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:cb7a5e9a6f672d3d94dc399a517f1a29e2ebb88efdbe07caf7f6ed4ed54a66c4
+oid sha256:ee15847a160a0884934b25170b0c794e962348b5b1095ab116d11adf972bb74f
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e390b4e5b762115f2593ead04daec04a5e1a4b667f2c98039a787866e91ea5c
+oid sha256:b71a1fd3c743e327250acb346af8581bbfcde2440e39d2b3b50e54810683c580
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9db2be3e17874a7238b20ca88de31d0ed9cbfaa0bcf14296319efacf25c331dc
+oid sha256:5d91bf29827d85239b4e7fd0c442dcb464b054fc92e2b95b52e4e3ea8402c904
 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": 3.5349371433258057,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008210180623973728,
+  "best_metric": 1.3548338413238525,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.016420361247947456,
   "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": 9.286,
       "eval_steps_per_second": 4.652,
       "step": 10
+    },
+    {
+      "epoch": 0.0090311986863711,
+      "grad_norm": 6.665732383728027,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 3.9181,
+      "step": 11
+    },
+    {
+      "epoch": 0.009852216748768473,
+      "grad_norm": 7.836021900177002,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.0558,
+      "step": 12
+    },
+    {
+      "epoch": 0.010673234811165846,
+      "grad_norm": 11.377631187438965,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.2821,
+      "step": 13
+    },
+    {
+      "epoch": 0.011494252873563218,
+      "grad_norm": 8.392828941345215,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.391,
+      "step": 14
+    },
+    {
+      "epoch": 0.012315270935960592,
+      "grad_norm": 7.50490665435791,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.895,
+      "step": 15
+    },
+    {
+      "epoch": 0.012315270935960592,
+      "eval_loss": 2.026073932647705,
+      "eval_runtime": 55.3509,
+      "eval_samples_per_second": 9.268,
+      "eval_steps_per_second": 4.643,
+      "step": 15
+    },
+    {
+      "epoch": 0.013136288998357963,
+      "grad_norm": 7.33989143371582,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.9689,
+      "step": 16
+    },
+    {
+      "epoch": 0.013957307060755337,
+      "grad_norm": 9.091341018676758,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.6151,
+      "step": 17
+    },
+    {
+      "epoch": 0.014778325123152709,
+      "grad_norm": 7.225343227386475,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.8492,
+      "step": 18
+    },
+    {
+      "epoch": 0.015599343185550082,
+      "grad_norm": 9.886344909667969,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.9566,
+      "step": 19
+    },
+    {
+      "epoch": 0.016420361247947456,
+      "grad_norm": 6.689027786254883,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.2539,
+      "step": 20
+    },
+    {
+      "epoch": 0.016420361247947456,
+      "eval_loss": 1.3548338413238525,
+      "eval_runtime": 56.0188,
+      "eval_samples_per_second": 9.158,
+      "eval_steps_per_second": 4.588,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 489477793382400.0,
+  "total_flos": 978955586764800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null