Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:779c0b6b2ee0872acb8f961f6f393ad63589f705080bc19ba8b816526de933ea
+oid sha256:1c202c720e2be409ab9780f988037fb933d0a9b89879d82c68228872d2007214
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:978d0ac7b8ea2d53249b899f6951bd5de943bbcd63613f45c7e46f0151cf6737
+oid sha256:8bdc713841dc80e45b376b230565f48c31ddb805621eac56e48f2b7d0f8e4d9a
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3bcb316e36a9f2f4e07cb4dc6a0d757ad7a205c3bb7aa6e78eccd16b334dcf
+oid sha256:c697c473a332dbf1920d763623c73e50ba54d83feaad77dca0c5311c25e79af0
 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": 2.3930716514587402,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.000830685523228044,
+  "best_metric": 1.5932053327560425,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.001661371046456088,
   "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": 7.138,
       "eval_steps_per_second": 3.569,
       "step": 10
+    },
+    {
+      "epoch": 0.0009137540755508484,
+      "grad_norm": 0.43717700242996216,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.3097,
+      "step": 11
+    },
+    {
+      "epoch": 0.0009968226278736527,
+      "grad_norm": 0.30268394947052,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.5942,
+      "step": 12
+    },
+    {
+      "epoch": 0.001079891180196457,
+      "grad_norm": 0.6315892934799194,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.9464,
+      "step": 13
+    },
+    {
+      "epoch": 0.0011629597325192615,
+      "grad_norm": 0.6325842142105103,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.3774,
+      "step": 14
+    },
+    {
+      "epoch": 0.0012460282848420659,
+      "grad_norm": 0.46130749583244324,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.2938,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012460282848420659,
+      "eval_loss": 1.8308182954788208,
+      "eval_runtime": 720.8588,
+      "eval_samples_per_second": 7.032,
+      "eval_steps_per_second": 3.517,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013290968371648703,
+      "grad_norm": 0.438463419675827,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.114,
+      "step": 16
+    },
+    {
+      "epoch": 0.0014121653894876747,
+      "grad_norm": 0.6048122048377991,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.6473,
+      "step": 17
+    },
+    {
+      "epoch": 0.001495233941810479,
+      "grad_norm": 1.1923956871032715,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.4638,
+      "step": 18
+    },
+    {
+      "epoch": 0.0015783024941332835,
+      "grad_norm": 0.5673062801361084,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6572,
+      "step": 19
+    },
+    {
+      "epoch": 0.001661371046456088,
+      "grad_norm": 0.7221763730049133,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.3469,
+      "step": 20
+    },
+    {
+      "epoch": 0.001661371046456088,
+      "eval_loss": 1.5932053327560425,
+      "eval_runtime": 718.0656,
+      "eval_samples_per_second": 7.059,
+      "eval_steps_per_second": 3.53,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1086564481105920.0,
+  "total_flos": 2234632612085760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null