Update training logs at step 3000

training_logs.jsonl

@@ -104,3 +104,24 @@
 {"step": 2475, "epoch": 2.0024271844660193, "time": "2026-06-26 22:30:39", "logs": {"loss": 0.11151561737060547, "grad_norm": 1.239059329032898, "learning_rate": 1.172102963455871e-05, "epoch": 2.0024271844660193}}
 {"step": 2500, "epoch": 2.0226537216828477, "time": "2026-06-26 22:31:02", "logs": {"loss": 0.07747174263000488, "grad_norm": 0.14050441980361938, "learning_rate": 1.1546910119410297e-05, "epoch": 2.0226537216828477}}
 {"step": 2500, "epoch": 2.0226537216828477, "time": "2026-06-26 22:31:36", "logs": {"eval_loss": 0.17465205490589142, "eval_accuracy": 0.966144517433047, "eval_precision": 0.9712230215827338, "eval_recall": 0.9847480106100795, "eval_f1": 0.977938755350675, "eval_runtime": 34.5204, "eval_samples_per_second": 57.328, "eval_steps_per_second": 3.592, "epoch": 2.0226537216828477}}
+{"step": 2525, "epoch": 2.042880258899676, "time": "2026-06-26 22:32:14", "logs": {"loss": 0.12494021415710449, "grad_norm": 0.5169682502746582, "learning_rate": 1.1372308752393144e-05, "epoch": 2.042880258899676}}
+{"step": 2550, "epoch": 2.063106796116505, "time": "2026-06-26 22:32:37", "logs": {"loss": 0.17911155700683593, "grad_norm": 2.469010829925537, "learning_rate": 1.1197279920632864e-05, "epoch": 2.063106796116505}}
+{"step": 2575, "epoch": 2.0833333333333335, "time": "2026-06-26 22:32:59", "logs": {"loss": 0.1611471939086914, "grad_norm": 0.20758801698684692, "learning_rate": 1.1021878144407408e-05, "epoch": 2.0833333333333335}}
+{"step": 2600, "epoch": 2.103559870550162, "time": "2026-06-26 22:33:21", "logs": {"loss": 0.09400986671447754, "grad_norm": 18.897438049316406, "learning_rate": 1.0846158060164359e-05, "epoch": 2.103559870550162}}
+{"step": 2625, "epoch": 2.1237864077669903, "time": "2026-06-26 22:33:43", "logs": {"loss": 0.10660056114196777, "grad_norm": 0.48710235953330994, "learning_rate": 1.0670174403502051e-05, "epoch": 2.1237864077669903}}
+{"step": 2650, "epoch": 2.144012944983819, "time": "2026-06-26 22:34:05", "logs": {"loss": 0.09857481956481934, "grad_norm": 5.023293972015381, "learning_rate": 1.0493981992119833e-05, "epoch": 2.144012944983819}}
+{"step": 2675, "epoch": 2.164239482200647, "time": "2026-06-26 22:34:27", "logs": {"loss": 0.1647811508178711, "grad_norm": 0.3322446942329407, "learning_rate": 1.03176357087427e-05, "epoch": 2.164239482200647}}
+{"step": 2700, "epoch": 2.1844660194174756, "time": "2026-06-26 22:34:50", "logs": {"loss": 0.21691896438598632, "grad_norm": 33.930667877197266, "learning_rate": 1.0141190484025722e-05, "epoch": 2.1844660194174756}}
+{"step": 2725, "epoch": 2.204692556634304, "time": "2026-06-26 22:35:12", "logs": {"loss": 0.20835105895996095, "grad_norm": 0.22541019320487976, "learning_rate": 9.964701279443509e-06, "epoch": 2.204692556634304}}
+{"step": 2750, "epoch": 2.2249190938511325, "time": "2026-06-26 22:35:34", "logs": {"loss": 0.1038576602935791, "grad_norm": 0.2086869329214096, "learning_rate": 9.788223070170112e-06, "epoch": 2.2249190938511325}}
+{"step": 2775, "epoch": 2.2451456310679614, "time": "2026-06-26 22:35:56", "logs": {"loss": 0.1402608013153076, "grad_norm": 1.6252963542938232, "learning_rate": 9.6118108279546e-06, "epoch": 2.2451456310679614}}
+{"step": 2800, "epoch": 2.26537216828479, "time": "2026-06-26 22:36:18", "logs": {"loss": 0.1478741455078125, "grad_norm": 1.1920742988586426, "learning_rate": 9.435519503997767e-06, "epoch": 2.26537216828479}}
+{"step": 2825, "epoch": 2.2855987055016183, "time": "2026-06-26 22:36:40", "logs": {"loss": 0.10929722785949707, "grad_norm": 0.6118252277374268, "learning_rate": 9.259404011835203e-06, "epoch": 2.2855987055016183}}
+{"step": 2850, "epoch": 2.3058252427184467, "time": "2026-06-26 22:37:03", "logs": {"loss": 0.11905492782592773, "grad_norm": 0.16680538654327393, "learning_rate": 9.083519210232096e-06, "epoch": 2.3058252427184467}}
+{"step": 2875, "epoch": 2.326051779935275, "time": "2026-06-26 22:37:25", "logs": {"loss": 0.08101269721984863, "grad_norm": 0.19600656628608704, "learning_rate": 8.907919886095115e-06, "epoch": 2.326051779935275}}
+{"step": 2900, "epoch": 2.3462783171521036, "time": "2026-06-26 22:37:47", "logs": {"loss": 0.09864620208740234, "grad_norm": 1.6680601835250854, "learning_rate": 8.732660737406663e-06, "epoch": 2.3462783171521036}}
+{"step": 2925, "epoch": 2.366504854368932, "time": "2026-06-26 22:38:09", "logs": {"loss": 0.16998577117919922, "grad_norm": 0.5449312925338745, "learning_rate": 8.557796356186818e-06, "epoch": 2.366504854368932}}
+{"step": 2950, "epoch": 2.3867313915857604, "time": "2026-06-26 22:38:31", "logs": {"loss": 0.23032936096191406, "grad_norm": 0.10003538429737091, "learning_rate": 8.383381211488321e-06, "epoch": 2.3867313915857604}}
+{"step": 2975, "epoch": 2.406957928802589, "time": "2026-06-26 22:38:53", "logs": {"loss": 0.08545310974121094, "grad_norm": 7.103508472442627, "learning_rate": 8.209469632429811e-06, "epoch": 2.406957928802589}}
+{"step": 3000, "epoch": 2.4271844660194173, "time": "2026-06-26 22:39:15", "logs": {"loss": 0.2049958038330078, "grad_norm": 6.692376136779785, "learning_rate": 8.036115791272697e-06, "epoch": 2.4271844660194173}}
+{"step": 3000, "epoch": 2.4271844660194173, "time": "2026-06-26 22:39:50", "logs": {"eval_loss": 0.1759410947561264, "eval_accuracy": 0.9631126831733199, "eval_precision": 0.9638009049773756, "eval_recall": 0.9887267904509284, "eval_f1": 0.9761047463175123, "eval_runtime": 34.2085, "eval_samples_per_second": 57.851, "eval_steps_per_second": 3.625, "epoch": 2.4271844660194173}}