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:f2ec3beeb7eef06b29e92a1dd886431a2fac64182bc9b0332518d7327e12a770
+oid sha256:0e0f372637e0c7150930c7bc438678212e19018dcb70b6aa2ba2db3101dbaade
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b7fe8f43c57129ed2170af3f9fdb511b708b6d3cf85b8000c59a8408466b69e
+oid sha256:e73012e58fffb212d8b7527be320dbc5c8fdf4b94c951e454f740d5a9c0709b3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0eefcdfff3e71f7b8936733ac676485e79ed929d70247065a544d4c15495eb
+oid sha256:7c85a5d20398029878a337e126c42e0d688a3349e9c9799e99f9ca3261cda24e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6146085262298584,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004243581582855931,
+  "best_metric": 0.4975270628929138,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.008487163165711862,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 2.911,
       "eval_steps_per_second": 1.457,
       "step": 10
+    },
+    {
+      "epoch": 0.0046679397411415234,
+      "grad_norm": 1.0744050741195679,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.5715,
+      "step": 11
+    },
+    {
+      "epoch": 0.005092297899427116,
+      "grad_norm": 1.0391552448272705,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.4976,
+      "step": 12
+    },
+    {
+      "epoch": 0.00551665605771271,
+      "grad_norm": 1.041351079940796,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.4692,
+      "step": 13
+    },
+    {
+      "epoch": 0.005941014215998302,
+      "grad_norm": 1.4768027067184448,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.5841,
+      "step": 14
+    },
+    {
+      "epoch": 0.006365372374283896,
+      "grad_norm": 0.9320117831230164,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.4774,
+      "step": 15
+    },
+    {
+      "epoch": 0.006365372374283896,
+      "eval_loss": 0.5234472751617432,
+      "eval_runtime": 352.8525,
+      "eval_samples_per_second": 2.814,
+      "eval_steps_per_second": 1.409,
+      "step": 15
+    },
+    {
+      "epoch": 0.006789730532569488,
+      "grad_norm": 1.1733794212341309,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6489,
+      "step": 16
+    },
+    {
+      "epoch": 0.007214088690855082,
+      "grad_norm": 0.9090507626533508,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.4878,
+      "step": 17
+    },
+    {
+      "epoch": 0.0076384468491406746,
+      "grad_norm": 0.8836754560470581,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.4936,
+      "step": 18
+    },
+    {
+      "epoch": 0.008062805007426267,
+      "grad_norm": 1.0243104696273804,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5002,
+      "step": 19
+    },
+    {
+      "epoch": 0.008487163165711862,
+      "grad_norm": 0.7337459921836853,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.4775,
+      "step": 20
+    },
+    {
+      "epoch": 0.008487163165711862,
+      "eval_loss": 0.4975270628929138,
+      "eval_runtime": 339.9864,
+      "eval_samples_per_second": 2.921,
+      "eval_steps_per_second": 1.462,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3282976540459008.0,
+  "total_flos": 6704670399528960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null