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:ab8a28bc4e4caa9a69cdd1fee02995f651eaa0cf46bda8cd1b18833486d164c6
+oid sha256:7cd03ec906ea03df622a4671506f1e40633f714368a2641dfef7150c97167c59
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7719c4dbc8b46b179ff3d6c242d7e5114be025bbcf64fa9128ccb0fb6f6fd64e
+oid sha256:ababed2efa73b56567d1e8a72efba9f4426d3c2acdb01a62920ad192f589ab72
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab77e0cb67af6bf237c14902de44d31095f33cc3f0aae29fedc6f0091531c9af
+oid sha256:f2766080ea7027b2f163db3c6579463a376deb2a371f204d529871549d481bf6
 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": 0.8521348237991333,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00046835665359171006,
+  "best_metric": 0.815974235534668,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0009367133071834201,
   "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": 3.178,
       "eval_steps_per_second": 1.589,
       "step": 10
+    },
+    {
+      "epoch": 0.000515192318950881,
+      "grad_norm": 0.6538496017456055,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.8828,
+      "step": 11
+    },
+    {
+      "epoch": 0.0005620279843100521,
+      "grad_norm": 0.7199555039405823,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.6093,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006088636496692231,
+      "grad_norm": 0.8212117552757263,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.842,
+      "step": 13
+    },
+    {
+      "epoch": 0.0006556993150283941,
+      "grad_norm": 0.6258594989776611,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.7928,
+      "step": 14
+    },
+    {
+      "epoch": 0.0007025349803875652,
+      "grad_norm": 0.8337199687957764,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8851,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007025349803875652,
+      "eval_loss": 0.8297687768936157,
+      "eval_runtime": 2839.0047,
+      "eval_samples_per_second": 3.167,
+      "eval_steps_per_second": 1.583,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007493706457467361,
+      "grad_norm": 0.5545913577079773,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.7313,
+      "step": 16
+    },
+    {
+      "epoch": 0.0007962063111059071,
+      "grad_norm": 0.6206797361373901,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.8542,
+      "step": 17
+    },
+    {
+      "epoch": 0.0008430419764650782,
+      "grad_norm": 0.6755259037017822,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.8265,
+      "step": 18
+    },
+    {
+      "epoch": 0.0008898776418242492,
+      "grad_norm": 0.46088144183158875,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6002,
+      "step": 19
+    },
+    {
+      "epoch": 0.0009367133071834201,
+      "grad_norm": 0.6171578764915466,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.9655,
+      "step": 20
+    },
+    {
+      "epoch": 0.0009367133071834201,
+      "eval_loss": 0.815974235534668,
+      "eval_runtime": 2833.2714,
+      "eval_samples_per_second": 3.173,
+      "eval_steps_per_second": 1.587,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2404433522589696.0,
+  "total_flos": 4716388832772096.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null