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:e7af10c4975416a76c6ec29bc5a3b644db6d5ce29fe6d4c2191cb460330f27a7
+oid sha256:737b3b81471290f216f550edbb32d5e2f8ccb70f50d6d7db78358015e02348aa
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca95666216aef53f3e1893dcecfe1df703cad4cf98453e6c65bd999b97ea1ea
+oid sha256:4685161137cec441ee867b2ec73724520377d281e573da60cd05c0a611235079
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aea56b1aafcc7ad39d9441accb4a268d63f2acbc37f0887603f1925be5dd39ad
+oid sha256:b00fe2703438caf8f34765aaa829ebca35723d3851968a6377698684b1653e32
 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": 1.2036751508712769,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0006487293014807246,
+  "best_metric": 0.8296452760696411,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0012974586029614492,
   "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": 10.942,
       "eval_steps_per_second": 5.472,
       "step": 10
+    },
+    {
+      "epoch": 0.0007136022316287971,
+      "grad_norm": 8.447565078735352,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.5169,
+      "step": 11
+    },
+    {
+      "epoch": 0.0007784751617768695,
+      "grad_norm": 6.3583149909973145,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.6096,
+      "step": 12
+    },
+    {
+      "epoch": 0.000843348091924942,
+      "grad_norm": 7.392266273498535,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 5.3685,
+      "step": 13
+    },
+    {
+      "epoch": 0.0009082210220730145,
+      "grad_norm": 7.1356730461120605,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.5941,
+      "step": 14
+    },
+    {
+      "epoch": 0.000973093952221087,
+      "grad_norm": 11.207259178161621,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 4.9803,
+      "step": 15
+    },
+    {
+      "epoch": 0.000973093952221087,
+      "eval_loss": 0.9349899291992188,
+      "eval_runtime": 594.6572,
+      "eval_samples_per_second": 10.916,
+      "eval_steps_per_second": 5.459,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010379668823691595,
+      "grad_norm": 8.692298889160156,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.5715,
+      "step": 16
+    },
+    {
+      "epoch": 0.0011028398125172319,
+      "grad_norm": 7.856359481811523,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 3.9533,
+      "step": 17
+    },
+    {
+      "epoch": 0.0011677127426653043,
+      "grad_norm": 11.625333786010742,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.167,
+      "step": 18
+    },
+    {
+      "epoch": 0.0012325856728133769,
+      "grad_norm": 11.39608097076416,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.4974,
+      "step": 19
+    },
+    {
+      "epoch": 0.0012974586029614492,
+      "grad_norm": 8.31639289855957,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.2432,
+      "step": 20
+    },
+    {
+      "epoch": 0.0012974586029614492,
+      "eval_loss": 0.8296452760696411,
+      "eval_runtime": 610.928,
+      "eval_samples_per_second": 10.625,
+      "eval_steps_per_second": 5.313,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 388395335417856.0,
+  "total_flos": 761852388704256.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null