Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d5489a3688b7063113df6f2ea8db9ceeca2824fcf9ef0b63b9b4a9639ba0e8
+oid sha256:948ce3df8de5f88bedf7a0d9c134994839cd943fc6c974c4b0a7866cbcc61a5d
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b0e205169a293b02af7ff4a3695d8da43cd92f9df0897bf6c981440e10238de
+oid sha256:bbf48eec840e36521100fdb0611fe1e64bde2bbc3a990f25ee67d320b312b849
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcdf765c0987b55a3d705255d663e95a07a75248577a199642c7659214171bd4
+oid sha256:1cb471a00377648163edcebbc32112eb1f202af215f062520c97ce9d8c504ad0
 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": 1.5156612396240234,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004253056884635832,
+  "best_metric": 1.4817118644714355,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.008506113769271665,
   "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": 16.228,
       "eval_steps_per_second": 8.114,
       "step": 10
+    },
+    {
+      "epoch": 0.004678362573099415,
+      "grad_norm": 45.95751953125,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 6.2321,
+      "step": 11
+    },
+    {
+      "epoch": 0.005103668261562998,
+      "grad_norm": 17.54123878479004,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 5.4011,
+      "step": 12
+    },
+    {
+      "epoch": 0.005528973950026581,
+      "grad_norm": 18.338685989379883,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 6.1812,
+      "step": 13
+    },
+    {
+      "epoch": 0.005954279638490165,
+      "grad_norm": 18.87067413330078,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 6.1219,
+      "step": 14
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "grad_norm": 18.159162521362305,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 6.4642,
+      "step": 15
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "eval_loss": 1.487715482711792,
+      "eval_runtime": 60.2255,
+      "eval_samples_per_second": 16.438,
+      "eval_steps_per_second": 8.219,
+      "step": 15
+    },
+    {
+      "epoch": 0.006804891015417331,
+      "grad_norm": 16.359085083007812,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.1706,
+      "step": 16
+    },
+    {
+      "epoch": 0.007230196703880914,
+      "grad_norm": 23.439176559448242,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 5.5563,
+      "step": 17
+    },
+    {
+      "epoch": 0.007655502392344498,
+      "grad_norm": 26.228099822998047,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 5.9734,
+      "step": 18
+    },
+    {
+      "epoch": 0.00808080808080808,
+      "grad_norm": 19.510398864746094,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 6.3272,
+      "step": 19
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "grad_norm": 25.489709854125977,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 6.0794,
+      "step": 20
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "eval_loss": 1.4817118644714355,
+      "eval_runtime": 61.227,
+      "eval_samples_per_second": 16.169,
+      "eval_steps_per_second": 8.085,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 162297846693888.0,
+  "total_flos": 320209265098752.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null