Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d944d1b19afe35ffe04d298b35a088edfa78c34538a0de4754d65f9a109cdbb
+oid sha256:774cfebe2763204b2445b18775f80def80e3950d9da0869711b13c1454507968
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e8e817b9004431641af0dad99debabd1a9e77e47f09ac303c2f912ffcd3e25
+oid sha256:82dda7aece667fd46fba56abc965f2e0c8600e97ad83b81a9b1c8a494ef1c56e
 size 85723732

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caaf30335ff5d41c24939218bc867f610adfabf7518ea645fd6efcb991b24d7c
+oid sha256:e16deb1582ca001dbb180f37009aca74673c34c1897aa485ebd6b2881634a482
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d9346c4fcc90fb1ec8546736583b76a4fae6bc25cb93181337c187d15da94a
+oid sha256:77c9b643e87499abdfb160399a4a6e4965274897c037cf91e4cd5d5d65b2b404
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.002148151397705,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.08191685439279131,
+  "best_metric": 1.9585822820663452,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.09556966345825654,
   "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": 25.175,
       "eval_steps_per_second": 6.294,
       "step": 300
+    },
+    {
+      "epoch": 0.08464741620588435,
+      "grad_norm": 10.377389907836914,
+      "learning_rate": 9.733794785622253e-05,
+      "loss": 7.7774,
+      "step": 310
+    },
+    {
+      "epoch": 0.0873779780189774,
+      "grad_norm": 10.131440162658691,
+      "learning_rate": 9.202138944469168e-05,
+      "loss": 7.7762,
+      "step": 320
+    },
+    {
+      "epoch": 0.09010853983207044,
+      "grad_norm": 12.15221118927002,
+      "learning_rate": 8.672744727162781e-05,
+      "loss": 7.8511,
+      "step": 330
+    },
+    {
+      "epoch": 0.0928391016451635,
+      "grad_norm": 13.989408493041992,
+      "learning_rate": 8.147112759128859e-05,
+      "loss": 7.7617,
+      "step": 340
+    },
+    {
+      "epoch": 0.09556966345825654,
+      "grad_norm": 24.143465042114258,
+      "learning_rate": 7.626733001288851e-05,
+      "loss": 8.1177,
+      "step": 350
+    },
+    {
+      "epoch": 0.09556966345825654,
+      "eval_loss": 1.9585822820663452,
+      "eval_runtime": 245.0532,
+      "eval_samples_per_second": 25.17,
+      "eval_steps_per_second": 6.293,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.109388496044032e+17,
+  "total_flos": 2.460953245384704e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null