Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0585f03a1ff1b9f5ef14e16b5c2e573706dabda8f5d4695f4cd39ff14e4c9abb
+oid sha256:7ea36639714e4fbb9d0e80166ec38e0fd571142c379ca289d5e9ec2b7e6d3f49
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:800e14bc2062c7822ccfbff4f46d8e8025e85d88052812aee7d1736549b0ee48
+oid sha256:a1549348ebf303b8302109de9f471966791b306b0279b2f5c1f7d2ffd4405e6e
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fddb71a9a3d250332f98e562706fe25ec1ff4e66f7c9c4eb0af41236fd2dde1a
+oid sha256:a7d08b0ef3c5bf4b6187f3763c791386d4f445254af7310d780d2b6c86cae405
 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": 2.496121883392334,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0007059529482360001,
+  "best_metric": 2.3560678958892822,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0014119058964720001,
   "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": 4.928,
       "eval_steps_per_second": 2.465,
       "step": 10
+    },
+    {
+      "epoch": 0.0007765482430596001,
+      "grad_norm": 1.0022832155227661,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 10.4845,
+      "step": 11
+    },
+    {
+      "epoch": 0.0008471435378832001,
+      "grad_norm": 1.335647463798523,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 9.594,
+      "step": 12
+    },
+    {
+      "epoch": 0.0009177388327068001,
+      "grad_norm": 1.406315565109253,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 9.5518,
+      "step": 13
+    },
+    {
+      "epoch": 0.0009883341275304,
+      "grad_norm": 1.4746501445770264,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 9.6602,
+      "step": 14
+    },
+    {
+      "epoch": 0.0010589294223540002,
+      "grad_norm": 1.2272251844406128,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 10.2344,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010589294223540002,
+      "eval_loss": 2.396404266357422,
+      "eval_runtime": 1226.905,
+      "eval_samples_per_second": 4.862,
+      "eval_steps_per_second": 2.431,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011295247171776,
+      "grad_norm": 1.6236687898635864,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 9.3855,
+      "step": 16
+    },
+    {
+      "epoch": 0.0012001200120012002,
+      "grad_norm": 1.5380558967590332,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 9.6669,
+      "step": 17
+    },
+    {
+      "epoch": 0.0012707153068248001,
+      "grad_norm": 1.3339756727218628,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 9.0667,
+      "step": 18
+    },
+    {
+      "epoch": 0.0013413106016484002,
+      "grad_norm": 1.3109127283096313,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 10.1132,
+      "step": 19
+    },
+    {
+      "epoch": 0.0014119058964720001,
+      "grad_norm": 1.509404182434082,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 9.3982,
+      "step": 20
+    },
+    {
+      "epoch": 0.0014119058964720001,
+      "eval_loss": 2.3560678958892822,
+      "eval_runtime": 1219.3739,
+      "eval_samples_per_second": 4.892,
+      "eval_steps_per_second": 2.446,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3324535520624640.0,
+  "total_flos": 6728226648883200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null