Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e2abbb1735f8877d5656b2ed34fb8aa60ff3819e2d3cce28072a98700980f30
+oid sha256:a615006941a0558bf913e17348dc6fa3d4df16ef1959cc50a79319d31978f35c
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce38b47ce36a136252bcf94df6e2762be65ff87bc54fb805735cd7c00cedee0b
+oid sha256:6e4dea673febd15cb0b141b2cf743de292d642e6db8e761c85e2bc0af9ecaaae
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96bcc9f2208627343efb282c69f858dfa3339a1ca3e40f4ad215b8dc03deb055
+oid sha256:17b6ab54758d6c72638402e84fae2aad65a221b35640878ae19e43b4230eac2d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15517f711b4d803046b15167942c5e55ce6a93d9447a6347918a0d65acdb3f4a
+oid sha256:b43450b88475bcf098065f8f055f5a22625a79b35c329b2a2da0516bc5608f62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0982829332351685,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.24441340782122906,
+  "best_metric": 1.0796287059783936,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.27932960893854747,
   "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": 11.63,
       "eval_steps_per_second": 2.912,
       "step": 350
+    },
+    {
+      "epoch": 0.25139664804469275,
+      "grad_norm": 0.40256136655807495,
+      "learning_rate": 4.782756997342398e-05,
+      "loss": 0.8455,
+      "step": 360
+    },
+    {
+      "epoch": 0.25837988826815644,
+      "grad_norm": 0.4019988775253296,
+      "learning_rate": 4.170072992716607e-05,
+      "loss": 0.8504,
+      "step": 370
+    },
+    {
+      "epoch": 0.26536312849162014,
+      "grad_norm": 0.46585512161254883,
+      "learning_rate": 3.5899329210063916e-05,
+      "loss": 0.7688,
+      "step": 380
+    },
+    {
+      "epoch": 0.2723463687150838,
+      "grad_norm": 0.49366164207458496,
+      "learning_rate": 3.045163166325637e-05,
+      "loss": 0.9192,
+      "step": 390
+    },
+    {
+      "epoch": 0.27932960893854747,
+      "grad_norm": 1.1542916297912598,
+      "learning_rate": 2.5384177921590895e-05,
+      "loss": 2.3411,
+      "step": 400
+    },
+    {
+      "epoch": 0.27932960893854747,
+      "eval_loss": 1.0796287059783936,
+      "eval_runtime": 51.6139,
+      "eval_samples_per_second": 11.683,
+      "eval_steps_per_second": 2.926,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.882126363131904e+16,
+  "total_flos": 1.1268467831341056e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null