Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2124cd5c842f16710a2916d64a5692be6fc67bfc863bb273786b882ddccea613
+oid sha256:7e8d954c7844c2ec37937de49ca81455e22c777b4ead8bd057f1a4371ad4a8b3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa80c8b9ba3f9f8e65e209853331596d0f3b271723ec99ccc615d7f2ab746835
+oid sha256:a0a15d4a5106ad9311c235e1d225edf1e03835ec932cf969ce7eee760cc81e3c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5a03af491a912f295faf6fa6852568637db55748dbbb2d135ab3bc62e8e1bd8
+oid sha256:4fd49d8ffdc507288356cd9d5ee3dbcd6398ee312f86ab554d873f3444e85b89
 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": 0.7292912006378174,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.002463661000246366,
+  "best_metric": 0.6183786392211914,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.004927322000492732,
   "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": 5.493,
       "eval_steps_per_second": 2.748,
       "step": 10
+    },
+    {
+      "epoch": 0.0027100271002710027,
+      "grad_norm": 0.4965437054634094,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.5197,
+      "step": 11
+    },
+    {
+      "epoch": 0.0029563932002956393,
+      "grad_norm": 0.6098279356956482,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.5851,
+      "step": 12
+    },
+    {
+      "epoch": 0.003202759300320276,
+      "grad_norm": 0.5826135873794556,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.643,
+      "step": 13
+    },
+    {
+      "epoch": 0.0034491254003449125,
+      "grad_norm": 0.4636547565460205,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.4137,
+      "step": 14
+    },
+    {
+      "epoch": 0.003695491500369549,
+      "grad_norm": 0.6051448583602905,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.3466,
+      "step": 15
+    },
+    {
+      "epoch": 0.003695491500369549,
+      "eval_loss": 0.6458022594451904,
+      "eval_runtime": 311.6704,
+      "eval_samples_per_second": 5.483,
+      "eval_steps_per_second": 2.743,
+      "step": 15
+    },
+    {
+      "epoch": 0.003941857600394186,
+      "grad_norm": 0.5250495672225952,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6101,
+      "step": 16
+    },
+    {
+      "epoch": 0.004188223700418822,
+      "grad_norm": 0.4610646367073059,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.5967,
+      "step": 17
+    },
+    {
+      "epoch": 0.004434589800443459,
+      "grad_norm": 0.4124172627925873,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.5159,
+      "step": 18
+    },
+    {
+      "epoch": 0.004680955900468096,
+      "grad_norm": 0.3477323651313782,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.4371,
+      "step": 19
+    },
+    {
+      "epoch": 0.004927322000492732,
+      "grad_norm": 0.36285078525543213,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.6104,
+      "step": 20
+    },
+    {
+      "epoch": 0.004927322000492732,
+      "eval_loss": 0.6183786392211914,
+      "eval_runtime": 317.4187,
+      "eval_samples_per_second": 5.384,
+      "eval_steps_per_second": 2.694,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3282976540459008.0,
+  "total_flos": 6196040231288832.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null