Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32733994e4f5220cb1c8b8cb7587ff52c7f06884fe773473d8e5b95a540d349
+oid sha256:813ec91451351ab11de28a2c07aec1edd3efeb566549c76b36f852d086d9afcd
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e9cc0f6d65e2d351b724b7a188ac14c9e339cb81ea63fe885efdbc52ec8ea3
+oid sha256:1e72f076784e458cebca5c4c4fad472dde49c4c4f237993b633db80a20a59480
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5e83a8d68021f72aa7f6ac24182160a7f72af908d654599ef0c0306176510d
+oid sha256:f5016d318ca8e3d6b8ca4b2a60622ca780cb9ab30c6b1c3967b8626d3aa409c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4779989421367645,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00028716034315661007,
+  "best_metric": 0.4588634967803955,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0005743206863132201,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 2.825,
       "eval_steps_per_second": 1.412,
       "step": 10
+    },
+    {
+      "epoch": 0.0003445924117879321,
+      "grad_norm": 1.510844349861145,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 1.7541,
+      "step": 12
+    },
+    {
+      "epoch": 0.0004307405147349151,
+      "grad_norm": 2.169722080230713,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.9345,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004307405147349151,
+      "eval_loss": 0.4659367501735687,
+      "eval_runtime": 5186.2567,
+      "eval_samples_per_second": 2.827,
+      "eval_steps_per_second": 1.414,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005168886176818981,
+      "grad_norm": 1.781753659248352,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 2.0342,
+      "step": 18
+    },
+    {
+      "epoch": 0.0005743206863132201,
+      "eval_loss": 0.4588634967803955,
+      "eval_runtime": 5182.4914,
+      "eval_samples_per_second": 2.829,
+      "eval_steps_per_second": 1.415,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7031294986813440.0,
+  "total_flos": 1.406258997362688e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null