Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0787b35665ca37b8c03c42333bcc732c461ca3fe238e041bde3d3d79e3013c
+oid sha256:e10170b222c14a25abc17ec155e4200145973b2a086037dc7f6c7219197759a5
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fc459a521c4c6d2e400e3583a14e4c2659e9f0ab9cddb65fd377e0b0ad53aef
+oid sha256:79216b2fcbb8f5baaca604b01131e26c77a4e7675c3a1c8d67522ff11e5f27a4
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5146f877cac63d1df05829adb491e83252ee9b055e9aa9b6bea9e733a841a72
+oid sha256:c2b15e73b6443c35deffc5668840769e193cde02231d3175b474b56f6d942c51
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5063281059265137,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0008897192935628809,
+  "best_metric": 1.344485878944397,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0017794385871257618,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 7.309,
       "eval_steps_per_second": 3.655,
       "step": 10
+    },
+    {
+      "epoch": 0.000978691222919169,
+      "grad_norm": 6.842349529266357,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 5.7354,
+      "step": 11
+    },
+    {
+      "epoch": 0.0010676631522754572,
+      "grad_norm": 7.970447063446045,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 5.5847,
+      "step": 12
+    },
+    {
+      "epoch": 0.0011566350816317452,
+      "grad_norm": 6.706606864929199,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.7859,
+      "step": 13
+    },
+    {
+      "epoch": 0.0012456070109880333,
+      "grad_norm": 10.090574264526367,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 6.1743,
+      "step": 14
+    },
+    {
+      "epoch": 0.0013345789403443214,
+      "grad_norm": 6.294565200805664,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 5.0437,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013345789403443214,
+      "eval_loss": 1.3769153356552124,
+      "eval_runtime": 643.8141,
+      "eval_samples_per_second": 7.352,
+      "eval_steps_per_second": 3.677,
+      "step": 15
+    },
+    {
+      "epoch": 0.0014235508697006095,
+      "grad_norm": 11.344293594360352,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.4785,
+      "step": 16
+    },
+    {
+      "epoch": 0.0015125227990568976,
+      "grad_norm": 7.5362138748168945,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 4.5365,
+      "step": 17
+    },
+    {
+      "epoch": 0.0016014947284131856,
+      "grad_norm": 9.856901168823242,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 6.8501,
+      "step": 18
+    },
+    {
+      "epoch": 0.0016904666577694737,
+      "grad_norm": 9.563337326049805,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 5.8593,
+      "step": 19
+    },
+    {
+      "epoch": 0.0017794385871257618,
+      "grad_norm": 7.136096000671387,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.8991,
+      "step": 20
+    },
+    {
+      "epoch": 0.0017794385871257618,
+      "eval_loss": 1.344485878944397,
+      "eval_runtime": 651.4638,
+      "eval_samples_per_second": 7.265,
+      "eval_steps_per_second": 3.633,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2081409489174528.0,
+  "total_flos": 4244442879885312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null