Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91c1d05924382f19691e001b615b69fe716ba1b70130af14c95c78e959e634f2
+oid sha256:451f8e923c38783c3caea70bfeb529d7e6ba1e6136b6d50f04f7ade0c173bcbe
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6aa0fc5999e70c2cfa08dd6028007c2cc38fad172d438c9f5bc346f5f99d5f8
+oid sha256:2387875b27260fcffef1771e841d52a434792c181e8c074f03d93c0cb35fa859
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02de894b6a0bf1fbb237922f83d964e9a6307821aa3cf5978b8f1eb893b723f
+oid sha256:cd47a6fd8d104bc4760b938058f654a290b5fa431f437b61f9faa73b9e08908e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa0f7e2faaa98aa485e5dc42922e1b1819381507fa6961c3be50a0b49af04c0
+oid sha256:b617d9f149fb11f5d9825dc6193f0b55aa7bf4899d1811982c0c93a389d7300b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3261062502861023,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.41058394160583944,
+  "best_metric": 0.3223314583301544,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.4562043795620438,
   "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": 16.209,
       "eval_steps_per_second": 4.07,
       "step": 450
+    },
+    {
+      "epoch": 0.4197080291970803,
+      "grad_norm": 1.013932466506958,
+      "learning_rate": 4.106260230538197e-06,
+      "loss": 0.2758,
+      "step": 460
+    },
+    {
+      "epoch": 0.42883211678832117,
+      "grad_norm": 1.0302541255950928,
+      "learning_rate": 2.316354322216597e-06,
+      "loss": 0.2785,
+      "step": 470
+    },
+    {
+      "epoch": 0.43795620437956206,
+      "grad_norm": 1.0060259103775024,
+      "learning_rate": 1.0315847133935416e-06,
+      "loss": 0.2277,
+      "step": 480
+    },
+    {
+      "epoch": 0.4470802919708029,
+      "grad_norm": 1.8722251653671265,
+      "learning_rate": 2.582106724586351e-07,
+      "loss": 0.3022,
+      "step": 490
+    },
+    {
+      "epoch": 0.4562043795620438,
+      "grad_norm": 2.6105024814605713,
+      "learning_rate": 0.0,
+      "loss": 0.4691,
+      "step": 500
+    },
+    {
+      "epoch": 0.4562043795620438,
+      "eval_loss": 0.3223314583301544,
+      "eval_runtime": 28.4724,
+      "eval_samples_per_second": 16.226,
+      "eval_steps_per_second": 4.074,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.48538888044544e+16,
+  "total_flos": 9.4282098671616e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null