Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f1ca4c9ca800ab7cef62b43022799eaf238902020ff82e01ceb4c79b33b7eaa
+oid sha256:a3b8fec0c62157c88a9a2252c60a7cedce684de0cad599533b0c6565e190bcc9
 size 389074464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7213eadcda674412fec55daf671e252891bf56017b1a8df4f491f3d8812c0ed8
+oid sha256:a3827eb8aa22b058c49bfa1b866517b495d5ec2153a9de8dbc1f1122987c98d8
 size 198011700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df5dd822aa84213b6c6ce0291c75117cea29332f2771c334aa15ad7608903c0b
+oid sha256:cfca8ab541977de743f31af87f1790135eed2b9eb87aa1d10a72a1414da51503
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a78bab0e108d3c186898a780257121eba92c7434d580326e33b855003a3757
+oid sha256:7720ce10f85dbd90d92bd34f3d3d0da56a95cd9c569195e83083bdc45d9452b4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5459651947021484,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.056417489421720736,
+  "best_metric": 0.5348652005195618,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.06582040432534085,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 20.302,
       "eval_steps_per_second": 5.078,
       "step": 300
+    },
+    {
+      "epoch": 0.05829807240244476,
+      "grad_norm": 0.7479456067085266,
+      "learning_rate": 8.035627906643523e-05,
+      "loss": 0.7484,
+      "step": 310
+    },
+    {
+      "epoch": 0.06017865538316878,
+      "grad_norm": 0.852773129940033,
+      "learning_rate": 7.324419859625559e-05,
+      "loss": 0.588,
+      "step": 320
+    },
+    {
+      "epoch": 0.06205923836389281,
+      "grad_norm": 0.653623640537262,
+      "learning_rate": 6.629170109791332e-05,
+      "loss": 0.5215,
+      "step": 330
+    },
+    {
+      "epoch": 0.06393982134461683,
+      "grad_norm": 0.9154057502746582,
+      "learning_rate": 5.9532658440357784e-05,
+      "loss": 0.4859,
+      "step": 340
+    },
+    {
+      "epoch": 0.06582040432534085,
+      "grad_norm": 0.7963242530822754,
+      "learning_rate": 5.300000000000002e-05,
+      "loss": 0.4577,
+      "step": 350
+    },
+    {
+      "epoch": 0.06582040432534085,
+      "eval_loss": 0.5348652005195618,
+      "eval_runtime": 110.893,
+      "eval_samples_per_second": 20.191,
+      "eval_steps_per_second": 5.05,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2535313083531264e+16,
+  "total_flos": 3.791008947398246e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null