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:d1b6fe4e3ec5e3bf29cf8d1f6600ee00220cc367518b7ccfd0252ea38c154bd5
+oid sha256:e7866a6e304b10d3e47c04a8ec454021944e84301a8ee223a129d207642dbede
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2698cf079baeb8f8c6f46635369bea4eceb9627f11e414ab5c8890b2fb94574d
+oid sha256:a08d0678848ef1502868d6a5fed74a90a07eeab284495a2c60baa261f772fef1
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d539fe4d67d4d8fda2e72f75d140391a0aaf6f7ce2131b7b9f8701adbd03b4
+oid sha256:4329764fc299dd85a84b7a55661e86fcab9bb1b815145a2c18430ce0fa85af0f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b8bc8abd4c9f82dfc46828b9bd127304694d7b33110834b4b23e29a7f6b47fd
+oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.3603010177612305,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00012026928292446788,
+  "best_metric": 3.3242831230163574,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00024053856584893576,
   "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": 11.473,
       "eval_steps_per_second": 5.737,
       "step": 10
+    },
+    {
+      "epoch": 0.00013229621121691468,
+      "grad_norm": 9.166821479797363,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 13.507,
+      "step": 11
+    },
+    {
+      "epoch": 0.00014432313950936147,
+      "grad_norm": 9.79527759552002,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 14.5831,
+      "step": 12
+    },
+    {
+      "epoch": 0.00015635006780180825,
+      "grad_norm": 13.353811264038086,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 12.4279,
+      "step": 13
+    },
+    {
+      "epoch": 0.00016837699609425504,
+      "grad_norm": 19.06542205810547,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 12.7872,
+      "step": 14
+    },
+    {
+      "epoch": 0.00018040392438670183,
+      "grad_norm": 19.6158390045166,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 13.3129,
+      "step": 15
+    },
+    {
+      "epoch": 0.00018040392438670183,
+      "eval_loss": 3.3403236865997314,
+      "eval_runtime": 3784.0295,
+      "eval_samples_per_second": 9.252,
+      "eval_steps_per_second": 4.626,
+      "step": 15
+    },
+    {
+      "epoch": 0.00019243085267914861,
+      "grad_norm": 12.81112289428711,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 12.9199,
+      "step": 16
+    },
+    {
+      "epoch": 0.0002044577809715954,
+      "grad_norm": 38.4151611328125,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 13.3895,
+      "step": 17
+    },
+    {
+      "epoch": 0.0002164847092640422,
+      "grad_norm": 8.710651397705078,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 14.4392,
+      "step": 18
+    },
+    {
+      "epoch": 0.00022851163755648897,
+      "grad_norm": 16.718015670776367,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 14.2077,
+      "step": 19
+    },
+    {
+      "epoch": 0.00024053856584893576,
+      "grad_norm": 17.698863983154297,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 11.7674,
+      "step": 20
+    },
+    {
+      "epoch": 0.00024053856584893576,
+      "eval_loss": 3.3242831230163574,
+      "eval_runtime": 2367.8712,
+      "eval_samples_per_second": 14.785,
+      "eval_steps_per_second": 7.393,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1628749242040320.0,
+  "total_flos": 3257498484080640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null