Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a263578247741991c4c046375ad311e88ce86c6aa12a03eaeff04ee87deceae
+oid sha256:b613a20d34db6c41f47f51d13d00f843c456db9353d4414d09862ca4cb297214
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca41a52d0e403c2d96972d2a8261ef7718672efa9d34204e1da2199e8c117e86
+oid sha256:9fffd955c7ebdc944aa9151adc47c6aee0634d2fcf79159963b63c77f158fc34
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771aba8a4e8fb219bd14601087487c802e830687ae8ba870683f0a0c56d57221
+oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
 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": 0.435401976108551,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00282585658777817,
+  "best_metric": 0.3312912583351135,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00565171317555634,
   "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": 3.289,
       "eval_steps_per_second": 1.644,
       "step": 10
+    },
+    {
+      "epoch": 0.0031084422465559873,
+      "grad_norm": 8.154427528381348,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.7293,
+      "step": 11
+    },
+    {
+      "epoch": 0.0033910279053338045,
+      "grad_norm": 3.9936041831970215,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.5691,
+      "step": 12
+    },
+    {
+      "epoch": 0.003673613564111621,
+      "grad_norm": 3.17008376121521,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.4452,
+      "step": 13
+    },
+    {
+      "epoch": 0.003956199222889438,
+      "grad_norm": 2.970133066177368,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.5994,
+      "step": 14
+    },
+    {
+      "epoch": 0.0042387848816672555,
+      "grad_norm": 3.0812292098999023,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.6177,
+      "step": 15
+    },
+    {
+      "epoch": 0.0042387848816672555,
+      "eval_loss": 0.3540613651275635,
+      "eval_runtime": 451.6427,
+      "eval_samples_per_second": 3.299,
+      "eval_steps_per_second": 1.65,
+      "step": 15
+    },
+    {
+      "epoch": 0.004521370540445073,
+      "grad_norm": 3.2199628353118896,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.3606,
+      "step": 16
+    },
+    {
+      "epoch": 0.00480395619922289,
+      "grad_norm": 2.6285812854766846,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.748,
+      "step": 17
+    },
+    {
+      "epoch": 0.005086541858000706,
+      "grad_norm": 2.7720754146575928,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.7257,
+      "step": 18
+    },
+    {
+      "epoch": 0.005369127516778523,
+      "grad_norm": 2.474501132965088,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.3987,
+      "step": 19
+    },
+    {
+      "epoch": 0.00565171317555634,
+      "grad_norm": 2.400693893432617,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.4751,
+      "step": 20
+    },
+    {
+      "epoch": 0.00565171317555634,
+      "eval_loss": 0.3312912583351135,
+      "eval_runtime": 450.7561,
+      "eval_samples_per_second": 3.306,
+      "eval_steps_per_second": 1.653,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3505343598428160.0,
+  "total_flos": 7010687196856320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null