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:e7340b35f9d907d1bd5b54afd57b40b71e6b29e1db5754d24c4bcbd388226f31
+oid sha256:fc0c99f4bdba2c20da46869fe9665f7e5ec2d3bf7f115392dbdc0d4d33556d1f
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e160db6ff3e26970429fa63021ba62942f36a0879dcbf4a2ea78e0709a4f4495
+oid sha256:e9034ad05d7b7c67ff80ee8b114a1adad3132801520a95013438cd92c94a11c0
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd99a4658dfec332ee6968e96d372e722985cc6df641834de9b1d2be914dae4b
+oid sha256:5d34319ff3df364313deadc6fed2a87af4dbaa25121577034e823762746bfdd8
 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": 2.6647682189941406,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0098015192354815,
+  "best_metric": 2.5634732246398926,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.019603038470963,
   "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": 104.014,
       "eval_steps_per_second": 52.007,
       "step": 10
+    },
+    {
+      "epoch": 0.0117618230825778,
+      "grad_norm": 0.5657535791397095,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 2.4843,
+      "step": 12
+    },
+    {
+      "epoch": 0.014702278853222249,
+      "grad_norm": 0.7222481966018677,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.5581,
+      "step": 15
+    },
+    {
+      "epoch": 0.014702278853222249,
+      "eval_loss": 2.601343870162964,
+      "eval_runtime": 4.0133,
+      "eval_samples_per_second": 107.145,
+      "eval_steps_per_second": 53.572,
+      "step": 15
+    },
+    {
+      "epoch": 0.017642734623866698,
+      "grad_norm": 0.8338580131530762,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 2.5049,
+      "step": 18
+    },
+    {
+      "epoch": 0.019603038470963,
+      "eval_loss": 2.5634732246398926,
+      "eval_runtime": 3.9308,
+      "eval_samples_per_second": 109.392,
+      "eval_steps_per_second": 54.696,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 69418793041920.0,
+  "total_flos": 138837586083840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null