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:b674fbcc06d0274c248a06b8be96a6d7270e2dd434e2f50710026bf09f3ab3e6
+oid sha256:53bbc102cce25bd2a1241498449b0ba801b43eee0dde8083394c50c2f2b8129d
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d710186172c2647769d2ae06182a629c546fd6694ab01b3dd3115cdd56cce04b
+oid sha256:e6f6bc771e287b7e88c539a590234ef6859c223f862ebe51903ca4bef54c8f3e
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f8028bf2e601d46cd909cf2f749997690f7adfaf6db75a2d7049ed26163b9b
+oid sha256:e03f64a4804debb81d6c16e51485bc4b1d54a7fc010363c6a95e60448214e4b8
 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": 2.5213193893432617,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.005420054200542005,
+  "best_metric": 2.413238525390625,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.01084010840108401,
   "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": 8.371,
       "eval_steps_per_second": 4.191,
       "step": 10
+    },
+    {
+      "epoch": 0.005962059620596206,
+      "grad_norm": 26.181333541870117,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 9.8918,
+      "step": 11
+    },
+    {
+      "epoch": 0.0065040650406504065,
+      "grad_norm": 24.101024627685547,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 8.1502,
+      "step": 12
+    },
+    {
+      "epoch": 0.007046070460704607,
+      "grad_norm": 34.53730010986328,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 9.925,
+      "step": 13
+    },
+    {
+      "epoch": 0.007588075880758808,
+      "grad_norm": 29.023534774780273,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 9.7495,
+      "step": 14
+    },
+    {
+      "epoch": 0.008130081300813009,
+      "grad_norm": 40.96164321899414,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 10.4518,
+      "step": 15
+    },
+    {
+      "epoch": 0.008130081300813009,
+      "eval_loss": 2.4435627460479736,
+      "eval_runtime": 94.0323,
+      "eval_samples_per_second": 8.263,
+      "eval_steps_per_second": 4.137,
+      "step": 15
+    },
+    {
+      "epoch": 0.008672086720867209,
+      "grad_norm": 32.43494415283203,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.5567,
+      "step": 16
+    },
+    {
+      "epoch": 0.00921409214092141,
+      "grad_norm": 32.65191650390625,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 8.9572,
+      "step": 17
+    },
+    {
+      "epoch": 0.00975609756097561,
+      "grad_norm": 50.91588592529297,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 10.5949,
+      "step": 18
+    },
+    {
+      "epoch": 0.010298102981029811,
+      "grad_norm": 35.54926681518555,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 6.8794,
+      "step": 19
+    },
+    {
+      "epoch": 0.01084010840108401,
+      "grad_norm": 28.28718376159668,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 7.4647,
+      "step": 20
+    },
+    {
+      "epoch": 0.01084010840108401,
+      "eval_loss": 2.413238525390625,
+      "eval_runtime": 91.443,
+      "eval_samples_per_second": 8.497,
+      "eval_steps_per_second": 4.254,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 118433563803648.0,
+  "total_flos": 245639984185344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null