Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f18440af0a47a3648e8e2493b41f8c69470684ab52a2f3f51fe86e66d9b485
+oid sha256:a9673b75ff65472cf57920ac8a5f565af82b0d021c9df5c932559e7fd1b14466
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7f854548d6f6813f20a24c97ccc4bb7783db372e5705aa9ae1b608b31636d3
-size 170920084
+oid sha256:e281237073b69b36f28fea5d91b0d182297d679b915d4c1aaeda68875c0d1637
+size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eba5341e98f7a2a22d7405d74e4126c56a8d134d8178ce64467fc6df1c2be05
+oid sha256:1a4c01728ceb4d2b09187d13e5e5264c8535951394a0a7a1619f2855925e0d60
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5182c64d745614fbc9217a3122cffdaa4b9683ea7cfb2e6909f3ad8f175d0a03
+oid sha256:ef9686b06e8feaa36ed10d72ecd8afef7e62f88744e516a900f077a3e6a083d3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5612239837646484,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.26504108136761195,
+  "best_metric": 1.4548931121826172,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.3180492976411344,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -97,6 +97,21 @@
       "eval_samples_per_second": 14.493,
       "eval_steps_per_second": 7.256,
       "step": 250
+    },
+    {
+      "epoch": 0.29684601113172543,
+      "grad_norm": 17.57182502746582,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.5103,
+      "step": 280
+    },
+    {
+      "epoch": 0.3180492976411344,
+      "eval_loss": 1.4548931121826172,
+      "eval_runtime": 54.8131,
+      "eval_samples_per_second": 14.504,
+      "eval_steps_per_second": 7.261,
+      "step": 300
     }
   ],
   "logging_steps": 40,
@@ -125,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.937905582820557e+16,
+  "total_flos": 1.0728138896886989e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null