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:ed23ab0fca898cde96ab18821d45ea04e9a6bc66ec048b8b781a8c3c403f59f0
+oid sha256:00608310cce1763710765a64da90f23982a661303651696191efd0282b72018a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f8cba8518680ee7d40c18e59cf9fbb106fcbcaf9944be9030bd4e5ff921a31d
+oid sha256:fa989f51ef45ac2680b0af076a2757a3fd7ccc4e5c6bceee40e63683a151de9e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af4cbe6dd62788676ba2597afaddb6a97ff06bf7b18f8e3a0ce4190a674ccd8
+oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
 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": 0.5959562063217163,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0013736263736263737,
+  "best_metric": 0.5544787645339966,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0027472527472527475,
   "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": 4.769,
       "eval_steps_per_second": 2.384,
       "step": 10
+    },
+    {
+      "epoch": 0.001510989010989011,
+      "grad_norm": 18.507549285888672,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.42,
+      "step": 11
+    },
+    {
+      "epoch": 0.0016483516483516484,
+      "grad_norm": 29.13274574279785,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.7384,
+      "step": 12
+    },
+    {
+      "epoch": 0.0017857142857142857,
+      "grad_norm": 29.826873779296875,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.5041,
+      "step": 13
+    },
+    {
+      "epoch": 0.0019230769230769232,
+      "grad_norm": 25.007963180541992,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 3.4518,
+      "step": 14
+    },
+    {
+      "epoch": 0.0020604395604395605,
+      "grad_norm": 22.43764877319336,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.7669,
+      "step": 15
+    },
+    {
+      "epoch": 0.0020604395604395605,
+      "eval_loss": 0.5621253252029419,
+      "eval_runtime": 639.6178,
+      "eval_samples_per_second": 4.793,
+      "eval_steps_per_second": 2.397,
+      "step": 15
+    },
+    {
+      "epoch": 0.002197802197802198,
+      "grad_norm": 17.68715476989746,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.9595,
+      "step": 16
+    },
+    {
+      "epoch": 0.002335164835164835,
+      "grad_norm": 17.10245132446289,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.0784,
+      "step": 17
+    },
+    {
+      "epoch": 0.0024725274725274724,
+      "grad_norm": 18.39337921142578,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 2.27,
+      "step": 18
+    },
+    {
+      "epoch": 0.0026098901098901097,
+      "grad_norm": 17.87843894958496,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.4016,
+      "step": 19
+    },
+    {
+      "epoch": 0.0027472527472527475,
+      "grad_norm": 33.74769592285156,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.3414,
+      "step": 20
+    },
+    {
+      "epoch": 0.0027472527472527475,
+      "eval_loss": 0.5544787645339966,
+      "eval_runtime": 637.3611,
+      "eval_samples_per_second": 4.81,
+      "eval_steps_per_second": 2.405,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1752669785948160.0,
+  "total_flos": 3505339571896320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null