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:be337bee70e4653001ea48c3f7d6eff4995d1887e12fe6ea25de6b86498b08bb
+oid sha256:cf0d2b85eab798d32545faa36db4ead74c4a47d46ee1e872548572ff83d28ee0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baf9220b58c165e5f97eed103d2c52c0e4fb3c9c7d1dd69a69a331412ec4a07b
+oid sha256:9986bd5993111eae9e4196dd03b7a4b6da8cf2deb8387cd50ad24abb74e0d868
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5a03af491a912f295faf6fa6852568637db55748dbbb2d135ab3bc62e8e1bd8
+oid sha256:accf9bedcce16bf41114efae3e98d5def5834f7019b44d6425eda4dfe4f295d3
 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": 0.6158913373947144,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004243581582855931,
+  "best_metric": 0.4959838390350342,
+  "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": 5.404,
       "eval_steps_per_second": 2.705,
       "step": 10
+    },
+    {
+      "epoch": 0.0046679397411415234,
+      "grad_norm": 0.9812945127487183,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.5798,
+      "step": 11
+    },
+    {
+      "epoch": 0.005092297899427116,
+      "grad_norm": 0.9407110810279846,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.5111,
+      "step": 12
+    },
+    {
+      "epoch": 0.00551665605771271,
+      "grad_norm": 0.9945716857910156,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.4749,
+      "step": 13
+    },
+    {
+      "epoch": 0.005941014215998302,
+      "grad_norm": 1.3098291158676147,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.5797,
+      "step": 14
+    },
+    {
+      "epoch": 0.006365372374283896,
+      "grad_norm": 0.945827841758728,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.4763,
+      "step": 15
+    },
+    {
+      "epoch": 0.006365372374283896,
+      "eval_loss": 0.5205870866775513,
+      "eval_runtime": 183.9724,
+      "eval_samples_per_second": 5.398,
+      "eval_steps_per_second": 2.701,
+      "step": 15
+    },
+    {
+      "epoch": 0.006789730532569488,
+      "grad_norm": 1.1491625308990479,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6383,
+      "step": 16
+    },
+    {
+      "epoch": 0.007214088690855082,
+      "grad_norm": 0.8612709641456604,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.4815,
+      "step": 17
+    },
+    {
+      "epoch": 0.0076384468491406746,
+      "grad_norm": 0.8541699051856995,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.4945,
+      "step": 18
+    },
+    {
+      "epoch": 0.008062805007426267,
+      "grad_norm": 1.076985239982605,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5025,
+      "step": 19
+    },
+    {
+      "epoch": 0.008487163165711862,
+      "grad_norm": 0.7121065855026245,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.4774,
+      "step": 20
+    },
+    {
+      "epoch": 0.008487163165711862,
+      "eval_loss": 0.4959838390350342,
+      "eval_runtime": 185.1092,
+      "eval_samples_per_second": 5.364,
+      "eval_steps_per_second": 2.685,
+      "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