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:aa87e4aaf0913c115ce89b309771c352257d3a5eb759996f5207f3346bf4e1cf
+oid sha256:c7abb7db7664824f9b99d55381d0dcb675f530fb79f26271dc148939c36ac1fd
 size 1006723888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba75799be91829a5a59efdb4d0086c4338be00a89cf104ff2f4d2e793466c29
+oid sha256:10338f323ee9598dc921000b563a1a867ee9769cd4e365d536e38b4bfde7ebb1
 size 511971668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9904ec9f30d77b1d264749908e7eb7567942888015aa815ac76ce38d414eed0
+oid sha256:ed2a10045379cb883a1fb249a06e1e128f5649c0bf5bd9fec5bdd35f11b3fb09
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aefa5c0989fb1076f44dee5ec81119730caab480902e567590e4c3defecd81d
+oid sha256:4be7b38aa7a01f117ebb95bff4f596a12bcbebf1c53b704b1e44c42b56276682
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4387960731983185,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.07278777165436207,
+  "best_metric": 0.4155665934085846,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.08318602474784237,
   "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": 6.271,
       "eval_steps_per_second": 1.571,
       "step": 350
+    },
+    {
+      "epoch": 0.07486742227305812,
+      "grad_norm": 0.8487042188644409,
+      "learning_rate": 4.804797352168861e-05,
+      "loss": 0.4459,
+      "step": 360
+    },
+    {
+      "epoch": 0.07694707289175419,
+      "grad_norm": 1.076621413230896,
+      "learning_rate": 4.189289918950325e-05,
+      "loss": 0.4533,
+      "step": 370
+    },
+    {
+      "epoch": 0.07902672351045024,
+      "grad_norm": 0.8744729161262512,
+      "learning_rate": 3.606476390688449e-05,
+      "loss": 0.4404,
+      "step": 380
+    },
+    {
+      "epoch": 0.0811063741291463,
+      "grad_norm": 0.8504107594490051,
+      "learning_rate": 3.0591961763087043e-05,
+      "loss": 0.4176,
+      "step": 390
+    },
+    {
+      "epoch": 0.08318602474784237,
+      "grad_norm": 0.8338978290557861,
+      "learning_rate": 2.550115570003141e-05,
+      "loss": 0.4642,
+      "step": 400
+    },
+    {
+      "epoch": 0.08318602474784237,
+      "eval_loss": 0.4155665934085846,
+      "eval_runtime": 80.7198,
+      "eval_samples_per_second": 6.281,
+      "eval_steps_per_second": 1.573,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.693949303016653e+16,
+  "total_flos": 5.360703465376973e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null