Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:361e8cb48dc12b55ccefa24b23e9bb3817cc47acd8b44869d48dac548f6601cd
+oid sha256:516fdc69a2be1f8ed55dd2ad4f50acde31d84050045426ec2001d8d7d48b1ef2
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:272f720864e0f342b1bb1d8205196e01cd3cca4de5c3646d2e858a1213e7458f
+oid sha256:f63645e08f9d62af1505242822d31f681bbe7cfb98c8b6a06c400d652f3b9a33
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935d993b21fda70c12f88fe1e791989f8500ea824d33d8cb59fa10d3462e1c7c
+oid sha256:d1a964cb3489f2e9abd0009809be93dd8b300705c9fd9f80a7b5db400b999dfb
 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": 2.016779899597168,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0008520246235116195,
+  "best_metric": 0.4509950280189514,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.001704049247023239,
   "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": 4.513,
       "eval_steps_per_second": 2.257,
       "step": 10
+    },
+    {
+      "epoch": 0.0009372270858627814,
+      "grad_norm": 7.080551624298096,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.8364,
+      "step": 11
+    },
+    {
+      "epoch": 0.0010224295482139435,
+      "grad_norm": 7.222623348236084,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.5561,
+      "step": 12
+    },
+    {
+      "epoch": 0.0011076320105651053,
+      "grad_norm": 8.51089096069336,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.6543,
+      "step": 13
+    },
+    {
+      "epoch": 0.0011928344729162674,
+      "grad_norm": 9.265571594238281,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.7747,
+      "step": 14
+    },
+    {
+      "epoch": 0.0012780369352674292,
+      "grad_norm": 5.150737285614014,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.9407,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012780369352674292,
+      "eval_loss": 0.961416482925415,
+      "eval_runtime": 1061.4126,
+      "eval_samples_per_second": 4.656,
+      "eval_steps_per_second": 2.328,
+      "step": 15
+    },
+    {
+      "epoch": 0.001363239397618591,
+      "grad_norm": 8.208329200744629,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.05,
+      "step": 16
+    },
+    {
+      "epoch": 0.0014484418599697531,
+      "grad_norm": 6.162915229797363,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.8887,
+      "step": 17
+    },
+    {
+      "epoch": 0.001533644322320915,
+      "grad_norm": 4.672049522399902,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.6028,
+      "step": 18
+    },
+    {
+      "epoch": 0.001618846784672077,
+      "grad_norm": 3.763162136077881,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.481,
+      "step": 19
+    },
+    {
+      "epoch": 0.001704049247023239,
+      "grad_norm": 3.6781723499298096,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.4966,
+      "step": 20
+    },
+    {
+      "epoch": 0.001704049247023239,
+      "eval_loss": 0.4509950280189514,
+      "eval_runtime": 1082.3453,
+      "eval_samples_per_second": 4.566,
+      "eval_steps_per_second": 2.283,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 76723802603520.0,
+  "total_flos": 153447605207040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null