Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b25a76f946ba6cc1682e6fee3ea0f716e3efb6e592876e9bec0d58a156fdf5
+oid sha256:5ea2e13943e20796577be056c05ee543a933f353f5332acad7a63d0766bb74c7
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6efacee881d09b2565abc17958bf76b6d88f973ea96fe7235d1e8527378c739
+oid sha256:156468a9244bdd69abd5afcb2d01abac7695c08236b11ec63482e3db4be27cf6
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24ea7c0a4e5d64117dc1930a990d2eb9b0c48cdce293e5ed0a75fe6de879d4a2
+oid sha256:fcc9b47b3ddbba5ee05716509f1870fbbce3c84b7c4fae2df6046aef0fa02c05
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18572f0adae215b3259455cf96083d95e78dc1ab7af393890cd3753bf61cc9f4
+oid sha256:ac6ee4c7143f9893927b533c972fc3aa0da9526c7e014b3849d291e400a8521c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.480776071548462,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.06755615605472048,
+  "best_metric": 1.4717568159103394,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.07600067556156055,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 11.123,
       "eval_steps_per_second": 2.783,
       "step": 400
+    },
+    {
+      "epoch": 0.0692450599560885,
+      "grad_norm": 2.1745190620422363,
+      "learning_rate": 2.0435181601880635e-05,
+      "loss": 2.6099,
+      "step": 410
+    },
+    {
+      "epoch": 0.07093396385745651,
+      "grad_norm": 2.9737164974212646,
+      "learning_rate": 1.625885371126242e-05,
+      "loss": 2.8922,
+      "step": 420
+    },
+    {
+      "epoch": 0.07262286775882452,
+      "grad_norm": 2.6742162704467773,
+      "learning_rate": 1.2524607564094813e-05,
+      "loss": 2.8869,
+      "step": 430
+    },
+    {
+      "epoch": 0.07431177166019254,
+      "grad_norm": 2.8387765884399414,
+      "learning_rate": 9.250636032241695e-06,
+      "loss": 3.2082,
+      "step": 440
+    },
+    {
+      "epoch": 0.07600067556156055,
+      "grad_norm": 5.102243900299072,
+      "learning_rate": 6.45288957590781e-06,
+      "loss": 3.0588,
+      "step": 450
+    },
+    {
+      "epoch": 0.07600067556156055,
+      "eval_loss": 1.4717568159103394,
+      "eval_runtime": 225.0055,
+      "eval_samples_per_second": 11.084,
+      "eval_steps_per_second": 2.773,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.28802361442304e+17,
+  "total_flos": 1.44902656622592e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null