Training in progress, step 269, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fef308b8921bdaa4b3462e88f1c7c0ade05615f1ab91ad36b5610d3f5b3c17d
+oid sha256:b2402ba3b7e185a4a682ad4a8dcd873d072db5bd9f26577594fe8c12692aa0ce
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a90254e302ec8b6d14e289c29594d11ebf0d484538ff3c10b69180beee9fbee6
+oid sha256:ef1132e125fdfa928ac6191c556ecf798bf1025bacae5051f64ada271bd69b63
 size 403961210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b3a0b8ae4b1ef3d273ffeb9e44259fa1cdfe737176b54fe581e2c5bb5beb35e
+oid sha256:c5111362039b3f73ecb7178a57b3d65b8c684f11cc8bf6dfc7918c1f6f7759a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0f2082f8ae2500626171b5f3c174135f50005132f4fb0d89617e1b5f611c23e
+oid sha256:6f9f3df9bf8d413fd91bebc4c208272404e0533fd2d3a72c098ffa93deb1063e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2524751424789429,
   "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 2.793296089385475,
+  "epoch": 3.005586592178771,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 269,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1805,6 +1805,139 @@
       "eval_samples_per_second": 42.603,
       "eval_steps_per_second": 21.442,
       "step": 250
+    },
+    {
+      "epoch": 2.804469273743017,
+      "grad_norm": 0.999933660030365,
+      "learning_rate": 1.3930347737136196e-06,
+      "loss": 1.1728,
+      "step": 251
+    },
+    {
+      "epoch": 2.815642458100559,
+      "grad_norm": 1.084299921989441,
+      "learning_rate": 1.2431795228615372e-06,
+      "loss": 1.1947,
+      "step": 252
+    },
+    {
+      "epoch": 2.826815642458101,
+      "grad_norm": 1.0853486061096191,
+      "learning_rate": 1.101748557319715e-06,
+      "loss": 1.1514,
+      "step": 253
+    },
+    {
+      "epoch": 2.8379888268156424,
+      "grad_norm": 1.0919440984725952,
+      "learning_rate": 9.687663137678604e-07,
+      "loss": 1.1536,
+      "step": 254
+    },
+    {
+      "epoch": 2.8491620111731844,
+      "grad_norm": 1.0306580066680908,
+      "learning_rate": 8.442557691013043e-07,
+      "loss": 1.1416,
+      "step": 255
+    },
+    {
+      "epoch": 2.8603351955307263,
+      "grad_norm": 1.1208820343017578,
+      "learning_rate": 7.282384364610206e-07,
+      "loss": 1.1873,
+      "step": 256
+    },
+    {
+      "epoch": 2.871508379888268,
+      "grad_norm": 1.0364559888839722,
+      "learning_rate": 6.207343615165561e-07,
+      "loss": 1.0184,
+      "step": 257
+    },
+    {
+      "epoch": 2.88268156424581,
+      "grad_norm": 0.9816321730613708,
+      "learning_rate": 5.217621190024779e-07,
+      "loss": 1.017,
+      "step": 258
+    },
+    {
+      "epoch": 2.893854748603352,
+      "grad_norm": 1.1331318616867065,
+      "learning_rate": 4.3133880950905205e-07,
+      "loss": 1.1131,
+      "step": 259
+    },
+    {
+      "epoch": 2.905027932960894,
+      "grad_norm": 1.209434151649475,
+      "learning_rate": 3.494800565275125e-07,
+      "loss": 1.18,
+      "step": 260
+    },
+    {
+      "epoch": 2.916201117318436,
+      "grad_norm": 1.2905470132827759,
+      "learning_rate": 2.762000037506485e-07,
+      "loss": 1.1171,
+      "step": 261
+    },
+    {
+      "epoch": 2.927374301675978,
+      "grad_norm": 1.216124176979065,
+      "learning_rate": 2.115113126290258e-07,
+      "loss": 1.0804,
+      "step": 262
+    },
+    {
+      "epoch": 2.9385474860335195,
+      "grad_norm": 1.300574541091919,
+      "learning_rate": 1.554251601833201e-07,
+      "loss": 1.0849,
+      "step": 263
+    },
+    {
+      "epoch": 2.9497206703910615,
+      "grad_norm": 1.376492977142334,
+      "learning_rate": 1.0795123707312283e-07,
+      "loss": 1.0931,
+      "step": 264
+    },
+    {
+      "epoch": 2.9608938547486034,
+      "grad_norm": 1.507287859916687,
+      "learning_rate": 6.909774592258056e-08,
+      "loss": 1.1502,
+      "step": 265
+    },
+    {
+      "epoch": 2.972067039106145,
+      "grad_norm": 1.6715766191482544,
+      "learning_rate": 3.8871399903134265e-08,
+      "loss": 1.0179,
+      "step": 266
+    },
+    {
+      "epoch": 2.983240223463687,
+      "grad_norm": 2.2043421268463135,
+      "learning_rate": 1.7277421573608232e-08,
+      "loss": 0.9667,
+      "step": 267
+    },
+    {
+      "epoch": 2.994413407821229,
+      "grad_norm": 1.0078221559524536,
+      "learning_rate": 4.319541977831909e-09,
+      "loss": 1.1912,
+      "step": 268
+    },
+    {
+      "epoch": 3.005586592178771,
+      "grad_norm": 2.012565851211548,
+      "learning_rate": 0.0,
+      "loss": 1.8972,
+      "step": 269
     }
   ],
   "logging_steps": 1,
@@ -1828,12 +1961,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.3328696311808e+16,
+  "total_flos": 5.738167723150541e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null