Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64bcf2a718b168375608e32d1cc280dfe2f28788649ea10c183e0791d08c49f
+oid sha256:e067aca1c018a83668abcd8925c73e67a5442cbb6a5afc2d652b88d5aa1d8769
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a34b94830f2e83ab22a10265115edf154f3657c704fb5590de79da0873f2626
+oid sha256:c0af9a1805c40473aad4250dc6455ee9a138ade47873e500662331501a774fb6
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e083c13100eefcdc1678fa692bdc076ef8e67364d18bdce5b52e875e0511f216
+oid sha256:ded88962bd9e6c57d8f624aeff4f98bc1285f407074b9cd60365403dd07af34a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1123dd497c9b8910fe9a2e80a4ab323c0694a06c711a817decbfc0ad393e20a4
+oid sha256:913ab8b0d366eeaae4f2a144c807ce2c591297e394af2372dd426dd4c3850119
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.8091001510620117,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.020814748736247397,
+  "best_metric": 2.798283100128174,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.023788284269997028,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 47.175,
       "eval_steps_per_second": 11.794,
       "step": 350
+    },
+    {
+      "epoch": 0.021409455842997322,
+      "grad_norm": 0.6833013296127319,
+      "learning_rate": 4.5623534490777714e-05,
+      "loss": 2.8396,
+      "step": 360
+    },
+    {
+      "epoch": 0.02200416294974725,
+      "grad_norm": 0.7645152807235718,
+      "learning_rate": 3.9779037303794365e-05,
+      "loss": 2.7683,
+      "step": 370
+    },
+    {
+      "epoch": 0.022598870056497175,
+      "grad_norm": 0.88221675157547,
+      "learning_rate": 3.42449822418582e-05,
+      "loss": 2.7769,
+      "step": 380
+    },
+    {
+      "epoch": 0.0231935771632471,
+      "grad_norm": 1.0650640726089478,
+      "learning_rate": 2.9048330664949622e-05,
+      "loss": 2.782,
+      "step": 390
+    },
+    {
+      "epoch": 0.023788284269997028,
+      "grad_norm": 1.8103938102722168,
+      "learning_rate": 2.4214400137185785e-05,
+      "loss": 2.8704,
+      "step": 400
+    },
+    {
+      "epoch": 0.023788284269997028,
+      "eval_loss": 2.798283100128174,
+      "eval_runtime": 149.8594,
+      "eval_samples_per_second": 47.244,
+      "eval_steps_per_second": 11.811,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3676866934210560.0,
+  "total_flos": 4204064766689280.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null