Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:425aca3fc35c9015a2ecd8ae4246bfdd3a622d4a74ff0a6fd8fa1eee3eb1a737
+oid sha256:5552501a1b1eeb30d6187431fca430ec92f684e7938ddd67f1ac1c281348b781
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b30431ec6632ba4a99f967f28c47863c227cab5d36dc2d66aa0f7b7e80a3963
+oid sha256:08fc0458ddc3bcd8d51c029ec793b4534ac50ffe946e5031cdd403e4e6b2c46c
 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": 1.5024336576461792,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0008897192935628809,
+  "best_metric": 1.3466814756393433,
+  "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": 8.55,
       "eval_steps_per_second": 4.276,
       "step": 10
+    },
+    {
+      "epoch": 0.000978691222919169,
+      "grad_norm": 6.583264350891113,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 5.7007,
+      "step": 11
+    },
+    {
+      "epoch": 0.0010676631522754572,
+      "grad_norm": 8.027876853942871,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 5.5208,
+      "step": 12
+    },
+    {
+      "epoch": 0.0011566350816317452,
+      "grad_norm": 6.920276641845703,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.769,
+      "step": 13
+    },
+    {
+      "epoch": 0.0012456070109880333,
+      "grad_norm": 11.122085571289062,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 6.2082,
+      "step": 14
+    },
+    {
+      "epoch": 0.0013345789403443214,
+      "grad_norm": 6.2180047035217285,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 5.03,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013345789403443214,
+      "eval_loss": 1.378574013710022,
+      "eval_runtime": 555.2308,
+      "eval_samples_per_second": 8.524,
+      "eval_steps_per_second": 4.263,
+      "step": 15
+    },
+    {
+      "epoch": 0.0014235508697006095,
+      "grad_norm": 11.972392082214355,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.4736,
+      "step": 16
+    },
+    {
+      "epoch": 0.0015125227990568976,
+      "grad_norm": 7.43595552444458,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 4.496,
+      "step": 17
+    },
+    {
+      "epoch": 0.0016014947284131856,
+      "grad_norm": 10.142023086547852,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 6.861,
+      "step": 18
+    },
+    {
+      "epoch": 0.0016904666577694737,
+      "grad_norm": 9.809549331665039,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 5.9308,
+      "step": 19
+    },
+    {
+      "epoch": 0.0017794385871257618,
+      "grad_norm": 7.383944034576416,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.9173,
+      "step": 20
+    },
+    {
+      "epoch": 0.0017794385871257618,
+      "eval_loss": 1.3466814756393433,
+      "eval_runtime": 555.5234,
+      "eval_samples_per_second": 8.52,
+      "eval_steps_per_second": 4.261,
+      "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