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:a4304f6a8584820be340c4310f48b498e5d0b0548eec60f67971ccd8f4aaba80
+oid sha256:c4955aff916e39abce33d1511ab184baf66423b5064c0d2fdd9a233cfedddb77
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcece0ca0b72181f42f388d48d2d3237eb9ea9172da02d5867ceba591a65d5db
+oid sha256:0023a21600ddfc952e42e8ccd00518fe25b5feecfde7d584e479dff5717164a5
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7fcc03839d1668b6b4487f47c49b7eb99157918f56c5b97b70d3b9dad5cee37
+oid sha256:04d898646c148612c83cdb951a736c820fa30dc4369223b34fe332ebed2cdcda
 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": 2.0206987857818604,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0035971223021582736,
+  "best_metric": 1.949695348739624,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.007194244604316547,
   "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": 3.783,
       "eval_steps_per_second": 1.893,
       "step": 10
+    },
+    {
+      "epoch": 0.003956834532374101,
+      "grad_norm": 1.3787400722503662,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.2416,
+      "step": 11
+    },
+    {
+      "epoch": 0.004316546762589928,
+      "grad_norm": 1.321842908859253,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.029,
+      "step": 12
+    },
+    {
+      "epoch": 0.004676258992805755,
+      "grad_norm": 1.261904239654541,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.1633,
+      "step": 13
+    },
+    {
+      "epoch": 0.005035971223021582,
+      "grad_norm": 1.3204586505889893,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.3555,
+      "step": 14
+    },
+    {
+      "epoch": 0.00539568345323741,
+      "grad_norm": 1.1878812313079834,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.984,
+      "step": 15
+    },
+    {
+      "epoch": 0.00539568345323741,
+      "eval_loss": 1.9619755744934082,
+      "eval_runtime": 310.7244,
+      "eval_samples_per_second": 3.769,
+      "eval_steps_per_second": 1.886,
+      "step": 15
+    },
+    {
+      "epoch": 0.0057553956834532375,
+      "grad_norm": 1.368757963180542,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.8076,
+      "step": 16
+    },
+    {
+      "epoch": 0.006115107913669065,
+      "grad_norm": 1.3265300989151,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.9355,
+      "step": 17
+    },
+    {
+      "epoch": 0.006474820143884892,
+      "grad_norm": 1.2753698825836182,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.5823,
+      "step": 18
+    },
+    {
+      "epoch": 0.006834532374100719,
+      "grad_norm": 1.0070078372955322,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.0167,
+      "step": 19
+    },
+    {
+      "epoch": 0.007194244604316547,
+      "grad_norm": 1.23676598072052,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.6254,
+      "step": 20
+    },
+    {
+      "epoch": 0.007194244604316547,
+      "eval_loss": 1.949695348739624,
+      "eval_runtime": 311.4876,
+      "eval_samples_per_second": 3.759,
+      "eval_steps_per_second": 1.881,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2054423272488960.0,
+  "total_flos": 4204401115791360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null