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:ddd6986e405224e056895570401295ef576f7ac8a83ecb6bdc84935f24356495
+oid sha256:d2d2ef9991b55609f07cd82eda51ca702decd22aa8a8a594d22558f16c46ca83
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffe8be580ff43ed4ef1c01e5f7a8d532fa7320bbbffd65abb34f297cfe41c24e
+oid sha256:ef2e88eb0341720b7d6d39a8e0ed3e6a1b1b6d5298ac189db94a20cad3d7bb33
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7739c28e2282b0be0ad3d8c5a3b0f7f9c2b0c36f696d58170b548e46acaedcc
+oid sha256:647617a5b8873881ec555b7bbc314145999492030dd45fc0b6e58c2f7c8f80a1
 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": 1.2409539222717285,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.020080321285140562,
+  "best_metric": 1.1177598237991333,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.040160642570281124,
   "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": 6.668,
       "eval_steps_per_second": 3.334,
       "step": 10
+    },
+    {
+      "epoch": 0.02208835341365462,
+      "grad_norm": 0.966452956199646,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.1709,
+      "step": 11
+    },
+    {
+      "epoch": 0.024096385542168676,
+      "grad_norm": 0.8635215163230896,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.1076,
+      "step": 12
+    },
+    {
+      "epoch": 0.02610441767068273,
+      "grad_norm": 0.9673819541931152,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.1629,
+      "step": 13
+    },
+    {
+      "epoch": 0.028112449799196786,
+      "grad_norm": 0.8269699215888977,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.1716,
+      "step": 14
+    },
+    {
+      "epoch": 0.030120481927710843,
+      "grad_norm": 0.8637534976005554,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.3285,
+      "step": 15
+    },
+    {
+      "epoch": 0.030120481927710843,
+      "eval_loss": 1.159950852394104,
+      "eval_runtime": 31.8128,
+      "eval_samples_per_second": 6.601,
+      "eval_steps_per_second": 3.301,
+      "step": 15
+    },
+    {
+      "epoch": 0.0321285140562249,
+      "grad_norm": 0.7454081177711487,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.1845,
+      "step": 16
+    },
+    {
+      "epoch": 0.03413654618473896,
+      "grad_norm": 0.8901392817497253,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.015,
+      "step": 17
+    },
+    {
+      "epoch": 0.03614457831325301,
+      "grad_norm": 0.875340461730957,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.0394,
+      "step": 18
+    },
+    {
+      "epoch": 0.03815261044176707,
+      "grad_norm": 1.2102932929992676,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.4032,
+      "step": 19
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "grad_norm": 0.7349887490272522,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.1259,
+      "step": 20
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "eval_loss": 1.1177598237991333,
+      "eval_runtime": 31.8229,
+      "eval_samples_per_second": 6.599,
+      "eval_steps_per_second": 3.3,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2311955310182400.0,
+  "total_flos": 4346475983142912.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null