Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c5dc03878434b70669f00d98a70cff6c6b88f48cd8a5130d6c16a309074181
+oid sha256:971511865a34cde982b550b88fb5be87eff5eb28f53513f321378ac2241f01e4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa283b2968063f154501ed5081051f4eca7961b268a6dab05f9f3b409389e38a
+oid sha256:c8280b2ecbc31b0c972574af848f18c4dcdf802a0e26b973d18c08ab35bf2e2c
 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": 0.6148068308830261,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004243581582855931,
+  "best_metric": 0.49634602665901184,
+  "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": 5.458,
       "eval_steps_per_second": 2.732,
       "step": 10
+    },
+    {
+      "epoch": 0.0046679397411415234,
+      "grad_norm": 0.9498071670532227,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.5765,
+      "step": 11
+    },
+    {
+      "epoch": 0.005092297899427116,
+      "grad_norm": 1.1527200937271118,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.4933,
+      "step": 12
+    },
+    {
+      "epoch": 0.00551665605771271,
+      "grad_norm": 1.1410077810287476,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.4746,
+      "step": 13
+    },
+    {
+      "epoch": 0.005941014215998302,
+      "grad_norm": 1.3380974531173706,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.5881,
+      "step": 14
+    },
+    {
+      "epoch": 0.006365372374283896,
+      "grad_norm": 0.948268711566925,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.4787,
+      "step": 15
+    },
+    {
+      "epoch": 0.006365372374283896,
+      "eval_loss": 0.5229542255401611,
+      "eval_runtime": 183.1912,
+      "eval_samples_per_second": 5.421,
+      "eval_steps_per_second": 2.713,
+      "step": 15
+    },
+    {
+      "epoch": 0.006789730532569488,
+      "grad_norm": 1.055385708808899,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6458,
+      "step": 16
+    },
+    {
+      "epoch": 0.007214088690855082,
+      "grad_norm": 0.8721186518669128,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.487,
+      "step": 17
+    },
+    {
+      "epoch": 0.0076384468491406746,
+      "grad_norm": 0.9416680335998535,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.501,
+      "step": 18
+    },
+    {
+      "epoch": 0.008062805007426267,
+      "grad_norm": 0.9576472043991089,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5011,
+      "step": 19
+    },
+    {
+      "epoch": 0.008487163165711862,
+      "grad_norm": 0.7585878372192383,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.475,
+      "step": 20
+    },
+    {
+      "epoch": 0.008487163165711862,
+      "eval_loss": 0.49634602665901184,
+      "eval_runtime": 182.8238,
+      "eval_samples_per_second": 5.431,
+      "eval_steps_per_second": 2.718,
+      "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