Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d9408fca7da7455efd2e2f890c713f81d1a2677a7484f660df7d4d79e1b500e
+oid sha256:006fdc03a4490ea6e19aebd8227fe78d79cd896b2d64209f83adcc2546367baf
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e0add7bb01243d97f7a76903243f8cb9d31abee807ba1871693e4e37dee0e4
+oid sha256:a3b8ee5e4a7275e055c83ffa1c9b42439b2ecd17790928fb2c6b701996f18ff2
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3ce032444240f10e99f84736458b10f00c802c16cd5dd2eda7d62f0a9a9135
+oid sha256:813842ccb6a5606b7a8ab80f7e71675de76d6f9db7f73c390878b4b9232afa2e
 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": 0.6406313180923462,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.04678362573099415,
+  "best_metric": 0.4118092954158783,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0935672514619883,
   "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": 7.892,
       "eval_steps_per_second": 3.946,
       "step": 10
+    },
+    {
+      "epoch": 0.05146198830409357,
+      "grad_norm": 1.1888481378555298,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.736,
+      "step": 11
+    },
+    {
+      "epoch": 0.056140350877192984,
+      "grad_norm": 1.0447313785552979,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.1931,
+      "step": 12
+    },
+    {
+      "epoch": 0.0608187134502924,
+      "grad_norm": 0.9865492582321167,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.8405,
+      "step": 13
+    },
+    {
+      "epoch": 0.06549707602339182,
+      "grad_norm": 1.2127184867858887,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.1726,
+      "step": 14
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 1.2068496942520142,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "eval_loss": 0.47981786727905273,
+      "eval_runtime": 11.2776,
+      "eval_samples_per_second": 7.98,
+      "eval_steps_per_second": 3.99,
+      "step": 15
+    },
+    {
+      "epoch": 0.07485380116959064,
+      "grad_norm": 1.0533158779144287,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.5592,
+      "step": 16
+    },
+    {
+      "epoch": 0.07953216374269007,
+      "grad_norm": 1.02470064163208,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.0986,
+      "step": 17
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 1.0912792682647705,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.8195,
+      "step": 18
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.276378870010376,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.7657,
+      "step": 19
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "grad_norm": 1.306107759475708,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.8758,
+      "step": 20
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "eval_loss": 0.4118092954158783,
+      "eval_runtime": 11.3147,
+      "eval_samples_per_second": 7.954,
+      "eval_steps_per_second": 3.977,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1422827735482368.0,
+  "total_flos": 2845655470964736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null