Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77920f7de14368be5876b8a9213dc63a7db7b78cf5eb4d53c92c5b175f27ef7c
+oid sha256:5ba51009c92a9e928d344568710ef7ce7a429dcb0f7c4992fb1450c2e7ae0f40
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6281b379c53041bab7560eb81371fe1d5b5034ef9784cd2b47fe3499690713e4
+oid sha256:ffd192f0af181f67e5d948646fcc9e9d76bebf9f10999aecc7a5e57ed8463631
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec134605e1e781fc705a3279e09b0cbaee66f077da601816e59f2b3169ff7952
+oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
 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": 0.45723438262939453,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008412197686645636,
+  "best_metric": 0.21308887004852295,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.016824395373291272,
   "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": 13.148,
       "eval_steps_per_second": 6.587,
       "step": 10
+    },
+    {
+      "epoch": 0.0092534174553102,
+      "grad_norm": 15.190485000610352,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.7798,
+      "step": 11
+    },
+    {
+      "epoch": 0.010094637223974764,
+      "grad_norm": 6.989818572998047,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.261,
+      "step": 12
+    },
+    {
+      "epoch": 0.010935856992639327,
+      "grad_norm": 11.157185554504395,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.839,
+      "step": 13
+    },
+    {
+      "epoch": 0.01177707676130389,
+      "grad_norm": 5.976316452026367,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.8346,
+      "step": 14
+    },
+    {
+      "epoch": 0.012618296529968454,
+      "grad_norm": 15.315306663513184,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.1456,
+      "step": 15
+    },
+    {
+      "epoch": 0.012618296529968454,
+      "eval_loss": 0.23096799850463867,
+      "eval_runtime": 38.559,
+      "eval_samples_per_second": 12.993,
+      "eval_steps_per_second": 6.51,
+      "step": 15
+    },
+    {
+      "epoch": 0.013459516298633017,
+      "grad_norm": 16.47820281982422,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.1177,
+      "step": 16
+    },
+    {
+      "epoch": 0.014300736067297582,
+      "grad_norm": 5.162192344665527,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.7871,
+      "step": 17
+    },
+    {
+      "epoch": 0.015141955835962145,
+      "grad_norm": 5.268097877502441,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.7459,
+      "step": 18
+    },
+    {
+      "epoch": 0.01598317560462671,
+      "grad_norm": 7.22558069229126,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.0371,
+      "step": 19
+    },
+    {
+      "epoch": 0.016824395373291272,
+      "grad_norm": 5.337489604949951,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.7747,
+      "step": 20
+    },
+    {
+      "epoch": 0.016824395373291272,
+      "eval_loss": 0.21308887004852295,
+      "eval_runtime": 32.5548,
+      "eval_samples_per_second": 15.389,
+      "eval_steps_per_second": 7.71,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 298572369100800.0,
+  "total_flos": 597144738201600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null