Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e84343b058816606cc843c1d051e958fca6d76475d5217f3c5abd45cbe46838
+oid sha256:2dbf8c6e0e171848caa7f36a646de50bb478599e6bc2d29a74ba9ac86ab970c0
 size 14293800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0ad563a683255d6f56cb69daa12abe67c2d061603e7e002ee0724654d709e15
+oid sha256:8608e52b83d9f0d6326604696bcb022ac343e6536708f8f48263220d8dd73e6c
 size 7579748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eeac713ab06dad645a8a0c3a78e1d8e186b26068bcd9f816d20110efc5d58c8
+oid sha256:62b014975fc6fe01bc747fcabac49eb3b60c5c8a7a3c91657e5b0b4af75e4149
 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": 4.316664218902588,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008343763037129746,
+  "best_metric": 2.962515354156494,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.016687526074259492,
   "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": 8.733,
       "eval_steps_per_second": 4.375,
       "step": 10
+    },
+    {
+      "epoch": 0.00917813934084272,
+      "grad_norm": 24.7475528717041,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 18.5352,
+      "step": 11
+    },
+    {
+      "epoch": 0.010012515644555695,
+      "grad_norm": 24.95964241027832,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 16.4059,
+      "step": 12
+    },
+    {
+      "epoch": 0.01084689194826867,
+      "grad_norm": 22.137861251831055,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 15.0218,
+      "step": 13
+    },
+    {
+      "epoch": 0.011681268251981644,
+      "grad_norm": 20.20884895324707,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 16.2653,
+      "step": 14
+    },
+    {
+      "epoch": 0.012515644555694618,
+      "grad_norm": 26.685359954833984,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 11.843,
+      "step": 15
+    },
+    {
+      "epoch": 0.012515644555694618,
+      "eval_loss": 3.342318534851074,
+      "eval_runtime": 58.0024,
+      "eval_samples_per_second": 8.707,
+      "eval_steps_per_second": 4.362,
+      "step": 15
+    },
+    {
+      "epoch": 0.013350020859407593,
+      "grad_norm": 24.334922790527344,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 12.9716,
+      "step": 16
+    },
+    {
+      "epoch": 0.014184397163120567,
+      "grad_norm": 28.592124938964844,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 14.8966,
+      "step": 17
+    },
+    {
+      "epoch": 0.015018773466833541,
+      "grad_norm": 28.8742733001709,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 14.9197,
+      "step": 18
+    },
+    {
+      "epoch": 0.015853149770546516,
+      "grad_norm": 23.675039291381836,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 11.3489,
+      "step": 19
+    },
+    {
+      "epoch": 0.016687526074259492,
+      "grad_norm": 27.08548927307129,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 13.8079,
+      "step": 20
+    },
+    {
+      "epoch": 0.016687526074259492,
+      "eval_loss": 2.962515354156494,
+      "eval_runtime": 58.0866,
+      "eval_samples_per_second": 8.694,
+      "eval_steps_per_second": 4.356,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 75429020958720.0,
+  "total_flos": 150858041917440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null