+      "grad_norm": 1.3167757987976074,
+      "learning_rate": 0.0,
+      "loss": 1.2601,
+      "step": 500
+    },
+    {
+      "epoch": 0.2841716396703609,
+      "eval_loss": 1.180171251296997,
+      "eval_runtime": 20.6202,
+      "eval_samples_per_second": 35.936,
+      "eval_steps_per_second": 9.02,
+      "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": 2.165353118642995e+16,
+  "total_flos": 2.4011222261170176e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null