Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e067aca1c018a83668abcd8925c73e67a5442cbb6a5afc2d652b88d5aa1d8769
+oid sha256:61f36653188746d1b72d6722a11425e10284ddba5898cb1147fad8ef023d7aef
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0af9a1805c40473aad4250dc6455ee9a138ade47873e500662331501a774fb6
+oid sha256:7b51be838ee3d89bf3a4a9d5129272e8b0fa1cc504a53050a5a9ff151a215e91
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded88962bd9e6c57d8f624aeff4f98bc1285f407074b9cd60365403dd07af34a
+oid sha256:3e39e4689ac13a606f0be2d9cb7c8daef4aea8051a82b777874fce363b5b84be
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913ab8b0d366eeaae4f2a144c807ce2c591297e394af2372dd426dd4c3850119
+oid sha256:d6f907450757c510bc85cf5ba3c442a20b76731dbae558c5d4cdc37061b46d99
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.798283100128174,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.023788284269997028,
+  "best_metric": 2.7940969467163086,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.026761819803746655,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 47.244,
       "eval_steps_per_second": 11.811,
       "step": 400
+    },
+    {
+      "epoch": 0.024382991376746953,
+      "grad_norm": 0.6215288639068604,
+      "learning_rate": 1.976674108219295e-05,
+      "loss": 2.8352,
+      "step": 410
+    },
+    {
+      "epoch": 0.024977698483496878,
+      "grad_norm": 0.7338668704032898,
+      "learning_rate": 1.572702204780991e-05,
+      "loss": 2.801,
+      "step": 420
+    },
+    {
+      "epoch": 0.025572405590246802,
+      "grad_norm": 0.9176461100578308,
+      "learning_rate": 1.2114924139101056e-05,
+      "loss": 2.7443,
+      "step": 430
+    },
+    {
+      "epoch": 0.02616711269699673,
+      "grad_norm": 1.041648507118225,
+      "learning_rate": 8.948045133990798e-06,
+      "loss": 2.7708,
+      "step": 440
+    },
+    {
+      "epoch": 0.026761819803746655,
+      "grad_norm": 1.8905234336853027,
+      "learning_rate": 6.241813748658489e-06,
+      "loss": 2.7077,
+      "step": 450
+    },
+    {
+      "epoch": 0.026761819803746655,
+      "eval_loss": 2.7940969467163086,
+      "eval_runtime": 149.9687,
+      "eval_samples_per_second": 47.21,
+      "eval_steps_per_second": 11.802,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4204064766689280.0,
+  "total_flos": 4749286456688640.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null