Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8699ee7a1e84a0b793a541cdc2fc3d1b06bed53ef07143e83d07e299cbccd55a
+oid sha256:79a202a843078dc784f4d9387ad32c010d794400e0e9b860bcf794c7df224d93
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e724bc3650fb9bf57c97bc1ceca9f6610bd2695415fecc02622d63ffaaa6fd5b
+oid sha256:a5de8e9042ed01b7a2ef2c2792a395f93506a811a87f3ea931d62f563da13049
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e922c0fa6776244d7074d76ccf4649797ba6d62791733c446c1464a3c3d0f6
+oid sha256:397a4d5b921b0a7f926976a42d7eee17e3390bee1ab0e059db66c0c3f4ebc6cb
 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": 2.2462997436523438,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.010314595152140279,
+  "best_metric": 2.0265042781829834,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.020629190304280558,
   "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": 5.971,
       "eval_steps_per_second": 2.993,
       "step": 10
+    },
+    {
+      "epoch": 0.011346054667354307,
+      "grad_norm": 2.9749982357025146,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 9.3068,
+      "step": 11
+    },
+    {
+      "epoch": 0.012377514182568335,
+      "grad_norm": 2.1659786701202393,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 8.5712,
+      "step": 12
+    },
+    {
+      "epoch": 0.013408973697782363,
+      "grad_norm": 2.9561119079589844,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 8.6487,
+      "step": 13
+    },
+    {
+      "epoch": 0.01444043321299639,
+      "grad_norm": 2.650712013244629,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 8.0862,
+      "step": 14
+    },
+    {
+      "epoch": 0.015471892728210418,
+      "grad_norm": 3.0634942054748535,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 9.3175,
+      "step": 15
+    },
+    {
+      "epoch": 0.015471892728210418,
+      "eval_loss": 2.1145219802856445,
+      "eval_runtime": 68.6027,
+      "eval_samples_per_second": 5.962,
+      "eval_steps_per_second": 2.988,
+      "step": 15
+    },
+    {
+      "epoch": 0.016503352243424446,
+      "grad_norm": 2.422914743423462,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 9.0833,
+      "step": 16
+    },
+    {
+      "epoch": 0.017534811758638472,
+      "grad_norm": 2.733120918273926,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 8.5553,
+      "step": 17
+    },
+    {
+      "epoch": 0.018566271273852502,
+      "grad_norm": 4.6515374183654785,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 9.3374,
+      "step": 18
+    },
+    {
+      "epoch": 0.019597730789066528,
+      "grad_norm": 3.3914477825164795,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 8.1143,
+      "step": 19
+    },
+    {
+      "epoch": 0.020629190304280558,
+      "grad_norm": 2.9778213500976562,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 8.22,
+      "step": 20
+    },
+    {
+      "epoch": 0.020629190304280558,
+      "eval_loss": 2.0265042781829834,
+      "eval_runtime": 68.4228,
+      "eval_samples_per_second": 5.978,
+      "eval_steps_per_second": 2.996,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3652169918054400.0,
+  "total_flos": 7644076572672000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null