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:a336260ccb5c38a91a984493682c9586aedcefff96a0f93bc8551f701576c261
+oid sha256:384bae3bcb1814d7caa79d8aa1145aa3d99cc75cad819e5e8a43ec06a62260a5
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00a22b7f38287e8ee9f199377b97ad2a0386b963d9787dd465bb5bfd1f2fdb2e
+oid sha256:a72013cfa5c4b60b1e46834d8a68e01afb64c3ea3622b4af391ffbee64cec013
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38cd220d45833eec6453b4e76b33f29c8b793e607411608ce8deec238dfde77b
+oid sha256:87186703aed64a28f7aa092aa66ac4cff9ccd6f164d6515ce692fb3a15c4760e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6549012660980225,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00016563146997929605,
+  "best_metric": 1.5705841779708862,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0003312629399585921,
   "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": 8.39,
       "eval_steps_per_second": 4.195,
       "step": 10
+    },
+    {
+      "epoch": 0.00019875776397515528,
+      "grad_norm": 0.5781303644180298,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.5987,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002484472049689441,
+      "grad_norm": 0.37722793221473694,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.7165,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002484472049689441,
+      "eval_loss": 1.5890259742736816,
+      "eval_runtime": 3030.0327,
+      "eval_samples_per_second": 8.39,
+      "eval_steps_per_second": 4.195,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002981366459627329,
+      "grad_norm": 0.30050724744796753,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.7152,
+      "step": 18
+    },
+    {
+      "epoch": 0.0003312629399585921,
+      "eval_loss": 1.5705841779708862,
+      "eval_runtime": 3031.3045,
+      "eval_samples_per_second": 8.386,
+      "eval_steps_per_second": 4.193,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1646346004070400.0,
+  "total_flos": 3292692008140800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null