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:ae9bee5994fcb39a96cac3394658b3fe909263fec260e102aea3399ed21ca29a
+oid sha256:1c0d1479f77d86fe6cebadc3d3fd30a998e4322a598b315657d0e268c6825e45
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7e4221eb7b5fb78d0df2872b9f58159a2bf02fb61f3f47d3c2bafa102216305
+oid sha256:e9d97a8dffa55d0ea23c54b77a8753e8a7a991dc536e9c60836bf4b27203be07
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb8b2308b9534cba747c9327142092e99ec2ffdc03f7bf25b43d35b404de67d4
+oid sha256:b869bc600b7edcf2d1cd3232d0914ff69fbcd4f635d56d0a5a02fa57ed2f8add
 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": 1.6352452039718628,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0026016260162601626,
+  "best_metric": 0.9712910652160645,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.005203252032520325,
   "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": 4.159,
       "eval_steps_per_second": 2.081,
       "step": 10
+    },
+    {
+      "epoch": 0.0031219512195121953,
+      "grad_norm": 0.8198975920677185,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 1.4937,
+      "step": 12
+    },
+    {
+      "epoch": 0.003902439024390244,
+      "grad_norm": 0.8055070638656616,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.4355,
+      "step": 15
+    },
+    {
+      "epoch": 0.003902439024390244,
+      "eval_loss": 1.1900770664215088,
+      "eval_runtime": 389.8734,
+      "eval_samples_per_second": 4.153,
+      "eval_steps_per_second": 2.078,
+      "step": 15
+    },
+    {
+      "epoch": 0.0046829268292682925,
+      "grad_norm": 0.759701132774353,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 1.0329,
+      "step": 18
+    },
+    {
+      "epoch": 0.005203252032520325,
+      "eval_loss": 0.9712910652160645,
+      "eval_runtime": 390.0118,
+      "eval_samples_per_second": 4.151,
+      "eval_steps_per_second": 2.077,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6990386933268480.0,
+  "total_flos": 1.398077386653696e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null